Training in progress, step 500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c691fc20bc081097cd8eeba3ecb439932d995a80f27df276c2e7bee3afd9c44b
+oid sha256:2a9edd40202ee9bdf83a9f4827636fe20841088385d615033eadefca3bdaa0d7
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e642aa3aadaad39eb5ba24a7138f75e05cfb8e04f0f46b6dec6c858a6e830d2e
+oid sha256:dd03f6f393ff738690b65d3fe4979497863b808868e53b447f27f154a47f61e0
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:433b20d5c0cacd84af924042d215e7b29768d81cd940f6181e72d73d7442eaec
+oid sha256:c381572d32a65fc1a155eecfa512281a474c4a471f1632383ddae55b8849c5e3
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a97db8e41139aa1239ba7fb79ddeb0af5998c6305a440c1fe182e6ad02f2f5
+oid sha256:d2b5691046896d865f067a1958689168fc2411c74d2f82d596bd6a636b2b141b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfb05f711fd9bb3d14fd3664cc7d698df71ec289614aa26046fdc74fe37e7e86
+oid sha256:5924175694b6d639a07e1869835f8c2275afefcb042e767ca76a1976be92d591
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.028107432854465958,
+  "epoch": 0.03123048094940662,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -403,6 +403,49 @@
       "eval_samples_per_second": 15.631,
       "eval_steps_per_second": 15.631,
       "step": 450
+    },
+    {
+      "epoch": 0.02873204247345409,
+      "grad_norm": 650117120.0,
+      "learning_rate": 0.02863637856194159,
+      "loss": 8.5855,
+      "step": 460
+    },
+    {
+      "epoch": 0.029356652092442224,
+      "grad_norm": 11008.0,
+      "learning_rate": 0.027849785247263517,
+      "loss": 8.1377,
+      "step": 470
+    },
+    {
+      "epoch": 0.029981261711430358,
+      "grad_norm": 2491081031680.0,
+      "learning_rate": 0.02706032244040741,
+      "loss": 8.1602,
+      "step": 480
+    },
+    {
+      "epoch": 0.030605871330418487,
+      "grad_norm": 15269888.0,
+      "learning_rate": 0.026268785063499858,
+      "loss": 7.909,
+      "step": 490
+    },
+    {
+      "epoch": 0.03123048094940662,
+      "grad_norm": 245366784.0,
+      "learning_rate": 0.025475970127583666,
+      "loss": 7.9959,
+      "step": 500
+    },
+    {
+      "epoch": 0.03123048094940662,
+      "eval_loss": 8.136107444763184,
+      "eval_runtime": 56.6292,
+      "eval_samples_per_second": 14.886,
+      "eval_steps_per_second": 14.886,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -417,7 +460,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 9
+        "early_stopping_patience_counter": 10
       }
     },
     "TrainerControl": {
@@ -431,7 +474,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.838079737856e+16,
+  "total_flos": 2.04231081984e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null