Training in progress, step 14000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcac825deb09f99c8b58bf218a215fb0831a9b6104dfa70908eed38b7a08cec7
+oid sha256:c24a6fee6197a7d0e0dc60fd3a17ae12371f686c25f8c59baa4e0a84062e4f9b
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc072c1cd1d41ca40eab8a494c79cf8f925c81c6864327c69062f3d4c832dec
+oid sha256:a7bb4a03ac656611f593c1f2ba0d38c8cbf04d907421b2c50bbdccb383e90608
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0903e6f7db48f2e5ba0b20aa2079c2e09445dec9fd55d4012bb690d0e9d8320f
+oid sha256:1729b2eea6571b9bf3c801be2729d60efb8e2cb8629926b7109ada2c3384ad31
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12e40c044fc20b06edb62b2decf2bd7a9ba13eb66fc4f9a7e953a32ef0d2f361
+oid sha256:23c844bc341ec75b5cad5ad0be21d7c0eeee0623194498c334d6946af672123e
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a739de5b001aa1d78ff9d8875c07e5a442aa2a281dfd8b2644a4e69f1e29b3f
+oid sha256:04b0bf137a45b36bdb178c3406191d51b6266f45964c2cad0b5dc4c8bc6aa400
 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": 0.65,
+  "epoch": 0.7,
   "eval_steps": 1000,
-  "global_step": 13000,
+  "global_step": 14000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -307,6 +307,29 @@
       "eval_samples_per_second": 52.577,
       "eval_steps_per_second": 3.286,
       "step": 13000
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 38.745670318603516,
+      "learning_rate": 6.501000000000001e-06,
+      "loss": 0.0232,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.0009748099255375564,
+      "learning_rate": 6.001e-06,
+      "loss": 0.0221,
+      "step": 14000
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.96125,
+      "eval_loss": 0.07062023133039474,
+      "eval_runtime": 380.5787,
+      "eval_samples_per_second": 52.552,
+      "eval_steps_per_second": 3.284,
+      "step": 14000
     }
   ],
   "logging_steps": 500,
@@ -326,7 +349,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.368177487872e+16,
+  "total_flos": 1.473421910016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null