Upload folder using huggingface_hub
Browse files- config.json +63 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- trainer_state.json +3553 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"ModernBertForSequenceClassification"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 50281,
|
| 8 |
+
"classifier_activation": "gelu",
|
| 9 |
+
"classifier_bias": false,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"classifier_pooling": "mean",
|
| 12 |
+
"cls_token_id": 50281,
|
| 13 |
+
"decoder_bias": true,
|
| 14 |
+
"deterministic_flash_attn": false,
|
| 15 |
+
"embedding_dropout": 0.0,
|
| 16 |
+
"eos_token_id": 50282,
|
| 17 |
+
"global_attn_every_n_layers": 3,
|
| 18 |
+
"global_rope_theta": 160000.0,
|
| 19 |
+
"gradient_checkpointing": false,
|
| 20 |
+
"hidden_activation": "gelu",
|
| 21 |
+
"hidden_size": 1024,
|
| 22 |
+
"id2label": {
|
| 23 |
+
"0": "law_heritage",
|
| 24 |
+
"1": "social_science_heritage",
|
| 25 |
+
"2": "biological_heritage",
|
| 26 |
+
"3": "cultural_heritage",
|
| 27 |
+
"4": "individual_heritage",
|
| 28 |
+
"5": "statistics_heritage"
|
| 29 |
+
},
|
| 30 |
+
"initializer_cutoff_factor": 2.0,
|
| 31 |
+
"initializer_range": 0.02,
|
| 32 |
+
"intermediate_size": 2624,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"biological_heritage": 2,
|
| 35 |
+
"cultural_heritage": 3,
|
| 36 |
+
"individual_heritage": 4,
|
| 37 |
+
"law_heritage": 0,
|
| 38 |
+
"social_science_heritage": 1,
|
| 39 |
+
"statistics_heritage": 5
|
| 40 |
+
},
|
| 41 |
+
"layer_norm_eps": 1e-05,
|
| 42 |
+
"local_attention": 128,
|
| 43 |
+
"local_rope_theta": 10000.0,
|
| 44 |
+
"max_position_embeddings": 8192,
|
| 45 |
+
"mlp_bias": false,
|
| 46 |
+
"mlp_dropout": 0.0,
|
| 47 |
+
"model_type": "modernbert",
|
| 48 |
+
"norm_bias": false,
|
| 49 |
+
"norm_eps": 1e-05,
|
| 50 |
+
"num_attention_heads": 16,
|
| 51 |
+
"num_hidden_layers": 28,
|
| 52 |
+
"pad_token_id": 50283,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"problem_type": "multi_label_classification",
|
| 55 |
+
"reference_compile": true,
|
| 56 |
+
"repad_logits_with_grad": false,
|
| 57 |
+
"sep_token_id": 50282,
|
| 58 |
+
"sparse_pred_ignore_index": -100,
|
| 59 |
+
"sparse_prediction": false,
|
| 60 |
+
"torch_dtype": "float32",
|
| 61 |
+
"transformers_version": "4.50.0",
|
| 62 |
+
"vocab_size": 50368
|
| 63 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4369ac40f29d9e72bd25c9c891814e954c8d27107ce6f5a46429725f1737927
|
| 3 |
+
size 1583368040
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5a1c6fe70deae03719b9079fd0332dfc1eb159c39fa096b9168b22e6276b8b84
|
| 3 |
+
size 3166845946
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
|
| 3 |
+
size 14244
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c3aff0cf16d2f848151dadfca5dab2ea7fd37a90c1b0ffd40df6b07cea38b87
|
| 3 |
+
size 988
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:420bb756d642e5717a9f602028144811c856bacb2622019cdaf8cd89bb5d0f5c
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"mask_token": {
|
| 10 |
+
"content": "[MASK]",
|
| 11 |
+
"lstrip": true,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "|||IP_ADDRESS|||",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": false
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<|padding|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"50254": {
|
| 20 |
+
"content": " ",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": false
|
| 26 |
+
},
|
| 27 |
+
"50255": {
|
| 28 |
+
"content": " ",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
},
|
| 35 |
+
"50256": {
|
| 36 |
+
"content": " ",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": true,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": false
|
| 42 |
+
},
|
| 43 |
+
"50257": {
|
| 44 |
+
"content": " ",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": true,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": false
|
| 50 |
+
},
|
| 51 |
+
"50258": {
|
| 52 |
+
"content": " ",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": true,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": false
|
| 58 |
+
},
|
| 59 |
+
"50259": {
|
| 60 |
+
"content": " ",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": true,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": false
|
| 66 |
+
},
|
| 67 |
+
"50260": {
|
| 68 |
+
"content": " ",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": true,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": false
|
| 74 |
+
},
|
| 75 |
+
"50261": {
|
| 76 |
+
"content": " ",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": true,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": false
|
| 82 |
+
},
|
| 83 |
+
"50262": {
|
| 84 |
+
"content": " ",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": true,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": false
|
| 90 |
+
},
|
| 91 |
+
"50263": {
|
| 92 |
+
"content": " ",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": true,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": false
|
| 98 |
+
},
|
| 99 |
+
"50264": {
|
| 100 |
+
"content": " ",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": true,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": false
|
| 106 |
+
},
|
| 107 |
+
"50265": {
|
| 108 |
+
"content": " ",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": true,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": false
|
| 114 |
+
},
|
| 115 |
+
"50266": {
|
| 116 |
+
"content": " ",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": true,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": false
|
| 122 |
+
},
|
| 123 |
+
"50267": {
|
| 124 |
+
"content": " ",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": true,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": false
|
| 130 |
+
},
|
| 131 |
+
"50268": {
|
| 132 |
+
"content": " ",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": true,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": false
|
| 138 |
+
},
|
| 139 |
+
"50269": {
|
| 140 |
+
"content": " ",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": true,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": false
|
| 146 |
+
},
|
| 147 |
+
"50270": {
|
| 148 |
+
"content": " ",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": true,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": false
|
| 154 |
+
},
|
| 155 |
+
"50271": {
|
| 156 |
+
"content": " ",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": true,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": false
|
| 162 |
+
},
|
| 163 |
+
"50272": {
|
| 164 |
+
"content": " ",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": true,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": false
|
| 170 |
+
},
|
| 171 |
+
"50273": {
|
| 172 |
+
"content": " ",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": true,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": false
|
| 178 |
+
},
|
| 179 |
+
"50274": {
|
| 180 |
+
"content": " ",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": true,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": false
|
| 186 |
+
},
|
| 187 |
+
"50275": {
|
| 188 |
+
"content": " ",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": true,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": false
|
| 194 |
+
},
|
| 195 |
+
"50276": {
|
| 196 |
+
"content": " ",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": true,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": false
|
| 202 |
+
},
|
| 203 |
+
"50277": {
|
| 204 |
+
"content": "|||EMAIL_ADDRESS|||",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": true,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": false
|
| 210 |
+
},
|
| 211 |
+
"50278": {
|
| 212 |
+
"content": "|||PHONE_NUMBER|||",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": true,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": false
|
| 218 |
+
},
|
| 219 |
+
"50279": {
|
| 220 |
+
"content": "<|endoftext|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"50280": {
|
| 228 |
+
"content": "[UNK]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"50281": {
|
| 236 |
+
"content": "[CLS]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"50282": {
|
| 244 |
+
"content": "[SEP]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"50283": {
|
| 252 |
+
"content": "[PAD]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"50284": {
|
| 260 |
+
"content": "[MASK]",
|
| 261 |
+
"lstrip": true,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"50285": {
|
| 268 |
+
"content": "[unused0]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": true,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": false
|
| 274 |
+
},
|
| 275 |
+
"50286": {
|
| 276 |
+
"content": "[unused1]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": true,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": false
|
| 282 |
+
},
|
| 283 |
+
"50287": {
|
| 284 |
+
"content": "[unused2]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": true,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": false
|
| 290 |
+
},
|
| 291 |
+
"50288": {
|
| 292 |
+
"content": "[unused3]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": true,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": false
|
| 298 |
+
},
|
| 299 |
+
"50289": {
|
| 300 |
+
"content": "[unused4]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": true,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": false
|
| 306 |
+
},
|
| 307 |
+
"50290": {
|
| 308 |
+
"content": "[unused5]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": true,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": false
|
| 314 |
+
},
|
| 315 |
+
"50291": {
|
| 316 |
+
"content": "[unused6]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": true,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": false
|
| 322 |
+
},
|
| 323 |
+
"50292": {
|
| 324 |
+
"content": "[unused7]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": true,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": false
|
| 330 |
+
},
|
| 331 |
+
"50293": {
|
| 332 |
+
"content": "[unused8]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": true,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": false
|
| 338 |
+
},
|
| 339 |
+
"50294": {
|
| 340 |
+
"content": "[unused9]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": true,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": false
|
| 346 |
+
},
|
| 347 |
+
"50295": {
|
| 348 |
+
"content": "[unused10]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": true,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": false
|
| 354 |
+
},
|
| 355 |
+
"50296": {
|
| 356 |
+
"content": "[unused11]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": true,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": false
|
| 362 |
+
},
|
| 363 |
+
"50297": {
|
| 364 |
+
"content": "[unused12]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": true,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": false
|
| 370 |
+
},
|
| 371 |
+
"50298": {
|
| 372 |
+
"content": "[unused13]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": true,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": false
|
| 378 |
+
},
|
| 379 |
+
"50299": {
|
| 380 |
+
"content": "[unused14]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": true,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": false
|
| 386 |
+
},
|
| 387 |
+
"50300": {
|
| 388 |
+
"content": "[unused15]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": true,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": false
|
| 394 |
+
},
|
| 395 |
+
"50301": {
|
| 396 |
+
"content": "[unused16]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": true,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": false
|
| 402 |
+
},
|
| 403 |
+
"50302": {
|
| 404 |
+
"content": "[unused17]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": true,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": false
|
| 410 |
+
},
|
| 411 |
+
"50303": {
|
| 412 |
+
"content": "[unused18]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": true,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": false
|
| 418 |
+
},
|
| 419 |
+
"50304": {
|
| 420 |
+
"content": "[unused19]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": true,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": false
|
| 426 |
+
},
|
| 427 |
+
"50305": {
|
| 428 |
+
"content": "[unused20]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": true,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": false
|
| 434 |
+
},
|
| 435 |
+
"50306": {
|
| 436 |
+
"content": "[unused21]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": true,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": false
|
| 442 |
+
},
|
| 443 |
+
"50307": {
|
| 444 |
+
"content": "[unused22]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": true,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": false
|
| 450 |
+
},
|
| 451 |
+
"50308": {
|
| 452 |
+
"content": "[unused23]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": true,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": false
|
| 458 |
+
},
|
| 459 |
+
"50309": {
|
| 460 |
+
"content": "[unused24]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": true,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": false
|
| 466 |
+
},
|
| 467 |
+
"50310": {
|
| 468 |
+
"content": "[unused25]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": true,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": false
|
| 474 |
+
},
|
| 475 |
+
"50311": {
|
| 476 |
+
"content": "[unused26]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": true,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": false
|
| 482 |
+
},
|
| 483 |
+
"50312": {
|
| 484 |
+
"content": "[unused27]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": true,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": false
|
| 490 |
+
},
|
| 491 |
+
"50313": {
|
| 492 |
+
"content": "[unused28]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": true,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": false
|
| 498 |
+
},
|
| 499 |
+
"50314": {
|
| 500 |
+
"content": "[unused29]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": true,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": false
|
| 506 |
+
},
|
| 507 |
+
"50315": {
|
| 508 |
+
"content": "[unused30]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": true,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": false
|
| 514 |
+
},
|
| 515 |
+
"50316": {
|
| 516 |
+
"content": "[unused31]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": true,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": false
|
| 522 |
+
},
|
| 523 |
+
"50317": {
|
| 524 |
+
"content": "[unused32]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": true,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": false
|
| 530 |
+
},
|
| 531 |
+
"50318": {
|
| 532 |
+
"content": "[unused33]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": true,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": false
|
| 538 |
+
},
|
| 539 |
+
"50319": {
|
| 540 |
+
"content": "[unused34]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": true,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": false
|
| 546 |
+
},
|
| 547 |
+
"50320": {
|
| 548 |
+
"content": "[unused35]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": true,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": false
|
| 554 |
+
},
|
| 555 |
+
"50321": {
|
| 556 |
+
"content": "[unused36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": true,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": false
|
| 562 |
+
},
|
| 563 |
+
"50322": {
|
| 564 |
+
"content": "[unused37]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": true,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": false
|
| 570 |
+
},
|
| 571 |
+
"50323": {
|
| 572 |
+
"content": "[unused38]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": true,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": false
|
| 578 |
+
},
|
| 579 |
+
"50324": {
|
| 580 |
+
"content": "[unused39]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": true,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": false
|
| 586 |
+
},
|
| 587 |
+
"50325": {
|
| 588 |
+
"content": "[unused40]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": true,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": false
|
| 594 |
+
},
|
| 595 |
+
"50326": {
|
| 596 |
+
"content": "[unused41]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": true,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": false
|
| 602 |
+
},
|
| 603 |
+
"50327": {
|
| 604 |
+
"content": "[unused42]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": true,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": false
|
| 610 |
+
},
|
| 611 |
+
"50328": {
|
| 612 |
+
"content": "[unused43]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": true,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": false
|
| 618 |
+
},
|
| 619 |
+
"50329": {
|
| 620 |
+
"content": "[unused44]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": true,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": false
|
| 626 |
+
},
|
| 627 |
+
"50330": {
|
| 628 |
+
"content": "[unused45]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": true,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": false
|
| 634 |
+
},
|
| 635 |
+
"50331": {
|
| 636 |
+
"content": "[unused46]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": true,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": false
