Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b18ffb83b321571c84ee2049f9a89d7f2127c4002f8f2e81a758bbcaa7316762
+oid sha256:dcac825deb09f99c8b58bf218a215fb0831a9b6104dfa70908eed38b7a08cec7
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:018a80bc391357a993d67f4ba85c028e5eafd5ab8f9508d07e40e007eec07c56
+oid sha256:3dc072c1cd1d41ca40eab8a494c79cf8f925c81c6864327c69062f3d4c832dec
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc6dd40ad32dbebd77019e456db3a874b17aba5a78f79de51afbfd288206e45
+oid sha256:0903e6f7db48f2e5ba0b20aa2079c2e09445dec9fd55d4012bb690d0e9d8320f
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae029a8e6af9f014c9ef8b713fcd28cef1f184648ddde977ce75efc89ca9a242
+oid sha256:12e40c044fc20b06edb62b2decf2bd7a9ba13eb66fc4f9a7e953a32ef0d2f361
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b311356e11f141aa25e5b76754bcaa4f9ff30c4f07dbebf9b694da2aecc6a91
+oid sha256:2a739de5b001aa1d78ff9d8875c07e5a442aa2a281dfd8b2644a4e69f1e29b3f
 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": 0.6,
+  "epoch": 0.65,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -284,6 +284,29 @@
       "eval_samples_per_second": 52.578,
       "eval_steps_per_second": 3.286,
       "step": 12000
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.02456793375313282,
+      "learning_rate": 7.501000000000001e-06,
+      "loss": 0.0246,
+      "step": 12500
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.001343235606327653,
+      "learning_rate": 7.001e-06,
+      "loss": 0.022,
+      "step": 13000
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9687,
+      "eval_loss": 0.0772382989525795,
+      "eval_runtime": 380.3973,
+      "eval_samples_per_second": 52.577,
+      "eval_steps_per_second": 3.286,
+      "step": 13000
     }
   ],
   "logging_steps": 500,
@@ -303,7 +326,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.262933065728e+16,
+  "total_flos": 1.368177487872e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null