Training in progress, step 900, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da079b9d8ca9edec5c19d40185ac34a5d967b988536e67ab8c54c5fc8c3731b0
+oid sha256:a213889093690708333a72ba85b3e173a26f185c33fba33332e53260dbd1c4aa
 size 4995335576

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d536b0da6ed2281687c34137ae7211c81201040fd7f921085d915c4552739c2
+oid sha256:972947c98f4763776af4efd2f002616917f749771c80dff97f83bfb67f4acd2d
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b86e924bddef11293e860631f6e1e1350720b1f64e7f8977d7267e36a24ee7
+oid sha256:e127ed7b7fc1b3994f8c17585153440be7f03c26e5b46dbf6c360aa0ff0978e4
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a2aa7bca84d2b8e7dd4e04a286714ba9169af11c46c739950a52df4c45259f
+oid sha256:82be7d57b17f6620866913ecd4ff8b7c828f1f4bbbb44f8426b657efc6ab9fa7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9109740607103fa260f8765f6910df83c4ef7244fe0858cce09056260804c468
+oid sha256:a9eac997032339e8d5b43afb42a0ae765d18d35f79086924503e8ce32f56fdeb
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.05309181761399125,
+  "epoch": 0.056214865708931916,
   "eval_steps": 50,
-  "global_step": 850,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,49 @@
       "eval_samples_per_second": 15.239,
       "eval_steps_per_second": 15.239,
       "step": 850
+    },
+    {
+      "epoch": 0.05371642723297939,
+      "grad_norm": 482.0,
+      "learning_rate": 0.002461047124653279,
+      "loss": 8.2881,
+      "step": 860
+    },
+    {
+      "epoch": 0.05434103685196752,
+      "grad_norm": 1864.0,
+      "learning_rate": 0.0021292109072704956,
+      "loss": 7.7393,
+      "step": 870
+    },
+    {
+      "epoch": 0.05496564647095565,
+      "grad_norm": 181.0,
+      "learning_rate": 0.0018204036358303172,
+      "loss": 7.7977,
+      "step": 880
+    },
+    {
+      "epoch": 0.055590256089943786,
+      "grad_norm": 70.0,
+      "learning_rate": 0.001534936253078606,
+      "loss": 7.4679,
+      "step": 890
+    },
+    {
+      "epoch": 0.056214865708931916,
+      "grad_norm": 756.0,
+      "learning_rate": 0.0012730962004717683,
+      "loss": 6.7936,
+      "step": 900
+    },
+    {
+      "epoch": 0.056214865708931916,
+      "eval_loss": 7.608245372772217,
+      "eval_runtime": 53.9447,
+      "eval_samples_per_second": 15.627,
+      "eval_steps_per_second": 15.627,
+      "step": 900
     }
   ],
   "logging_steps": 10,
@@ -761,7 +804,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 17
+        "early_stopping_patience_counter": 18
       }
     },
     "TrainerControl": {
@@ -775,7 +818,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.471928393728e+16,
+  "total_flos": 3.676159475712e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null