Training in progress, step 380000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8884578ecff20bdc143758e28e0d85c34dad8dbfa37132c1e5318c8f80a9a1be
+oid sha256:e0bfce1b1773be96f0d3fe813d2ed231bcc619aa9d86090dabfebda938938679
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797df8ba5787bd4a5fbf872ca4b3fe3fdb3db1dba64902a8c55adee164838ae0
+oid sha256:fd79899bdba4b0a42b6695b21b791ea0a1c2b1e7f7e8aeb0419ab9a5bb16c136
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc84ada216c0172437f14147bb53f92637e055287492931833e7c516a6d9eed3
+oid sha256:1aa9c03b0f188995dd79f725ff6a9978a0d337dceeebc68b1530033452b02bc6
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:580594f4768ecd1bd92e87dca92e874365a397305161c1f8781b79f1f0b613ba
+oid sha256:7c2047b5f47fc3de929bb0738f7fbdd248300ab063f6fd4eddcabc29f5482852
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.429634537947909,
-  "global_step": 370000,
+  "epoch": 9.684489525460013,
+  "global_step": 380000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7406,11 +7406,211 @@
       "eval_samples_per_second": 766.44,
       "eval_steps_per_second": 12.263,
       "step": 370000
+    },
+    {
+      "epoch": 9.44,
+      "learning_rate": 6.0012253629189544e-05,
+      "loss": 0.2753,
+      "step": 370500
+    },
+    {
+      "epoch": 9.46,
+      "learning_rate": 5.965048145015944e-05,
+      "loss": 0.2745,
+      "step": 371000
+    },
+    {
+      "epoch": 9.46,
+      "eval_loss": 0.807996928691864,
+      "eval_runtime": 1.2961,
+      "eval_samples_per_second": 771.545,
+      "eval_steps_per_second": 12.345,
+      "step": 371000
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 5.928975199818785e-05,
+      "loss": 0.2744,
+      "step": 371500
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 5.893006921815428e-05,
+      "loss": 0.2745,
+      "step": 372000
+    },
+    {
+      "epoch": 9.48,
+      "eval_loss": 0.8102282881736755,
+      "eval_runtime": 1.3228,
+      "eval_samples_per_second": 755.978,
+      "eval_steps_per_second": 12.096,
+      "step": 372000
+    },
+    {
+      "epoch": 9.49,
+      "learning_rate": 5.857143704349198e-05,
+      "loss": 0.2749,
+      "step": 372500
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 5.8213859396144986e-05,
+      "loss": 0.2747,
+      "step": 373000
+    },
+    {
+      "epoch": 9.51,
+      "eval_loss": 0.8059311509132385,
+      "eval_runtime": 1.3365,
+      "eval_samples_per_second": 748.226,
+      "eval_steps_per_second": 11.972,
+      "step": 373000
+    },
+    {
+      "epoch": 9.52,
+      "learning_rate": 5.785734018652507e-05,
+      "loss": 0.2743,
+      "step": 373500
+    },
+    {
+      "epoch": 9.53,
+      "learning_rate": 5.750188331346927e-05,
+      "loss": 0.2742,
+      "step": 374000
+    },
+    {
+      "epoch": 9.53,
+      "eval_loss": 0.8084880113601685,
+      "eval_runtime": 1.3112,
+      "eval_samples_per_second": 762.675,
+      "eval_steps_per_second": 12.203,
+      "step": 374000
+    },
+    {
+      "epoch": 9.54,
+      "learning_rate": 5.714749266419695e-05,
+      "loss": 0.2741,
+      "step": 374500
+    },
+    {
+      "epoch": 9.56,
+      "learning_rate": 5.6794172114267566e-05,
+      "loss": 0.2742,
+      "step": 375000
+    },
+    {
+      "epoch": 9.56,
+      "eval_loss": 0.8031001091003418,
+      "eval_runtime": 1.2768,
+      "eval_samples_per_second": 783.2,
+      "eval_steps_per_second": 12.531,
+      "step": 375000
+    },
+    {
+      "epoch": 9.57,
+      "learning_rate": 5.6441925527537914e-05,
+      "loss": 0.2738,
+      "step": 375500
+    },
+    {
+      "epoch": 9.58,
+      "learning_rate": 5.60907567561203e-05,
+      "loss": 0.274,
+      "step": 376000
+    },
+    {
+      "epoch": 9.58,
+      "eval_loss": 0.8067184090614319,
+      "eval_runtime": 1.3299,
+      "eval_samples_per_second": 751.95,
+      "eval_steps_per_second": 12.031,
+      "step": 376000
+    },
+    {
+      "epoch": 9.6,
+      "learning_rate": 5.574066964034012e-05,
+      "loss": 0.274,
+      "step": 376500
+    },
+    {
+      "epoch": 9.61,
+      "learning_rate": 5.539166800869402e-05,
+      "loss": 0.274,
+      "step": 377000
+    },
+    {
+      "epoch": 9.61,
+      "eval_loss": 0.8057398200035095,
+      "eval_runtime": 1.2808,
+      "eval_samples_per_second": 780.764,
+      "eval_steps_per_second": 12.492,
+      "step": 377000
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 5.5043755677807955e-05,
+      "loss": 0.2738,
+      "step": 377500
+    },
+    {
+      "epoch": 9.63,
+      "learning_rate": 5.4696936452395344e-05,
+      "loss": 0.274,
+      "step": 378000
+    },
+    {
+      "epoch": 9.63,
+      "eval_loss": 0.8031483292579651,
+      "eval_runtime": 1.2827,
+      "eval_samples_per_second": 779.634,
+      "eval_steps_per_second": 12.474,
+      "step": 378000
+    },
+    {
+      "epoch": 9.65,
+      "learning_rate": 5.435121412521576e-05,
+      "loss": 0.2738,
+      "step": 378500
+    },
+    {
+      "epoch": 9.66,
+      "learning_rate": 5.400659247703307e-05,
+      "loss": 0.2738,
+      "step": 379000
+    },
+    {
+      "epoch": 9.66,
+      "eval_loss": 0.8066932559013367,
+      "eval_runtime": 1.3559,
+      "eval_samples_per_second": 737.531,
+      "eval_steps_per_second": 11.8,
+      "step": 379000
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 5.36630752765745e-05,
+      "loss": 0.2739,
+      "step": 379500
+    },
+    {
+      "epoch": 9.68,
+      "learning_rate": 5.3320666280489146e-05,
+      "loss": 0.2737,
+      "step": 380000
+    },
+    {
+      "epoch": 9.68,
+      "eval_loss": 0.8089754581451416,
+      "eval_runtime": 1.319,
+      "eval_samples_per_second": 758.149,
+      "eval_steps_per_second": 12.13,
+      "step": 380000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 1.1820902824439095e+22,
+  "total_flos": 1.2140389963213595e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797df8ba5787bd4a5fbf872ca4b3fe3fdb3db1dba64902a8c55adee164838ae0
+oid sha256:fd79899bdba4b0a42b6695b21b791ea0a1c2b1e7f7e8aeb0419ab9a5bb16c136
 size 102501541