Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36e2c4fe221f6e002a64a6542fe252dc11fe2eeb3baad0a50e243eb48ac0477c
+oid sha256:b76cd3dd8f3af0bdc418b56e3cffdf73e51cdc2486e299e0e3037780b470dad2
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564221fca98ee313eab1cc9389cfb0447418634a94396a7972b154d5e5db62e7
+oid sha256:7d0560b2a56e05543f23bf5dc0ad584db7470790d75684eb4f29c73dea8532c6
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f52e94aad094152bab1abd51bbfe9a23da0e3d88dc3e4bf0f079bdb4cdb0f3c
+oid sha256:98d764b7a99b8ed179d4df939f9536e72a7d94978db9a5c37328a6aaf12f5c3e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2778c77cbcc9544d4789828882de4085d91013efc5164967facada5a73f269
+oid sha256:0e3962c21f6062f8f3c755e0be0db565d65f484e53aa2e30812e9a1dd0cde7e4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.29886579513549805,
-  "best_model_checkpoint": "./opt_trained/checkpoint-644",
-  "epoch": 3.0,
+  "best_metric": 0.2978520393371582,
+  "best_model_checkpoint": "./opt_trained/checkpoint-1288",
+  "epoch": 4.0,
   "eval_steps": 500,
-  "global_step": 966,
+  "global_step": 1288,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -38,6 +38,21 @@
       "eval_samples_per_second": 19.627,
       "eval_steps_per_second": 4.907,
       "step": 966
+    },
+    {
+      "epoch": 3.1058365758754864,
+      "grad_norm": 2.7013330459594727,
+      "learning_rate": 3.765282187493851e-05,
+      "loss": 0.2968,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.2978520393371582,
+      "eval_runtime": 145.3893,
+      "eval_samples_per_second": 19.644,
+      "eval_steps_per_second": 4.911,
+      "step": 1288
     }
   ],
   "logging_steps": 500,
@@ -57,7 +72,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.028339257344e+16,
+  "total_flos": 5.371119009792e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null