Training in progress, step 250, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:126f178711fbc9dc02adb12aecf7c2e316048690bf9f666ebf5e533924ca5759
+oid sha256:41f22bec139eccefcabcaecfd30023a76c8ebfb3073337f09e75777d65a579c2
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a6a27ff45511a566f230b94929be575d47e80f94f11e46684241a9807432ad
+oid sha256:9b7d12ae0be9d05ec1cbc892152d8fdafaff4e73de9aa5873b148d1c273a89e2
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0c0971e1ca60fceb5fa43e0a83baf4624d8bf23bd31003292a1606de1c74861
+oid sha256:f3314d1f8528b0e933c3f5d6b0f4d79675fd95a3db3b829e6780f177bc655d78
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95b6047bd8cc6f4cdf7c46dea47edb8e542435510070c6cd1e0a7d9ccf5fd7da
+oid sha256:068fbd993087219c15b8c0baa13fc39644a4dcdfe92d8be3fa6434deece90371
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95d2a50364bc7f3078838455f012433d9b89075114f0547db53c7e328906dec9
+oid sha256:c14236e1aaafe2e25b01597ed1466b255761963d528e38fe935aa925971b2510
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.012492192379762648,
+  "epoch": 0.01561524047470331,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -188,6 +188,49 @@
       "eval_samples_per_second": 15.876,
       "eval_steps_per_second": 15.876,
       "step": 200
+    },
+    {
+      "epoch": 0.01311680199875078,
+      "grad_norm": 100.5,
+      "learning_rate": 0.045178692248428534,
+      "loss": 10.0078,
+      "step": 210
+    },
+    {
+      "epoch": 0.013741411617738912,
+      "grad_norm": 51.5,
+      "learning_rate": 0.04470026884016805,
+      "loss": 9.4955,
+      "step": 220
+    },
+    {
+      "epoch": 0.014366021236727046,
+      "grad_norm": 7.71875,
+      "learning_rate": 0.0442020089311058,
+      "loss": 8.3445,
+      "step": 230
+    },
+    {
+      "epoch": 0.014990630855715179,
+      "grad_norm": 13.0,
+      "learning_rate": 0.043684414226734525,
+      "loss": 8.7676,
+      "step": 240
+    },
+    {
+      "epoch": 0.01561524047470331,
+      "grad_norm": 15.625,
+      "learning_rate": 0.04314800590104691,
+      "loss": 9.141,
+      "step": 250
+    },
+    {
+      "epoch": 0.01561524047470331,
+      "eval_loss": 8.216238975524902,
+      "eval_runtime": 55.3897,
+      "eval_samples_per_second": 15.219,
+      "eval_steps_per_second": 15.219,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -202,7 +245,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 4
+        "early_stopping_patience_counter": 5
       }
     },
     "TrainerControl": {
@@ -216,7 +259,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8169243279360000.0,
+  "total_flos": 1.02115540992e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null