Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:666d633bec65db8ed6a7530aafd26a5948ed171903e34e71c0b7589519221d1e
+oid sha256:163d0316127e011032f25810b17fdf03e77683c4c6ac95cd5392b6a4fbd28172
 size 2239622772

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f3cc1f86ce2a1deb737dce2ebad11d7ca792e9c9145b03806ffc38aaa2dc59
+oid sha256:588231c2baa7de3ccd5eb8ee8faba488739485773c2a26cc67c28b4f6b912594
 size 4479480977

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abe3b5b1bf4466e1d86bee61b93fa6fa432b68ee2c1feb8376037a6260b9fc2d
+oid sha256:5a5b3cea691b10ae19c1e49f6804df914f7b89a25c557a910e1189b080b25ceb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:847a12e4b28920e0115e27969fec3e6eedf96555f3aee93e49bb208452bfde15
+oid sha256:28ebe1c31b7026d80410a75270b86dea3e72ea7b338468838cd12128b1ae3a84
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7635431918008785,
-  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-199",
-  "epoch": 1.0,
+  "best_metric": 0.773792093704246,
+  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-398",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 199,
+  "global_step": 398,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -16,6 +16,15 @@
       "eval_samples_per_second": 11.39,
       "eval_steps_per_second": 5.695,
       "step": 199
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.773792093704246,
+      "eval_loss": 0.5396685004234314,
+      "eval_runtime": 124.413,
+      "eval_samples_per_second": 10.98,
+      "eval_steps_per_second": 5.49,
+      "step": 398
     }
   ],
   "logging_steps": 500,
@@ -35,7 +44,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2955688551120960.0,
+  "total_flos": 5911377102241920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null