Training in progress, step 450, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566da4bce3713a63f6c726908dcc895eb0274adcdaddfbea000cedb49718089f
+oid sha256:c691fc20bc081097cd8eeba3ecb439932d995a80f27df276c2e7bee3afd9c44b
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db064a177e765bdf23f52a02747fe4af86eed8952e498f4defb16a673f2f6b49
+oid sha256:e642aa3aadaad39eb5ba24a7138f75e05cfb8e04f0f46b6dec6c858a6e830d2e
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a91ed35e885a988551da8e36baa2edecdc8b067a287cd36226dada8e0f8f0f3
+oid sha256:433b20d5c0cacd84af924042d215e7b29768d81cd940f6181e72d73d7442eaec
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
+oid sha256:b1a97db8e41139aa1239ba7fb79ddeb0af5998c6305a440c1fe182e6ad02f2f5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97d77772d015237116c653131e7ea932ab54323cc0a66e7c4895f90aecb97a1a
+oid sha256:bfb05f711fd9bb3d14fd3664cc7d698df71ec289614aa26046fdc74fe37e7e86
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.024984384759525295,
+  "epoch": 0.028107432854465958,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -360,6 +360,49 @@
       "eval_samples_per_second": 15.257,
       "eval_steps_per_second": 15.257,
       "step": 400
+    },
+    {
+      "epoch": 0.02560899437851343,
+      "grad_norm": 64768.0,
+      "learning_rate": 0.032498727281925266,
+      "loss": 9.7613,
+      "step": 410
+    },
+    {
+      "epoch": 0.02623360399750156,
+      "grad_norm": 2179072.0,
+      "learning_rate": 0.0317382763040017,
+      "loss": 9.7948,
+      "step": 420
+    },
+    {
+      "epoch": 0.026858213616489695,
+      "grad_norm": 27136.0,
+      "learning_rate": 0.030971040453019225,
+      "loss": 9.0155,
+      "step": 430
+    },
+    {
+      "epoch": 0.027482823235477825,
+      "grad_norm": 71168.0,
+      "learning_rate": 0.03019779227044398,
+      "loss": 11.3283,
+      "step": 440
+    },
+    {
+      "epoch": 0.028107432854465958,
+      "grad_norm": 8768.0,
+      "learning_rate": 0.029419310351650393,
+      "loss": 8.5037,
+      "step": 450
+    },
+    {
+      "epoch": 0.028107432854465958,
+      "eval_loss": 8.112160682678223,
+      "eval_runtime": 53.9319,
+      "eval_samples_per_second": 15.631,
+      "eval_steps_per_second": 15.631,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -374,7 +417,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 8
+        "early_stopping_patience_counter": 9
       }
     },
     "TrainerControl": {
@@ -388,7 +431,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.633848655872e+16,
+  "total_flos": 1.838079737856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null