Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67c8fe930490649ce5cc11a5fe193cfd48bc0b97b88299ffd6ad76afde0040b4
+oid sha256:989292e28f46dd6f0df4532e0dda10c72a82df895ad59806e1ad4eb0f00f3737
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:043ea3e469648caba58a57596dc37634719c22f8059e744b1a94bd1ae02825a6
+oid sha256:d8f1f84bc456597fb5c2700b82cca9533a78045c18a462826756c01550f7ba36
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ce8dfd2d06984e08483a3aee4cbb4be06065cfb35a021428755194fc5c9a8b5
+oid sha256:49210297757a71fde0369659ddff3f1ed351704ff09f7c069bf6fb7a6ca02751
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de31fecea0d88f3221e03053e0cf20c02baea118bf0e2b1c0433dcc126081364
+oid sha256:196ac9dde7c4927b37b8bc53da35fc7da10f580fa77c1ee80824d56438d0a24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6979166210878224,
   "best_model_checkpoint": "training_dir/checkpoint-5000",
-  "epoch": 0.5298293949348309,
+  "epoch": 0.6357952739217971,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,25 @@
       "eval_samples_per_second": 88.162,
       "eval_steps_per_second": 11.02,
       "step": 5000
+    },
+    {
+      "epoch": 0.6357952739217971,
+      "grad_norm": 7.738587379455566,
+      "learning_rate": 9.414083306700758e-06,
+      "loss": 0.4964,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6357952739217971,
+      "eval_accuracy": 0.7106643356643356,
+      "eval_f1": 0.6933251320034988,
+      "eval_loss": 0.7791977524757385,
+      "eval_precision": 0.7149995516226468,
+      "eval_recall": 0.7106643356643356,
+      "eval_runtime": 26.0573,
+      "eval_samples_per_second": 87.806,
+      "eval_steps_per_second": 10.976,
+      "step": 6000
     }
   ],
   "logging_steps": 1000,
@@ -121,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4845766626498096.0,
+  "total_flos": 5815153429751520.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null