Training in progress, step 200000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae8b37bb3ef93266027d70d0e00d87efb44bc4019ad917063c09c81cee6c0fef
+oid sha256:66a034e9e1a9ae7c11a38b09da94316f7af857583cc75efaab5288ad761a4759
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef92818d243a4d1828d62172dbe43bff5dcd02b87cc9982faba5e24c9f7d637
+oid sha256:cfe293a94506a0e024ec476b57e64723da55912f72fe82601c25ed8e88dd3d77
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27ac61f2483d09b304f5bf47988fc50deadbc74a73d6e7fefa73c39e537290c
-size 14439
+oid sha256:27b65aef852c56a6070eb0b0c0dcb2609bdee33892af326659c5e916144ee935
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e0fb22612ddda1e707530c7b94de033aded05bbe199ff38f1fecf009e4774c0
-size 14439
+oid sha256:50df4816cbaa34ba1b53e6066397f6b5dfa9e0b5a42191fa041b389e35141af5
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2215278ab48eb111ec43fff1ae065a4f7afae50fbcb1a654d0f802e588d405a9
-size 14503
+oid sha256:99c375b0eb05f3b84a9ffd242709f5cafdfac9ec9f6eb782f404bfa519ad8d88
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dd18359c537f071111eb3e8deb7a71a5fcf4dbb9405ac62ad7e7fda32e4ae8a
+oid sha256:f1225a9177adba9ce38ceb1af0c8098a1a68d43fed76f6471ce68525b7fe2bef
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382b413dfab48b07c22c47e33b4e458bbb779fe715bce1ce251c374236864125
-size 14439
+oid sha256:2159e22012f5706c7baac54c9475075e6a80f8026c23532336808d0140a2feea
+size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb8e841c948ba30f2f4604f711e7d297aa99f75c94f47e268088ac349f37f65
-size 14439
+oid sha256:ad5204915df8edf520dd956c8e88b1a505319e42237567e2e0d2cc11f8993db5
+size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c349e058fdec7be9df0364808b4348ab83fd3dc0926ee604186a2bf094abe0b
+oid sha256:0083ff5459b01e74d8269a09b7fb0407b955c9098992dc865792b4c832e05385
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7ced809382dda0f6a1445f89e0ce2bdd33b73bdfa295160cd94e6048944943
-size 14439
+oid sha256:ef9a8f48c4b1e1e02dc723041280e57b4a38fe76785f0eae322407bb67501005
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0439027dd6f55adc764cb1317d963df8ccf36442066dafecce10b3f538efa8e
+oid sha256:6e461416c63c82734faef19b4949af829ad430bff342d30400b1c1da0cafb58f
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.821256778700328,
-  "global_step": 190000,
+  "epoch": 6.127638714421398,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3806,11 +3806,211 @@
       "eval_samples_per_second": 1917.115,
       "eval_steps_per_second": 30.674,
       "step": 190000
+    },
+    {
+      "epoch": 5.84,
+      "learning_rate": 0.00022146867474920118,
+      "loss": 0.347,
+      "step": 190500
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 0.00022104215397571484,
+      "loss": 0.3473,
+      "step": 191000
+    },
+    {
+      "epoch": 5.85,
+      "eval_loss": 0.7774147391319275,
+      "eval_runtime": 0.5178,
+      "eval_samples_per_second": 1931.312,
+      "eval_steps_per_second": 30.901,
+      "step": 191000
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 0.0002206149109758135,
+      "loss": 0.3472,
+      "step": 191500
+    },
+    {
+      "epoch": 5.88,
+      "learning_rate": 0.00022018695042175818,
+      "loss": 0.3482,
+      "step": 192000
+    },
+    {
+      "epoch": 5.88,
+      "eval_loss": 0.7872973680496216,
+      "eval_runtime": 0.5262,
+      "eval_samples_per_second": 1900.242,
+      "eval_steps_per_second": 30.404,
+      "step": 192000
+    },
+    {
+      "epoch": 5.9,
+      "learning_rate": 0.00021975827699365693,
+      "loss": 0.3467,
+      "step": 192500
+    },
+    {
+      "epoch": 5.91,
+      "learning_rate": 0.00021932889537941365,
+      "loss": 0.3482,
+      "step": 193000
+    },
+    {
+      "epoch": 5.91,