|
| 642 |
+
},
|
| 643 |
+
"50332": {
|
| 644 |
+
"content": "[unused47]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": true,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": false
|
| 650 |
+
},
|
| 651 |
+
"50333": {
|
| 652 |
+
"content": "[unused48]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": true,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": false
|
| 658 |
+
},
|
| 659 |
+
"50334": {
|
| 660 |
+
"content": "[unused49]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": true,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": false
|
| 666 |
+
},
|
| 667 |
+
"50335": {
|
| 668 |
+
"content": "[unused50]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": true,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": false
|
| 674 |
+
},
|
| 675 |
+
"50336": {
|
| 676 |
+
"content": "[unused51]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": true,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": false
|
| 682 |
+
},
|
| 683 |
+
"50337": {
|
| 684 |
+
"content": "[unused52]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": true,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": false
|
| 690 |
+
},
|
| 691 |
+
"50338": {
|
| 692 |
+
"content": "[unused53]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": true,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": false
|
| 698 |
+
},
|
| 699 |
+
"50339": {
|
| 700 |
+
"content": "[unused54]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": true,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": false
|
| 706 |
+
},
|
| 707 |
+
"50340": {
|
| 708 |
+
"content": "[unused55]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": true,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": false
|
| 714 |
+
},
|
| 715 |
+
"50341": {
|
| 716 |
+
"content": "[unused56]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": true,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": false
|
| 722 |
+
},
|
| 723 |
+
"50342": {
|
| 724 |
+
"content": "[unused57]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": true,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": false
|
| 730 |
+
},
|
| 731 |
+
"50343": {
|
| 732 |
+
"content": "[unused58]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": true,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": false
|
| 738 |
+
},
|
| 739 |
+
"50344": {
|
| 740 |
+
"content": "[unused59]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": true,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": false
|
| 746 |
+
},
|
| 747 |
+
"50345": {
|
| 748 |
+
"content": "[unused60]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": true,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": false
|
| 754 |
+
},
|
| 755 |
+
"50346": {
|
| 756 |
+
"content": "[unused61]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": true,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": false
|
| 762 |
+
},
|
| 763 |
+
"50347": {
|
| 764 |
+
"content": "[unused62]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": true,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": false
|
| 770 |
+
},
|
| 771 |
+
"50348": {
|
| 772 |
+
"content": "[unused63]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": true,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": false
|
| 778 |
+
},
|
| 779 |
+
"50349": {
|
| 780 |
+
"content": "[unused64]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": true,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": false
|
| 786 |
+
},
|
| 787 |
+
"50350": {
|
| 788 |
+
"content": "[unused65]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": true,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": false
|
| 794 |
+
},
|
| 795 |
+
"50351": {
|
| 796 |
+
"content": "[unused66]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": true,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": false
|
| 802 |
+
},
|
| 803 |
+
"50352": {
|
| 804 |
+
"content": "[unused67]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": true,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": false
|
| 810 |
+
},
|
| 811 |
+
"50353": {
|
| 812 |
+
"content": "[unused68]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": true,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": false
|
| 818 |
+
},
|
| 819 |
+
"50354": {
|
| 820 |
+
"content": "[unused69]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": true,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": false
|
| 826 |
+
},
|
| 827 |
+
"50355": {
|
| 828 |
+
"content": "[unused70]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": true,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": false
|
| 834 |
+
},
|
| 835 |
+
"50356": {
|
| 836 |
+
"content": "[unused71]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
+
},
|
| 843 |
+
"50357": {
|
| 844 |
+
"content": "[unused72]",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": true,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": false
|
| 850 |
+
},
|
| 851 |
+
"50358": {
|
| 852 |
+
"content": "[unused73]",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": true,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": false
|
| 858 |
+
},
|
| 859 |
+
"50359": {
|
| 860 |
+
"content": "[unused74]",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": true,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": false
|
| 866 |
+
},
|
| 867 |
+
"50360": {
|
| 868 |
+
"content": "[unused75]",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": true,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": false
|
| 874 |
+
},
|
| 875 |
+
"50361": {
|
| 876 |
+
"content": "[unused76]",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": true,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": false
|
| 882 |
+
},
|
| 883 |
+
"50362": {
|
| 884 |
+
"content": "[unused77]",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": true,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": false
|
| 890 |
+
},
|
| 891 |
+
"50363": {
|
| 892 |
+
"content": "[unused78]",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": true,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": false
|
| 898 |
+
},
|
| 899 |
+
"50364": {
|
| 900 |
+
"content": "[unused79]",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": true,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": false
|
| 906 |
+
},
|
| 907 |
+
"50365": {
|
| 908 |
+
"content": "[unused80]",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": true,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": false
|
| 914 |
+
},
|
| 915 |
+
"50366": {
|
| 916 |
+
"content": "[unused81]",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": true,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": false
|
| 922 |
+
},
|
| 923 |
+
"50367": {
|
| 924 |
+
"content": "[unused82]",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": true,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": false
|
| 930 |
+
}
|
| 931 |
+
},
|
| 932 |
+
"clean_up_tokenization_spaces": true,
|
| 933 |
+
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"mask_token": "[MASK]",
|
| 936 |
+
"model_input_names": [
|
| 937 |
+
"input_ids",
|
| 938 |
+
"attention_mask"
|
| 939 |
+
],
|
| 940 |
+
"model_max_length": 8192,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 944 |
+
"unk_token": "[UNK]"
|
| 945 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3553 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 166236,
|
| 3 |
+
"best_metric": 0.7059909142532652,
|
| 4 |
+
"best_model_checkpoint": "modernbert-heritage-classification/checkpoint-166236",
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 249354,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0060155441661252675,
|
| 14 |
+
"grad_norm": 3.192460536956787,
|
| 15 |
+
"learning_rate": 1.996005678673693e-05,
|
| 16 |
+
"loss": 0.4511,
|
| 17 |
+
"step": 500
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012031088332250535,
|
| 21 |
+
"grad_norm": 2.3000173568725586,
|
| 22 |
+
"learning_rate": 1.992003336621831e-05,
|
| 23 |
+
"loss": 0.4198,
|
| 24 |
+
"step": 1000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.018046632498375802,
|
| 28 |
+
"grad_norm": 6.538833141326904,
|
| 29 |
+
"learning_rate": 1.9879929738444142e-05,
|
| 30 |
+
"loss": 0.4086,
|
| 31 |
+
"step": 1500
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.02406217666450107,
|
| 35 |
+
"grad_norm": 0.18448229134082794,
|
| 36 |
+
"learning_rate": 1.9839826110669975e-05,
|
| 37 |
+
"loss": 0.3574,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.030077720830626337,
|
| 42 |
+
"grad_norm": 5.782385349273682,
|
| 43 |
+
"learning_rate": 1.9799722482895804e-05,
|
| 44 |
+
"loss": 0.3798,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.036093264996751605,
|
| 49 |
+
"grad_norm": 2.290853500366211,
|
| 50 |
+
"learning_rate": 1.9759699062377184e-05,
|
| 51 |
+
"loss": 0.38,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.042108809162876876,
|
| 56 |
+
"grad_norm": 4.156062126159668,
|
| 57 |
+
"learning_rate": 1.9719595434603017e-05,
|
| 58 |
+
"loss": 0.3838,
|
| 59 |
+
"step": 3500
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04812435332900214,
|
| 63 |
+
"grad_norm": 2.1094439029693604,
|
| 64 |
+
"learning_rate": 1.967949180682885e-05,
|
| 65 |
+
"loss": 0.3625,
|
| 66 |
+
"step": 4000
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.05413989749512741,
|
| 70 |
+
"grad_norm": 8.78498363494873,
|
| 71 |
+
"learning_rate": 1.963938817905468e-05,
|
| 72 |
+
"loss": 0.3834,
|
| 73 |
+
"step": 4500
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.060155441661252675,
|
| 77 |
+
"grad_norm": 0.003325940575450659,
|
| 78 |
+
"learning_rate": 1.959928455128051e-05,
|
| 79 |
+
"loss": 0.3395,
|
| 80 |
+
"step": 5000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.06617098582737795,
|
| 84 |
+
"grad_norm": 0.030467336997389793,
|
| 85 |
+
"learning_rate": 1.9559180923506344e-05,
|
| 86 |
+
"loss": 0.3605,
|
| 87 |
+
"step": 5500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07218652999350321,
|
| 91 |
+
"grad_norm": 0.7140659689903259,
|
| 92 |
+
"learning_rate": 1.9519077295732173e-05,
|
| 93 |
+
"loss": 0.352,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.07820207415962847,
|
| 98 |
+
"grad_norm": 0.013019168749451637,
|
| 99 |
+
"learning_rate": 1.9479053875213553e-05,
|
| 100 |
+
"loss": 0.3533,
|
| 101 |
+
"step": 6500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.08421761832575375,
|
| 105 |
+
"grad_norm": 3.8174266815185547,
|
| 106 |
+
"learning_rate": 1.9438950247439386e-05,
|
| 107 |
+
"loss": 0.316,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.09023316249187902,
|
| 112 |
+
"grad_norm": 7.174667835235596,
|
| 113 |
+
"learning_rate": 1.939884661966522e-05,
|
| 114 |
+
"loss": 0.3495,
|
| 115 |
+
"step": 7500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.09624870665800428,
|
| 119 |
+
"grad_norm": 1.6871285438537598,
|
| 120 |
+
"learning_rate": 1.9358742991891048e-05,
|
| 121 |
+
"loss": 0.3449,
|
| 122 |
+
"step": 8000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.10226425082412956,
|
| 126 |
+
"grad_norm": 0.04142903909087181,
|
| 127 |
+
"learning_rate": 1.931863936411688e-05,
|
| 128 |
+
"loss": 0.3212,
|
| 129 |
+
"step": 8500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.10827979499025482,
|
| 133 |
+
"grad_norm": 0.0040322355926036835,
|
| 134 |
+
"learning_rate": 1.9278535736342713e-05,
|
| 135 |
+
"loss": 0.3416,
|
| 136 |
+
"step": 9000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.11429533915638009,
|
| 140 |
+
"grad_norm": 7.649967193603516,
|
| 141 |
+
"learning_rate": 1.9238512315824093e-05,
|
| 142 |
+
"loss": 0.3615,
|
| 143 |
+
"step": 9500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.12031088332250535,
|
| 147 |
+
"grad_norm": 2.4331884384155273,
|
| 148 |
+
"learning_rate": 1.9198408688049922e-05,
|
| 149 |
+
"loss": 0.354,
|
| 150 |
+
"step": 10000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.12632642748863063,
|
| 154 |
+
"grad_norm": 8.657504081726074,
|
| 155 |
+
"learning_rate": 1.9158305060275755e-05,
|
| 156 |
+
"loss": 0.3413,
|
| 157 |
+
"step": 10500
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.1323419716547559,
|
| 161 |
+
"grad_norm": 8.941267013549805,
|
| 162 |
+
"learning_rate": 1.9118201432501588e-05,
|
| 163 |
+
"loss": 0.3211,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.13835751582088116,
|
| 168 |
+
"grad_norm": 16.12137794494629,
|
| 169 |
+
"learning_rate": 1.9078178011982968e-05,
|
| 170 |
+
"loss": 0.3323,
|
| 171 |
+
"step": 11500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14437305998700642,
|
| 175 |
+
"grad_norm": 0.30122852325439453,
|
| 176 |
+
"learning_rate": 1.9038074384208797e-05,
|
| 177 |
+
"loss": 0.3163,
|
| 178 |
+
"step": 12000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.15038860415313168,
|
| 182 |
+
"grad_norm": 0.2980821132659912,
|
| 183 |
+
"learning_rate": 1.899797075643463e-05,
|
| 184 |
+
"loss": 0.3264,
|
| 185 |
+
"step": 12500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.15640414831925695,
|
| 189 |
+
"grad_norm": 0.006154663860797882,
|
| 190 |
+
"learning_rate": 1.8957867128660462e-05,
|
| 191 |
+
"loss": 0.3453,
|
| 192 |
+
"step": 13000
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.16241969248538224,
|
| 196 |
+
"grad_norm": 0.8030881285667419,
|
| 197 |
+
"learning_rate": 1.8917763500886292e-05,
|
| 198 |
+
"loss": 0.3152,
|
| 199 |
+
"step": 13500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1684352366515075,
|
| 203 |
+
"grad_norm": 17.813459396362305,
|
| 204 |
+
"learning_rate": 1.8877659873112124e-05,
|
| 205 |
+
"loss": 0.3189,
|
| 206 |
+
"step": 14000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.17445078081763277,
|
| 210 |
+
"grad_norm": 1.1400656700134277,
|
| 211 |
+
"learning_rate": 1.8837556245337957e-05,
|
| 212 |
+
"loss": 0.3434,
|
| 213 |
+
"step": 14500
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.18046632498375803,
|
| 217 |
+
"grad_norm": 0.09848301857709885,
|
| 218 |
+
"learning_rate": 1.8797452617563786e-05,
|
| 219 |
+
"loss": 0.3087,
|
| 220 |
+
"step": 15000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.1864818691498833,
|
| 224 |
+
"grad_norm": 0.04860129952430725,
|
| 225 |
+
"learning_rate": 1.875734898978962e-05,
|
| 226 |
+
"loss": 0.3289,
|
| 227 |
+
"step": 15500
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.19249741331600856,
|
| 231 |
+
"grad_norm": 0.012527902610599995,
|
| 232 |
+
"learning_rate": 1.8717325569271e-05,
|
| 233 |
+
"loss": 0.3324,
|
| 234 |
+
"step": 16000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.19851295748213382,
|
| 238 |
+
"grad_norm": 5.626002788543701,
|
| 239 |
+
"learning_rate": 1.867730214875238e-05,
|
| 240 |
+
"loss": 0.3351,
|
| 241 |
+
"step": 16500
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.20452850164825911,
|
| 245 |
+
"grad_norm": 0.2671683430671692,
|
| 246 |
+
"learning_rate": 1.8637198520978212e-05,
|
| 247 |
+
"loss": 0.3467,
|
| 248 |
+
"step": 17000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.21054404581438438,
|
| 252 |
+
"grad_norm": 0.4044207036495209,
|
| 253 |
+
"learning_rate": 1.859709489320404e-05,
|
| 254 |
+
"loss": 0.3248,
|
| 255 |
+
"step": 17500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.21655958998050964,
|
| 259 |
+
"grad_norm": 0.19454579055309296,
|
| 260 |
+
"learning_rate": 1.8556991265429874e-05,
|
| 261 |
+
"loss": 0.339,
|
| 262 |
+
"step": 18000
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.2225751341466349,
|
| 266 |
+
"grad_norm": 13.63963508605957,
|
| 267 |
+
"learning_rate": 1.8516887637655703e-05,
|
| 268 |
+
"loss": 0.3252,
|
| 269 |
+
"step": 18500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.22859067831276017,
|
| 273 |
+
"grad_norm": 3.8693294525146484,
|
| 274 |
+
"learning_rate": 1.8476784009881536e-05,
|
| 275 |
+
"loss": 0.3311,
|
| 276 |
+
"step": 19000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.23460622247888543,
|
| 280 |
+
"grad_norm": 2.644678831100464,
|
| 281 |
+
"learning_rate": 1.8436760589362916e-05,
|
| 282 |
+
"loss": 0.3378,
|
| 283 |
+
"step": 19500
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.2406217666450107,
|
| 287 |
+
"grad_norm": 1.1504566669464111,
|
| 288 |
+
"learning_rate": 1.8396656961588745e-05,
|
| 289 |
+
"loss": 0.3162,
|
| 290 |
+
"step": 20000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.24663731081113596,
|
| 294 |
+
"grad_norm": 0.33002209663391113,
|
| 295 |
+
"learning_rate": 1.8356553333814578e-05,
|
| 296 |
+
"loss": 0.3112,
|
| 297 |
+
"step": 20500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.25265285497726125,
|
| 301 |
+
"grad_norm": 5.884070873260498,
|
| 302 |
+
"learning_rate": 1.831644970604041e-05,
|
| 303 |
+
"loss": 0.3375,
|
| 304 |
+
"step": 21000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.2586683991433865,
|
| 308 |
+
"grad_norm": 0.004158430732786655,
|
| 309 |
+
"learning_rate": 1.827634607826624e-05,
|
| 310 |
+
"loss": 0.2711,
|
| 311 |
+
"step": 21500
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2646839433095118,
|
| 315 |
+
"grad_norm": 6.601622581481934,
|
| 316 |
+
"learning_rate": 1.8236242450492072e-05,
|
| 317 |
+
"loss": 0.3031,
|
| 318 |
+
"step": 22000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.27069948747563705,
|
| 322 |
+
"grad_norm": 4.164157390594482,
|
| 323 |
+
"learning_rate": 1.8196138822717905e-05,
|
| 324 |
+
"loss": 0.3228,
|
| 325 |
+
