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 sha256:7f5f9255725605487651553474d42729c3791d88527cbfe70be08f227ba93d02
+oid sha256:0d40108708aeca3eaee7f0ad206931c6971e2dc1c0db296b59b7b54ba6a7fda9
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba1692113682075d05c8538281ed10f16cc53750332b8d944f63354f6a35b874
+oid sha256:dafdcb23d62ea12e96105611e45ce3d28675d5347aa244e71634b87bbe5c0410
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf62cd19bf8959d6d09d9c8c80713365bfb839ba7535e2750b045e9490e8abdc
+oid sha256:34513f8c50c565c1da3397b555076bf3d95cd033739a8c628616c520dab385df
 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": 15.957,
       "eval_steps_per_second": 15.957,
       "step": 200
+    },
+    {
+      "epoch": 0.01311680199875078,
+      "grad_norm": 230.0,
+      "learning_rate": 0.045178692248428534,
+      "loss": 11.6545,
+      "step": 210
+    },
+    {
+      "epoch": 0.013741411617738912,
+      "grad_norm": 50.5,
+      "learning_rate": 0.04470026884016805,
+      "loss": 9.9724,
+      "step": 220
+    },
+    {
+      "epoch": 0.014366021236727046,
+      "grad_norm": 89.0,
+      "learning_rate": 0.0442020089311058,
+      "loss": 10.161,
+      "step": 230
+    },
+    {
+      "epoch": 0.014990630855715179,
+      "grad_norm": 1152.0,
+      "learning_rate": 0.043684414226734525,
+      "loss": 9.1416,
+      "step": 240
+    },
+    {
+      "epoch": 0.01561524047470331,
+      "grad_norm": 233.0,
+      "learning_rate": 0.04314800590104691,
+      "loss": 8.8728,
+      "step": 250
+    },
+    {
+      "epoch": 0.01561524047470331,
+      "eval_loss": 8.775226593017578,
+      "eval_runtime": 56.6712,
+      "eval_samples_per_second": 14.875,
+      "eval_steps_per_second": 14.875,
+      "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