Training in progress, step 300000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f3c58283d58c48daa19f5eb603db483b025adeae0cdf1cd66544ead24e8ccf7
+oid sha256:db51f55bf1a16f0aa27746b583a094e054e9a9dfc4763b285a75a463ec28ba4e
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5699b0b7ef50cd33ac6f4846dedf2f505fecf3d7ff9d78dc3ed3e85c757275a
+oid sha256:daf63bd5c42184ed6348a862f43229e825f00ce4dfcc6c106b3192d2a71460f8
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac290f112ea8baf2c071fbd5a9b36dcbeb3439f0cac85d64dccb4a0169569875
+oid sha256:ddc2096dd2c2f53f22fb4b877201d9217020b1902bfdb0e198941bfd92059ed8
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bc196d8aea9810b9698ff8cd04e2aeef8774f706fbd61ae0f0055bbacd0eaf
+oid sha256:7914b9f1e3709b1198ec189eb9bb9105cd6b88dedbcbbdd4128934a703cf33e3
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.468593861527481,
-  "global_step": 290000,
+  "epoch": 6.691648822269808,
+  "global_step": 300000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5806,11 +5806,211 @@
       "eval_samples_per_second": 1164.356,
       "eval_steps_per_second": 18.249,
       "step": 290000
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 0.00012830086996475274,
+      "loss": 0.2707,
+      "step": 290500
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 0.00012782970938506988,
+      "loss": 0.2707,
+      "step": 291000
+    },
+    {
+      "epoch": 6.49,
+      "eval_loss": 0.2514384388923645,
+      "eval_runtime": 2.0121,
+      "eval_samples_per_second": 1141.574,
+      "eval_steps_per_second": 17.891,
+      "step": 291000
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 0.00012735884593533222,
+      "loss": 0.2706,
+      "step": 291500
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 0.0001268882847648268,
+      "loss": 0.2702,
+      "step": 292000
+    },
+    {
+      "epoch": 6.51,
+      "eval_loss": 0.2527428865432739,
+      "eval_runtime": 2.1423,
+      "eval_samples_per_second": 1072.197,
+      "eval_steps_per_second": 16.804,
+      "step": 292000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 0.00012641803101953535,
+      "loss": 0.271,
+      "step": 292500
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 0.00012594808984207743,
+      "loss": 0.2702,
+      "step": 293000
+    },
+    {
+      "epoch": 6.54,
+      "eval_loss": 0.2542712688446045,
+      "eval_runtime": 2.0253,
+      "eval_samples_per_second": 1134.154,
+      "eval_steps_per_second": 17.775,
+      "step": 293000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 0.00012547846637165445,
+      "loss": 0.2698,
+      "step": 293500
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 0.00012500916574399346,
+      "loss": 0.27,
+      "step": 294000
+    },
+    {
+      "epoch": 6.56,
+      "eval_loss": 0.25084540247917175,
+      "eval_runtime": 1.9928,
+      "eval_samples_per_second": 1152.639,
+      "eval_steps_per_second": 18.065,
+      "step": 294000
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 0.00012454019309129095,
+      "loss": 0.2698,
+      "step": 294500
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 0.0001240715535421567,
+      "loss": 0.27,
+      "step": 295000
+    },
+    {
+      "epoch": 6.58,
+      "eval_loss": 0.252863347530365,
+      "eval_runtime": 1.9718,
+      "eval_samples_per_second": 1164.945,
+      "eval_steps_per_second": 18.258,
+      "step": 295000
+    },
+    {
+      "epoch": 6.59,
+      "learning_rate": 0.00012360325222155773,
+      "loss": 0.2701,
+      "step": 295500
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 0.00012313529425076228,
+      "loss": 0.2697,
+      "step": 296000
+    },
+    {
+      "epoch": 6.6,
+      "eval_loss": 0.25461703538894653,
+      "eval_runtime": 1.9521,
+      "eval_samples_per_second": 1176.688,
+      "eval_steps_per_second": 18.442,
+      "step": 296000
+    },
+    {
+      "epoch": 6.61,
+      "learning_rate": 0.00012266768474728372,
+      "loss": 0.2698,
+      "step": 296500
+    },
+    {
+      "epoch": 6.62,
+      "learning_rate": 0.00012220042882482468,
+      "loss": 0.2703,
+      "step": 297000
+    },
+    {
+      "epoch": 6.62,
+      "eval_loss": 0.2524978220462799,
+      "eval_runtime": 2.026,
+      "eval_samples_per_second": 1133.755,
+      "eval_steps_per_second": 17.769,
+      "step": 297000
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 0.00012173353159322102,
+      "loss": 0.2695,
+      "step": 297500
+    },
+    {
+      "epoch": 6.65,
+      "learning_rate": 0.00012126699815838609,
+      "loss": 0.2697,
+      "step": 298000
+    },
+    {
+      "epoch": 6.65,
+      "eval_loss": 0.2543928623199463,
+      "eval_runtime": 1.9625,
+      "eval_samples_per_second": 1170.438,
+      "eval_steps_per_second": 18.344,
+      "step": 298000
+    },
+    {
+      "epoch": 6.66,
+      "learning_rate": 0.00012080083362225484,
+      "loss": 0.2696,
+      "step": 298500
+    },
+    {
+      "epoch": 6.67,
+      "learning_rate": 0.00012033504308272786,
+      "loss": 0.2698,
+      "step": 299000
+    },
+    {
+      "epoch": 6.67,
+      "eval_loss": 0.24954737722873688,
+      "eval_runtime": 1.9913,
+      "eval_samples_per_second": 1153.505,
+      "eval_steps_per_second": 18.078,
+      "step": 299000
+    },
+    {
+      "epoch": 6.68,
+      "learning_rate": 0.00011986963163361598,
+      "loss": 0.2715,
+      "step": 299500
+    },
+    {
+      "epoch": 6.69,
+      "learning_rate": 0.0001194046043645841,
+      "loss": 0.274,
+      "step": 300000
+    },
+    {
+      "epoch": 6.69,
+      "eval_loss": 0.2508510649204254,
+      "eval_runtime": 1.967,
+      "eval_samples_per_second": 1167.773,
+      "eval_steps_per_second": 18.302,
+      "step": 300000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 9.264956298892008e+21,
+  "total_flos": 9.584443437666508e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5699b0b7ef50cd33ac6f4846dedf2f505fecf3d7ff9d78dc3ed3e85c757275a
+oid sha256:daf63bd5c42184ed6348a862f43229e825f00ce4dfcc6c106b3192d2a71460f8
 size 102501541