Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:172a879e54f0613ed34fc2ebe311f2f27a68a3f88d233f7000673e5598a77685
+oid sha256:377015a2f2d0a1d535fd0614cb6e75174ab1a81ff78e3fadd2e4923bce2c9638
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0385300931157697e4a915b5ce3364c3ef452b5cc6f19883fa9a9bcbdfdaf3b4
+oid sha256:502a84f2960672887c9f9567e71498adf67f718978d01edd09c4a50418162bd8
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b2cbbcfce68a465b5dc9649714636223f26c4334afe4a2b30c904f877d83a7
+oid sha256:1e6f92a8b13bcc897bf3bb961d25b22aa9f5e3b3c3e1dda5ed2738319d087e7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2410c1bb6e04ddda81f1a5814723f61652cb286cac246e7b64a7b46322f8b053
+oid sha256:3ee86abee0989df8e1c5461d5ecfc6d42b43c8879a30063d7c1ee114f0c589f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6361710372570955,
   "best_model_checkpoint": "training_dir/checkpoint-250",
-  "epoch": 3.0,
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 375,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,25 @@
       "eval_samples_per_second": 76.446,
       "eval_steps_per_second": 9.556,
       "step": 375
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 27.72207260131836,
+      "learning_rate": 0.0001,
+      "loss": 0.2795,
+      "step": 500
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.611451048951049,
+      "eval_f1": 0.5839059582567918,
+      "eval_loss": 1.4940129518508911,
+      "eval_precision": 0.6264845385709801,
+      "eval_recall": 0.611451048951049,
+      "eval_runtime": 29.8938,
+      "eval_samples_per_second": 76.538,
+      "eval_steps_per_second": 9.567,
+      "step": 500
     }
   ],
   "logging_steps": 500,
@@ -83,7 +102,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 611637724728000.0,
+  "total_flos": 815516966304000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null