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 sha256:0d40108708aeca3eaee7f0ad206931c6971e2dc1c0db296b59b7b54ba6a7fda9
+oid sha256:61114c6a92e58ce464f00de9c099e8f03dc4230c177b928f5956c816d7725990
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dafdcb23d62ea12e96105611e45ce3d28675d5347aa244e71634b87bbe5c0410
+oid sha256:fbbf4da0f14a88e52ba3a2a4073b4aaa1c19709f107ca0ea0f7d394e7b8943e5
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34513f8c50c565c1da3397b555076bf3d95cd033739a8c628616c520dab385df
+oid sha256:d42dcce8c9a2d0c024270cf90f873168e73cdade4af51b5e3849a0fd68c66911
 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": 14.875,
       "eval_steps_per_second": 14.875,
       "step": 250
+    },
+    {
+      "epoch": 0.016239850093691444,
+      "grad_norm": 2976.0,
+      "learning_rate": 0.04259332407175751,
+      "loss": 8.7117,
+      "step": 260
+    },
+    {
+      "epoch": 0.016864459712679577,
+      "grad_norm": 604.0,
+      "learning_rate": 0.04202092725645009,
+      "loss": 10.3623,
+      "step": 270
+    },
+    {
+      "epoch": 0.017489069331667707,
+      "grad_norm": 2688.0,
+      "learning_rate": 0.04143139181019764,
+      "loss": 10.8841,
+      "step": 280
+    },
+    {
+      "epoch": 0.01811367895065584,
+      "grad_norm": 141.0,
+      "learning_rate": 0.040825311345221764,
+      "loss": 9.8937,
+      "step": 290
+    },
+    {
+      "epoch": 0.018738288569643973,
+      "grad_norm": 252.0,
+      "learning_rate": 0.04020329613317545,
+      "loss": 12.0118,
+      "step": 300
+    },
+    {
+      "epoch": 0.018738288569643973,
+      "eval_loss": 9.644805908203125,
+      "eval_runtime": 56.3116,
+      "eval_samples_per_second": 14.97,
+      "eval_steps_per_second": 14.97,
+      "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