Training in progress, step 120000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0c13c2b4862e7a34ebc8b922768e1e9178a36b674a1308c54623a6b682441d
+oid sha256:84c27558da026f6ac6f829599c8d9ba0e7ad0551d0a475705ca3d50371f47fe6
 size 50044689

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a822dc652f5b5007dd659ff9a97261c9af2e549d16d025cb7bff7d5d1f73941
+oid sha256:741994f4c9e1568601969909c18e19f79331bf84d435cca376c7e346bb47a00d
 size 25761253

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b376139e7a9e28339f66d6b916608b35982b8acd6efb16cc7b604be132a5044c
+oid sha256:ad6f74feb9a4e4b8282d7fcaa0ade2acc29050c48ee19da4d55b9134c586370c
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe4bb2f202e1c5bfac6f58d7d7aff54991c6919cce0ee2976f31297f1718992f
+oid sha256:c534c69c702472a462ee5c5c8e40f09fd7295b5cb464c1c3364c271724c3d05b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.740196078431373,
-  "global_step": 110000,
+  "epoch": 7.352941176470588,
+  "global_step": 120000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2206,11 +2206,211 @@
       "eval_samples_per_second": 777.303,
       "eval_steps_per_second": 12.437,
       "step": 110000
+    },
+    {
+      "epoch": 6.77,
+      "learning_rate": 0.00038495756080926107,
+      "loss": 0.4802,
+      "step": 110500
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 0.0003830777659310416,
+      "loss": 0.4801,
+      "step": 111000
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 0.8152140974998474,
+      "eval_runtime": 1.3248,
+      "eval_samples_per_second": 754.82,
+      "eval_steps_per_second": 12.077,
+      "step": 111000
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 0.0003811945556784033,
+      "loss": 0.4795,
+      "step": 111500
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 0.00037930801242906366,
+      "loss": 0.4792,
+      "step": 112000
+    },
+    {
+      "epoch": 6.86,
+      "eval_loss": 0.8089267015457153,
+      "eval_runtime": 1.2928,
+      "eval_samples_per_second": 773.538,
+      "eval_steps_per_second": 12.377,
+      "step": 112000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 0.00037741821870653576,
+      "loss": 0.4789,
+      "step": 112500
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 0.00037552525717651905,
+      "loss": 0.4785,
+      "step": 113000
+    },
+    {
+      "epoch": 6.92,
+      "eval_loss": 0.808442234992981,
+      "eval_runtime": 1.3221,
+      "eval_samples_per_second": 756.389,
+      "eval_steps_per_second": 12.102,
+      "step": 113000
+    },
+    {
+      "epoch": 6.95,
+      "learning_rate": 0.0003736292106432834,
+      "loss": 0.4782,
+      "step": 113500
+    },
+    {
+      "epoch": 6.99,
+      "learning_rate": 0.00037173016204604647,
+      "loss": 0.4777,
+      "step": 114000
+    },
+    {
+      "epoch": 6.99,
+      "eval_loss": 0.8103413581848145,
+      "eval_runtime": 1.3239,
+      "eval_samples_per_second": 755.361,
+      "eval_steps_per_second": 12.086,
+      "step": 114000
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 0.0003698281944553456,
+      "loss": 0.4774,
+      "step": 114500
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 0.0003679233910694053,
+      "loss": 0.477,
+      "step": 115000
+    },
+    {
+      "epoch": 7.05,
+      "eval_loss": 0.8103800415992737,
+      "eval_runtime": 1.3524,
+      "eval_samples_per_second": 739.44,
+      "eval_steps_per_second": 11.831,
+      "step": 115000
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 0.000366015835210496,
+      "loss": 0.4767,
+      "step": 115500
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 0.0003641056103212908,
+      "loss": 0.4772,
+      "step": 116000
+    },
+    {
+      "epoch": 7.11,
+      "eval_loss": 0.8142406344413757,
+      "eval_runtime": 1.3149,
+      "eval_samples_per_second": 760.539,
+      "eval_steps_per_second": 12.169,
+      "step": 116000
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.00036219279996121446,
+      "loss": 0.4758,
+      "step": 116500
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 0.0003602774878027888,
+      "loss": 0.4754,
+      "step": 117000
+    },
+    {
+      "epoch": 7.17,
+      "eval_loss": 0.8158754706382751,
+      "eval_runtime": 1.2794,
+      "eval_samples_per_second": 781.632,
+      "eval_steps_per_second": 12.506,
+      "step": 117000
+    },
+    {
+      "epoch": 7.2,
+      "learning_rate": 0.00035835975762797245,
+      "loss": 0.4749,
+      "step": 117500
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 0.0003564396933244957,
+      "loss": 0.4748,
+      "step": 118000
+    },
+    {
+      "epoch": 7.23,
+      "eval_loss": 0.8092423677444458,
+      "eval_runtime": 1.319,
+      "eval_samples_per_second": 758.146,
+      "eval_steps_per_second": 12.13,
+      "step": 118000
+    },
+    {
+      "epoch": 7.26,
+      "learning_rate": 0.0003545173788821915,
+      "loss": 0.4742,
+      "step": 118500
+    },
+    {
+      "epoch": 7.29,
+      "learning_rate": 0.00035259289838932104,
+      "loss": 0.4738,
+      "step": 119000
+    },
+    {
+      "epoch": 7.29,
+      "eval_loss": 0.8036469221115112,
+      "eval_runtime": 1.3425,
+      "eval_samples_per_second": 744.902,
+      "eval_steps_per_second": 11.918,
+      "step": 119000
+    },
+    {
+      "epoch": 7.32,
+      "learning_rate": 0.0003506663360288954,
+      "loss": 0.4736,
+      "step": 119500
+    },
+    {
+      "epoch": 7.35,
+      "learning_rate": 0.00034873777607499334,
+      "loss": 0.473,
+      "step": 120000
+    },
+    {
+      "epoch": 7.35,
+      "eval_loss": 0.8085124492645264,
+      "eval_runtime": 1.3135,
+      "eval_samples_per_second": 761.353,
+      "eval_steps_per_second": 12.182,
+      "step": 120000
     }
   ],
   "max_steps": 250000,
   "num_train_epochs": 16,
-  "total_flos": 1.7617879685021544e+21,
+  "total_flos": 1.9219459608643434e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a822dc652f5b5007dd659ff9a97261c9af2e549d16d025cb7bff7d5d1f73941
+oid sha256:741994f4c9e1568601969909c18e19f79331bf84d435cca376c7e346bb47a00d
 size 25761253