+      "eval_loss": 0.7847963571548462,
+      "eval_runtime": 0.5508,
+      "eval_samples_per_second": 1815.574,
+      "eval_steps_per_second": 29.049,
+      "step": 193000
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 0.0002188988102746769,
+      "loss": 0.3467,
+      "step": 193500
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 0.0002184680263827885,
+      "loss": 0.3484,
+      "step": 194000
+    },
+    {
+      "epoch": 5.94,
+      "eval_loss": 0.7891322374343872,
+      "eval_runtime": 0.5219,
+      "eval_samples_per_second": 1915.989,
+      "eval_steps_per_second": 30.656,
+      "step": 194000
+    },
+    {
+      "epoch": 5.96,
+      "learning_rate": 0.00021803654841473204,
+      "loss": 0.346,
+      "step": 194500
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 0.00021760438108908142,
+      "loss": 0.3457,
+      "step": 195000
+    },
+    {
+      "epoch": 5.97,
+      "eval_loss": 0.784561276435852,
+      "eval_runtime": 0.5317,
+      "eval_samples_per_second": 1880.904,
+      "eval_steps_per_second": 30.094,
+      "step": 195000
+    },
+    {
+      "epoch": 5.99,
+      "learning_rate": 0.0002171715291319494,
+      "loss": 0.3479,
+      "step": 195500
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 0.0002167379972769355,
+      "loss": 0.3465,
+      "step": 196000
+    },
+    {
+      "epoch": 6.01,
+      "eval_loss": 0.7826551795005798,
+      "eval_runtime": 0.519,
+      "eval_samples_per_second": 1926.794,
+      "eval_steps_per_second": 30.829,
+      "step": 196000
+    },
+    {
+      "epoch": 6.02,
+      "learning_rate": 0.0002163037902650747,
+      "loss": 0.3459,
+      "step": 196500
+    },
+    {
+      "epoch": 6.04,
+      "learning_rate": 0.0002158689128447853,
+      "loss": 0.3456,
+      "step": 197000
+    },
+    {
+      "epoch": 6.04,
+      "eval_loss": 0.7869973182678223,
+      "eval_runtime": 0.5199,
+      "eval_samples_per_second": 1923.629,
+      "eval_steps_per_second": 30.778,
+      "step": 197000
+    },
+    {
+      "epoch": 6.05,
+      "learning_rate": 0.00021543336977181704,
+      "loss": 0.3456,
+      "step": 197500
+    },
+    {
+      "epoch": 6.07,
+      "learning_rate": 0.00021499716580919933,
+      "loss": 0.3458,
+      "step": 198000
+    },
+    {
+      "epoch": 6.07,
+      "eval_loss": 0.7797828912734985,
+      "eval_runtime": 0.5178,
+      "eval_samples_per_second": 1931.291,
+      "eval_steps_per_second": 30.901,
+      "step": 198000
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 0.00021456030572718866,
+      "loss": 0.3456,
+      "step": 198500
+    },
+    {
+      "epoch": 6.1,
+      "learning_rate": 0.000214122794303217,
+      "loss": 0.3454,
+      "step": 199000
+    },
+    {
+      "epoch": 6.1,
+      "eval_loss": 0.7822918891906738,
+      "eval_runtime": 0.5124,
+      "eval_samples_per_second": 1951.652,
+      "eval_steps_per_second": 31.226,
+      "step": 199000
+    },
+    {
+      "epoch": 6.11,
+      "learning_rate": 0.00021368463632183912,
+      "loss": 0.3454,
+      "step": 199500
+    },
+    {
+      "epoch": 6.13,
+      "learning_rate": 0.00021324583657468055,
+      "loss": 0.3454,
+      "step": 200000
+    },
+    {
+      "epoch": 6.13,
+      "eval_loss": 0.779866635799408,
+      "eval_runtime": 0.5273,
+      "eval_samples_per_second": 1896.43,
+      "eval_steps_per_second": 30.343,
+      "step": 200000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 16,
-  "total_flos": 6.070215696955621e+21,
+  "total_flos": 6.389694847778145e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eef92818d243a4d1828d62172dbe43bff5dcd02b87cc9982faba5e24c9f7d637
+oid sha256:cfe293a94506a0e024ec476b57e64723da55912f72fe82601c25ed8e88dd3d77
 size 102501541