"step": 22500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.2767150316417623,
|
| 329 |
+
"grad_norm": 34.43812942504883,
|
| 330 |
+
"learning_rate": 1.8156035194943734e-05,
|
| 331 |
+
"loss": 0.3061,
|
| 332 |
+
"step": 23000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2827305758078876,
|
| 336 |
+
"grad_norm": 0.02143733762204647,
|
| 337 |
+
"learning_rate": 1.8115931567169567e-05,
|
| 338 |
+
"loss": 0.3163,
|
| 339 |
+
"step": 23500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.28874611997401284,
|
| 343 |
+
"grad_norm": 9.730279922485352,
|
| 344 |
+
"learning_rate": 1.8075908146650947e-05,
|
| 345 |
+
"loss": 0.2817,
|
| 346 |
+
"step": 24000
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2947616641401381,
|
| 350 |
+
"grad_norm": 9.340431213378906,
|
| 351 |
+
"learning_rate": 1.803580451887678e-05,
|
| 352 |
+
"loss": 0.3105,
|
| 353 |
+
"step": 24500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.30077720830626337,
|
| 357 |
+
"grad_norm": 9.22760009765625,
|
| 358 |
+
"learning_rate": 1.799570089110261e-05,
|
| 359 |
+
"loss": 0.309,
|
| 360 |
+
"step": 25000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.30679275247238863,
|
| 364 |
+
"grad_norm": 3.7310335636138916,
|
| 365 |
+
"learning_rate": 1.795567747058399e-05,
|
| 366 |
+
"loss": 0.3075,
|
| 367 |
+
"step": 25500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3128082966385139,
|
| 371 |
+
"grad_norm": 4.968273639678955,
|
| 372 |
+
"learning_rate": 1.7915573842809822e-05,
|
| 373 |
+
"loss": 0.3056,
|
| 374 |
+
"step": 26000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3188238408046392,
|
| 378 |
+
"grad_norm": 15.309103012084961,
|
| 379 |
+
"learning_rate": 1.7875470215035654e-05,
|
| 380 |
+
"loss": 0.3063,
|
| 381 |
+
"step": 26500
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3248393849707645,
|
| 385 |
+
"grad_norm": 0.028000958263874054,
|
| 386 |
+
"learning_rate": 1.7835366587261484e-05,
|
| 387 |
+
"loss": 0.3251,
|
| 388 |
+
"step": 27000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.33085492913688974,
|
| 392 |
+
"grad_norm": 11.808887481689453,
|
| 393 |
+
"learning_rate": 1.7795262959487316e-05,
|
| 394 |
+
"loss": 0.3335,
|
| 395 |
+
"step": 27500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.336870473303015,
|
| 399 |
+
"grad_norm": 6.1232123374938965,
|
| 400 |
+
"learning_rate": 1.775515933171315e-05,
|
| 401 |
+
"loss": 0.2928,
|
| 402 |
+
"step": 28000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.34288601746914027,
|
| 406 |
+
"grad_norm": 2.071223258972168,
|
| 407 |
+
"learning_rate": 1.771505570393898e-05,
|
| 408 |
+
"loss": 0.3228,
|
| 409 |
+
"step": 28500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.34890156163526553,
|
| 413 |
+
"grad_norm": 6.20293664932251,
|
| 414 |
+
"learning_rate": 1.767495207616481e-05,
|
| 415 |
+
"loss": 0.3115,
|
| 416 |
+
"step": 29000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.3549171058013908,
|
| 420 |
+
"grad_norm": 0.5319348573684692,
|
| 421 |
+
"learning_rate": 1.7634848448390644e-05,
|
| 422 |
+
"loss": 0.3424,
|
| 423 |
+
"step": 29500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.36093264996751606,
|
| 427 |
+
"grad_norm": 0.15102390944957733,
|
| 428 |
+
"learning_rate": 1.7594825027872024e-05,
|
| 429 |
+
"loss": 0.3198,
|
| 430 |
+
"step": 30000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.3669481941336413,
|
| 434 |
+
"grad_norm": 10.45068359375,
|
| 435 |
+
"learning_rate": 1.7554721400097853e-05,
|
| 436 |
+
"loss": 0.3083,
|
| 437 |
+
"step": 30500
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.3729637382997666,
|
| 441 |
+
"grad_norm": 0.3780848979949951,
|
| 442 |
+
"learning_rate": 1.7514697979579233e-05,
|
| 443 |
+
"loss": 0.3079,
|
| 444 |
+
"step": 31000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.37897928246589185,
|
| 448 |
+
"grad_norm": 0.02213098295032978,
|
| 449 |
+
"learning_rate": 1.7474674559060613e-05,
|
| 450 |
+
"loss": 0.301,
|
| 451 |
+
"step": 31500
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.3849948266320171,
|
| 455 |
+
"grad_norm": 2.598281145095825,
|
| 456 |
+
"learning_rate": 1.7434570931286446e-05,
|
| 457 |
+
"loss": 0.2878,
|
| 458 |
+
"step": 32000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.3910103707981424,
|
| 462 |
+
"grad_norm": 0.14519445598125458,
|
| 463 |
+
"learning_rate": 1.739446730351228e-05,
|
| 464 |
+
"loss": 0.3231,
|
| 465 |
+
"step": 32500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.39702591496426765,
|
| 469 |
+
"grad_norm": 0.04602254554629326,
|
| 470 |
+
"learning_rate": 1.7354363675738108e-05,
|
| 471 |
+
"loss": 0.2972,
|
| 472 |
+
"step": 33000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.4030414591303929,
|
| 476 |
+
"grad_norm": 18.00914192199707,
|
| 477 |
+
"learning_rate": 1.731426004796394e-05,
|
| 478 |
+
"loss": 0.323,
|
| 479 |
+
"step": 33500
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.40905700329651823,
|
| 483 |
+
"grad_norm": 6.137303829193115,
|
| 484 |
+
"learning_rate": 1.7274156420189773e-05,
|
| 485 |
+
"loss": 0.3179,
|
| 486 |
+
"step": 34000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.4150725474626435,
|
| 490 |
+
"grad_norm": 3.145047187805176,
|
| 491 |
+
"learning_rate": 1.7234052792415602e-05,
|
| 492 |
+
"loss": 0.306,
|
| 493 |
+
"step": 34500
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.42108809162876876,
|
| 497 |
+
"grad_norm": 4.087808609008789,
|
| 498 |
+
"learning_rate": 1.7193949164641435e-05,
|
| 499 |
+
"loss": 0.325,
|
| 500 |
+
"step": 35000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.427103635794894,
|
| 504 |
+
"grad_norm": 0.009332289919257164,
|
| 505 |
+
"learning_rate": 1.7153845536867268e-05,
|
| 506 |
+
"loss": 0.2979,
|
| 507 |
+
"step": 35500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4331191799610193,
|
| 511 |
+
"grad_norm": 9.885307312011719,
|
| 512 |
+
"learning_rate": 1.7113741909093097e-05,
|
| 513 |
+
"loss": 0.3247,
|
| 514 |
+
"step": 36000
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.43913472412714455,
|
| 518 |
+
"grad_norm": 0.0056028529070317745,
|
| 519 |
+
"learning_rate": 1.707363828131893e-05,
|
| 520 |
+
"loss": 0.2949,
|
| 521 |
+
"step": 36500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4451502682932698,
|
| 525 |
+
"grad_norm": 8.444794654846191,
|
| 526 |
+
"learning_rate": 1.7033534653544762e-05,
|
| 527 |
+
"loss": 0.306,
|
| 528 |
+
"step": 37000
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.4511658124593951,
|
| 532 |
+
"grad_norm": 2.0681827068328857,
|
| 533 |
+
"learning_rate": 1.699343102577059e-05,
|
| 534 |
+
"loss": 0.2792,
|
| 535 |
+
"step": 37500
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.45718135662552034,
|
| 539 |
+
"grad_norm": 0.017593583092093468,
|
| 540 |
+
"learning_rate": 1.695340760525197e-05,
|
| 541 |
+
"loss": 0.3225,
|
| 542 |
+
"step": 38000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4631969007916456,
|
| 546 |
+
"grad_norm": 3.3854148387908936,
|
| 547 |
+
"learning_rate": 1.6913303977477804e-05,
|
| 548 |
+
"loss": 0.2962,
|
| 549 |
+
"step": 38500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.46921244495777087,
|
| 553 |
+
"grad_norm": 0.4375062584877014,
|
| 554 |
+
"learning_rate": 1.6873200349703637e-05,
|
| 555 |
+
"loss": 0.3146,
|
| 556 |
+
"step": 39000
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.47522798912389613,
|
| 560 |
+
"grad_norm": 0.24493420124053955,
|
| 561 |
+
"learning_rate": 1.6833096721929466e-05,
|
| 562 |
+
"loss": 0.2745,
|
| 563 |
+
"step": 39500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4812435332900214,
|
| 567 |
+
"grad_norm": 5.30033540725708,
|
| 568 |
+
"learning_rate": 1.6793153508666397e-05,
|
| 569 |
+
"loss": 0.3242,
|
| 570 |
+
"step": 40000
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.48725907745614666,
|
| 574 |
+
"grad_norm": 0.08991783857345581,
|
| 575 |
+
"learning_rate": 1.6753049880892226e-05,
|
| 576 |
+
"loss": 0.2889,
|
| 577 |
+
"step": 40500
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.4932746216222719,
|
| 581 |
+
"grad_norm": 0.16233447194099426,
|
| 582 |
+
"learning_rate": 1.671294625311806e-05,
|
| 583 |
+
"loss": 0.3147,
|
| 584 |
+
"step": 41000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.49929016578839724,
|
| 588 |
+
"grad_norm": 21.49981117248535,
|
| 589 |
+
"learning_rate": 1.6672842625343892e-05,
|
| 590 |
+
"loss": 0.3097,
|
| 591 |
+
"step": 41500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5053057099545225,
|
| 595 |
+
"grad_norm": 0.07683174312114716,
|
| 596 |
+
"learning_rate": 1.663281920482527e-05,
|
| 597 |
+
"loss": 0.3283,
|
| 598 |
+
"step": 42000
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.5113212541206478,
|
| 602 |
+
"grad_norm": 5.969061374664307,
|
| 603 |
+
"learning_rate": 1.65927155770511e-05,
|
| 604 |
+
"loss": 0.2973,
|
| 605 |
+
"step": 42500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.517336798286773,
|
| 609 |
+
"grad_norm": 0.1165817528963089,
|
| 610 |
+
"learning_rate": 1.6552611949276934e-05,
|
| 611 |
+
"loss": 0.2865,
|
| 612 |
+
"step": 43000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5233523424528983,
|
| 616 |
+
"grad_norm": 4.852444648742676,
|
| 617 |
+
"learning_rate": 1.6512508321502766e-05,
|
| 618 |
+
"loss": 0.2995,
|
| 619 |
+
"step": 43500
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5293678866190236,
|
| 623 |
+
"grad_norm": 0.3422677218914032,
|
| 624 |
+
"learning_rate": 1.6472404693728596e-05,
|
| 625 |
+
"loss": 0.3078,
|
| 626 |
+
"step": 44000
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5353834307851488,
|
| 630 |
+
"grad_norm": 0.02138070948421955,
|
| 631 |
+
"learning_rate": 1.643230106595443e-05,
|
| 632 |
+
"loss": 0.3041,
|
| 633 |
+
"step": 44500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.5413989749512741,
|
| 637 |
+
"grad_norm": 19.726158142089844,
|
| 638 |
+
"learning_rate": 1.639219743818026e-05,
|
| 639 |
+
"loss": 0.2747,
|
| 640 |
+
"step": 45000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.5474145191173994,
|
| 644 |
+
"grad_norm": 0.8494102358818054,
|
| 645 |
+
"learning_rate": 1.635209381040609e-05,
|
| 646 |
+
"loss": 0.3165,
|
| 647 |
+
"step": 45500
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.5534300632835246,
|
| 651 |
+
"grad_norm": 69.28723907470703,
|
| 652 |
+
"learning_rate": 1.6311990182631923e-05,
|
| 653 |
+
"loss": 0.286,
|
| 654 |
+
"step": 46000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5594456074496499,
|
| 658 |
+
"grad_norm": 5.112706661224365,
|
| 659 |
+
"learning_rate": 1.6271886554857756e-05,
|
| 660 |
+
"loss": 0.3103,
|
| 661 |
+
"step": 46500
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5654611516157751,
|
| 665 |
+
"grad_norm": 0.0373302698135376,
|
| 666 |
+
"learning_rate": 1.6231782927083585e-05,
|
| 667 |
+
"loss": 0.2966,
|
| 668 |
+
"step": 47000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.5714766957819004,
|
| 672 |
+
"grad_norm": 0.3029526472091675,
|
| 673 |
+
"learning_rate": 1.6191679299309418e-05,
|
| 674 |
+
"loss": 0.2785,
|
| 675 |
+
"step": 47500
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5774922399480257,
|
| 679 |
+
"grad_norm": 0.18373580276966095,
|
| 680 |
+
"learning_rate": 1.6151655878790798e-05,
|
| 681 |
+
"loss": 0.3328,
|
| 682 |
+
"step": 48000
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5835077841141509,
|
| 686 |
+
"grad_norm": 0.8737627267837524,
|
| 687 |
+
"learning_rate": 1.611155225101663e-05,
|
| 688 |
+
"loss": 0.2909,
|
| 689 |
+
"step": 48500
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.5895233282802762,
|
| 693 |
+
"grad_norm": 2.7465710639953613,
|
| 694 |
+
"learning_rate": 1.607144862324246e-05,
|
| 695 |
+
"loss": 0.2991,
|
| 696 |
+
"step": 49000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.5955388724464015,
|
| 700 |
+
"grad_norm": 19.38477325439453,
|
| 701 |
+
"learning_rate": 1.6031344995468292e-05,
|
| 702 |
+
"loss": 0.2785,
|
| 703 |
+
"step": 49500
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6015544166125267,
|
| 707 |
+
"grad_norm": 0.013609528541564941,
|
| 708 |
+
"learning_rate": 1.5991241367694125e-05,
|
| 709 |
+
"loss": 0.3198,
|
| 710 |
+
"step": 50000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.607569960778652,
|
| 714 |
+
"grad_norm": 6.444379806518555,
|
| 715 |
+
"learning_rate": 1.5951137739919954e-05,
|
| 716 |
+
"loss": 0.2816,
|
| 717 |
+
"step": 50500
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.6135855049447773,
|
| 721 |
+
"grad_norm": 6.260073661804199,
|
| 722 |
+
"learning_rate": 1.5911114319401334e-05,
|
| 723 |
+
"loss": 0.3193,
|
| 724 |
+
"step": 51000
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.6196010491109025,
|
| 728 |
+
"grad_norm": 8.19072151184082,
|
| 729 |
+
"learning_rate": 1.5871010691627167e-05,
|
| 730 |
+
"loss": 0.3021,
|
| 731 |
+
"step": 51500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.6256165932770278,
|
| 735 |
+
"grad_norm": 5.27684211730957,
|
| 736 |
+
"learning_rate": 1.5830907063853e-05,
|
| 737 |
+
"loss": 0.2925,
|
| 738 |
+
"step": 52000
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.631632137443153,
|
| 742 |
+
"grad_norm": 0.031686898320913315,
|
| 743 |
+
"learning_rate": 1.579080343607883e-05,
|
| 744 |
+
"loss": 0.3063,
|
| 745 |
+
"step": 52500
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.6376476816092784,
|
| 749 |
+
"grad_norm": 0.15889908373355865,
|
| 750 |
+
"learning_rate": 1.575078001556021e-05,
|
| 751 |
+
"loss": 0.2893,
|
| 752 |
+
"step": 53000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.6436632257754037,
|
| 756 |
+
"grad_norm": 5.396053314208984,
|
| 757 |
+
"learning_rate": 1.571067638778604e-05,
|
| 758 |
+
"loss": 0.3009,
|
| 759 |
+
"step": 53500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.649678769941529,
|
| 763 |
+
"grad_norm": 0.15985211730003357,
|
| 764 |
+
"learning_rate": 1.5670572760011874e-05,
|
| 765 |
+
"loss": 0.2985,
|
| 766 |
+
"step": 54000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.6556943141076542,
|
| 770 |
+
"grad_norm": 2.195845127105713,
|
| 771 |
+
"learning_rate": 1.5630469132237704e-05,
|
| 772 |
+
"loss": 0.2886,
|
| 773 |
+
"step": 54500
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.6617098582737795,
|
| 777 |
+
"grad_norm": 0.000236680411035195,
|
| 778 |
+
"learning_rate": 1.5590365504463536e-05,
|
| 779 |
+
"loss": 0.3041,
|
| 780 |
+
"step": 55000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.6677254024399047,
|
| 784 |
+
"grad_norm": 0.012887202203273773,
|
| 785 |
+
"learning_rate": 1.555026187668937e-05,
|
| 786 |
+
"loss": 0.2848,
|
| 787 |
+
"step": 55500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.67374094660603,
|
| 791 |
+
"grad_norm": 0.025558780878782272,
|
| 792 |
+
"learning_rate": 1.5510158248915198e-05,
|
| 793 |
+
"loss": 0.3037,
|
| 794 |
+
"step": 56000
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.6797564907721553,
|
| 798 |
+
"grad_norm": 13.303611755371094,
|
| 799 |
+
"learning_rate": 1.547013482839658e-05,
|
| 800 |
+
"loss": 0.3052,
|
| 801 |
+
"step": 56500
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6857720349382805,
|
| 805 |
+
"grad_norm": 7.728808403015137,
|
| 806 |
+
"learning_rate": 1.543003120062241e-05,
|
| 807 |
+
"loss": 0.3076,
|
| 808 |
+
"step": 57000
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.6917875791044058,
|
| 812 |
+
"grad_norm": 7.381441593170166,
|
| 813 |
+
"learning_rate": 1.538992757284824e-05,
|
| 814 |
+
"loss": 0.2838,
|
| 815 |
+
"step": 57500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.6978031232705311,
|
| 819 |
+
"grad_norm": 47.043766021728516,
|
| 820 |
+
"learning_rate": 1.5349823945074073e-05,
|
| 821 |
+
"loss": 0.2894,
|
| 822 |
+
"step": 58000
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.7038186674366563,
|
| 826 |
+
"grad_norm": 1.3084138631820679,
|
| 827 |
+
"learning_rate": 1.5309720317299902e-05,
|
| 828 |
+
"loss": 0.3089,
|
| 829 |
+
"step": 58500
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.7098342116027816,
|
| 833 |
+
"grad_norm": 0.28533193469047546,
|
| 834 |
+
"learning_rate": 1.5269616689525735e-05,
|
| 835 |
+
"loss": 0.3291,
|
| 836 |
+
"step": 59000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.7158497557689069,
|
| 840 |
+
"grad_norm": 0.006308581214398146,
|
| 841 |
+
"learning_rate": 1.5229513061751566e-05,
|
| 842 |
+
"loss": 0.2842,
|
| 843 |
+
"step": 59500
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.7218652999350321,
|
| 847 |
+
"grad_norm": 0.18038663268089294,
|
| 848 |
+
"learning_rate": 1.5189409433977399e-05,
|
| 849 |
+
"loss": 0.2964,
|
| 850 |
+
"step": 60000
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.7278808441011574,
|
| 854 |
+
"grad_norm": 9.797381401062012,
|
| 855 |
+
"learning_rate": 1.514930580620323e-05,
|
| 856 |
+
"loss": 0.3303,
|
| 857 |
+
"step": 60500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.7338963882672827,
|
| 861 |
+
"grad_norm": 0.27853924036026,
|
| 862 |
+
"learning_rate": 1.510920217842906e-05,
|
| 863 |
+
"loss": 0.2762,
|
| 864 |
+
"step": 61000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.7399119324334079,
|
| 868 |
+
"grad_norm": 0.13307029008865356,
|
| 869 |
+
"learning_rate": 1.506917875791044e-05,
|
| 870 |
+
"loss": 0.2798,
|
| 871 |
+
"step": 61500
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.7459274765995332,
|
| 875 |
+
"grad_norm": 4.89689826965332,
|
| 876 |
+
"learning_rate": 1.5029075130136273e-05,
|
| 877 |
+
"loss": 0.3202,
|
| 878 |
+
"step": 62000
