Training in progress, epoch 1, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2678736b1fa6a2ec23edbe78d3bf52e0f673a718aa7b90ea8a0039d7634c313c
+oid sha256:d114f4944859c21ae92ea0eb0b943899662d9af06da7c5843dc8f86afae9982a
 size 2283652852

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e8df18a2a005819fd5723ce90f5a12239b7acd87613701d990635f9116c85e
+oid sha256:3ba13fff683be102a2f5a60643dcfb4cf63f83a82f79b06e2710fa2ef8374c57
 size 4550170737

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46f24561c335f40eb17ec95146b857178f95940c7cb908915b6d14c7d5535855
+oid sha256:45d8e6c563be6ec5a3a9657dd6b824461e4544dc9c54dfb3606f83a26755d1b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77e8eeef64980e9c08a90105caf16905e90445485f619f78db107a0103aaab9c
+oid sha256:ef03d4f4b4b1eccb7ca5122818641365e2122b6eb5ecbe490c2373bd5fd932c3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.997943797121316,
+  "epoch": 1.995887594242632,
   "eval_steps": 500,
-  "global_step": 91,
+  "global_step": 182,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 1.378787878787879e-05,
       "loss": 6.5853,
       "step": 91
+    },
+    {
+      "epoch": 1.995887594242632,
+      "grad_norm": 3.2100038528442383,
+      "learning_rate": 0.0,
+      "loss": 5.8617,
+      "step": 182
     }
   ],
   "logging_steps": 2,
@@ -35,12 +42,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4083106678505472.0,
+  "total_flos": 8149539680034816.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null