Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d93af6b070094148dfc3c2004e4aec24e25586fe06b45e8796b998d8cc7e2a2a
+oid sha256:24d5dff093a432a5eb5282bfdd86ae2416dc3aca3ae2dcf7c7b93bb828742254
 size 2239647372

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8df875358177620549416ae8cd21a4bf769c228af9cbdb8dcc84dbbfe4d45452
+oid sha256:1bb2d041b144809f2caa73323e0b7cc022dc2d5ebdcfd1b8e7590657d984df7e
 size 4479530129

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474ed59e44a96690485aa267e28741f930f12c408ee6a6090faf325b2090550e
+oid sha256:8a105e433a7700673c26b9c7278261e31311e890567b4f9e7e49a5b2f356e0cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da70d674c7df75d777418290e3779cdd654b083cf22d636cc438f1a0580aa29d
+oid sha256:8e6a8b78b43d8a7789266e20d2a66bd79cbd8d65e3b2aaa76564d25b3082924d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4931787175989086,
-  "best_model_checkpoint": "../../modelParams/TrainingArguments_output\\checkpoint-182",
-  "epoch": 1.9911262798634812,
+  "best_metric": 0.5068212824010914,
+  "best_model_checkpoint": "../../modelParams/TrainingArguments_output\\checkpoint-273",
+  "epoch": 2.98839590443686,
   "eval_steps": 500,
-  "global_step": 182,
+  "global_step": 273,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25,6 +25,15 @@
       "eval_samples_per_second": 4.95,
       "eval_steps_per_second": 1.239,
       "step": 182
+    },
+    {
+      "epoch": 2.98839590443686,
+      "eval_accuracy": 0.5068212824010914,
+      "eval_loss": 1.3609565496444702,
+      "eval_runtime": 297.4155,
+      "eval_samples_per_second": 4.929,
+      "eval_steps_per_second": 1.234,
+      "step": 273
     }
   ],
   "logging_steps": 500,
@@ -44,7 +53,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.088521576955904e+16,
+  "total_flos": 1.632782365433856e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null