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.7519430207656584,
|
| 882 |
+
"grad_norm": 14.662346839904785,
|
| 883 |
+
"learning_rate": 1.4988971502362104e-05,
|
| 884 |
+
"loss": 0.3051,
|
| 885 |
+
"step": 62500
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.7579585649317837,
|
| 889 |
+
"grad_norm": 0.15676206350326538,
|
| 890 |
+
"learning_rate": 1.4948867874587935e-05,
|
| 891 |
+
"loss": 0.3065,
|
| 892 |
+
"step": 63000
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.763974109097909,
|
| 896 |
+
"grad_norm": 10.646651268005371,
|
| 897 |
+
"learning_rate": 1.4908764246813768e-05,
|
| 898 |
+
"loss": 0.2741,
|
| 899 |
+
"step": 63500
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.7699896532640342,
|
| 903 |
+
"grad_norm": 7.507605075836182,
|
| 904 |
+
"learning_rate": 1.4868740826295148e-05,
|
| 905 |
+
"loss": 0.3195,
|
| 906 |
+
"step": 64000
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7760051974301595,
|
| 910 |
+
"grad_norm": 0.24443697929382324,
|
| 911 |
+
"learning_rate": 1.4828717405776526e-05,
|
| 912 |
+
"loss": 0.2662,
|
| 913 |
+
"step": 64500
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.7820207415962848,
|
| 917 |
+
"grad_norm": 7.655556678771973,
|
| 918 |
+
"learning_rate": 1.4788613778002359e-05,
|
| 919 |
+
"loss": 0.3168,
|
| 920 |
+
"step": 65000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.78803628576241,
|
| 924 |
+
"grad_norm": 7.646127223968506,
|
| 925 |
+
"learning_rate": 1.474851015022819e-05,
|
| 926 |
+
"loss": 0.2803,
|
| 927 |
+
"step": 65500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.7940518299285353,
|
| 931 |
+
"grad_norm": 0.0017321036430075765,
|
| 932 |
+
"learning_rate": 1.4708406522454023e-05,
|
| 933 |
+
"loss": 0.2779,
|
| 934 |
+
"step": 66000
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.8000673740946606,
|
| 938 |
+
"grad_norm": 0.004854683298617601,
|
| 939 |
+
"learning_rate": 1.4668302894679854e-05,
|
| 940 |
+
"loss": 0.3048,
|
| 941 |
+
"step": 66500
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.8060829182607858,
|
| 945 |
+
"grad_norm": 5.331120491027832,
|
| 946 |
+
"learning_rate": 1.4628199266905685e-05,
|
| 947 |
+
"loss": 0.3121,
|
| 948 |
+
"step": 67000
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.8120984624269111,
|
| 952 |
+
"grad_norm": 4.585981369018555,
|
| 953 |
+
"learning_rate": 1.4588095639131517e-05,
|
| 954 |
+
"loss": 0.2968,
|
| 955 |
+
"step": 67500
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.8181140065930365,
|
| 959 |
+
"grad_norm": 0.0019534584134817123,
|
| 960 |
+
"learning_rate": 1.4548072218612896e-05,
|
| 961 |
+
"loss": 0.2869,
|
| 962 |
+
"step": 68000
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.8241295507591617,
|
| 966 |
+
"grad_norm": 0.03927936032414436,
|
| 967 |
+
"learning_rate": 1.4507968590838728e-05,
|
| 968 |
+
"loss": 0.2942,
|
| 969 |
+
"step": 68500
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.830145094925287,
|
| 973 |
+
"grad_norm": 0.018528884276747704,
|
| 974 |
+
"learning_rate": 1.446786496306456e-05,
|
| 975 |
+
"loss": 0.2929,
|
| 976 |
+
"step": 69000
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.8361606390914122,
|
| 980 |
+
"grad_norm": 2.7401936054229736,
|
| 981 |
+
"learning_rate": 1.4427761335290392e-05,
|
| 982 |
+
"loss": 0.272,
|
| 983 |
+
"step": 69500
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8421761832575375,
|
| 987 |
+
"grad_norm": 0.07152987271547318,
|
| 988 |
+
"learning_rate": 1.4387657707516223e-05,
|
| 989 |
+
"loss": 0.3162,
|
| 990 |
+
"step": 70000
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8481917274236628,
|
| 994 |
+
"grad_norm": 5.40221643447876,
|
| 995 |
+
"learning_rate": 1.4347634286997603e-05,
|
| 996 |
+
"loss": 0.2717,
|
| 997 |
+
"step": 70500
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.854207271589788,
|
| 1001 |
+
"grad_norm": 2.5662572383880615,
|
| 1002 |
+
"learning_rate": 1.4307530659223434e-05,
|
| 1003 |
+
"loss": 0.2913,
|
| 1004 |
+
"step": 71000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.8602228157559133,
|
| 1008 |
+
"grad_norm": 6.399110794067383,
|
| 1009 |
+
"learning_rate": 1.4267427031449267e-05,
|
| 1010 |
+
"loss": 0.279,
|
| 1011 |
+
"step": 71500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.8662383599220386,
|
| 1015 |
+
"grad_norm": 4.513882160186768,
|
| 1016 |
+
"learning_rate": 1.4227323403675098e-05,
|
| 1017 |
+
"loss": 0.3091,
|
| 1018 |
+
"step": 72000
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.8722539040881638,
|
| 1022 |
+
"grad_norm": 2.024488925933838,
|
| 1023 |
+
"learning_rate": 1.4187219775900929e-05,
|
| 1024 |
+
"loss": 0.2831,
|
| 1025 |
+
"step": 72500
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.8782694482542891,
|
| 1029 |
+
"grad_norm": 9.901945114135742,
|
| 1030 |
+
"learning_rate": 1.4147116148126761e-05,
|
| 1031 |
+
"loss": 0.2863,
|
| 1032 |
+
"step": 73000
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.8842849924204144,
|
| 1036 |
+
"grad_norm": 1.1856168508529663,
|
| 1037 |
+
"learning_rate": 1.410709272760814e-05,
|
| 1038 |
+
"loss": 0.2754,
|
| 1039 |
+
"step": 73500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.8903005365865396,
|
| 1043 |
+
"grad_norm": 4.077794075012207,
|
| 1044 |
+
"learning_rate": 1.4066989099833972e-05,
|
| 1045 |
+
"loss": 0.298,
|
| 1046 |
+
"step": 74000
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.8963160807526649,
|
| 1050 |
+
"grad_norm": 0.2611056864261627,
|
| 1051 |
+
"learning_rate": 1.4026885472059803e-05,
|
| 1052 |
+
"loss": 0.2985,
|
| 1053 |
+
"step": 74500
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.9023316249187902,
|
| 1057 |
+
"grad_norm": 0.1290031224489212,
|
| 1058 |
+
"learning_rate": 1.3986781844285636e-05,
|
| 1059 |
+
"loss": 0.2798,
|
| 1060 |
+
"step": 75000
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.9083471690849154,
|
| 1064 |
+
"grad_norm": 0.1582382321357727,
|
| 1065 |
+
"learning_rate": 1.3946678216511467e-05,
|
| 1066 |
+
"loss": 0.2908,
|
| 1067 |
+
"step": 75500
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.9143627132510407,
|
| 1071 |
+
"grad_norm": 6.692793369293213,
|
| 1072 |
+
"learning_rate": 1.3906574588737298e-05,
|
| 1073 |
+
"loss": 0.2905,
|
| 1074 |
+
"step": 76000
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.920378257417166,
|
| 1078 |
+
"grad_norm": 12.920578002929688,
|
| 1079 |
+
"learning_rate": 1.386647096096313e-05,
|
| 1080 |
+
"loss": 0.306,
|
| 1081 |
+
"step": 76500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.9263938015832912,
|
| 1085 |
+
"grad_norm": 0.14715702831745148,
|
| 1086 |
+
"learning_rate": 1.3826367333188961e-05,
|
| 1087 |
+
"loss": 0.2911,
|
| 1088 |
+
"step": 77000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.9324093457494165,
|
| 1092 |
+
"grad_norm": 7.250746726989746,
|
| 1093 |
+
"learning_rate": 1.3786343912670342e-05,
|
| 1094 |
+
"loss": 0.2911,
|
| 1095 |
+
"step": 77500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.9384248899155417,
|
| 1099 |
+
"grad_norm": 9.904165267944336,
|
| 1100 |
+
"learning_rate": 1.3746240284896173e-05,
|
| 1101 |
+
"loss": 0.2893,
|
| 1102 |
+
"step": 78000
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.944440434081667,
|
| 1106 |
+
"grad_norm": 1.3197027444839478,
|
| 1107 |
+
"learning_rate": 1.3706136657122005e-05,
|
| 1108 |
+
"loss": 0.295,
|
| 1109 |
+
"step": 78500
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.9504559782477923,
|
| 1113 |
+
"grad_norm": 0.5488787889480591,
|
| 1114 |
+
"learning_rate": 1.3666033029347836e-05,
|
| 1115 |
+
"loss": 0.2617,
|
| 1116 |
+
"step": 79000
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.9564715224139175,
|
| 1120 |
+
"grad_norm": 0.007599683478474617,
|
| 1121 |
+
"learning_rate": 1.3625929401573667e-05,
|
| 1122 |
+
"loss": 0.2874,
|
| 1123 |
+
"step": 79500
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.9624870665800428,
|
| 1127 |
+
"grad_norm": 28.689912796020508,
|
| 1128 |
+
"learning_rate": 1.35858257737995e-05,
|
| 1129 |
+
"loss": 0.2954,
|
| 1130 |
+
"step": 80000
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.9685026107461681,
|
| 1134 |
+
"grad_norm": 1.1681454181671143,
|
| 1135 |
+
"learning_rate": 1.354572214602533e-05,
|
| 1136 |
+
"loss": 0.2893,
|
| 1137 |
+
"step": 80500
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.9745181549122933,
|
| 1141 |
+
"grad_norm": 26.251056671142578,
|
| 1142 |
+
"learning_rate": 1.3505618518251162e-05,
|
| 1143 |
+
"loss": 0.2771,
|
| 1144 |
+
"step": 81000
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.9805336990784186,
|
| 1148 |
+
"grad_norm": 19.04422950744629,
|
| 1149 |
+
"learning_rate": 1.3465514890476994e-05,
|
| 1150 |
+
"loss": 0.2556,
|
| 1151 |
+
"step": 81500
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.9865492432445438,
|
| 1155 |
+
"grad_norm": 6.7204909324646,
|
| 1156 |
+
"learning_rate": 1.3425411262702825e-05,
|
| 1157 |
+
"loss": 0.2999,
|
| 1158 |
+
"step": 82000
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.9925647874106691,
|
| 1162 |
+
"grad_norm": 0.3453606069087982,
|
| 1163 |
+
"learning_rate": 1.3385307634928656e-05,
|
| 1164 |
+
"loss": 0.2795,
|
| 1165 |
+
"step": 82500
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.9985803315767945,
|
| 1169 |
+
"grad_norm": 2.7078826427459717,
|
| 1170 |
+
"learning_rate": 1.3345204007154489e-05,
|
| 1171 |
+
"loss": 0.2727,
|
| 1172 |
+
"step": 83000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.0,
|
| 1176 |
+
"eval_accuracy": 0.6738478320152713,
|
| 1177 |
+
"eval_f1": 0.69947127247092,
|
| 1178 |
+
"eval_loss": 0.287530779838562,
|
| 1179 |
+
"eval_roc_auc": 0.8124488682847013,
|
| 1180 |
+
"eval_runtime": 111.0668,
|
| 1181 |
+
"eval_samples_per_second": 66.032,
|
| 1182 |
+
"eval_steps_per_second": 66.032,
|
| 1183 |
+
"step": 83118
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 1.0045958757429196,
|
| 1187 |
+
"grad_norm": 8.754840850830078,
|
| 1188 |
+
"learning_rate": 1.3305180586635869e-05,
|
| 1189 |
+
"loss": 0.2439,
|
| 1190 |
+
"step": 83500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 1.010611419909045,
|
| 1194 |
+
"grad_norm": 23.18345069885254,
|
| 1195 |
+
"learning_rate": 1.3265237373372797e-05,
|
| 1196 |
+
"loss": 0.2343,
|
| 1197 |
+
"step": 84000
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 1.0166269640751702,
|
| 1201 |
+
"grad_norm": 0.2795548141002655,
|
| 1202 |
+
"learning_rate": 1.322513374559863e-05,
|
| 1203 |
+
"loss": 0.2591,
|
| 1204 |
+
"step": 84500
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 1.0226425082412955,
|
| 1208 |
+
"grad_norm": 23.055418014526367,
|
| 1209 |
+
"learning_rate": 1.318503011782446e-05,
|
| 1210 |
+
"loss": 0.2403,
|
| 1211 |
+
"step": 85000
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 1.0286580524074207,
|
| 1215 |
+
"grad_norm": 0.0004251549835316837,
|
| 1216 |
+
"learning_rate": 1.3144926490050291e-05,
|
| 1217 |
+
"loss": 0.2575,
|
| 1218 |
+
"step": 85500
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 1.034673596573546,
|
| 1222 |
+
"grad_norm": 0.0705941691994667,
|
| 1223 |
+
"learning_rate": 1.3104822862276124e-05,
|
| 1224 |
+
"loss": 0.2298,
|
| 1225 |
+
"step": 86000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 1.0406891407396712,
|
| 1229 |
+
"grad_norm": 0.14872965216636658,
|
| 1230 |
+
"learning_rate": 1.3064719234501955e-05,
|
| 1231 |
+
"loss": 0.2556,
|
| 1232 |
+
"step": 86500
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.0467046849057966,
|
| 1236 |
+
"grad_norm": 29.70933723449707,
|
| 1237 |
+
"learning_rate": 1.3024615606727786e-05,
|
| 1238 |
+
"loss": 0.246,
|
| 1239 |
+
"step": 87000
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 1.0527202290719218,
|
| 1243 |
+
"grad_norm": 0.12189821898937225,
|
| 1244 |
+
"learning_rate": 1.2984511978953618e-05,
|
| 1245 |
+
"loss": 0.2486,
|
| 1246 |
+
"step": 87500
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.0587357732380471,
|
| 1250 |
+
"grad_norm": 16.819997787475586,
|
| 1251 |
+
"learning_rate": 1.2944488558434999e-05,
|
| 1252 |
+
"loss": 0.2738,
|
| 1253 |
+
"step": 88000
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 1.0647513174041723,
|
| 1257 |
+
"grad_norm": 0.504358172416687,
|
| 1258 |
+
"learning_rate": 1.290438493066083e-05,
|
| 1259 |
+
"loss": 0.2512,
|
| 1260 |
+
"step": 88500
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 1.0707668615702977,
|
| 1264 |
+
"grad_norm": 33.048221588134766,
|
| 1265 |
+
"learning_rate": 1.286428130288666e-05,
|
| 1266 |
+
"loss": 0.2464,
|
| 1267 |
+
"step": 89000
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 1.0767824057364228,
|
| 1271 |
+
"grad_norm": 10.764643669128418,
|
| 1272 |
+
"learning_rate": 1.2824177675112493e-05,
|
| 1273 |
+
"loss": 0.2633,
|
| 1274 |
+
"step": 89500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 1.0827979499025482,
|
| 1278 |
+
"grad_norm": 0.08640070259571075,
|
| 1279 |
+
"learning_rate": 1.2784074047338324e-05,
|
| 1280 |
+
"loss": 0.2406,
|
| 1281 |
+
"step": 90000
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.0888134940686736,
|
| 1285 |
+
"grad_norm": 14.491482734680176,
|
| 1286 |
+
"learning_rate": 1.2744050626819704e-05,
|
| 1287 |
+
"loss": 0.2914,
|
| 1288 |
+
"step": 90500
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.0948290382347987,
|
| 1292 |
+
"grad_norm": 6.458908557891846,
|
| 1293 |
+
"learning_rate": 1.2703946999045535e-05,
|
| 1294 |
+
"loss": 0.2768,
|
| 1295 |
+
"step": 91000
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 1.100844582400924,
|
| 1299 |
+
"grad_norm": 3.36252498626709,
|
| 1300 |
+
"learning_rate": 1.2663923578526915e-05,
|
| 1301 |
+
"loss": 0.2275,
|
| 1302 |
+
"step": 91500
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 1.1068601265670492,
|
| 1306 |
+
"grad_norm": 7.332001209259033,
|
| 1307 |
+
"learning_rate": 1.2623819950752746e-05,
|
| 1308 |
+
"loss": 0.2561,
|
| 1309 |
+
"step": 92000
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 1.1128756707331746,
|
| 1313 |
+
"grad_norm": 0.10880118608474731,
|
| 1314 |
+
"learning_rate": 1.2583796530234126e-05,
|
| 1315 |
+
"loss": 0.26,
|
| 1316 |
+
"step": 92500
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 1.1188912148992998,
|
| 1320 |
+
"grad_norm": 0.041975826025009155,
|
| 1321 |
+
"learning_rate": 1.2543692902459959e-05,
|
| 1322 |
+
"loss": 0.2588,
|
| 1323 |
+
"step": 93000
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 1.1249067590654251,
|
| 1327 |
+
"grad_norm": 19.071786880493164,
|
| 1328 |
+
"learning_rate": 1.250358927468579e-05,
|
| 1329 |
+
"loss": 0.2537,
|
| 1330 |
+
"step": 93500
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.1309223032315503,
|
| 1334 |
+
"grad_norm": 0.5620952248573303,
|
| 1335 |
+
"learning_rate": 1.2463485646911621e-05,
|
| 1336 |
+
"loss": 0.2694,
|
| 1337 |
+
"step": 94000
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.1369378473976757,
|
| 1341 |
+
"grad_norm": 0.4685472548007965,
|
| 1342 |
+
"learning_rate": 1.2423382019137454e-05,
|
| 1343 |
+
"loss": 0.2255,
|
| 1344 |
+
"step": 94500
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 1.1429533915638008,
|
| 1348 |
+
"grad_norm": 0.004374380223453045,
|
| 1349 |
+
"learning_rate": 1.2383278391363285e-05,
|
| 1350 |
+
"loss": 0.2979,
|
| 1351 |
+
"step": 95000
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 1.1489689357299262,
|
| 1355 |
+
"grad_norm": 0.21592481434345245,
|
| 1356 |
+
"learning_rate": 1.2343174763589117e-05,
|
| 1357 |
+
"loss": 0.2425,
|
| 1358 |
+
"step": 95500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 1.1549844798960514,
|
| 1362 |
+
"grad_norm": 38.64509963989258,
|
| 1363 |
+
"learning_rate": 1.2303071135814946e-05,
|
| 1364 |
+
"loss": 0.2534,
|
| 1365 |
+
"step": 96000
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 1.1610000240621767,
|
| 1369 |
+
"grad_norm": 0.1709357500076294,
|
| 1370 |
+
"learning_rate": 1.2262967508040777e-05,
|
| 1371 |
+
"loss": 0.2277,
|
| 1372 |
+
"step": 96500
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 1.1670155682283019,
|
| 1376 |
+
"grad_norm": 0.02226692996919155,
|
| 1377 |
+
"learning_rate": 1.2222863880266608e-05,
|
| 1378 |
+
"loss": 0.248,
|
| 1379 |
+
"step": 97000
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 1.1730311123944273,
|
| 1383 |
+
"grad_norm": 0.11720846593379974,
|
| 1384 |
+
"learning_rate": 1.2182760252492441e-05,
|
| 1385 |
+
"loss": 0.2818,
|
| 1386 |
+
"step": 97500
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 1.1790466565605524,
|
| 1390 |
+
"grad_norm": 0.17743727564811707,
|
| 1391 |
+
"learning_rate": 1.2142656624718272e-05,
|
| 1392 |
+
"loss": 0.2625,
|
| 1393 |
+
"step": 98000
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.1850622007266778,
|
| 1397 |
+
"grad_norm": 0.5575046539306641,
|
| 1398 |
+
"learning_rate": 1.2102633204199652e-05,
|
| 1399 |
+
"loss": 0.274,
|
| 1400 |
+
"step": 98500
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 1.191077744892803,
|
| 1404 |
+
"grad_norm": 0.0813954770565033,
|
| 1405 |
+
"learning_rate": 1.2062529576425483e-05,
|
| 1406 |
+
"loss": 0.2764,
|
| 1407 |
+
"step": 99000
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 1.1970932890589283,
|
| 1411 |
+
"grad_norm": 6.563291549682617,
|
| 1412 |
+
"learning_rate": 1.2022425948651316e-05,
|
| 1413 |
+
"loss": 0.2426,
|
| 1414 |
+
"step": 99500
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 1.2031088332250535,
|
| 1418 |
+
"grad_norm": 4.957773126079701e-05,
|
| 1419 |
+
