Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:163d0316127e011032f25810b17fdf03e77683c4c6ac95cd5392b6a4fbd28172
+oid sha256:3107d0171e12bc030f60428b511566260b8239cfd81cc8e53e29bf5b724029dc
 size 2239622772

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:588231c2baa7de3ccd5eb8ee8faba488739485773c2a26cc67c28b4f6b912594
+oid sha256:6b52df42832dcb733698ad4731d2837f58db9f9498c38835165f0f1973b87535
 size 4479480977

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a5b3cea691b10ae19c1e49f6804df914f7b89a25c557a910e1189b080b25ceb
+oid sha256:dbd7e6867cdd584d70cd3119b80f7b9f150350fda588b771b41d839e6666bc06
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ebe1c31b7026d80410a75270b86dea3e72ea7b338468838cd12128b1ae3a84
+oid sha256:61637a1b134b88aa9a983de441031529029bb0700c525538264c73c5607eb051
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.773792093704246,
   "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-398",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 398,
+  "global_step": 597,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -25,6 +25,22 @@
       "eval_samples_per_second": 10.98,
       "eval_steps_per_second": 5.49,
       "step": 398
+    },
+    {
+      "epoch": 2.5125628140703515,
+      "grad_norm": 592.5914916992188,
+      "learning_rate": 7.487437185929649e-06,
+      "loss": 0.5014,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7730600292825769,
+      "eval_loss": 0.5995632410049438,
+      "eval_runtime": 59.0331,
+      "eval_samples_per_second": 23.14,
+      "eval_steps_per_second": 11.57,
+      "step": 597
     }
   ],
   "logging_steps": 500,
@@ -44,7 +60,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5911377102241920.0,
+  "total_flos": 8867065653362880.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null