Training in progress, epoch 4, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8576f642c5757e556ee9cfbced0cb31b1146534cdf8c3cb4e54d0643bd835278
+oid sha256:875e40632ed4d1f9dd1708bc5cb6f6e7678f7a30daedadd29609f0f0ca0c6d15
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92ed717c177d02754e9e2348e429a02681ac26e8389c32e91e990c1d68142d23
+oid sha256:b4a5499cc3b6cb923fa7ad27aadbe37d704284cc0fec834fa3bbe2044d1db617
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:510cda659afc9c3a8ca423ee402f04659f1fe8269e49747ed5aecf921b4895c4
+oid sha256:0b9839161f4469812f20ea61a7aad297dbb7cf5e3bed085713c5f3d6b8e6f561
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c18bd5ddb3eb55c4b03daed49e07d8c29d11cced41552f35f41fbfaa47eec6c6
+oid sha256:6fed124530d6fc34dff4e5380c8d4c498048e3a753e209d175a99261714ee23d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.003442406654358,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-2436",
-  "epoch": 3.998769987699877,
+  "best_metric": 0.9986960887908936,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-3045",
+  "epoch": 4.998769987699877,
   "eval_steps": 500,
-  "global_step": 2436,
+  "global_step": 3045,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,28 @@
       "eval_samples_per_second": 49.657,
       "eval_steps_per_second": 12.416,
       "step": 2436
+    },
+    {
+      "epoch": 4.1049610496104965,
+      "grad_norm": 1.7222294807434082,
+      "learning_rate": 6.39223072714725e-05,
+      "loss": 1.0105,
+      "step": 2500
+    },
+    {
+      "epoch": 4.924969249692497,
+      "grad_norm": 3.702568292617798,
+      "learning_rate": 5.121215425983256e-05,
+      "loss": 1.0048,
+      "step": 3000
+    },
+    {
+      "epoch": 4.998769987699877,
+      "eval_loss": 0.9986960887908936,
+      "eval_runtime": 258.2811,
+      "eval_samples_per_second": 50.356,
+      "eval_steps_per_second": 12.591,
+      "step": 3045
     }
   ],
   "logging_steps": 500,
@@ -86,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.676876916736e+16,
+  "total_flos": 1.209609614592e+17,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null