"learning_rate": 1.1982322320877147e-05,
|
| 1420 |
+
"loss": 0.2558,
|
| 1421 |
+
"step": 100000
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 1.2091243773911788,
|
| 1425 |
+
"grad_norm": 0.08407856523990631,
|
| 1426 |
+
"learning_rate": 1.1942218693102978e-05,
|
| 1427 |
+
"loss": 0.244,
|
| 1428 |
+
"step": 100500
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 1.215139921557304,
|
| 1432 |
+
"grad_norm": 0.04238196834921837,
|
| 1433 |
+
"learning_rate": 1.1902195272584358e-05,
|
| 1434 |
+
"loss": 0.2635,
|
| 1435 |
+
"step": 101000
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 1.2211554657234294,
|
| 1439 |
+
"grad_norm": 0.10858649015426636,
|
| 1440 |
+
"learning_rate": 1.186209164481019e-05,
|
| 1441 |
+
"loss": 0.2536,
|
| 1442 |
+
"step": 101500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.2271710098895545,
|
| 1446 |
+
"grad_norm": 0.14419694244861603,
|
| 1447 |
+
"learning_rate": 1.1821988017036021e-05,
|
| 1448 |
+
"loss": 0.2803,
|
| 1449 |
+
"step": 102000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.23318655405568,
|
| 1453 |
+
"grad_norm": 0.1416100561618805,
|
| 1454 |
+
"learning_rate": 1.1781964596517402e-05,
|
| 1455 |
+
"loss": 0.2198,
|
| 1456 |
+
"step": 102500
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 1.239202098221805,
|
| 1460 |
+
"grad_norm": 0.16191110014915466,
|
| 1461 |
+
"learning_rate": 1.1741860968743232e-05,
|
| 1462 |
+
"loss": 0.2687,
|
| 1463 |
+
"step": 103000
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 1.2452176423879304,
|
| 1467 |
+
"grad_norm": 3.2424659729003906,
|
| 1468 |
+
"learning_rate": 1.1701757340969065e-05,
|
| 1469 |
+
"loss": 0.2531,
|
| 1470 |
+
"step": 103500
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 1.2512331865540558,
|
| 1474 |
+
"grad_norm": 0.009034248068928719,
|
| 1475 |
+
"learning_rate": 1.1661653713194896e-05,
|
| 1476 |
+
"loss": 0.2144,
|
| 1477 |
+
"step": 104000
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 1.257248730720181,
|
| 1481 |
+
"grad_norm": 4.68690299987793,
|
| 1482 |
+
"learning_rate": 1.1621550085420727e-05,
|
| 1483 |
+
"loss": 0.2536,
|
| 1484 |
+
"step": 104500
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 1.263264274886306,
|
| 1488 |
+
"grad_norm": 0.04760544002056122,
|
| 1489 |
+
"learning_rate": 1.158144645764656e-05,
|
| 1490 |
+
"loss": 0.2394,
|
| 1491 |
+
"step": 105000
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 1.2692798190524315,
|
| 1495 |
+
"grad_norm": 0.027170976623892784,
|
| 1496 |
+
"learning_rate": 1.154134282987239e-05,
|
| 1497 |
+
"loss": 0.2644,
|
| 1498 |
+
"step": 105500
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.2752953632185569,
|
| 1502 |
+
"grad_norm": 29.608776092529297,
|
| 1503 |
+
"learning_rate": 1.1501239202098222e-05,
|
| 1504 |
+
"loss": 0.2456,
|
| 1505 |
+
"step": 106000
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.281310907384682,
|
| 1509 |
+
"grad_norm": 3.261889934539795,
|
| 1510 |
+
"learning_rate": 1.1461135574324054e-05,
|
| 1511 |
+
"loss": 0.2182,
|
| 1512 |
+
"step": 106500
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 1.2873264515508072,
|
| 1516 |
+
"grad_norm": 0.0033520832657814026,
|
| 1517 |
+
"learning_rate": 1.1421031946549885e-05,
|
| 1518 |
+
"loss": 0.2612,
|
| 1519 |
+
"step": 107000
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 1.2933419957169325,
|
| 1523 |
+
"grad_norm": 0.0770372673869133,
|
| 1524 |
+
"learning_rate": 1.1380928318775716e-05,
|
| 1525 |
+
"loss": 0.2517,
|
| 1526 |
+
"step": 107500
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 1.299357539883058,
|
| 1530 |
+
"grad_norm": 0.004508438985794783,
|
| 1531 |
+
"learning_rate": 1.1340904898257096e-05,
|
| 1532 |
+
"loss": 0.2552,
|
| 1533 |
+
"step": 108000
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 1.305373084049183,
|
| 1537 |
+
"grad_norm": 0.05816527456045151,
|
| 1538 |
+
"learning_rate": 1.1300801270482929e-05,
|
| 1539 |
+
"loss": 0.2577,
|
| 1540 |
+
"step": 108500
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 1.3113886282153084,
|
| 1544 |
+
"grad_norm": 8.914427757263184,
|
| 1545 |
+
"learning_rate": 1.126069764270876e-05,
|
| 1546 |
+
"loss": 0.2177,
|
| 1547 |
+
"step": 109000
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 1.3174041723814336,
|
| 1551 |
+
"grad_norm": 0.0006245987024158239,
|
| 1552 |
+
"learning_rate": 1.1220594014934591e-05,
|
| 1553 |
+
"loss": 0.2321,
|
| 1554 |
+
"step": 109500
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.323419716547559,
|
| 1558 |
+
"grad_norm": 10.717325210571289,
|
| 1559 |
+
"learning_rate": 1.1180490387160424e-05,
|
| 1560 |
+
"loss": 0.2532,
|
| 1561 |
+
"step": 110000
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 1.3294352607136841,
|
| 1565 |
+
"grad_norm": 3.988328218460083,
|
| 1566 |
+
"learning_rate": 1.1140386759386255e-05,
|
| 1567 |
+
"loss": 0.2733,
|
| 1568 |
+
"step": 110500
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 1.3354508048798095,
|
| 1572 |
+
"grad_norm": 9.221200942993164,
|
| 1573 |
+
"learning_rate": 1.1100363338867635e-05,
|
| 1574 |
+
"loss": 0.2611,
|
| 1575 |
+
"step": 111000
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 1.3414663490459346,
|
| 1579 |
+
"grad_norm": 0.08797607570886612,
|
| 1580 |
+
"learning_rate": 1.1060259711093466e-05,
|
| 1581 |
+
"loss": 0.2608,
|
| 1582 |
+
"step": 111500
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 1.34748189321206,
|
| 1586 |
+
"grad_norm": 0.018298862501978874,
|
| 1587 |
+
"learning_rate": 1.1020156083319298e-05,
|
| 1588 |
+
"loss": 0.2579,
|
| 1589 |
+
"step": 112000
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 1.3534974373781852,
|
| 1593 |
+
"grad_norm": 0.033742956817150116,
|
| 1594 |
+
"learning_rate": 1.098005245554513e-05,
|
| 1595 |
+
"loss": 0.2431,
|
| 1596 |
+
"step": 112500
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 1.3595129815443106,
|
| 1600 |
+
"grad_norm": 0.06899914145469666,
|
| 1601 |
+
"learning_rate": 1.093994882777096e-05,
|
| 1602 |
+
"loss": 0.253,
|
| 1603 |
+
"step": 113000
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 1.3655285257104357,
|
| 1607 |
+
"grad_norm": 0.1469135880470276,
|
| 1608 |
+
"learning_rate": 1.0899845199996793e-05,
|
| 1609 |
+
"loss": 0.244,
|
| 1610 |
+
"step": 113500
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.371544069876561,
|
| 1614 |
+
"grad_norm": 5.18328857421875,
|
| 1615 |
+
"learning_rate": 1.0859821779478173e-05,
|
| 1616 |
+
"loss": 0.2654,
|
| 1617 |
+
"step": 114000
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 1.3775596140426862,
|
| 1621 |
+
"grad_norm": 24.231332778930664,
|
| 1622 |
+
"learning_rate": 1.0819718151704004e-05,
|
| 1623 |
+
"loss": 0.237,
|
| 1624 |
+
"step": 114500
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 1.3835751582088116,
|
| 1628 |
+
"grad_norm": 0.2826213240623474,
|
| 1629 |
+
"learning_rate": 1.0779614523929835e-05,
|
| 1630 |
+
"loss": 0.2602,
|
| 1631 |
+
"step": 115000
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 1.3895907023749368,
|
| 1635 |
+
"grad_norm": 0.09144386649131775,
|
| 1636 |
+
"learning_rate": 1.0739510896155668e-05,
|
| 1637 |
+
"loss": 0.249,
|
| 1638 |
+
"step": 115500
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 1.3956062465410621,
|
| 1642 |
+
"grad_norm": 40.423797607421875,
|
| 1643 |
+
"learning_rate": 1.0699407268381499e-05,
|
| 1644 |
+
"loss": 0.2621,
|
| 1645 |
+
"step": 116000
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 1.4016217907071873,
|
| 1649 |
+
"grad_norm": 0.01249714009463787,
|
| 1650 |
+
"learning_rate": 1.0659383847862879e-05,
|
| 1651 |
+
"loss": 0.2451,
|
| 1652 |
+
"step": 116500
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 1.4076373348733127,
|
| 1656 |
+
"grad_norm": 0.14570143818855286,
|
| 1657 |
+
"learning_rate": 1.061928022008871e-05,
|
| 1658 |
+
"loss": 0.2481,
|
| 1659 |
+
"step": 117000
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 1.413652879039438,
|
| 1663 |
+
"grad_norm": 8.342629432678223,
|
| 1664 |
+
"learning_rate": 1.0579176592314542e-05,
|
| 1665 |
+
"loss": 0.2813,
|
| 1666 |
+
"step": 117500
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.4196684232055632,
|
| 1670 |
+
"grad_norm": 0.0001358153240289539,
|
| 1671 |
+
"learning_rate": 1.0539072964540373e-05,
|
| 1672 |
+
"loss": 0.2425,
|
| 1673 |
+
"step": 118000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 1.4256839673716883,
|
| 1677 |
+
"grad_norm": 0.2505891025066376,
|
| 1678 |
+
"learning_rate": 1.0498969336766204e-05,
|
| 1679 |
+
"loss": 0.243,
|
| 1680 |
+
"step": 118500
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 1.4316995115378137,
|
| 1684 |
+
"grad_norm": 0.25133442878723145,
|
| 1685 |
+
"learning_rate": 1.0458865708992037e-05,
|
| 1686 |
+
"loss": 0.2313,
|
| 1687 |
+
"step": 119000
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 1.437715055703939,
|
| 1691 |
+
"grad_norm": 0.00044232659274712205,
|
| 1692 |
+
"learning_rate": 1.0418762081217868e-05,
|
| 1693 |
+
"loss": 0.2426,
|
| 1694 |
+
"step": 119500
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 1.4437305998700642,
|
| 1698 |
+
"grad_norm": 0.0011125517776235938,
|
| 1699 |
+
"learning_rate": 1.0378658453443699e-05,
|
| 1700 |
+
"loss": 0.2418,
|
| 1701 |
+
"step": 120000
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 1.4497461440361894,
|
| 1705 |
+
"grad_norm": 7.526780605316162,
|
| 1706 |
+
"learning_rate": 1.0338635032925079e-05,
|
| 1707 |
+
"loss": 0.2797,
|
| 1708 |
+
"step": 120500
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 1.4557616882023148,
|
| 1712 |
+
"grad_norm": 6.034137725830078,
|
| 1713 |
+
"learning_rate": 1.0298531405150912e-05,
|
| 1714 |
+
"loss": 0.2655,
|
| 1715 |
+
"step": 121000
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 1.4617772323684401,
|
| 1719 |
+
"grad_norm": 0.021329816430807114,
|
| 1720 |
+
"learning_rate": 1.0258427777376743e-05,
|
| 1721 |
+
"loss": 0.2633,
|
| 1722 |
+
"step": 121500
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.4677927765345653,
|
| 1726 |
+
"grad_norm": 0.013099109753966331,
|
| 1727 |
+
"learning_rate": 1.0218324149602574e-05,
|
| 1728 |
+
"loss": 0.2739,
|
| 1729 |
+
"step": 122000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 1.4738083207006905,
|
| 1733 |
+
"grad_norm": 71.02497863769531,
|
| 1734 |
+
"learning_rate": 1.0178300729083954e-05,
|
| 1735 |
+
"loss": 0.254,
|
| 1736 |
+
"step": 122500
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 1.4798238648668158,
|
| 1740 |
+
"grad_norm": 15.551078796386719,
|
| 1741 |
+
"learning_rate": 1.0138197101309786e-05,
|
| 1742 |
+
"loss": 0.2602,
|
| 1743 |
+
"step": 123000
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 1.4858394090329412,
|
| 1747 |
+
"grad_norm": 4.560909655992873e-05,
|
| 1748 |
+
"learning_rate": 1.0098093473535617e-05,
|
| 1749 |
+
"loss": 0.2387,
|
| 1750 |
+
"step": 123500
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 1.4918549531990664,
|
| 1754 |
+
"grad_norm": 0.14415931701660156,
|
| 1755 |
+
"learning_rate": 1.0057989845761448e-05,
|
| 1756 |
+
"loss": 0.2823,
|
| 1757 |
+
"step": 124000
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 1.4978704973651917,
|
| 1761 |
+
"grad_norm": 43.61802673339844,
|
| 1762 |
+
"learning_rate": 1.0017886217987281e-05,
|
| 1763 |
+
"loss": 0.2378,
|
| 1764 |
+
"step": 124500
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 1.5038860415313169,
|
| 1768 |
+
"grad_norm": 0.20755548775196075,
|
| 1769 |
+
"learning_rate": 9.977782590213112e-06,
|
| 1770 |
+
"loss": 0.2433,
|
| 1771 |
+
"step": 125000
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 1.5099015856974423,
|
| 1775 |
+
"grad_norm": 0.2520395815372467,
|
| 1776 |
+
"learning_rate": 9.937678962438943e-06,
|
| 1777 |
+
"loss": 0.2539,
|
| 1778 |
+
"step": 125500
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.5159171298635674,
|
| 1782 |
+
"grad_norm": 0.3743610382080078,
|
| 1783 |
+
"learning_rate": 9.897575334664774e-06,
|
| 1784 |
+
"loss": 0.2789,
|
| 1785 |
+
"step": 126000
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 1.5219326740296926,
|
| 1789 |
+
"grad_norm": 0.0024790179450064898,
|
| 1790 |
+
"learning_rate": 9.857551914146154e-06,
|
| 1791 |
+
"loss": 0.2258,
|
| 1792 |
+
"step": 126500
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 1.527948218195818,
|
| 1796 |
+
"grad_norm": 21.557737350463867,
|
| 1797 |
+
"learning_rate": 9.817448286371985e-06,
|
| 1798 |
+
"loss": 0.2692,
|
| 1799 |
+
"step": 127000
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"epoch": 1.5339637623619433,
|
| 1803 |
+
"grad_norm": 0.00022073234140407294,
|
| 1804 |
+
"learning_rate": 9.777344658597818e-06,
|
| 1805 |
+
"loss": 0.2674,
|
| 1806 |
+
"step": 127500
|
| 1807 |
+
},
|
| 1808 |
+
{
|
| 1809 |
+
"epoch": 1.5399793065280685,
|
| 1810 |
+
"grad_norm": 0.0013155222404748201,
|
| 1811 |
+
"learning_rate": 9.737241030823649e-06,
|
| 1812 |
+
"loss": 0.242,
|
| 1813 |
+
"step": 128000
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 1.5459948506941938,
|
| 1817 |
+
"grad_norm": 0.2000940591096878,
|
| 1818 |
+
"learning_rate": 9.69713740304948e-06,
|
| 1819 |
+
"loss": 0.2487,
|
| 1820 |
+
"step": 128500
|
| 1821 |
+
},
|
| 1822 |
+
{
|
| 1823 |
+
"epoch": 1.5520103948603192,
|
| 1824 |
+
"grad_norm": 0.0021518643479794264,
|
| 1825 |
+
"learning_rate": 9.657033775275312e-06,
|
| 1826 |
+
"loss": 0.2123,
|
| 1827 |
+
"step": 129000
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 1.5580259390264444,
|
| 1831 |
+
"grad_norm": 0.24494774639606476,
|
| 1832 |
+
"learning_rate": 9.616930147501143e-06,
|
| 1833 |
+
"loss": 0.2975,
|
| 1834 |
+
"step": 129500
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.5640414831925695,
|
| 1838 |
+
"grad_norm": 9.558631896972656,
|
| 1839 |
+
"learning_rate": 9.576906726982523e-06,
|
| 1840 |
+
"loss": 0.2485,
|
| 1841 |
+
"step": 130000
|
| 1842 |
+
},
|
| 1843 |
+
{
|
| 1844 |
+
"epoch": 1.570057027358695,
|
| 1845 |
+
"grad_norm": 6.8279128074646,
|
| 1846 |
+
"learning_rate": 9.536803099208354e-06,
|
| 1847 |
+
"loss": 0.2589,
|
| 1848 |
+
"step": 130500
|
| 1849 |
+
},
|
| 1850 |
+
{
|
| 1851 |
+
"epoch": 1.5760725715248203,
|
| 1852 |
+
"grad_norm": 0.018290262669324875,
|
| 1853 |
+
"learning_rate": 9.496699471434187e-06,
|
| 1854 |
+
"loss": 0.2605,
|
| 1855 |
+
"step": 131000
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 1.5820881156909454,
|
| 1859 |
+
"grad_norm": 0.19554129242897034,
|
| 1860 |
+
"learning_rate": 9.456595843660018e-06,
|
| 1861 |
+
"loss": 0.2405,
|
| 1862 |
+
"step": 131500
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 1.5881036598570706,
|
| 1866 |
+
"grad_norm": 26.12983512878418,
|
| 1867 |
+
"learning_rate": 9.416492215885849e-06,
|
| 1868 |
+
"loss": 0.2261,
|
| 1869 |
+
"step": 132000
|
| 1870 |
+
},
|
| 1871 |
+
{
|
| 1872 |
+
"epoch": 1.594119204023196,
|
| 1873 |
+
"grad_norm": 19.12807273864746,
|
| 1874 |
+
"learning_rate": 9.376388588111682e-06,
|
| 1875 |
+
"loss": 0.2454,
|
| 1876 |
+
"step": 132500
|
| 1877 |
+
},
|
| 1878 |
+
{
|
| 1879 |
+
"epoch": 1.6001347481893213,
|
| 1880 |
+
"grad_norm": 48.97768020629883,
|
| 1881 |
+
"learning_rate": 9.336284960337513e-06,
|
| 1882 |
+
"loss": 0.2488,
|
| 1883 |
+
"step": 133000
|
| 1884 |
+
},
|
| 1885 |
+
{
|
| 1886 |
+
"epoch": 1.6061502923554465,
|
| 1887 |
+
"grad_norm": 0.10775639116764069,
|
| 1888 |
+
"learning_rate": 9.296261539818893e-06,
|
| 1889 |
+
"loss": 0.2712,
|
| 1890 |
+
"step": 133500
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.6121658365215716,
|
| 1894 |
+
"grad_norm": 18.01923942565918,
|
| 1895 |
+
"learning_rate": 9.256157912044724e-06,
|
| 1896 |
+
"loss": 0.2898,
|
| 1897 |
+
"step": 134000
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 1.618181380687697,
|
| 1901 |
+
"grad_norm": 0.057373084127902985,
|
| 1902 |
+
"learning_rate": 9.216054284270556e-06,
|
| 1903 |
+
"loss": 0.2235,
|
| 1904 |
+
"step": 134500
|
| 1905 |
+
},
|
| 1906 |
+
{
|
| 1907 |
+
"epoch": 1.6241969248538224,
|
| 1908 |
+
"grad_norm": 0.0020849681459367275,
|
| 1909 |
+
"learning_rate": 9.175950656496387e-06,
|
| 1910 |
+
"loss": 0.2355,
|
| 1911 |
+
"step": 135000
|
| 1912 |
+
},
|
| 1913 |
+
{
|
| 1914 |
+
"epoch": 1.6302124690199475,
|
| 1915 |
+
"grad_norm": 0.15205715596675873,
|
| 1916 |
+
"learning_rate": 9.135847028722218e-06,
|
| 1917 |
+
"loss": 0.2791,
|
| 1918 |
+
"step": 135500
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 1.6362280131860727,
|
| 1922 |
+
"grad_norm": 0.06727798283100128,
|
| 1923 |
+
"learning_rate": 9.095823608203598e-06,
|
| 1924 |
+
"loss": 0.2412,
|
| 1925 |
+
"step": 136000
|
| 1926 |
+
},
|
| 1927 |
+
{
|
| 1928 |
+
"epoch": 1.642243557352198,
|
| 1929 |
+
"grad_norm": 0.19422870874404907,
|
| 1930 |
+
"learning_rate": 9.055719980429431e-06,
|
| 1931 |
+
"loss": 0.2431,
|
| 1932 |
+
"step": 136500
|
| 1933 |
+
},
|
| 1934 |
+
{
|
| 1935 |
+
"epoch": 1.6482591015183234,
|
| 1936 |
+
"grad_norm": 0.06913313269615173,
|
| 1937 |
+
"learning_rate": 9.015616352655262e-06,
|
| 1938 |
+
"loss": 0.2687,
|
| 1939 |
+
"step": 137000
|
| 1940 |
+
},
|
| 1941 |
+
{
|
| 1942 |
+
"epoch": 1.6542746456844486,
|
| 1943 |
+
"grad_norm": 0.06762461364269257,
|
| 1944 |
+
"learning_rate": 8.975512724881093e-06,
|
| 1945 |
+
"loss": 0.2498,
|
| 1946 |
+
"step": 137500
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.6602901898505737,
|
| 1950 |
+
"grad_norm": 0.1282985806465149,
|
| 1951 |
+
"learning_rate": 8.935409097106926e-06,
|
| 1952 |
+
"loss": 0.2503,
