Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9de85df0c4209e87e0ef125eeec11e1d408bc55d2fe1a30f42a16611ce2de01
+oid sha256:8576f642c5757e556ee9cfbced0cb31b1146534cdf8c3cb4e54d0643bd835278
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1c796ed551b1540e72e4e28411f88d4fa8a6b62f61174baf53079696cb15781
+oid sha256:92ed717c177d02754e9e2348e429a02681ac26e8389c32e91e990c1d68142d23
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7a8b7ac9333d9d6a4e3842856e0cd76aa0b955dc4f3cc734d3e564ef3223c59
+oid sha256:510cda659afc9c3a8ca423ee402f04659f1fe8269e49747ed5aecf921b4895c4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b81f447cd68ab96983e3188c3e045c2f452531c980dec6455a36a530387bf572
+oid sha256:c18bd5ddb3eb55c4b03daed49e07d8c29d11cced41552f35f41fbfaa47eec6c6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0066354274749756,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-1827",
-  "epoch": 2.998769987699877,
+  "best_metric": 1.003442406654358,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-2436",
+  "epoch": 3.998769987699877,
   "eval_steps": 500,
-  "global_step": 1827,
+  "global_step": 2436,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,21 @@
       "eval_samples_per_second": 49.527,
       "eval_steps_per_second": 12.384,
       "step": 1827
+    },
+    {
+      "epoch": 3.2837228372283724,
+      "grad_norm": 1.8426792621612549,
+      "learning_rate": 7.571135915407219e-05,
+      "loss": 1.0148,
+      "step": 2000
+    },
+    {
+      "epoch": 3.998769987699877,
+      "eval_loss": 1.003442406654358,
+      "eval_runtime": 261.9157,
+      "eval_samples_per_second": 49.657,
+      "eval_steps_per_second": 12.416,
+      "step": 2436
     }
   ],
   "logging_steps": 500,
@@ -71,7 +86,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.257657687552e+16,
+  "total_flos": 9.676876916736e+16,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null