Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032d1f93a89bef5a4e64182cbeb8e221b55b87409dead7625b15fd63cedf015b
+oid sha256:36e2c4fe221f6e002a64a6542fe252dc11fe2eeb3baad0a50e243eb48ac0477c
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f733621e52e00f6d64ba4374098874452aa756f85fe823b91375af9a4a36051
+oid sha256:564221fca98ee313eab1cc9389cfb0447418634a94396a7972b154d5e5db62e7
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f03ae66707858875add1c111a5b9a3e1f42672fa5c26b423a5d20685cc13fa
+oid sha256:7f52e94aad094152bab1abd51bbfe9a23da0e3d88dc3e4bf0f079bdb4cdb0f3c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7a770b70428dfed1a10bfbdcc4cef7f7b33a77cec109d7ca386d39d3192a3b3
+oid sha256:4c2778c77cbcc9544d4789828882de4085d91013efc5164967facada5a73f269
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.29886579513549805,
   "best_model_checkpoint": "./opt_trained/checkpoint-644",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 644,
+  "global_step": 966,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,14 @@
       "eval_samples_per_second": 19.619,
       "eval_steps_per_second": 4.905,
       "step": 644
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.29954472184181213,
+      "eval_runtime": 145.5114,
+      "eval_samples_per_second": 19.627,
+      "eval_steps_per_second": 4.907,
+      "step": 966
     }
   ],
   "logging_steps": 500,
@@ -49,7 +57,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.685559504896e+16,
+  "total_flos": 4.028339257344e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null