Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c871537e60075bfb3489556aafd3189cb389d9f771c3b038cd68d18648dc4c51
+oid sha256:180799923d60094382644c54290e59e477207941e6639fc451e41236d3e1eb4a
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e17967af6c6a6182fc9f28b28fae49dc7777a8262ac32bfd5cdffad338f53734
+oid sha256:d29276ef613a478783a8b31a7b2c7f90cd8b1790f90084070a56b470439ccc13
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f851f9fcf8f9fad3c79a18ff4e2f6430c43dce0659f5f180b8393cafa847ebe7
+oid sha256:07e1a0159d4af8f2aff362ffe79d7838d580f34554f42bcc8b39206c91c36519
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3986678719520569,
-  "best_model_checkpoint": "./opt_trained2/checkpoint-1606",
-  "epoch": 2.0,
+  "best_metric": 0.3892712891101837,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-2409",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1606,
+  "global_step": 2409,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,21 @@
       "eval_samples_per_second": 10.444,
       "eval_steps_per_second": 2.611,
       "step": 1606
+    },
+    {
+      "epoch": 2.4906600249066004,
+      "grad_norm": 0.363370418548584,
+      "learning_rate": 0.0003502864259028643,
+      "loss": 3.1553,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3892712891101837,
+      "eval_runtime": 273.5885,
+      "eval_samples_per_second": 10.439,
+      "eval_steps_per_second": 2.61,
+      "step": 2409
     }
   ],
   "logging_steps": 500,
@@ -63,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.257442833136e+16,
+  "total_flos": 9.386164249704e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null