Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875e40632ed4d1f9dd1708bc5cb6f6e7678f7a30daedadd29609f0f0ca0c6d15
+oid sha256:7a40dec7e30253e75e422b47ab951addd60730e7951035834622549ac801367e
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4a5499cc3b6cb923fa7ad27aadbe37d704284cc0fec834fa3bbe2044d1db617
+oid sha256:ddc053d38b879409c8034df7340972100796763466dd69d9c7b037470814f772
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b9839161f4469812f20ea61a7aad297dbb7cf5e3bed085713c5f3d6b8e6f561
+oid sha256:ebdf656e7a36761328b5fb073dd978028ede2fdcdc132424304899457e59ad39
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fed124530d6fc34dff4e5380c8d4c498048e3a753e209d175a99261714ee23d
+oid sha256:1a9e472ef49de9b8b8e7b375a6d84ff735f7d72dc421adbe419aa4444b7c6057
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9986960887908936,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-3045",
-  "epoch": 4.998769987699877,
+  "best_metric": 0.9929500818252563,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-3654",
+  "epoch": 5.998769987699877,
   "eval_steps": 500,
-  "global_step": 3045,
+  "global_step": 3654,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,21 @@
       "eval_samples_per_second": 50.356,
       "eval_steps_per_second": 12.591,
       "step": 3045
+    },
+    {
+      "epoch": 5.74620746207462,
+      "grad_norm": 1.9525970220565796,
+      "learning_rate": 3.842180501092163e-05,
+      "loss": 1.0013,
+      "step": 3500
+    },
+    {
+      "epoch": 5.998769987699877,
+      "eval_loss": 0.9929500818252563,
+      "eval_runtime": 260.4505,
+      "eval_samples_per_second": 49.937,
+      "eval_steps_per_second": 12.486,
+      "step": 3654
     }
   ],
   "logging_steps": 500,
@@ -108,7 +123,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.209609614592e+17,
+  "total_flos": 1.4515315375104e+17,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null