Model save

README.md

@@ -0,0 +1,58 @@
+---
+base_model: openchat/openchat_3.5
+library_name: transformers
+model_name: openchat_3.5_minecraft
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for openchat_3.5_minecraft
+
+This model is a fine-tuned version of [openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="gsantopaolo/openchat_3.5_minecraft", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0
+- Transformers: 4.46.3
+- Pytorch: 2.4.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 2.076446432428032e+16,
+    "train_loss": 0.35404008832471123,
+    "train_runtime": 641.0129,
+    "train_samples": 1000,
+    "train_samples_per_second": 0.729,
+    "train_steps_per_second": 0.045
+}

runs/Feb26_23-08-42_Ubuntu-2204-jammy-amd64-base/events.out.tfevents.1740611328.Ubuntu-2204-jammy-amd64-base.3880085.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177f77719095149cbe16e5b959d5fa8216babbb8b22029d4ec8d32ff5429fc76
-size 6917
+oid sha256:e29b0b56e7230d33dc2e65e0139dffe5b6a7ca0bbf6e027c347f73179bc6b9bc
+size 7265

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 2.076446432428032e+16,
+    "train_loss": 0.35404008832471123,
+    "train_runtime": 641.0129,
+    "train_samples": 1000,
+    "train_samples_per_second": 0.729,
+    "train_steps_per_second": 0.045
+}

trainer_state.json

@@ -0,0 +1,77 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9914529914529915,
+  "eval_steps": 500,
+  "global_step": 29,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17094017094017094,
+      "grad_norm": 9.959121704101562,
+      "learning_rate": 0.0002,
+      "loss": 0.6806,
+      "step": 5
+    },
+    {
+      "epoch": 0.3418803418803419,
+      "grad_norm": 5.6184234619140625,
+      "learning_rate": 0.0002,
+      "loss": 0.3159,
+      "step": 10
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 4.505366802215576,
+      "learning_rate": 0.0002,
+      "loss": 0.3051,
+      "step": 15
+    },
+    {
+      "epoch": 0.6837606837606838,
+      "grad_norm": 225.4312286376953,
+      "learning_rate": 0.0002,
+      "loss": 0.2811,
+      "step": 20
+    },
+    {
+      "epoch": 0.8547008547008547,
+      "grad_norm": 2.728710889816284,
+      "learning_rate": 0.0002,
+      "loss": 0.2533,
+      "step": 25
+    },
+    {
+      "epoch": 0.9914529914529915,
+      "step": 29,
+      "total_flos": 2.076446432428032e+16,
+      "train_loss": 0.35404008832471123,
+      "train_runtime": 641.0129,
+      "train_samples_per_second": 0.729,
+      "train_steps_per_second": 0.045
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 29,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.076446432428032e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}