Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:494c66eb6b674f51436f4513b4c9351a943d1d674fb3f18af798b7a2a6686de9
+oid sha256:b18ffb83b321571c84ee2049f9a89d7f2127c4002f8f2e81a758bbcaa7316762
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77840905c13cb9385a51c293cbe0a2bcb18e80be93245e995e886437de62501f
+oid sha256:018a80bc391357a993d67f4ba85c028e5eafd5ab8f9508d07e40e007eec07c56
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b860bdc3e5de508c782673fa65ec92d555dc444109c980e964a866ddf5d27c
+oid sha256:dfc6dd40ad32dbebd77019e456db3a874b17aba5a78f79de51afbfd288206e45
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01903b6f628f65f68918eac51237e59dd0d0b2affabd2cd100779d9eb7ee7430
+oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed6182874e1b92e628fa7d9cd2ddaf65f3929f6ef8ce9c0a0094022a1bb4538
+oid sha256:4b311356e11f141aa25e5b76754bcaa4f9ff30c4f07dbebf9b694da2aecc6a91
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 9000,
   "best_metric": 0.04935265704989433,
   "best_model_checkpoint": "./training_output/checkpoint-9000",
-  "epoch": 0.55,
+  "epoch": 0.6,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -261,6 +261,29 @@
       "eval_samples_per_second": 52.583,
       "eval_steps_per_second": 3.286,
       "step": 11000
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.07327098399400711,
+      "learning_rate": 8.501e-06,
+      "loss": 0.022,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 32.43045425415039,
+      "learning_rate": 8.001000000000002e-06,
+      "loss": 0.0362,
+      "step": 12000
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.9428,
+      "eval_loss": 0.08979687839746475,
+      "eval_runtime": 380.3892,
+      "eval_samples_per_second": 52.578,
+      "eval_steps_per_second": 3.286,
+      "step": 12000
     }
   ],
   "logging_steps": 500,
@@ -280,7 +303,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.157688643584e+16,
+  "total_flos": 1.262933065728e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null