Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb7c732da4b2a52d9ab572e9f0256aaa611d1c3c4749adeef14c3a01acff708
+oid sha256:c3b6fd49dcb51d58987ba238c28571b6262d52f8709e141cdffd5141a977b307
 size 2239622772

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a32fae39eb24dd15598de7ef11da03c2ace5a69c6609c9b987d43c80b6f005d
+oid sha256:f78255ca9cf2a135abd321d6297f1632c4cd363dbac2e62500a0bfeb939cb8be
 size 4479480977

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:104c6f000557e8d1a5b1d392bc5868658285737e2ecb2da709ed8e19e45715d0
+oid sha256:d0b14f2fa17aed792a194336b75f1cee9a25d8f7c703a6aaafa7f7365361b1ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee805eb4c7ef2b7ea2677b099655b11650eb14c11114d04fa36fb582d9b02f63
+oid sha256:491c58b5642033f99f7c2115fead8df27804a68b4ef32e8aee5ac48551abbb29
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7774524158125915,
   "best_model_checkpoint": "modelParams/TrainingArguments_output\\checkpoint-796",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 1393,
+  "global_step": 1592,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -84,6 +84,22 @@
       "eval_samples_per_second": 12.317,
       "eval_steps_per_second": 6.158,
       "step": 1393
+    },
+    {
+      "epoch": 7.5376884422110555,
+      "grad_norm": 1611.986083984375,
+      "learning_rate": 2.462311557788945e-06,
+      "loss": 0.0881,
+      "step": 1500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.773792093704246,
+      "eval_loss": 1.5597944259643555,
+      "eval_runtime": 115.9058,
+      "eval_samples_per_second": 11.785,
+      "eval_steps_per_second": 5.893,
+      "step": 1592
     }
   ],
   "logging_steps": 500,
@@ -103,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.068981985784672e+16,
+  "total_flos": 2.364550840896768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null