Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:734a2080aeb8b234856db56b501df0d6a8b93f9db7e4f19aa755eb1cca19b4ce
+oid sha256:7aeecd089b104e2c073b031b465f8079945d3bb4155718e480145b58ce9313f6
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8837fa91ace6c6b9aa324ab04a1618a72468931fac6ee3964460d89bb2fbf656
+oid sha256:79b6894e556cbc9eb256c3bdbd248a6cbaca0f063d088fb068dd54e567666484
 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 sha256:350bc2964da995e89f1edcfd77857f78843f160ccef873eaed540186a8325344
+oid sha256:03f1fa9180eceb118e79cf9ece924886edcd4a542c2d656b58a25c8b3e5beabe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5468895435333252,
   "best_model_checkpoint": "./opt_trained2/checkpoint-170",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 170,
+  "global_step": 255,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,14 @@
       "eval_samples_per_second": 10.416,
       "eval_steps_per_second": 2.604,
       "step": 170
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.5483385324478149,
+      "eval_runtime": 28.8239,
+      "eval_samples_per_second": 10.408,
+      "eval_steps_per_second": 2.602,
+      "step": 255
     }
   ],
   "logging_steps": 500,
@@ -42,7 +50,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6560634750912000.0,
+  "total_flos": 9840952126368000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null