Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3107d0171e12bc030f60428b511566260b8239cfd81cc8e53e29bf5b724029dc
+oid sha256:bac2e2ecc21261b7ccd68a22683479e36c058e52d611d0034cb27519c2500818
 size 2239622772

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b52df42832dcb733698ad4731d2837f58db9f9498c38835165f0f1973b87535
+oid sha256:bde10c6dbb8b12b5496590d67cc996983e261439d3bce428af592d8292391aae
 size 4479480977

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbd7e6867cdd584d70cd3119b80f7b9f150350fda588b771b41d839e6666bc06
+oid sha256:738832b61485fe70353dc16c84fe7362d0a70bc3c5778dce02f6e763f6510e54
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61637a1b134b88aa9a983de441031529029bb0700c525538264c73c5607eb051
+oid sha256:d89876c47613ab569b633acc41c8bf81a96e31eef455a8043600205ab5cf9c20
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.773792093704246,
-  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-398",
-  "epoch": 3.0,
+  "best_metric": 0.7774524158125915,
+  "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 597,
+  "global_step": 796,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -41,6 +41,15 @@
       "eval_samples_per_second": 23.14,
       "eval_steps_per_second": 11.57,
       "step": 597
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7774524158125915,
+      "eval_loss": 0.7029575109481812,
+      "eval_runtime": 123.6878,
+      "eval_samples_per_second": 11.044,
+      "eval_steps_per_second": 5.522,
+      "step": 796
     }
   ],
   "logging_steps": 500,
@@ -60,7 +69,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8867065653362880.0,
+  "total_flos": 1.182275420448384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null