Training in progress, step 380000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba96dd35e00ace18b94e8b7c9d6ac3847b25cde1f7484591538c5649c4a08f7b
+oid sha256:acfe31078427c2466c04f91ee9954112b94b597697f50ae668465f7dbaa80c33
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd745c45e4cdbda8372d987841bb70690d37f324dbbf3f318e5d8354379d61b
+oid sha256:671a639f98cfc5cfe3a76fa4d953a2396bd5fea5c2da42dd392d72e90b22a992
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d54975af93d0f6d21dde5cd497a48c2f9e6eccddf61cadc650b6ec7a212011a
+oid sha256:a6efc0dba6eb98b22955214199c73c4905ac919dfd211579a6b4dec17e2f9c75
 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": 8.253033547466096,
-  "global_step": 370000,
+  "epoch": 8.476088508208422,
+  "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": 1151.317,
       "eval_steps_per_second": 18.044,
       "step": 370000
+    },
+    {
+      "epoch": 8.26,
+      "learning_rate": 6.0012253629189544e-05,
+      "loss": 0.261,
+      "step": 370500
+    },
+    {
+      "epoch": 8.28,
+      "learning_rate": 5.965048145015944e-05,
+      "loss": 0.2611,
+      "step": 371000
+    },
+    {
+      "epoch": 8.28,
+      "eval_loss": 0.24591800570487976,
+      "eval_runtime": 1.9624,
+      "eval_samples_per_second": 1170.514,
+      "eval_steps_per_second": 18.345,
+      "step": 371000
+    },
+    {
+      "epoch": 8.29,
+      "learning_rate": 5.928975199818785e-05,
+      "loss": 0.2611,
+      "step": 371500
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 5.893006921815428e-05,
+      "loss": 0.2608,
+      "step": 372000
+    },
+    {
+      "epoch": 8.3,
+      "eval_loss": 0.2432386726140976,
+      "eval_runtime": 2.0093,
+      "eval_samples_per_second": 1143.209,
+      "eval_steps_per_second": 17.917,
+      "step": 372000
+    },
+    {
+      "epoch": 8.31,
+      "learning_rate": 5.857143704349198e-05,
+      "loss": 0.2608,
+      "step": 372500
+    },
+    {
+      "epoch": 8.32,
+      "learning_rate": 5.8213859396144986e-05,
+      "loss": 0.2605,
+      "step": 373000
+    },
+    {
+      "epoch": 8.32,
+      "eval_loss": 0.2445555180311203,
+      "eval_runtime": 1.9525,
+      "eval_samples_per_second": 1176.451,
+      "eval_steps_per_second": 18.438,
+      "step": 373000
+    },
+    {
+      "epoch": 8.33,
+      "learning_rate": 5.785734018652507e-05,
+      "loss": 0.2609,
+      "step": 373500
+    },
+    {
+      "epoch": 8.34,
+      "learning_rate": 5.750188331346927e-05,
+      "loss": 0.2609,
+      "step": 374000
+    },
+    {
+      "epoch": 8.34,
+      "eval_loss": 0.24143685400485992,
+      "eval_runtime": 1.9945,
+      "eval_samples_per_second": 1151.665,
+      "eval_steps_per_second": 18.05,
+      "step": 374000
+    },
+    {
+      "epoch": 8.35,
+      "learning_rate": 5.714749266419695e-05,
+      "loss": 0.2605,
+      "step": 374500
+    },
+    {
+      "epoch": 8.36,
+      "learning_rate": 5.6794172114267566e-05,
+      "loss": 0.2614,
+      "step": 375000
+    },
+    {
+      "epoch": 8.36,
+      "eval_loss": 0.2436528205871582,
+      "eval_runtime": 1.9628,
+      "eval_samples_per_second": 1170.242,
+      "eval_steps_per_second": 18.341,
+      "step": 375000
+    },
+    {
+      "epoch": 8.38,
+      "learning_rate": 5.6441925527537914e-05,
+      "loss": 0.2614,
+      "step": 375500
+    },
+    {
+      "epoch": 8.39,
+      "learning_rate": 5.60907567561203e-05,
+      "loss": 0.2624,
+      "step": 376000
+    },
+    {
+      "epoch": 8.39,
+      "eval_loss": 0.24615313112735748,
+      "eval_runtime": 1.9915,
+      "eval_samples_per_second": 1153.415,
+      "eval_steps_per_second": 18.077,
+      "step": 376000
+    },
+    {
+      "epoch": 8.4,
+      "learning_rate": 5.574066964034012e-05,
+      "loss": 0.2614,
+      "step": 376500
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 5.539166800869402e-05,
+      "loss": 0.2611,
+      "step": 377000
+    },
+    {
+      "epoch": 8.41,
+      "eval_loss": 0.24158482253551483,
+      "eval_runtime": 1.9896,
+      "eval_samples_per_second": 1154.526,
+      "eval_steps_per_second": 18.094,
+      "step": 377000
+    },
+    {
+      "epoch": 8.42,
+      "learning_rate": 5.5043755677807955e-05,
+      "loss": 0.261,
+      "step": 377500
+    },
+    {
+      "epoch": 8.43,
+      "learning_rate": 5.4696936452395344e-05,
+      "loss": 0.2604,
+      "step": 378000
+    },
+    {
+      "epoch": 8.43,
+      "eval_loss": 0.2432401180267334,
+      "eval_runtime": 1.9707,
+      "eval_samples_per_second": 1165.6,
+      "eval_steps_per_second": 18.268,
+      "step": 378000
+    },
+    {
+      "epoch": 8.44,
+      "learning_rate": 5.435121412521576e-05,
+      "loss": 0.2604,
+      "step": 378500
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 5.400659247703307e-05,
+      "loss": 0.2605,
+      "step": 379000
+    },
+    {
+      "epoch": 8.45,
+      "eval_loss": 0.24426017701625824,
+      "eval_runtime": 2.017,
+      "eval_samples_per_second": 1138.839,
+      "eval_steps_per_second": 17.849,
+      "step": 379000
+    },
+    {
+      "epoch": 8.46,
+      "learning_rate": 5.36630752765745e-05,
+      "loss": 0.2605,
+      "step": 379500
+    },
+    {
+      "epoch": 8.48,
+      "learning_rate": 5.3320666280489146e-05,
+      "loss": 0.26,
+      "step": 380000
+    },
+    {
+      "epoch": 8.48,
+      "eval_loss": 0.24248941242694855,
+      "eval_runtime": 2.0075,
+      "eval_samples_per_second": 1144.188,
+      "eval_steps_per_second": 17.932,
+      "step": 380000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 12,
-  "total_flos": 1.1820796500565178e+22,
+  "total_flos": 1.2140283639339678e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdd745c45e4cdbda8372d987841bb70690d37f324dbbf3f318e5d8354379d61b
+oid sha256:671a639f98cfc5cfe3a76fa4d953a2396bd5fea5c2da42dd392d72e90b22a992
 size 102501541