Training in progress, step 17000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d5cc0f066a9ff7f9709202c6b1ea302b25d4fc82b916383dba6b74bf14639e
+oid sha256:29092f5f5db264a2400cbdf899cfe4d1d0b56eea50bccf442b1a8266a8341365
 size 498612824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:529961f9c3d396e3bfd95d8632f4c919c1c8d7d7aebb25605e81bf65fca66018
+oid sha256:2006153fb5c31670f4af411fe67c8d23146ccd874f0518cd0d2d69cb0d6a474c
 size 997345931

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e29be2623b9f70496e9bea6cd43302d895456299b445e94e0c3906aa73899453
+oid sha256:78bd9fea4ddfe3f89b1b98598cf1ed1a56bdd71a677e5b5657ad459f1c6e4adf
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e8f14715c120c1b82640d08ff4b50ac8ef3a482a39de36f9dee0ad364309a0
+oid sha256:9c792eca26ddd2cafb935aabba9dbf816b7c25feaa4b191867652327a92bef5c
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bdd55dc4830a374b47a354ba8f1d6b80b053f25bf45716e5f0fe65d5ff8db6b
+oid sha256:bfc30f32fda7dd6d5c4749a3c53203c86e0c2f047676577a42c798629798e937
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 16000,
   "best_metric": 0.042671315371990204,
   "best_model_checkpoint": "./training_output/checkpoint-16000",
-  "epoch": 0.8,
+  "epoch": 0.85,
   "eval_steps": 1000,
-  "global_step": 16000,
+  "global_step": 17000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -376,6 +376,29 @@
       "eval_samples_per_second": 52.567,
       "eval_steps_per_second": 3.285,
       "step": 16000
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.01499607227742672,
+      "learning_rate": 3.5010000000000004e-06,
+      "loss": 0.0253,
+      "step": 16500
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.0003527141234371811,
+      "learning_rate": 3.001e-06,
+      "loss": 0.0162,
+      "step": 17000
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.97425,
+      "eval_loss": 0.04368801414966583,
+      "eval_runtime": 380.357,
+      "eval_samples_per_second": 52.582,
+      "eval_steps_per_second": 3.286,
+      "step": 17000
     }
   ],
   "logging_steps": 500,
@@ -395,7 +418,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.683910754304e+16,
+  "total_flos": 1.789155176448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null