Training in progress, epoch 2, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6786fc0948935b0bf9a95e1240734dfe4a10a6c043a2e18e1403870e1fb275a1
+oid sha256:610aeb0cae11943ac229dd161a4cba3f7ac2c6c4a5228df85ee96f46ce3f6a37
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4459b71c6cd4be840d583af247bf313be6ae39923f23b22394565da386903adc
+oid sha256:081d184c3a09c40305064c7b7db7573966885c1810f831eac5b01bd70f2e2757
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec48fff64bd5166ec8dd87c9044f1137e425ce986dcb848f4e16f7b2f748232a
+oid sha256:1a06e53d3b8db8cc45595ffd5e46327d27c2e05c52ebbf3fbc6aae1a160aa1f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da4b833a21434fbfbf211a74ba8d02328096ced5e0d0c765db219a56f4cf6915
+oid sha256:f071afedb6f79dad7634efb3c11b5cadc1617244cc1febacfa77506e4d908406
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.18951324487670584,
-  "best_model_checkpoint": "training_dir/checkpoint-250",
-  "epoch": 1.0,
+  "best_metric": 0.57190397933845,
+  "best_model_checkpoint": "training_dir/checkpoint-500",
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 250,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -26,6 +26,25 @@
       "eval_samples_per_second": 46.914,
       "eval_steps_per_second": 5.864,
       "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.063375473022461,
+      "learning_rate": 6e-05,
+      "loss": 0.6685,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6062062937062938,
+      "eval_f1": 0.57190397933845,
+      "eval_loss": 0.8881105780601501,
+      "eval_precision": 0.5980584671844231,
+      "eval_recall": 0.6062062937062938,
+      "eval_runtime": 48.5739,
+      "eval_samples_per_second": 47.104,
+      "eval_steps_per_second": 5.888,
+      "step": 500
     }
   ],
   "logging_steps": 500,
@@ -45,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 417223879867872.0,
+  "total_flos": 834505315795872.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null