|
| 1953 |
+
"step": 138000
|
| 1954 |
+
},
|
| 1955 |
+
{
|
| 1956 |
+
"epoch": 1.6663057340166991,
|
| 1957 |
+
"grad_norm": 0.6339439153671265,
|
| 1958 |
+
"learning_rate": 8.895305469332756e-06,
|
| 1959 |
+
"loss": 0.2454,
|
| 1960 |
+
"step": 138500
|
| 1961 |
+
},
|
| 1962 |
+
{
|
| 1963 |
+
"epoch": 1.6723212781828245,
|
| 1964 |
+
"grad_norm": 0.15219150483608246,
|
| 1965 |
+
"learning_rate": 8.855201841558587e-06,
|
| 1966 |
+
"loss": 0.2845,
|
| 1967 |
+
"step": 139000
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 1.6783368223489497,
|
| 1971 |
+
"grad_norm": 5.600707054138184,
|
| 1972 |
+
"learning_rate": 8.815178421039968e-06,
|
| 1973 |
+
"loss": 0.2459,
|
| 1974 |
+
"step": 139500
|
| 1975 |
+
},
|
| 1976 |
+
{
|
| 1977 |
+
"epoch": 1.6843523665150748,
|
| 1978 |
+
"grad_norm": 0.36313244700431824,
|
| 1979 |
+
"learning_rate": 8.775155000521348e-06,
|
| 1980 |
+
"loss": 0.2374,
|
| 1981 |
+
"step": 140000
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"epoch": 1.6903679106812002,
|
| 1985 |
+
"grad_norm": 4.401086807250977,
|
| 1986 |
+
"learning_rate": 8.73505137274718e-06,
|
| 1987 |
+
"loss": 0.2425,
|
| 1988 |
+
"step": 140500
|
| 1989 |
+
},
|
| 1990 |
+
{
|
| 1991 |
+
"epoch": 1.6963834548473256,
|
| 1992 |
+
"grad_norm": 0.00033720143255777657,
|
| 1993 |
+
"learning_rate": 8.694947744973011e-06,
|
| 1994 |
+
"loss": 0.2341,
|
| 1995 |
+
"step": 141000
|
| 1996 |
+
},
|
| 1997 |
+
{
|
| 1998 |
+
"epoch": 1.7023989990134507,
|
| 1999 |
+
"grad_norm": 0.0821937769651413,
|
| 2000 |
+
"learning_rate": 8.654844117198842e-06,
|
| 2001 |
+
"loss": 0.2326,
|
| 2002 |
+
"step": 141500
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.7084145431795759,
|
| 2006 |
+
"grad_norm": 0.000721343734767288,
|
| 2007 |
+
"learning_rate": 8.614740489424675e-06,
|
| 2008 |
+
"loss": 0.2553,
|
| 2009 |
+
"step": 142000
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 1.7144300873457012,
|
| 2013 |
+
"grad_norm": 0.3059915602207184,
|
| 2014 |
+
"learning_rate": 8.574636861650506e-06,
|
| 2015 |
+
"loss": 0.2743,
|
| 2016 |
+
"step": 142500
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 1.7204456315118266,
|
| 2020 |
+
"grad_norm": 0.13650359213352203,
|
| 2021 |
+
"learning_rate": 8.534533233876337e-06,
|
| 2022 |
+
"loss": 0.255,
|
| 2023 |
+
"step": 143000
|
| 2024 |
+
},
|
| 2025 |
+
{
|
| 2026 |
+
"epoch": 1.7264611756779518,
|
| 2027 |
+
"grad_norm": 0.16923360526561737,
|
| 2028 |
+
"learning_rate": 8.49442960610217e-06,
|
| 2029 |
+
"loss": 0.2832,
|
| 2030 |
+
"step": 143500
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 1.7324767198440771,
|
| 2034 |
+
"grad_norm": 0.0067064897157251835,
|
| 2035 |
+
"learning_rate": 8.454325978328e-06,
|
| 2036 |
+
"loss": 0.2425,
|
| 2037 |
+
"step": 144000
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 1.7384922640102025,
|
| 2041 |
+
"grad_norm": 0.33390843868255615,
|
| 2042 |
+
"learning_rate": 8.41430255780938e-06,
|
| 2043 |
+
"loss": 0.2577,
|
| 2044 |
+
"step": 144500
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 1.7445078081763277,
|
| 2048 |
+
"grad_norm": 0.11052338778972626,
|
| 2049 |
+
"learning_rate": 8.374198930035212e-06,
|
| 2050 |
+
"loss": 0.253,
|
| 2051 |
+
"step": 145000
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 1.7505233523424528,
|
| 2055 |
+
"grad_norm": 0.06620516628026962,
|
| 2056 |
+
"learning_rate": 8.334095302261042e-06,
|
| 2057 |
+
"loss": 0.2555,
|
| 2058 |
+
"step": 145500
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.7565388965085782,
|
| 2062 |
+
"grad_norm": 0.00559147447347641,
|
| 2063 |
+
"learning_rate": 8.293991674486873e-06,
|
| 2064 |
+
"loss": 0.2387,
|
| 2065 |
+
"step": 146000
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 1.7625544406747036,
|
| 2069 |
+
"grad_norm": 0.1951608508825302,
|
| 2070 |
+
"learning_rate": 8.253888046712706e-06,
|
| 2071 |
+
"loss": 0.2249,
|
| 2072 |
+
"step": 146500
|
| 2073 |
+
},
|
| 2074 |
+
{
|
| 2075 |
+
"epoch": 1.7685699848408287,
|
| 2076 |
+
"grad_norm": 0.16532181203365326,
|
| 2077 |
+
"learning_rate": 8.213784418938537e-06,
|
| 2078 |
+
"loss": 0.2779,
|
| 2079 |
+
"step": 147000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 1.7745855290069539,
|
| 2083 |
+
"grad_norm": 0.024670429527759552,
|
| 2084 |
+
"learning_rate": 8.17368079116437e-06,
|
| 2085 |
+
"loss": 0.24,
|
| 2086 |
+
"step": 147500
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 1.7806010731730793,
|
| 2090 |
+
"grad_norm": 0.7060034275054932,
|
| 2091 |
+
"learning_rate": 8.1335771633902e-06,
|
| 2092 |
+
"loss": 0.2646,
|
| 2093 |
+
"step": 148000
|
| 2094 |
+
},
|
| 2095 |
+
{
|
| 2096 |
+
"epoch": 1.7866166173392046,
|
| 2097 |
+
"grad_norm": 0.16653361916542053,
|
| 2098 |
+
"learning_rate": 8.093473535616032e-06,
|
| 2099 |
+
"loss": 0.2829,
|
| 2100 |
+
"step": 148500
|
| 2101 |
+
},
|
| 2102 |
+
{
|
| 2103 |
+
"epoch": 1.7926321615053298,
|
| 2104 |
+
"grad_norm": 9.015371322631836,
|
| 2105 |
+
"learning_rate": 8.053369907841864e-06,
|
| 2106 |
+
"loss": 0.2465,
|
| 2107 |
+
"step": 149000
|
| 2108 |
+
},
|
| 2109 |
+
{
|
| 2110 |
+
"epoch": 1.798647705671455,
|
| 2111 |
+
"grad_norm": 0.08503203839063644,
|
| 2112 |
+
"learning_rate": 8.013346487323243e-06,
|
| 2113 |
+
"loss": 0.2476,
|
| 2114 |
+
"step": 149500
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.8046632498375803,
|
| 2118 |
+
"grad_norm": 0.31652989983558655,
|
| 2119 |
+
"learning_rate": 7.973242859549075e-06,
|
| 2120 |
+
"loss": 0.2807,
|
| 2121 |
+
"step": 150000
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 1.8106787940037057,
|
| 2125 |
+
"grad_norm": 20.23206329345703,
|
| 2126 |
+
"learning_rate": 7.933139231774906e-06,
|
| 2127 |
+
"loss": 0.2393,
|
| 2128 |
+
"step": 150500
|
| 2129 |
+
},
|
| 2130 |
+
{
|
| 2131 |
+
"epoch": 1.8166943381698308,
|
| 2132 |
+
"grad_norm": 0.0023623614106327295,
|
| 2133 |
+
"learning_rate": 7.893035604000739e-06,
|
| 2134 |
+
"loss": 0.2606,
|
| 2135 |
+
"step": 151000
|
| 2136 |
+
},
|
| 2137 |
+
{
|
| 2138 |
+
"epoch": 1.822709882335956,
|
| 2139 |
+
"grad_norm": 0.0003463963221292943,
|
| 2140 |
+
"learning_rate": 7.85293197622657e-06,
|
| 2141 |
+
"loss": 0.2377,
|
| 2142 |
+
"step": 151500
|
| 2143 |
+
},
|
| 2144 |
+
{
|
| 2145 |
+
"epoch": 1.8287254265020814,
|
| 2146 |
+
"grad_norm": 22.177343368530273,
|
| 2147 |
+
"learning_rate": 7.81290855570795e-06,
|
| 2148 |
+
"loss": 0.225,
|
| 2149 |
+
"step": 152000
|
| 2150 |
+
},
|
| 2151 |
+
{
|
| 2152 |
+
"epoch": 1.8347409706682067,
|
| 2153 |
+
"grad_norm": 0.16396382451057434,
|
| 2154 |
+
"learning_rate": 7.772804927933781e-06,
|
| 2155 |
+
"loss": 0.2749,
|
| 2156 |
+
"step": 152500
|
| 2157 |
+
},
|
| 2158 |
+
{
|
| 2159 |
+
"epoch": 1.840756514834332,
|
| 2160 |
+
"grad_norm": 0.06666311621665955,
|
| 2161 |
+
"learning_rate": 7.732701300159614e-06,
|
| 2162 |
+
"loss": 0.2449,
|
| 2163 |
+
"step": 153000
|
| 2164 |
+
},
|
| 2165 |
+
{
|
| 2166 |
+
"epoch": 1.846772059000457,
|
| 2167 |
+
"grad_norm": 0.2808719575405121,
|
| 2168 |
+
"learning_rate": 7.692597672385445e-06,
|
| 2169 |
+
"loss": 0.2201,
|
| 2170 |
+
"step": 153500
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 1.8527876031665824,
|
| 2174 |
+
"grad_norm": 0.02584654837846756,
|
| 2175 |
+
"learning_rate": 7.652574251866825e-06,
|
| 2176 |
+
"loss": 0.2555,
|
| 2177 |
+
"step": 154000
|
| 2178 |
+
},
|
| 2179 |
+
{
|
| 2180 |
+
"epoch": 1.8588031473327078,
|
| 2181 |
+
"grad_norm": 6.074542999267578,
|
| 2182 |
+
"learning_rate": 7.612470624092656e-06,
|
| 2183 |
+
"loss": 0.2652,
|
| 2184 |
+
"step": 154500
|
| 2185 |
+
},
|
| 2186 |
+
{
|
| 2187 |
+
"epoch": 1.864818691498833,
|
| 2188 |
+
"grad_norm": 0.007166345603764057,
|
| 2189 |
+
"learning_rate": 7.572447203574036e-06,
|
| 2190 |
+
"loss": 0.2777,
|
| 2191 |
+
"step": 155000
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 1.870834235664958,
|
| 2195 |
+
"grad_norm": 2.7224321365356445,
|
| 2196 |
+
"learning_rate": 7.532423783055416e-06,
|
| 2197 |
+
"loss": 0.2614,
|
| 2198 |
+
"step": 155500
|
| 2199 |
+
},
|
| 2200 |
+
{
|
| 2201 |
+
"epoch": 1.8768497798310835,
|
| 2202 |
+
"grad_norm": 8.61175537109375,
|
| 2203 |
+
"learning_rate": 7.492320155281248e-06,
|
| 2204 |
+
"loss": 0.2716,
|
| 2205 |
+
"step": 156000
|
| 2206 |
+
},
|
| 2207 |
+
{
|
| 2208 |
+
"epoch": 1.8828653239972089,
|
| 2209 |
+
"grad_norm": 0.4761998951435089,
|
| 2210 |
+
"learning_rate": 7.452216527507079e-06,
|
| 2211 |
+
"loss": 0.2617,
|
| 2212 |
+
"step": 156500
|
| 2213 |
+
},
|
| 2214 |
+
{
|
| 2215 |
+
"epoch": 1.888880868163334,
|
| 2216 |
+
"grad_norm": 0.041520122438669205,
|
| 2217 |
+
"learning_rate": 7.4121128997329105e-06,
|
| 2218 |
+
"loss": 0.2233,
|
| 2219 |
+
"step": 157000
|
| 2220 |
+
},
|
| 2221 |
+
{
|
| 2222 |
+
"epoch": 1.8948964123294592,
|
| 2223 |
+
"grad_norm": 0.3298840820789337,
|
| 2224 |
+
"learning_rate": 7.372009271958742e-06,
|
| 2225 |
+
"loss": 0.2905,
|
| 2226 |
+
"step": 157500
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 1.9009119564955848,
|
| 2230 |
+
"grad_norm": 0.14137232303619385,
|
| 2231 |
+
"learning_rate": 7.331905644184573e-06,
|
| 2232 |
+
"loss": 0.2489,
|
| 2233 |
+
"step": 158000
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 1.90692750066171,
|
| 2237 |
+
"grad_norm": 0.017581721767783165,
|
| 2238 |
+
"learning_rate": 7.291802016410405e-06,
|
| 2239 |
+
"loss": 0.2531,
|
| 2240 |
+
"step": 158500
|
| 2241 |
+
},
|
| 2242 |
+
{
|
| 2243 |
+
"epoch": 1.912943044827835,
|
| 2244 |
+
"grad_norm": 0.10974815487861633,
|
| 2245 |
+
"learning_rate": 7.251698388636237e-06,
|
| 2246 |
+
"loss": 0.2387,
|
| 2247 |
+
"step": 159000
|
| 2248 |
+
},
|
| 2249 |
+
{
|
| 2250 |
+
"epoch": 1.9189585889939604,
|
| 2251 |
+
"grad_norm": 0.09865211695432663,
|
| 2252 |
+
"learning_rate": 7.211674968117617e-06,
|
| 2253 |
+
"loss": 0.2364,
|
| 2254 |
+
"step": 159500
|
| 2255 |
+
},
|
| 2256 |
+
{
|
| 2257 |
+
"epoch": 1.9249741331600858,
|
| 2258 |
+
"grad_norm": 0.004849567078053951,
|
| 2259 |
+
"learning_rate": 7.171571340343448e-06,
|
| 2260 |
+
"loss": 0.2751,
|
| 2261 |
+
"step": 160000
|
| 2262 |
+
},
|
| 2263 |
+
{
|
| 2264 |
+
"epoch": 1.930989677326211,
|
| 2265 |
+
"grad_norm": 0.017855796962976456,
|
| 2266 |
+
"learning_rate": 7.13146771256928e-06,
|
| 2267 |
+
"loss": 0.2422,
|
| 2268 |
+
"step": 160500
|
| 2269 |
+
},
|
| 2270 |
+
{
|
| 2271 |
+
"epoch": 1.9370052214923361,
|
| 2272 |
+
"grad_norm": 0.22124846279621124,
|
| 2273 |
+
"learning_rate": 7.091364084795112e-06,
|
| 2274 |
+
"loss": 0.2409,
|
| 2275 |
+
"step": 161000
|
| 2276 |
+
},
|
| 2277 |
+
{
|
| 2278 |
+
"epoch": 1.9430207656584615,
|
| 2279 |
+
"grad_norm": 0.0023982899729162455,
|
| 2280 |
+
"learning_rate": 7.051340664276492e-06,
|
| 2281 |
+
"loss": 0.2699,
|
| 2282 |
+
"step": 161500
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 1.9490363098245869,
|
| 2286 |
+
"grad_norm": 8.00629997253418,
|
| 2287 |
+
"learning_rate": 7.011237036502323e-06,
|
| 2288 |
+
"loss": 0.2399,
|
| 2289 |
+
"step": 162000
|
| 2290 |
+
},
|
| 2291 |
+
{
|
| 2292 |
+
"epoch": 1.955051853990712,
|
| 2293 |
+
"grad_norm": 7.468501091003418,
|
| 2294 |
+
"learning_rate": 6.9711334087281545e-06,
|
| 2295 |
+
"loss": 0.2535,
|
| 2296 |
+
"step": 162500
|
| 2297 |
+
},
|
| 2298 |
+
{
|
| 2299 |
+
"epoch": 1.9610673981568372,
|
| 2300 |
+
"grad_norm": 0.4242821931838989,
|
| 2301 |
+
"learning_rate": 6.931029780953986e-06,
|
| 2302 |
+
"loss": 0.2506,
|
| 2303 |
+
"step": 163000
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 1.9670829423229625,
|
| 2307 |
+
"grad_norm": 0.020416131243109703,
|
| 2308 |
+
"learning_rate": 6.890926153179817e-06,
|
| 2309 |
+
"loss": 0.2482,
|
| 2310 |
+
"step": 163500
|
| 2311 |
+
},
|
| 2312 |
+
{
|
| 2313 |
+
"epoch": 1.973098486489088,
|
| 2314 |
+
"grad_norm": 0.06718198210000992,
|
| 2315 |
+
"learning_rate": 6.850822525405649e-06,
|
| 2316 |
+
"loss": 0.2505,
|
| 2317 |
+
"step": 164000
|
| 2318 |
+
},
|
| 2319 |
+
{
|
| 2320 |
+
"epoch": 1.979114030655213,
|
| 2321 |
+
"grad_norm": 0.7040701508522034,
|
| 2322 |
+
"learning_rate": 6.81071889763148e-06,
|
| 2323 |
+
"loss": 0.2196,
|
| 2324 |
+
"step": 164500
|
| 2325 |
+
},
|
| 2326 |
+
{
|
| 2327 |
+
"epoch": 1.9851295748213382,
|
| 2328 |
+
"grad_norm": 0.1061306744813919,
|
| 2329 |
+
"learning_rate": 6.770615269857311e-06,
|
| 2330 |
+
"loss": 0.2699,
|
| 2331 |
+
"step": 165000
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 1.9911451189874636,
|
| 2335 |
+
"grad_norm": 0.1626858115196228,
|
| 2336 |
+
"learning_rate": 6.730511642083143e-06,
|
| 2337 |
+
"loss": 0.2428,
|
| 2338 |
+
"step": 165500
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.997160663153589,
|
| 2342 |
+
"grad_norm": 0.9182321429252625,
|
| 2343 |
+
"learning_rate": 6.690408014308975e-06,
|
| 2344 |
+
"loss": 0.2723,
|
| 2345 |
+
"step": 166000
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 2.0,
|
| 2349 |
+
"eval_accuracy": 0.6772566130351786,
|
| 2350 |
+
"eval_f1": 0.7059909142532652,
|
| 2351 |
+
"eval_loss": 0.30793967843055725,
|
| 2352 |
+
"eval_roc_auc": 0.8147532042541586,
|
| 2353 |
+
"eval_runtime": 109.0185,
|
| 2354 |
+
"eval_samples_per_second": 67.273,
|
| 2355 |
+
"eval_steps_per_second": 67.273,
|
| 2356 |
+
"step": 166236
|
| 2357 |
+
},
|
| 2358 |
+
{
|
| 2359 |
+
"epoch": 2.003176207319714,
|
| 2360 |
+
"grad_norm": 0.0028744570445269346,
|
| 2361 |
+
"learning_rate": 6.650304386534806e-06,
|
| 2362 |
+
"loss": 0.2161,
|
| 2363 |
+
"step": 166500
|
| 2364 |
+
},
|
| 2365 |
+
{
|
| 2366 |
+
"epoch": 2.0091917514858393,
|
| 2367 |
+
"grad_norm": 0.10508907586336136,
|
| 2368 |
+
"learning_rate": 6.6102007587606375e-06,
|
| 2369 |
+
"loss": 0.1802,
|
| 2370 |
+
"step": 167000
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 2.015207295651965,
|
| 2374 |
+
"grad_norm": 0.023608388379216194,
|
| 2375 |
+
"learning_rate": 6.570257545497566e-06,
|
| 2376 |
+
"loss": 0.1646,
|
| 2377 |
+
"step": 167500
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 2.02122283981809,
|
| 2381 |
+
"grad_norm": 0.0004214489890728146,
|
| 2382 |
+
"learning_rate": 6.530153917723398e-06,
|
| 2383 |
+
"loss": 0.1425,
|
| 2384 |
+
"step": 168000
|
| 2385 |
+
},
|
| 2386 |
+
{
|
| 2387 |
+
"epoch": 2.027238383984215,
|
| 2388 |
+
"grad_norm": 0.15282946825027466,
|
| 2389 |
+
"learning_rate": 6.490050289949229e-06,
|
| 2390 |
+
"loss": 0.1767,
|
| 2391 |
+
"step": 168500
|
| 2392 |
+
},
|
| 2393 |
+
{
|
| 2394 |
+
"epoch": 2.0332539281503403,
|
| 2395 |
+
"grad_norm": 0.5594785213470459,
|
| 2396 |
+
"learning_rate": 6.4499466621750605e-06,
|
| 2397 |
+
"loss": 0.1431,
|
| 2398 |
+
"step": 169000
|
| 2399 |
+
},
|
| 2400 |
+
{
|
| 2401 |
+
"epoch": 2.039269472316466,
|
| 2402 |
+
"grad_norm": 0.006397734861820936,
|
| 2403 |
+
"learning_rate": 6.409843034400892e-06,
|
| 2404 |
+
"loss": 0.1433,
|
| 2405 |
+
"step": 169500
|
| 2406 |
+
},
|
| 2407 |
+
{
|
| 2408 |
+
"epoch": 2.045285016482591,
|
| 2409 |
+
"grad_norm": 0.02048441767692566,
|
| 2410 |
+
"learning_rate": 6.369739406626724e-06,
|
| 2411 |
+
"loss": 0.1751,
|
| 2412 |
+
"step": 170000
|
| 2413 |
+
},
|
| 2414 |
+
{
|
| 2415 |
+
"epoch": 2.0513005606487162,
|
| 2416 |
+
"grad_norm": 0.08668813109397888,
|
| 2417 |
+
"learning_rate": 6.329635778852555e-06,
|
| 2418 |
+
"loss": 0.1904,
|
| 2419 |
+
"step": 170500
|
| 2420 |
+
},
|
| 2421 |
+
{
|
| 2422 |
+
"epoch": 2.0573161048148414,
|
| 2423 |
+
"grad_norm": 1.3654146194458008,
|
| 2424 |
+
"learning_rate": 6.289612358333935e-06,
|
| 2425 |
+
"loss": 0.1477,
|
| 2426 |
+
"step": 171000
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 2.063331648980967,
|
| 2430 |
+
"grad_norm": 0.10657373815774918,
|
| 2431 |
+
"learning_rate": 6.249508730559767e-06,
|
| 2432 |
+
"loss": 0.1651,
|
| 2433 |
+
"step": 171500
|
| 2434 |
+
},
|
| 2435 |
+
{
|
| 2436 |
+
"epoch": 2.069347193147092,
|
| 2437 |
+
"grad_norm": 0.0666826069355011,
|
| 2438 |
+
"learning_rate": 6.209405102785599e-06,
|
| 2439 |
+
"loss": 0.1896,
|
| 2440 |
+
"step": 172000
|
| 2441 |
+
},
|
| 2442 |
+
{
|
| 2443 |
+
"epoch": 2.0753627373132173,
|
| 2444 |
+
"grad_norm": 0.03260161355137825,
|
| 2445 |
+
"learning_rate": 6.16930147501143e-06,
|
| 2446 |
+
"loss": 0.1595,
|
| 2447 |
+
"step": 172500
|
| 2448 |
+
},
|
| 2449 |
+
{
|
| 2450 |
+
"epoch": 2.0813782814793425,
|
| 2451 |
+
"grad_norm": 11.851826667785645,
|
| 2452 |
+
"learning_rate": 6.129197847237262e-06,
|
| 2453 |
+
"loss": 0.1664,
|
| 2454 |
+
"step": 173000
|
| 2455 |
+
},
|
| 2456 |
+
{
|
| 2457 |
+
"epoch": 2.087393825645468,
|
| 2458 |
+
"grad_norm": 0.0001777495490387082,
|
| 2459 |
+
"learning_rate": 6.089094219463093e-06,
|
| 2460 |
+
"loss": 0.1719,
|
| 2461 |
+
"step": 173500
|
| 2462 |
+
},
|
| 2463 |
+
{
|
| 2464 |
+
"epoch": 2.093409369811593,
|
| 2465 |
+
"grad_norm": 0.001742048654705286,
|
| 2466 |
+
"learning_rate": 6.048990591688924e-06,
|
| 2467 |
+
"loss": 0.1336,
|
| 2468 |
+
"step": 174000
|
| 2469 |
+
},
|
| 2470 |
+
{
|
| 2471 |
+
"epoch": 2.0994249139777184,
|
| 2472 |
+
"grad_norm": 0.233998104929924,
|
| 2473 |
+
"learning_rate": 6.008886963914756e-06,
|
| 2474 |
+
"loss": 0.1659,
|
| 2475 |
+
"step": 174500
|
| 2476 |
+
},
|
| 2477 |
+
{
|
| 2478 |
+
"epoch": 2.1054404581438435,
|
| 2479 |
+
"grad_norm": 0.011589854955673218,
|
| 2480 |
+
"learning_rate": 5.968863543396136e-06,
|
| 2481 |
+
"loss": 0.1662,
|
| 2482 |
+
"step": 175000
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 2.111456002309969,
|
| 2486 |
+
"grad_norm": 0.003179445629939437,
|
| 2487 |
+
