Training in progress, step 2000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1fa392e57ce9e1991791b65ba841fe7dfdb4ca0e4220048cdd0cabb8262c92d
+oid sha256:c63ac2740529d45592199af761ef88351d8bf33a0ced6a1c7bfa51ae6a262e3e
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:298cdd5b13c78bbc6a8b7d7a2ce81194b191b99b3aed92a13cb4b3892561952c
+oid sha256:44796c23481279b04feeb89690334c50fc7938f1076fc5c8d84157bb2cd2e390
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8822f5e506d851ca018edd79c9800bcb8685c675b49ff6103207a8ee51448333
+oid sha256:d406d538cd09764f86141c5283b0697ea9959a1fda63bbb795129d06c6b2a1d8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfab133851876645445ae2b9f9400b9840925f2757663b7c86b3b3ccda42693
+oid sha256:d4841384879f1112c4a211310579ca4e33089f588151f1074a18f817f4e1294d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5486997676789124,
-  "best_model_checkpoint": "training_dir/checkpoint-1000",
-  "epoch": 0.1059658789869662,
+  "best_metric": 0.6366336108184594,
+  "best_model_checkpoint": "training_dir/checkpoint-2000",
+  "epoch": 0.2119317579739324,
   "eval_steps": 1000,
-  "global_step": 1000,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26,6 +26,25 @@
       "eval_samples_per_second": 85.857,
       "eval_steps_per_second": 10.732,
       "step": 1000
+    },
+    {
+      "epoch": 0.2119317579739324,
+      "grad_norm": 14.981549263000488,
+      "learning_rate": 9.840204538191116e-06,
+      "loss": 0.5828,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2119317579739324,
+      "eval_accuracy": 0.6682692307692307,
+      "eval_f1": 0.6366336108184594,
+      "eval_loss": 0.9371851086616516,
+      "eval_precision": 0.6852715704153842,
+      "eval_recall": 0.6682692307692307,
+      "eval_runtime": 25.9805,
+      "eval_samples_per_second": 88.066,
+      "eval_steps_per_second": 11.008,
+      "step": 2000
     }
   ],
   "logging_steps": 1000,
@@ -45,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 970057431418608.0,
+  "total_flos": 1940081745396960.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null