Training in progress, step 300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f22bec139eccefcabcaecfd30023a76c8ebfb3073337f09e75777d65a579c2
+oid sha256:d8184d250b7999dee69332883ea324c78ec4c7f4598ad2667207642efe3aaeca
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7d12ae0be9d05ec1cbc892152d8fdafaff4e73de9aa5873b148d1c273a89e2
+oid sha256:e6319531c096fbc443a5808f5c7fda0178e30925ef23e76c2b4b0ff1e5dee0da
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3314d1f8528b0e933c3f5d6b0f4d79675fd95a3db3b829e6780f177bc655d78
+oid sha256:c62165be0f53737e55f3e75f021e8f584796137fe98feeca985918f86f5097e3
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068fbd993087219c15b8c0baa13fc39644a4dcdfe92d8be3fa6434deece90371
+oid sha256:e2768285b45b2a0c05f6f50bbb8c0287fca6f62a8cde6d1b1f02151ac72ee8dc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c14236e1aaafe2e25b01597ed1466b255761963d528e38fe935aa925971b2510
+oid sha256:ac5948dcd3223dd0e3f4d6f300a2e7a88ae966cce604338b85ff6032bc67f692
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.01561524047470331,
+  "epoch": 0.018738288569643973,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -231,6 +231,49 @@
       "eval_samples_per_second": 15.219,
       "eval_steps_per_second": 15.219,
       "step": 250
+    },
+    {
+      "epoch": 0.016239850093691444,
+      "grad_norm": 19.0,
+      "learning_rate": 0.04259332407175751,
+      "loss": 8.5766,
+      "step": 260
+    },
+    {
+      "epoch": 0.016864459712679577,
+      "grad_norm": 282.0,
+      "learning_rate": 0.04202092725645009,
+      "loss": 10.2655,
+      "step": 270
+    },
+    {
+      "epoch": 0.017489069331667707,
+      "grad_norm": 7.53125,
+      "learning_rate": 0.04143139181019764,
+      "loss": 8.9695,
+      "step": 280
+    },
+    {
+      "epoch": 0.01811367895065584,
+      "grad_norm": 31.5,
+      "learning_rate": 0.040825311345221764,
+      "loss": 8.7729,
+      "step": 290
+    },
+    {
+      "epoch": 0.018738288569643973,
+      "grad_norm": 14.125,
+      "learning_rate": 0.04020329613317545,
+      "loss": 9.6525,
+      "step": 300
+    },
+    {
+      "epoch": 0.018738288569643973,
+      "eval_loss": 8.672038078308105,
+      "eval_runtime": 52.539,
+      "eval_samples_per_second": 16.045,
+      "eval_steps_per_second": 16.045,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -245,7 +288,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 5
+        "early_stopping_patience_counter": 6
       }
     },
     "TrainerControl": {
@@ -259,7 +302,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.02115540992e+16,
+  "total_flos": 1.225386491904e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null