"learning_rate": 5.928759915621968e-06,
|
| 2488 |
+
"loss": 0.201,
|
| 2489 |
+
"step": 175500
|
| 2490 |
+
},
|
| 2491 |
+
{
|
| 2492 |
+
"epoch": 2.1174715464760943,
|
| 2493 |
+
"grad_norm": 0.05272052437067032,
|
| 2494 |
+
"learning_rate": 5.888656287847799e-06,
|
| 2495 |
+
"loss": 0.1648,
|
| 2496 |
+
"step": 176000
|
| 2497 |
+
},
|
| 2498 |
+
{
|
| 2499 |
+
"epoch": 2.1234870906422194,
|
| 2500 |
+
"grad_norm": 17.65900421142578,
|
| 2501 |
+
"learning_rate": 5.848552660073631e-06,
|
| 2502 |
+
"loss": 0.1499,
|
| 2503 |
+
"step": 176500
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 2.1295026348083446,
|
| 2507 |
+
"grad_norm": 0.017062697559595108,
|
| 2508 |
+
"learning_rate": 5.808449032299463e-06,
|
| 2509 |
+
"loss": 0.1812,
|
| 2510 |
+
"step": 177000
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 2.13551817897447,
|
| 2514 |
+
"grad_norm": 0.062195923179388046,
|
| 2515 |
+
"learning_rate": 5.768505819036391e-06,
|
| 2516 |
+
"loss": 0.1745,
|
| 2517 |
+
"step": 177500
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 2.1415337231405953,
|
| 2521 |
+
"grad_norm": 0.00937980879098177,
|
| 2522 |
+
"learning_rate": 5.728402191262222e-06,
|
| 2523 |
+
"loss": 0.138,
|
| 2524 |
+
"step": 178000
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 2.1475492673067205,
|
| 2528 |
+
"grad_norm": 13.196198463439941,
|
| 2529 |
+
"learning_rate": 5.688298563488054e-06,
|
| 2530 |
+
"loss": 0.1717,
|
| 2531 |
+
"step": 178500
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 2.1535648114728456,
|
| 2535 |
+
"grad_norm": 0.1440310925245285,
|
| 2536 |
+
"learning_rate": 5.648194935713886e-06,
|
| 2537 |
+
"loss": 0.1515,
|
| 2538 |
+
"step": 179000
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 2.159580355638971,
|
| 2542 |
+
"grad_norm": 0.032506223767995834,
|
| 2543 |
+
"learning_rate": 5.608091307939717e-06,
|
| 2544 |
+
"loss": 0.1401,
|
| 2545 |
+
"step": 179500
|
| 2546 |
+
},
|
| 2547 |
+
{
|
| 2548 |
+
"epoch": 2.1655958998050964,
|
| 2549 |
+
"grad_norm": 6.104779458837584e-05,
|
| 2550 |
+
"learning_rate": 5.5679876801655484e-06,
|
| 2551 |
+
"loss": 0.1881,
|
| 2552 |
+
"step": 180000
|
| 2553 |
+
},
|
| 2554 |
+
{
|
| 2555 |
+
"epoch": 2.1716114439712215,
|
| 2556 |
+
"grad_norm": 0.04752574488520622,
|
| 2557 |
+
"learning_rate": 5.52788405239138e-06,
|
| 2558 |
+
"loss": 0.1603,
|
| 2559 |
+
"step": 180500
|
| 2560 |
+
},
|
| 2561 |
+
{
|
| 2562 |
+
"epoch": 2.177626988137347,
|
| 2563 |
+
"grad_norm": 0.005751811899244785,
|
| 2564 |
+
"learning_rate": 5.487780424617212e-06,
|
| 2565 |
+
"loss": 0.1983,
|
| 2566 |
+
"step": 181000
|
| 2567 |
+
},
|
| 2568 |
+
{
|
| 2569 |
+
"epoch": 2.1836425323034723,
|
| 2570 |
+
"grad_norm": 0.03546688333153725,
|
| 2571 |
+
"learning_rate": 5.447757004098591e-06,
|
| 2572 |
+
"loss": 0.1831,
|
| 2573 |
+
"step": 181500
|
| 2574 |
+
},
|
| 2575 |
+
{
|
| 2576 |
+
"epoch": 2.1896580764695974,
|
| 2577 |
+
"grad_norm": 0.21516333520412445,
|
| 2578 |
+
"learning_rate": 5.407653376324423e-06,
|
| 2579 |
+
"loss": 0.1708,
|
| 2580 |
+
"step": 182000
|
| 2581 |
+
},
|
| 2582 |
+
{
|
| 2583 |
+
"epoch": 2.1956736206357226,
|
| 2584 |
+
"grad_norm": 0.061349764466285706,
|
| 2585 |
+
"learning_rate": 5.367549748550255e-06,
|
| 2586 |
+
"loss": 0.1737,
|
| 2587 |
+
"step": 182500
|
| 2588 |
+
},
|
| 2589 |
+
{
|
| 2590 |
+
"epoch": 2.201689164801848,
|
| 2591 |
+
"grad_norm": 67.89110565185547,
|
| 2592 |
+
"learning_rate": 5.327446120776087e-06,
|
| 2593 |
+
"loss": 0.1465,
|
| 2594 |
+
"step": 183000
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 2.2077047089679733,
|
| 2598 |
+
"grad_norm": 0.0042543611489236355,
|
| 2599 |
+
"learning_rate": 5.287342493001918e-06,
|
| 2600 |
+
"loss": 0.2034,
|
| 2601 |
+
"step": 183500
|
| 2602 |
+
},
|
| 2603 |
+
{
|
| 2604 |
+
"epoch": 2.2137202531340985,
|
| 2605 |
+
"grad_norm": 8.772153854370117,
|
| 2606 |
+
"learning_rate": 5.247238865227749e-06,
|
| 2607 |
+
"loss": 0.1354,
|
| 2608 |
+
"step": 184000
|
| 2609 |
+
},
|
| 2610 |
+
{
|
| 2611 |
+
"epoch": 2.2197357973002236,
|
| 2612 |
+
"grad_norm": 0.46139106154441833,
|
| 2613 |
+
"learning_rate": 5.207215444709128e-06,
|
| 2614 |
+
"loss": 0.1838,
|
| 2615 |
+
"step": 184500
|
| 2616 |
+
},
|
| 2617 |
+
{
|
| 2618 |
+
"epoch": 2.2257513414663492,
|
| 2619 |
+
"grad_norm": 0.007118485402315855,
|
| 2620 |
+
"learning_rate": 5.16711181693496e-06,
|
| 2621 |
+
"loss": 0.1702,
|
| 2622 |
+
"step": 185000
|
| 2623 |
+
},
|
| 2624 |
+
{
|
| 2625 |
+
"epoch": 2.2317668856324744,
|
| 2626 |
+
"grad_norm": 0.01587226428091526,
|
| 2627 |
+
"learning_rate": 5.127008189160792e-06,
|
| 2628 |
+
"loss": 0.1566,
|
| 2629 |
+
"step": 185500
|
| 2630 |
+
},
|
| 2631 |
+
{
|
| 2632 |
+
"epoch": 2.2377824297985995,
|
| 2633 |
+
"grad_norm": 0.006735761184245348,
|
| 2634 |
+
"learning_rate": 5.086904561386623e-06,
|
| 2635 |
+
"loss": 0.1644,
|
| 2636 |
+
"step": 186000
|
| 2637 |
+
},
|
| 2638 |
+
{
|
| 2639 |
+
"epoch": 2.2437979739647247,
|
| 2640 |
+
"grad_norm": 111.12641143798828,
|
| 2641 |
+
"learning_rate": 5.046881140868003e-06,
|
| 2642 |
+
"loss": 0.1578,
|
| 2643 |
+
"step": 186500
|
| 2644 |
+
},
|
| 2645 |
+
{
|
| 2646 |
+
"epoch": 2.2498135181308503,
|
| 2647 |
+
"grad_norm": 0.004494801629334688,
|
| 2648 |
+
"learning_rate": 5.0067775130938344e-06,
|
| 2649 |
+
"loss": 0.1625,
|
| 2650 |
+
"step": 187000
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 2.2558290622969754,
|
| 2654 |
+
"grad_norm": 61.42302703857422,
|
| 2655 |
+
"learning_rate": 4.966673885319666e-06,
|
| 2656 |
+
"loss": 0.1725,
|
| 2657 |
+
"step": 187500
|
| 2658 |
+
},
|
| 2659 |
+
{
|
| 2660 |
+
"epoch": 2.2618446064631006,
|
| 2661 |
+
"grad_norm": 102.92018127441406,
|
| 2662 |
+
"learning_rate": 4.926570257545498e-06,
|
| 2663 |
+
"loss": 0.1503,
|
| 2664 |
+
"step": 188000
|
| 2665 |
+
},
|
| 2666 |
+
{
|
| 2667 |
+
"epoch": 2.2678601506292257,
|
| 2668 |
+
"grad_norm": 0.15618078410625458,
|
| 2669 |
+
"learning_rate": 4.886466629771329e-06,
|
| 2670 |
+
"loss": 0.1586,
|
| 2671 |
+
"step": 188500
|
| 2672 |
+
},
|
| 2673 |
+
{
|
| 2674 |
+
"epoch": 2.2738756947953513,
|
| 2675 |
+
"grad_norm": 0.1413143128156662,
|
| 2676 |
+
"learning_rate": 4.846363001997161e-06,
|
| 2677 |
+
"loss": 0.1985,
|
| 2678 |
+
"step": 189000
|
| 2679 |
+
},
|
| 2680 |
+
{
|
| 2681 |
+
"epoch": 2.2798912389614765,
|
| 2682 |
+
"grad_norm": 40.41890335083008,
|
| 2683 |
+
"learning_rate": 4.806259374222993e-06,
|
| 2684 |
+
"loss": 0.1302,
|
| 2685 |
+
"step": 189500
|
| 2686 |
+
},
|
| 2687 |
+
{
|
| 2688 |
+
"epoch": 2.2859067831276016,
|
| 2689 |
+
"grad_norm": 0.0008507597958669066,
|
| 2690 |
+
"learning_rate": 4.766235953704372e-06,
|
| 2691 |
+
"loss": 0.1409,
|
| 2692 |
+
"step": 190000
|
| 2693 |
+
},
|
| 2694 |
+
{
|
| 2695 |
+
"epoch": 2.291922327293727,
|
| 2696 |
+
"grad_norm": 2.4075923647615127e-05,
|
| 2697 |
+
"learning_rate": 4.726132325930204e-06,
|
| 2698 |
+
"loss": 0.1463,
|
| 2699 |
+
"step": 190500
|
| 2700 |
+
},
|
| 2701 |
+
{
|
| 2702 |
+
"epoch": 2.2979378714598524,
|
| 2703 |
+
"grad_norm": 0.05570465698838234,
|
| 2704 |
+
"learning_rate": 4.6860286981560356e-06,
|
| 2705 |
+
"loss": 0.1641,
|
| 2706 |
+
"step": 191000
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 2.3039534156259776,
|
| 2710 |
+
"grad_norm": 177.34120178222656,
|
| 2711 |
+
"learning_rate": 4.645925070381867e-06,
|
| 2712 |
+
"loss": 0.1766,
|
| 2713 |
+
"step": 191500
|
| 2714 |
+
},
|
| 2715 |
+
{
|
| 2716 |
+
"epoch": 2.3099689597921027,
|
| 2717 |
+
"grad_norm": 25.356895446777344,
|
| 2718 |
+
"learning_rate": 4.605821442607698e-06,
|
| 2719 |
+
"loss": 0.1788,
|
| 2720 |
+
"step": 192000
|
| 2721 |
+
},
|
| 2722 |
+
{
|
| 2723 |
+
"epoch": 2.3159845039582283,
|
| 2724 |
+
"grad_norm": 26.419334411621094,
|
| 2725 |
+
"learning_rate": 4.56571781483353e-06,
|
| 2726 |
+
"loss": 0.1875,
|
| 2727 |
+
"step": 192500
|
| 2728 |
+
},
|
| 2729 |
+
{
|
| 2730 |
+
"epoch": 2.3220000481243535,
|
| 2731 |
+
"grad_norm": 0.05582762509584427,
|
| 2732 |
+
"learning_rate": 4.525614187059362e-06,
|
| 2733 |
+
"loss": 0.1357,
|
| 2734 |
+
"step": 193000
|
| 2735 |
+
},
|
| 2736 |
+
{
|
| 2737 |
+
"epoch": 2.3280155922904786,
|
| 2738 |
+
"grad_norm": 0.01142974104732275,
|
| 2739 |
+
"learning_rate": 4.485510559285193e-06,
|
| 2740 |
+
"loss": 0.148,
|
| 2741 |
+
"step": 193500
|
| 2742 |
+
},
|
| 2743 |
+
{
|
| 2744 |
+
"epoch": 2.3340311364566038,
|
| 2745 |
+
"grad_norm": 0.013201882131397724,
|
| 2746 |
+
"learning_rate": 4.445487138766573e-06,
|
| 2747 |
+
"loss": 0.1279,
|
| 2748 |
+
"step": 194000
|
| 2749 |
+
},
|
| 2750 |
+
{
|
| 2751 |
+
"epoch": 2.340046680622729,
|
| 2752 |
+
"grad_norm": 0.007936575450003147,
|
| 2753 |
+
"learning_rate": 4.405383510992405e-06,
|
| 2754 |
+
"loss": 0.1492,
|
| 2755 |
+
"step": 194500
|
| 2756 |
+
},
|
| 2757 |
+
{
|
| 2758 |
+
"epoch": 2.3460622247888545,
|
| 2759 |
+
"grad_norm": 0.030919533222913742,
|
| 2760 |
+
"learning_rate": 4.365360090473785e-06,
|
| 2761 |
+
"loss": 0.1298,
|
| 2762 |
+
"step": 195000
|
| 2763 |
+
},
|
| 2764 |
+
{
|
| 2765 |
+
"epoch": 2.3520777689549797,
|
| 2766 |
+
"grad_norm": 0.0013994334731251001,
|
| 2767 |
+
"learning_rate": 4.325256462699616e-06,
|
| 2768 |
+
"loss": 0.1555,
|
| 2769 |
+
"step": 195500
|
| 2770 |
+
},
|
| 2771 |
+
{
|
| 2772 |
+
"epoch": 2.358093313121105,
|
| 2773 |
+
"grad_norm": 0.004653325304389,
|
| 2774 |
+
"learning_rate": 4.285152834925448e-06,
|
| 2775 |
+
"loss": 0.1612,
|
| 2776 |
+
"step": 196000
|
| 2777 |
+
},
|
| 2778 |
+
{
|
| 2779 |
+
"epoch": 2.3641088572872304,
|
| 2780 |
+
"grad_norm": 0.034009434282779694,
|
| 2781 |
+
"learning_rate": 4.2450492071512796e-06,
|
| 2782 |
+
"loss": 0.1543,
|
| 2783 |
+
"step": 196500
|
| 2784 |
+
},
|
| 2785 |
+
{
|
| 2786 |
+
"epoch": 2.3701244014533556,
|
| 2787 |
+
"grad_norm": 0.6855669021606445,
|
| 2788 |
+
"learning_rate": 4.20502578663266e-06,
|
| 2789 |
+
"loss": 0.2072,
|
| 2790 |
+
"step": 197000
|
| 2791 |
+
},
|
| 2792 |
+
{
|
| 2793 |
+
"epoch": 2.3761399456194807,
|
| 2794 |
+
"grad_norm": 45.97907257080078,
|
| 2795 |
+
"learning_rate": 4.164922158858491e-06,
|
| 2796 |
+
"loss": 0.1637,
|
| 2797 |
+
"step": 197500
|
| 2798 |
+
},
|
| 2799 |
+
{
|
| 2800 |
+
"epoch": 2.382155489785606,
|
| 2801 |
+
"grad_norm": 0.36125409603118896,
|
| 2802 |
+
"learning_rate": 4.1248185310843216e-06,
|
| 2803 |
+
"loss": 0.142,
|
| 2804 |
+
"step": 198000
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 2.388171033951731,
|
| 2808 |
+
"grad_norm": 0.013704453594982624,
|
| 2809 |
+
"learning_rate": 4.084714903310153e-06,
|
| 2810 |
+
"loss": 0.1702,
|
| 2811 |
+
"step": 198500
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 2.3941865781178566,
|
| 2815 |
+
"grad_norm": 28.00567626953125,
|
| 2816 |
+
"learning_rate": 4.044611275535985e-06,
|
| 2817 |
+
"loss": 0.1641,
|
| 2818 |
+
"step": 199000
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 2.4002021222839818,
|
| 2822 |
+
"grad_norm": 0.4930565655231476,
|
| 2823 |
+
"learning_rate": 4.0046680622729135e-06,
|
| 2824 |
+
"loss": 0.147,
|
| 2825 |
+
"step": 199500
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 2.406217666450107,
|
| 2829 |
+
"grad_norm": 1.68142831325531,
|
| 2830 |
+
"learning_rate": 3.964564434498745e-06,
|
| 2831 |
+
"loss": 0.1543,
|
| 2832 |
+
"step": 200000
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 2.4122332106162325,
|
| 2836 |
+
"grad_norm": 0.00046357992687262595,
|
| 2837 |
+
"learning_rate": 3.924460806724576e-06,
|
| 2838 |
+
"loss": 0.1383,
|
| 2839 |
+
"step": 200500
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 2.4182487547823577,
|
| 2843 |
+
"grad_norm": 0.08767001330852509,
|
| 2844 |
+
"learning_rate": 3.884357178950408e-06,
|
| 2845 |
+
"loss": 0.1697,
|
| 2846 |
+
"step": 201000
|
| 2847 |
+
},
|
| 2848 |
+
{
|
| 2849 |
+
"epoch": 2.424264298948483,
|
| 2850 |
+
"grad_norm": 14.962833404541016,
|
| 2851 |
+
"learning_rate": 3.84425355117624e-06,
|
| 2852 |
+
"loss": 0.1919,
|
| 2853 |
+
"step": 201500
|
| 2854 |
+
},
|
| 2855 |
+
{
|
| 2856 |
+
"epoch": 2.430279843114608,
|
| 2857 |
+
"grad_norm": 0.0750858262181282,
|
| 2858 |
+
"learning_rate": 3.8041499234020714e-06,
|
| 2859 |
+
"loss": 0.1238,
|
| 2860 |
+
"step": 202000
|
| 2861 |
+
},
|
| 2862 |
+
{
|
| 2863 |
+
"epoch": 2.4362953872807336,
|
| 2864 |
+
"grad_norm": 0.011100132018327713,
|
| 2865 |
+
"learning_rate": 3.7640462956279028e-06,
|
| 2866 |
+
"loss": 0.1584,
|
| 2867 |
+
"step": 202500
|
| 2868 |
+
},
|
| 2869 |
+
{
|
| 2870 |
+
"epoch": 2.4423109314468587,
|
| 2871 |
+
"grad_norm": 0.0002675870491657406,
|
| 2872 |
+
"learning_rate": 3.723942667853734e-06,
|
| 2873 |
+
"loss": 0.1393,
|
| 2874 |
+
"step": 203000
|
| 2875 |
+
},
|
| 2876 |
+
{
|
| 2877 |
+
"epoch": 2.448326475612984,
|
| 2878 |
+
"grad_norm": 22.56096839904785,
|
| 2879 |
+
"learning_rate": 3.683839040079566e-06,
|
| 2880 |
+
"loss": 0.1284,
|
| 2881 |
+
"step": 203500
|
| 2882 |
+
},
|
| 2883 |
+
{
|
| 2884 |
+
"epoch": 2.454342019779109,
|
| 2885 |
+
"grad_norm": 0.0010695152450352907,
|
| 2886 |
+
"learning_rate": 3.643815619560946e-06,
|
| 2887 |
+
"loss": 0.1636,
|
| 2888 |
+
"step": 204000
|
| 2889 |
+
},
|
| 2890 |
+
{
|
| 2891 |
+
"epoch": 2.4603575639452346,
|
| 2892 |
+
"grad_norm": 0.05840376392006874,
|
| 2893 |
+
"learning_rate": 3.6037119917867774e-06,
|
| 2894 |
+
"loss": 0.1824,
|
| 2895 |
+
"step": 204500
|
| 2896 |
+
},
|
| 2897 |
+
{
|
| 2898 |
+
"epoch": 2.46637310811136,
|
| 2899 |
+
"grad_norm": 0.0005692685954272747,
|
| 2900 |
+
"learning_rate": 3.563608364012609e-06,
|
| 2901 |
+
"loss": 0.1189,
|
| 2902 |
+
"step": 205000
|
| 2903 |
+
},
|
| 2904 |
+
{
|
| 2905 |
+
"epoch": 2.472388652277485,
|
| 2906 |
+
"grad_norm": 12.676384925842285,
|
| 2907 |
+
"learning_rate": 3.5235047362384407e-06,
|
| 2908 |
+
"loss": 0.1589,
|
| 2909 |
+
"step": 205500
|
| 2910 |
+
},
|
| 2911 |
+
{
|
| 2912 |
+
"epoch": 2.47840419644361,
|
| 2913 |
+
"grad_norm": 0.024767233058810234,
|
| 2914 |
+
"learning_rate": 3.483401108464272e-06,
|
| 2915 |
+
"loss": 0.179,
|
| 2916 |
+
"step": 206000
|
| 2917 |
+
},
|
| 2918 |
+
{
|
| 2919 |
+
"epoch": 2.4844197406097357,
|
| 2920 |
+
"grad_norm": 0.014465268701314926,
|
| 2921 |
+
"learning_rate": 3.443297480690104e-06,
|
| 2922 |
+
"loss": 0.134,
|
| 2923 |
+
"step": 206500
|
| 2924 |
+
},
|
| 2925 |
+
{
|
| 2926 |
+
"epoch": 2.490435284775861,
|
| 2927 |
+
"grad_norm": 46.07574462890625,
|
| 2928 |
+
"learning_rate": 3.4031938529159353e-06,
|
| 2929 |
+
"loss": 0.1839,
|
| 2930 |
+
"step": 207000
|
| 2931 |
+
},
|
| 2932 |
+
{
|
| 2933 |
+
"epoch": 2.496450828941986,
|
| 2934 |
+
"grad_norm": 2.9257161617279053,
|
| 2935 |
+
"learning_rate": 3.3630902251417667e-06,
|
| 2936 |
+
"loss": 0.1522,
|
| 2937 |
+
"step": 207500
|
| 2938 |
+
},
|
| 2939 |
+
{
|
| 2940 |
+
"epoch": 2.5024663731081116,
|
| 2941 |
+
"grad_norm": 0.010684625245630741,
|
| 2942 |
+
"learning_rate": 3.3230668046231463e-06,
|
| 2943 |
+
"loss": 0.137,
|
| 2944 |
+
"step": 208000
|
| 2945 |
+
},
|
| 2946 |
+
{
|
| 2947 |
+
"epoch": 2.5084819172742367,
|
| 2948 |
+
"grad_norm": 0.023651426658034325,
|
| 2949 |
+
"learning_rate": 3.2829631768489777e-06,
|
| 2950 |
+
"loss": 0.1893,
|
| 2951 |
+
"step": 208500
|
| 2952 |
+
},
|
| 2953 |
+
{
|
| 2954 |
+
"epoch": 2.514497461440362,
|
| 2955 |
+
"grad_norm": 5.37974214553833,
|
| 2956 |
+
"learning_rate": 3.242939756330358e-06,
|
| 2957 |
+
"loss": 0.1688,
|
| 2958 |
+
"step": 209000
|
| 2959 |
+
},
|
| 2960 |
+
{
|
| 2961 |
+
"epoch": 2.520513005606487,
|
| 2962 |
+
"grad_norm": 0.21090950071811676,
|
| 2963 |
+
"learning_rate": 3.202836128556189e-06,
|
| 2964 |
+
"loss": 0.173,
|
| 2965 |
+
"step": 209500
|
| 2966 |
+
},
|
| 2967 |
+
{
|
| 2968 |
+
"epoch": 2.526528549772612,
|
| 2969 |
+
"grad_norm": 24.091960906982422,
|
| 2970 |
+
"learning_rate": 3.162732500782021e-06,
|
| 2971 |
+
"loss": 0.1614,
|
| 2972 |
+
"step": 210000
|
| 2973 |
+
},
|
| 2974 |
+
{
|
| 2975 |
+
"epoch": 2.532544093938738,
|
| 2976 |
+
"grad_norm": 0.032513245940208435,
|
| 2977 |
+
"learning_rate": 3.1226288730078524e-06,
|
| 2978 |
+
"loss": 0.1816,
|
| 2979 |
+
"step": 210500
|
| 2980 |
+
},
|
| 2981 |
+
{
|
| 2982 |
+
"epoch": 2.538559638104863,
|
| 2983 |
+
"grad_norm": 0.045939259231090546,
|
| 2984 |
+
"learning_rate": 3.082525245233684e-06,
|
| 2985 |
+
"loss": 0.1646,
|
| 2986 |
+
"step": 211000
|
| 2987 |
+
},
|
| 2988 |
+
{
|
| 2989 |
+
"epoch": 2.544575182270988,
|
| 2990 |
+
"grad_norm": 0.7573652863502502,
|
| 2991 |
+
"learning_rate": 3.0424216174595156e-06,
|
| 2992 |
+
"loss": 0.1224,
|
| 2993 |
+
"step": 211500
|
| 2994 |
+
},
|
| 2995 |
+
{
|
| 2996 |
+
"epoch": 2.5505907264371137,
|
| 2997 |
+
"grad_norm": 3.404059648513794,
|
| 2998 |
+
"learning_rate": 3.0023981969408957e-06,
|
| 2999 |
+
"loss": 0.1475,
|
| 3000 |
+
"step": 212000
|
| 3001 |
+
},
|
| 3002 |
+
{
|
| 3003 |
+
"epoch": 2.556606270603239,
|
| 3004 |
+
"grad_norm": 0.0026354603469371796,
|
| 3005 |
+
"learning_rate": 2.962294569166727e-06,
|
| 3006 |
+
"loss": 0.1591,
|
| 3007 |
+
"step": 212500
|
| 3008 |
+
},
|
| 3009 |
+
{
|
| 3010 |
+
"epoch": 2.562621814769364,
|
| 3011 |
+
"grad_norm": 21.002397537231445,
|
| 3012 |
+
"learning_rate": 2.9221909413925585e-06,
|
| 3013 |
+
"loss": 0.133,
|
| 3014 |
+
"step": 213000
|
| 3015 |
+
},
|
| 3016 |
+
{
|
| 3017 |
+
"epoch": 2.568637358935489,
|
| 3018 |
+
"grad_norm": 0.020220952108502388,
|
| 3019 |
+
"learning_rate": 2.8820873136183903e-06,
|
| 3020 |
+
"loss": 0.144,
|
| 3021 |
+
"step": 213500
|
| 3022 |
+
},
|
| 3023 |
+
{
|
| 3024 |
