Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aeecd089b104e2c073b031b465f8079945d3bb4155718e480145b58ce9313f6
+oid sha256:1d4b0b4a59e85d7e6af4b7a34158cec3d0e0c3e8fada19f60fb8d999dde0b04d
 size 1447317080

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b6894e556cbc9eb256c3bdbd248a6cbaca0f063d088fb068dd54e567666484
+oid sha256:5215a327ce7bfdf3f861f72783d0a6dc057750c800a758bac5edb9af32981fc9
 size 2894813242

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03f1fa9180eceb118e79cf9ece924886edcd4a542c2d656b58a25c8b3e5beabe
+oid sha256:fc1f40e5ed3949f09823dd3019104a35d1148f043d89b682818a1cc328fe11e9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5468895435333252,
-  "best_model_checkpoint": "./opt_trained2/checkpoint-170",
-  "epoch": 3.0,
+  "best_metric": 0.5381163358688354,
+  "best_model_checkpoint": "./opt_trained2/checkpoint-340",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 255,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -31,6 +31,14 @@
       "eval_samples_per_second": 10.408,
       "eval_steps_per_second": 2.602,
       "step": 255
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.5381163358688354,
+      "eval_runtime": 28.8298,
+      "eval_samples_per_second": 10.406,
+      "eval_steps_per_second": 2.601,
+      "step": 340
     }
   ],
   "logging_steps": 500,
@@ -50,7 +58,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9840952126368000.0,
+  "total_flos": 1.3121269501824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null