Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:548fe575ed72fd429e9fd72d2063ff329da383114295521f2d644f05dd0f118b
+oid sha256:2004ebbab03de74d00c60e27573907a37373fc0055ecb5c433827b13812ce0ed
 size 438032472

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41609801c77675eff7749f85d6fa09c477b156569ed13abaa28fe2b14a39f6ee
+oid sha256:6458c45bb22e19e9697b93fdf578d5b1611dd3db0c74d9ad1f2cf8625ef5be48
 size 876185914

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de5d76c4e89cee19260e89a6c72add76e5fd233fa0407a0c8086c769fbebc94b
+oid sha256:c6b9361df27a0d1575bc9d13b96c3afa7adc7c7aa5590196bb3a80cbc6d4fe17
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1efd8476d96a816ea45c36f3aff908881920abfb89fbb50a379d2343347897d5
+oid sha256:c049b2e3ea1cce3b5a07099de3f2a7712b4074618db3d2296051173e338de365
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.564910352230072,
-  "best_model_checkpoint": "/kaggle/working/results/checkpoint-2500",
-  "epoch": 0.17940437746681018,
+  "best_metric": 0.5547525882720947,
+  "best_model_checkpoint": "/kaggle/working/results/checkpoint-3000",
+  "epoch": 0.21528525296017223,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,6 +82,21 @@
       "eval_samples_per_second": 63.839,
       "eval_steps_per_second": 0.503,
       "step": 2500
+    },
+    {
+      "epoch": 0.21528525296017223,
+      "grad_norm": 3.9764771461486816,
+      "learning_rate": 3.1388589881593114e-05,
+      "loss": 0.5103,
+      "step": 3000
+    },
+    {
+      "epoch": 0.21528525296017223,
+      "eval_loss": 0.5547525882720947,
+      "eval_runtime": 162.9245,
+      "eval_samples_per_second": 63.833,
+      "eval_steps_per_second": 0.503,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -101,7 +116,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.105342017536e+16,
+  "total_flos": 2.5264104210432e+16,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null