+
"epoch": 2.5746529031016143,
|
| 3025 |
+
"grad_norm": 0.02407023496925831,
|
| 3026 |
+
"learning_rate": 2.84206389309977e-06,
|
| 3027 |
+
"loss": 0.1522,
|
| 3028 |
+
"step": 214000
|
| 3029 |
+
},
|
| 3030 |
+
{
|
| 3031 |
+
"epoch": 2.58066844726774,
|
| 3032 |
+
"grad_norm": 0.05026541277766228,
|
| 3033 |
+
"learning_rate": 2.8019602653256018e-06,
|
| 3034 |
+
"loss": 0.1751,
|
| 3035 |
+
"step": 214500
|
| 3036 |
+
},
|
| 3037 |
+
{
|
| 3038 |
+
"epoch": 2.586683991433865,
|
| 3039 |
+
"grad_norm": 0.0013814900303259492,
|
| 3040 |
+
"learning_rate": 2.761856637551433e-06,
|
| 3041 |
+
"loss": 0.1606,
|
| 3042 |
+
"step": 215000
|
| 3043 |
+
},
|
| 3044 |
+
{
|
| 3045 |
+
"epoch": 2.5926995355999902,
|
| 3046 |
+
"grad_norm": 0.09587771445512772,
|
| 3047 |
+
"learning_rate": 2.721753009777265e-06,
|
| 3048 |
+
"loss": 0.1553,
|
| 3049 |
+
"step": 215500
|
| 3050 |
+
},
|
| 3051 |
+
{
|
| 3052 |
+
"epoch": 2.598715079766116,
|
| 3053 |
+
"grad_norm": 0.014226296916604042,
|
| 3054 |
+
"learning_rate": 2.6816493820030964e-06,
|
| 3055 |
+
"loss": 0.1732,
|
| 3056 |
+
"step": 216000
|
| 3057 |
+
},
|
| 3058 |
+
{
|
| 3059 |
+
"epoch": 2.604730623932241,
|
| 3060 |
+
"grad_norm": 0.020662061870098114,
|
| 3061 |
+
"learning_rate": 2.641545754228928e-06,
|
| 3062 |
+
"loss": 0.1851,
|
| 3063 |
+
"step": 216500
|
| 3064 |
+
},
|
| 3065 |
+
{
|
| 3066 |
+
"epoch": 2.610746168098366,
|
| 3067 |
+
"grad_norm": 0.020077265799045563,
|
| 3068 |
+
"learning_rate": 2.6015223337103074e-06,
|
| 3069 |
+
"loss": 0.1672,
|
| 3070 |
+
"step": 217000
|
| 3071 |
+
},
|
| 3072 |
+
{
|
| 3073 |
+
"epoch": 2.6167617122644913,
|
| 3074 |
+
"grad_norm": 17.917278289794922,
|
| 3075 |
+
"learning_rate": 2.561418705936139e-06,
|
| 3076 |
+
"loss": 0.1757,
|
| 3077 |
+
"step": 217500
|
| 3078 |
+
},
|
| 3079 |
+
{
|
| 3080 |
+
"epoch": 2.622777256430617,
|
| 3081 |
+
"grad_norm": 0.010099813342094421,
|
| 3082 |
+
"learning_rate": 2.5213150781619707e-06,
|
| 3083 |
+
"loss": 0.154,
|
| 3084 |
+
"step": 218000
|
| 3085 |
+
},
|
| 3086 |
+
{
|
| 3087 |
+
"epoch": 2.628792800596742,
|
| 3088 |
+
"grad_norm": 50.070430755615234,
|
| 3089 |
+
"learning_rate": 2.4812114503878025e-06,
|
| 3090 |
+
"loss": 0.1557,
|
| 3091 |
+
"step": 218500
|
| 3092 |
+
},
|
| 3093 |
+
{
|
| 3094 |
+
"epoch": 2.634808344762867,
|
| 3095 |
+
"grad_norm": 0.0430847629904747,
|
| 3096 |
+
"learning_rate": 2.441107822613634e-06,
|
| 3097 |
+
"loss": 0.1578,
|
| 3098 |
+
"step": 219000
|
| 3099 |
+
},
|
| 3100 |
+
{
|
| 3101 |
+
"epoch": 2.640823888928993,
|
| 3102 |
+
"grad_norm": 45.390384674072266,
|
| 3103 |
+
"learning_rate": 2.4010844020950135e-06,
|
| 3104 |
+
"loss": 0.1584,
|
| 3105 |
+
"step": 219500
|
| 3106 |
+
},
|
| 3107 |
+
{
|
| 3108 |
+
"epoch": 2.646839433095118,
|
| 3109 |
+
"grad_norm": 0.01655266433954239,
|
| 3110 |
+
"learning_rate": 2.361141188831942e-06,
|
| 3111 |
+
"loss": 0.1926,
|
| 3112 |
+
"step": 220000
|
| 3113 |
+
},
|
| 3114 |
+
{
|
| 3115 |
+
"epoch": 2.652854977261243,
|
| 3116 |
+
"grad_norm": 0.006697576493024826,
|
| 3117 |
+
"learning_rate": 2.3210375610577732e-06,
|
| 3118 |
+
"loss": 0.1469,
|
| 3119 |
+
"step": 220500
|
| 3120 |
+
},
|
| 3121 |
+
{
|
| 3122 |
+
"epoch": 2.6588705214273682,
|
| 3123 |
+
"grad_norm": 0.055724818259477615,
|
| 3124 |
+
"learning_rate": 2.280933933283605e-06,
|
| 3125 |
+
"loss": 0.1548,
|
| 3126 |
+
"step": 221000
|
| 3127 |
+
},
|
| 3128 |
+
{
|
| 3129 |
+
"epoch": 2.6648860655934934,
|
| 3130 |
+
"grad_norm": 0.09359436482191086,
|
| 3131 |
+
"learning_rate": 2.2408303055094365e-06,
|
| 3132 |
+
"loss": 0.1523,
|
| 3133 |
+
"step": 221500
|
| 3134 |
+
},
|
| 3135 |
+
{
|
| 3136 |
+
"epoch": 2.670901609759619,
|
| 3137 |
+
"grad_norm": 0.005888832733035088,
|
| 3138 |
+
"learning_rate": 2.2007266777352683e-06,
|
| 3139 |
+
"loss": 0.1896,
|
| 3140 |
+
"step": 222000
|
| 3141 |
+
},
|
| 3142 |
+
{
|
| 3143 |
+
"epoch": 2.676917153925744,
|
| 3144 |
+
"grad_norm": 0.018979087471961975,
|
| 3145 |
+
"learning_rate": 2.1606230499610997e-06,
|
| 3146 |
+
"loss": 0.123,
|
| 3147 |
+
"step": 222500
|
| 3148 |
+
},
|
| 3149 |
+
{
|
| 3150 |
+
"epoch": 2.6829326980918693,
|
| 3151 |
+
"grad_norm": 0.11329194158315659,
|
| 3152 |
+
"learning_rate": 2.1205194221869315e-06,
|
| 3153 |
+
"loss": 0.1556,
|
| 3154 |
+
"step": 223000
|
| 3155 |
+
},
|
| 3156 |
+
{
|
| 3157 |
+
"epoch": 2.688948242257995,
|
| 3158 |
+
"grad_norm": 0.018361905589699745,
|
| 3159 |
+
"learning_rate": 2.080415794412763e-06,
|
| 3160 |
+
"loss": 0.1621,
|
| 3161 |
+
"step": 223500
|
| 3162 |
+
},
|
| 3163 |
+
{
|
| 3164 |
+
"epoch": 2.69496378642412,
|
| 3165 |
+
"grad_norm": 0.00052923389011994,
|
| 3166 |
+
"learning_rate": 2.0403121666385943e-06,
|
| 3167 |
+
"loss": 0.1309,
|
| 3168 |
+
"step": 224000
|
| 3169 |
+
},
|
| 3170 |
+
{
|
| 3171 |
+
"epoch": 2.700979330590245,
|
| 3172 |
+
"grad_norm": 0.030753634870052338,
|
| 3173 |
+
"learning_rate": 2.0002085388644257e-06,
|
| 3174 |
+
"loss": 0.1401,
|
| 3175 |
+
"step": 224500
|
| 3176 |
+
},
|
| 3177 |
+
{
|
| 3178 |
+
"epoch": 2.7069948747563704,
|
| 3179 |
+
"grad_norm": 0.01107688806951046,
|
| 3180 |
+
"learning_rate": 1.9601049110902575e-06,
|
| 3181 |
+
"loss": 0.1444,
|
| 3182 |
+
"step": 225000
|
| 3183 |
+
},
|
| 3184 |
+
{
|
| 3185 |
+
"epoch": 2.7130104189224955,
|
| 3186 |
+
"grad_norm": 0.0049855210818350315,
|
| 3187 |
+
"learning_rate": 1.920001283316089e-06,
|
| 3188 |
+
"loss": 0.1398,
|
| 3189 |
+
"step": 225500
|
| 3190 |
+
},
|
| 3191 |
+
{
|
| 3192 |
+
"epoch": 2.719025963088621,
|
| 3193 |
+
"grad_norm": 52.67742156982422,
|
| 3194 |
+
"learning_rate": 1.8798976555419205e-06,
|
| 3195 |
+
"loss": 0.1743,
|
| 3196 |
+
"step": 226000
|
| 3197 |
+
},
|
| 3198 |
+
{
|
| 3199 |
+
"epoch": 2.7250415072547463,
|
| 3200 |
+
"grad_norm": 0.17802126705646515,
|
| 3201 |
+
"learning_rate": 1.839794027767752e-06,
|
| 3202 |
+
"loss": 0.1774,
|
| 3203 |
+
"step": 226500
|
| 3204 |
+
},
|
| 3205 |
+
{
|
| 3206 |
+
"epoch": 2.7310570514208714,
|
| 3207 |
+
"grad_norm": 0.03584326431155205,
|
| 3208 |
+
"learning_rate": 1.7996903999935835e-06,
|
| 3209 |
+
"loss": 0.1282,
|
| 3210 |
+
"step": 227000
|
| 3211 |
+
},
|
| 3212 |
+
{
|
| 3213 |
+
"epoch": 2.737072595586997,
|
| 3214 |
+
"grad_norm": 0.08680440485477448,
|
| 3215 |
+
"learning_rate": 1.7595867722194151e-06,
|
| 3216 |
+
"loss": 0.1281,
|
| 3217 |
+
"step": 227500
|
| 3218 |
+
},
|
| 3219 |
+
{
|
| 3220 |
+
"epoch": 2.743088139753122,
|
| 3221 |
+
"grad_norm": 0.2684645354747772,
|
| 3222 |
+
"learning_rate": 1.719563351700795e-06,
|
| 3223 |
+
"loss": 0.1414,
|
| 3224 |
+
"step": 228000
|
| 3225 |
+
},
|
| 3226 |
+
{
|
| 3227 |
+
"epoch": 2.7491036839192473,
|
| 3228 |
+
"grad_norm": 0.027800705283880234,
|
| 3229 |
+
"learning_rate": 1.679539931182175e-06,
|
| 3230 |
+
"loss": 0.1622,
|
| 3231 |
+
"step": 228500
|
| 3232 |
+
},
|
| 3233 |
+
{
|
| 3234 |
+
"epoch": 2.7551192280853725,
|
| 3235 |
+
"grad_norm": 11.01578140258789,
|
| 3236 |
+
"learning_rate": 1.6394363034080062e-06,
|
| 3237 |
+
"loss": 0.1396,
|
| 3238 |
+
"step": 229000
|
| 3239 |
+
},
|
| 3240 |
+
{
|
| 3241 |
+
"epoch": 2.7611347722514976,
|
| 3242 |
+
"grad_norm": 0.0035239350982010365,
|
| 3243 |
+
"learning_rate": 1.5993326756338379e-06,
|
| 3244 |
+
"loss": 0.1867,
|
| 3245 |
+
"step": 229500
|
| 3246 |
+
},
|
| 3247 |
+
{
|
| 3248 |
+
"epoch": 2.767150316417623,
|
| 3249 |
+
"grad_norm": 0.04345840960741043,
|
| 3250 |
+
"learning_rate": 1.5592290478596695e-06,
|
| 3251 |
+
"loss": 0.1404,
|
| 3252 |
+
"step": 230000
|
| 3253 |
+
},
|
| 3254 |
+
{
|
| 3255 |
+
"epoch": 2.7731658605837484,
|
| 3256 |
+
"grad_norm": 0.003262243466451764,
|
| 3257 |
+
"learning_rate": 1.5192056273410493e-06,
|
| 3258 |
+
"loss": 0.1605,
|
| 3259 |
+
"step": 230500
|
| 3260 |
+
},
|
| 3261 |
+
{
|
| 3262 |
+
"epoch": 2.7791814047498735,
|
| 3263 |
+
"grad_norm": 0.4090683162212372,
|
| 3264 |
+
"learning_rate": 1.479101999566881e-06,
|
| 3265 |
+
"loss": 0.1547,
|
| 3266 |
+
"step": 231000
|
| 3267 |
+
},
|
| 3268 |
+
{
|
| 3269 |
+
"epoch": 2.785196948915999,
|
| 3270 |
+
"grad_norm": 0.012451679445803165,
|
| 3271 |
+
"learning_rate": 1.4389983717927125e-06,
|
| 3272 |
+
"loss": 0.1147,
|
| 3273 |
+
"step": 231500
|
| 3274 |
+
},
|
| 3275 |
+
{
|
| 3276 |
+
"epoch": 2.7912124930821243,
|
| 3277 |
+
"grad_norm": 0.008698958903551102,
|
| 3278 |
+
"learning_rate": 1.3988947440185442e-06,
|
| 3279 |
+
"loss": 0.1869,
|
| 3280 |
+
"step": 232000
|
| 3281 |
+
},
|
| 3282 |
+
{
|
| 3283 |
+
"epoch": 2.7972280372482494,
|
| 3284 |
+
"grad_norm": 1.2418529987335205,
|
| 3285 |
+
"learning_rate": 1.3587911162443755e-06,
|
| 3286 |
+
"loss": 0.1428,
|
| 3287 |
+
"step": 232500
|
| 3288 |
+
},
|
| 3289 |
+
{
|
| 3290 |
+
"epoch": 2.8032435814143746,
|
| 3291 |
+
"grad_norm": 0.24010685086250305,
|
| 3292 |
+
"learning_rate": 1.3186874884702072e-06,
|
| 3293 |
+
"loss": 0.172,
|
| 3294 |
+
"step": 233000
|
| 3295 |
+
},
|
| 3296 |
+
{
|
| 3297 |
+
"epoch": 2.8092591255805,
|
| 3298 |
+
"grad_norm": 0.008175286464393139,
|
| 3299 |
+
"learning_rate": 1.2785838606960388e-06,
|
| 3300 |
+
"loss": 0.1932,
|
| 3301 |
+
"step": 233500
|
| 3302 |
+
},
|
| 3303 |
+
{
|
| 3304 |
+
"epoch": 2.8152746697466253,
|
| 3305 |
+
"grad_norm": 0.009441105648875237,
|
| 3306 |
+
"learning_rate": 1.2384802329218702e-06,
|
| 3307 |
+
"loss": 0.1202,
|
| 3308 |
+
"step": 234000
|
| 3309 |
+
},
|
| 3310 |
+
{
|
| 3311 |
+
"epoch": 2.8212902139127505,
|
| 3312 |
+
"grad_norm": 0.0015565038193017244,
|
| 3313 |
+
"learning_rate": 1.1984568124032502e-06,
|
| 3314 |
+
"loss": 0.1215,
|
| 3315 |
+
"step": 234500
|
| 3316 |
+
},
|
| 3317 |
+
{
|
| 3318 |
+
"epoch": 2.827305758078876,
|
| 3319 |
+
"grad_norm": 71.70852661132812,
|
| 3320 |
+
"learning_rate": 1.1583531846290816e-06,
|
| 3321 |
+
"loss": 0.1498,
|
| 3322 |
+
"step": 235000
|
| 3323 |
+
},
|
| 3324 |
+
{
|
| 3325 |
+
"epoch": 2.8333213022450012,
|
| 3326 |
+
"grad_norm": 4.693429470062256,
|
| 3327 |
+
"learning_rate": 1.1182495568549132e-06,
|
| 3328 |
+
"loss": 0.1463,
|
| 3329 |
+
"step": 235500
|
| 3330 |
+
},
|
| 3331 |
+
{
|
| 3332 |
+
"epoch": 2.8393368464111264,
|
| 3333 |
+
"grad_norm": 0.04238261282444,
|
| 3334 |
+
"learning_rate": 1.0781459290807446e-06,
|
| 3335 |
+
"loss": 0.1874,
|
| 3336 |
+
"step": 236000
|
| 3337 |
+
},
|
| 3338 |
+
{
|
| 3339 |
+
"epoch": 2.8453523905772515,
|
| 3340 |
+
"grad_norm": 0.091603122651577,
|
| 3341 |
+
"learning_rate": 1.0380423013065762e-06,
|
| 3342 |
+
"loss": 0.1495,
|
| 3343 |
+
"step": 236500
|
| 3344 |
+
},
|
| 3345 |
+
{
|
| 3346 |
+
"epoch": 2.8513679347433767,
|
| 3347 |
+
"grad_norm": 26.191734313964844,
|
| 3348 |
+
"learning_rate": 9.979386735324079e-07,
|
| 3349 |
+
"loss": 0.1246,
|
| 3350 |
+
"step": 237000
|
| 3351 |
+
},
|
| 3352 |
+
{
|
| 3353 |
+
"epoch": 2.8573834789095023,
|
| 3354 |
+
"grad_norm": 0.0009205593378283083,
|
| 3355 |
+
"learning_rate": 9.579152530137877e-07,
|
| 3356 |
+
"loss": 0.1417,
|
| 3357 |
+
"step": 237500
|
| 3358 |
+
},
|
| 3359 |
+
{
|
| 3360 |
+
"epoch": 2.8633990230756274,
|
| 3361 |
+
"grad_norm": 0.0035299675073474646,
|
| 3362 |
+
"learning_rate": 9.178116252396192e-07,
|
| 3363 |
+
"loss": 0.1665,
|
| 3364 |
+
"step": 238000
|
| 3365 |
+
},
|
| 3366 |
+
{
|
| 3367 |
+
"epoch": 2.8694145672417526,
|
| 3368 |
+
"grad_norm": 0.004722926300019026,
|
| 3369 |
+
"learning_rate": 8.777079974654508e-07,
|
| 3370 |
+
"loss": 0.144,
|
| 3371 |
+
"step": 238500
|
| 3372 |
+
},
|
| 3373 |
+
{
|
| 3374 |
+
"epoch": 2.875430111407878,
|
| 3375 |
+
"grad_norm": 0.007760610897094011,
|
| 3376 |
+
"learning_rate": 8.376043696912823e-07,
|
| 3377 |
+
"loss": 0.1325,
|
| 3378 |
+
"step": 239000
|
| 3379 |
+
},
|
| 3380 |
+
{
|
| 3381 |
+
"epoch": 2.8814456555740033,
|
| 3382 |
+
"grad_norm": 0.0008993456140160561,
|
| 3383 |
+
"learning_rate": 7.975007419171139e-07,
|
| 3384 |
+
"loss": 0.1572,
|
| 3385 |
+
"step": 239500
|
| 3386 |
+
},
|
| 3387 |
+
{
|
| 3388 |
+
"epoch": 2.8874611997401285,
|
| 3389 |
+
"grad_norm": 0.18450585007667542,
|
| 3390 |
+
"learning_rate": 7.574773213984937e-07,
|
| 3391 |
+
"loss": 0.1473,
|
| 3392 |
+
"step": 240000
|
| 3393 |
+
},
|
| 3394 |
+
{
|
| 3395 |
+
"epoch": 2.8934767439062536,
|
| 3396 |
+
"grad_norm": 0.0713871493935585,
|
| 3397 |
+
"learning_rate": 7.173736936243253e-07,
|
| 3398 |
+
"loss": 0.1216,
|
| 3399 |
+
"step": 240500
|
| 3400 |
+
},
|
| 3401 |
+
{
|
| 3402 |
+
"epoch": 2.899492288072379,
|
| 3403 |
+
"grad_norm": 0.0023451121523976326,
|
| 3404 |
+
"learning_rate": 6.773502731057053e-07,
|
| 3405 |
+
"loss": 0.1409,
|
| 3406 |
+
"step": 241000
|
| 3407 |
+
},
|
| 3408 |
+
{
|
| 3409 |
+
"epoch": 2.9055078322385044,
|
| 3410 |
+
"grad_norm": 0.014280580915510654,
|
| 3411 |
+
"learning_rate": 6.372466453315368e-07,
|
| 3412 |
+
"loss": 0.1946,
|
| 3413 |
+
"step": 241500
|
| 3414 |
+
},
|
| 3415 |
+
{
|
| 3416 |
+
"epoch": 2.9115233764046295,
|
| 3417 |
+
"grad_norm": 0.008721483871340752,
|
| 3418 |
+
"learning_rate": 5.971430175573683e-07,
|
| 3419 |
+
"loss": 0.1555,
|
| 3420 |
+
"step": 242000
|
| 3421 |
+
},
|
| 3422 |
+
{
|
| 3423 |
+
"epoch": 2.9175389205707547,
|
| 3424 |
+
"grad_norm": 0.039840217679739,
|
| 3425 |
+
"learning_rate": 5.570393897831999e-07,
|
| 3426 |
+
"loss": 0.1427,
|
| 3427 |
+
"step": 242500
|
| 3428 |
+
},
|
| 3429 |
+
{
|
| 3430 |
+
"epoch": 2.9235544647368803,
|
| 3431 |
+
"grad_norm": 0.002139493590220809,
|
| 3432 |
+
"learning_rate": 5.170159692645797e-07,
|
| 3433 |
+
"loss": 0.1436,
|
| 3434 |
+
"step": 243000
|
| 3435 |
+
},
|
| 3436 |
+
{
|
| 3437 |
+
"epoch": 2.9295700089030055,
|
| 3438 |
+
"grad_norm": 0.0007610457250848413,
|
| 3439 |
+
"learning_rate": 4.769123414904113e-07,
|
| 3440 |
+
"loss": 0.1393,
|
| 3441 |
+
"step": 243500
|
| 3442 |
+
},
|
| 3443 |
+
{
|
| 3444 |
+
"epoch": 2.9355855530691306,
|
| 3445 |
+
"grad_norm": 0.05628383159637451,
|
| 3446 |
+
"learning_rate": 4.368087137162428e-07,
|
| 3447 |
+
"loss": 0.1699,
|
| 3448 |
+
"step": 244000
|
| 3449 |
+
},
|
| 3450 |
+
{
|
| 3451 |
+
"epoch": 2.9416010972352558,
|
| 3452 |
+
"grad_norm": 0.02916884608566761,
|
| 3453 |
+
"learning_rate": 3.9670508594207435e-07,
|
| 3454 |
+
"loss": 0.1401,
|
| 3455 |
+
"step": 244500
|
| 3456 |
+
},
|
| 3457 |
+
{
|
| 3458 |
+
"epoch": 2.947616641401381,
|
| 3459 |
+
"grad_norm": 0.11827978491783142,
|
| 3460 |
+
"learning_rate": 3.5660145816790586e-07,
|
| 3461 |
+
"loss": 0.168,
|
| 3462 |
+
"step": 245000
|
| 3463 |
+
},
|
| 3464 |
+
{
|
| 3465 |
+
"epoch": 2.9536321855675065,
|
| 3466 |
+
"grad_norm": 0.0027151680551469326,
|
| 3467 |
+
"learning_rate": 3.165780376492858e-07,
|
| 3468 |
+
"loss": 0.1561,
|
| 3469 |
+
"step": 245500
|
| 3470 |
+
},
|
| 3471 |
+
{
|
| 3472 |
+
"epoch": 2.9596477297336317,
|
| 3473 |
+
"grad_norm": 0.040678609162569046,
|
| 3474 |
+
"learning_rate": 2.764744098751173e-07,
|
| 3475 |
+
"loss": 0.1305,
|
| 3476 |
+
"step": 246000
|
| 3477 |
+
},
|
| 3478 |
+
{
|
| 3479 |
+
"epoch": 2.965663273899757,
|
| 3480 |
+
"grad_norm": 7.518092632293701,
|
| 3481 |
+
"learning_rate": 2.3637078210094888e-07,
|
| 3482 |
+
"loss": 0.2053,
|
| 3483 |
+
"step": 246500
|
| 3484 |
+
},
|
| 3485 |
+
{
|
| 3486 |
+
"epoch": 2.9716788180658824,
|
| 3487 |
+
"grad_norm": 0.18074116110801697,
|
| 3488 |
+
"learning_rate": 1.962671543267804e-07,
|
| 3489 |
+
"loss": 0.1548,
|
| 3490 |
+
"step": 247000
|
| 3491 |
+
},
|
| 3492 |
+
{
|
| 3493 |
+
"epoch": 2.9776943622320076,
|
| 3494 |
+
"grad_norm": 7.7608208656311035,
|
| 3495 |
+
"learning_rate": 1.5616352655261197e-07,
|
| 3496 |
+
"loss": 0.1676,
|
| 3497 |
+
"step": 247500
|
| 3498 |
+
},
|
| 3499 |
+
{
|
| 3500 |
+
"epoch": 2.9837099063981327,
|
| 3501 |
+
"grad_norm": 0.00906237680464983,
|
| 3502 |
+
"learning_rate": 1.1605989877844351e-07,
|
| 3503 |
+
"loss": 0.1534,
|
| 3504 |
+
"step": 248000
|
| 3505 |
+
},
|
| 3506 |
+
{
|
| 3507 |
+
"epoch": 2.989725450564258,
|
| 3508 |
+
"grad_norm": 179.03021240234375,
|
| 3509 |
+
"learning_rate": 7.595627100427505e-08,
|
| 3510 |
+
"loss": 0.1176,
|
| 3511 |
+
"step": 248500
|
| 3512 |
+
},
|
| 3513 |
+
{
|
| 3514 |
+
"epoch": 2.9957409947303835,
|
| 3515 |
+
"grad_norm": 0.00344484462402761,
|
| 3516 |
+
"learning_rate": 3.58526432301066e-08,
|
| 3517 |
+
"loss": 0.1711,
|
| 3518 |
+
"step": 249000
|
| 3519 |
+
},
|
| 3520 |
+
{
|
| 3521 |
+
"epoch": 3.0,
|
| 3522 |
+
"eval_accuracy": 0.6820289064630488,
|
| 3523 |
+
"eval_f1": 0.7003498950314906,
|
| 3524 |
+
"eval_loss": 0.4521113932132721,
|
| 3525 |
+
"eval_roc_auc": 0.8145350422688847,
|
| 3526 |
+
"eval_runtime": 110.6722,
|
| 3527 |
+
"eval_samples_per_second": 66.268,
|
| 3528 |
+
"eval_steps_per_second": 66.268,
|
| 3529 |
+
"step": 249354
|
| 3530 |
+
}
|
| 3531 |
+
],
|
| 3532 |
+
"logging_steps": 500,
|
| 3533 |
+
"max_steps": 249354,
|
| 3534 |
+
"num_input_tokens_seen": 0,
|
| 3535 |
+
"num_train_epochs": 3,
|
| 3536 |
+
"save_steps": 500,
|
| 3537 |
+
"stateful_callbacks": {
|
| 3538 |
+
"TrainerControl": {
|
| 3539 |
+
"args": {
|
| 3540 |
+
"should_epoch_stop": false,
|
| 3541 |
+
"should_evaluate": false,
|
| 3542 |
+
"should_log": false,
|
| 3543 |
+
"should_save": true,
|
| 3544 |
+
"should_training_stop": true
|
| 3545 |
+
},
|
| 3546 |
+
"attributes": {}
|
| 3547 |
+
}
|
| 3548 |
+
},
|
| 3549 |
+
"total_flos": 2.6370896223238963e+17,
|
| 3550 |
+
"train_batch_size": 1,
|
| 3551 |
+
"trial_name": null,
|
| 3552 |
+
"trial_params": null
|
| 3553 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:218237e271086699b6de5ced31fd1aa0e37b6ecf241c2dd4235bc7b87eb1ddbc
|
| 3 |
+
size 5368
|