Training in progress, step 330000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e953bb14c52ac73828ddbb8d0fdec2f5d345e3cbc51fce0abb2a9e0782d8fb45
+oid sha256:e7d2a5e73283aa1880b29f29feb6316701d271842328e195271c3e399e6c920a
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbb0a403c4c85850b5f1bad1d089cdec8ce35c071f9b4d707f0145c3de24b2e
+oid sha256:4fb067e8d99d964806b68ae99e0f39bdecb3dd4f00cbe7958a115e1392dffcc7
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15759c491e0cbc3c20a789defaa3eb9b1ba5f51f160318f99e2a7896f2394a59
+oid sha256:623a6385c6947219614a206f325f0d5bbe602621d1fd3e48972b7fdd72be25d2
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7549533ede2b1dd6fe53e5571a6126478875eb81cddb6c662ba0261be0e9f079
+oid sha256:02ac5973a9776fb5558d0d5471ce91f9f5f08200895aa832ab0411732da0bb62
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17b33604be61df5ac96216c3e2908cb72d7bc7445f1fbb6123710e746f63011f
-size 14503
+oid sha256:bbe8a6d91f7528a2132dc105f5a011209849ce078b5ae84cd752340614efc89b
+size 14439

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecf67d692ebf3eeab712f96e8bcf2b206bea3bf44b342d23dd61fb929784bb0
-size 14503
+oid sha256:57da30fd98664b01593e067ac432f0638ebe9389fdcddf47146e4e5d78f9b45b
+size 14439

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e51637100435f199d054651c862159e9a427229daea6570b6d23739f5a17de3
+oid sha256:41ab9ece5cf2fe3d99e3bf57fddd4aebe29db0bd41b88067fc2fa8ae9ef5bedb
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.886466016155878,
-  "global_step": 320000,
+  "epoch": 5.039168079160749,
+  "global_step": 330000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2374,11 +2374,85 @@
       "eval_samples_per_second": 961.537,
       "eval_steps_per_second": 15.385,
       "step": 320000
+    },
+    {
+      "epoch": 4.9,
+      "learning_rate": 0.00012372180635716656,
+      "loss": 0.2874,
+      "step": 321000
+    },
+    {
+      "epoch": 4.92,
+      "learning_rate": 0.00012354078948651604,
+      "loss": 0.2873,
+      "step": 322000
+    },
+    {
+      "epoch": 4.93,
+      "learning_rate": 0.00012335929646076758,
+      "loss": 0.2868,
+      "step": 323000
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 0.00012317732926469976,
+      "loss": 0.2871,
+      "step": 324000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 0.00012299488988827675,
+      "loss": 0.2869,
+      "step": 325000
+    },
+    {
+      "epoch": 4.96,
+      "eval_runtime": 1.3977,
+      "eval_samples_per_second": 715.452,
+      "eval_steps_per_second": 11.447,
+      "step": 325000
+    },
+    {
+      "epoch": 4.98,
+      "learning_rate": 0.0001228119803266263,
+      "loss": 0.2867,
+      "step": 326000
+    },
+    {
+      "epoch": 4.99,
+      "learning_rate": 0.0001226286025800181,
+      "loss": 0.2866,
+      "step": 327000
+    },
+    {
+      "epoch": 5.01,
+      "learning_rate": 0.00012244475865384177,
+      "loss": 0.2862,
+      "step": 328000
+    },
+    {
+      "epoch": 5.02,
+      "learning_rate": 0.00012226045055858505,
+      "loss": 0.2858,
+      "step": 329000
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 0.00012207568030981174,
+      "loss": 0.2859,
+      "step": 330000
+    },
+    {
+      "epoch": 5.04,
+      "eval_runtime": 1.1314,
+      "eval_samples_per_second": 883.862,
+      "eval_steps_per_second": 14.142,
+      "step": 330000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.2432057246985136e+22,
+  "total_flos": 2.313305328660712e+22,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fdc190c32c2fc157093936156e63e0f60bf6e1f2fe248e7ec37847891ea89ae
-size 3183
+oid sha256:69d9dd505c56ab02fdd4405a013eaa211c194bd407e1877bba9642905743e82c
+size 3311

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbb0a403c4c85850b5f1bad1d089cdec8ce35c071f9b4d707f0145c3de24b2e
+oid sha256:4fb067e8d99d964806b68ae99e0f39bdecb3dd4f00cbe7958a115e1392dffcc7
 size 449471589

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fdc190c32c2fc157093936156e63e0f60bf6e1f2fe248e7ec37847891ea89ae
-size 3183
+oid sha256:69d9dd505c56ab02fdd4405a013eaa211c194bd407e1877bba9642905743e82c
+size 3311