Training in progress, step 400, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64c8f22073f810e14ea11a51c997d214e79493ceb718231c712f6890686cd0a
+oid sha256:02e5d1b25f242c4059e38af761fe20109094cf4ff071e1b42eae5fe27d3898d9
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f58b607dd2bb3376b1a270f24d36d7e6ad6b3fbcf77fb0f3a3fa5f5a10a5ee3
+oid sha256:7d3a2fe70770abb05b9a17211f4d92b1c5c9b9326c74929f9fd7a6b607ab5e01
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb5daaf1199744204be7b2c0227bbbc86b8f02198eb2753856850454b418ba43
+oid sha256:8de433ccc2eb550cd1203215b586d51ab7806aea1bd10df48f783bc82071b584
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ef0a11ec368bc2c0da98c701c736f96e203337d9c97fab18e13b92ce5dd6d5b
+oid sha256:2af68b5e1729c4169c5bcdf83d662c94d2aac05a4d0e5f5a1fd64f69c1c27280
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972684576ff55802aec9ad573b837fe663d45ec783d38050b5b6dc1fc7271117
+oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 26.923076923076923,
+  "epoch": 30.76923076923077,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 285.129,
       "eval_steps_per_second": 4.559,
       "step": 350
+    },
+    {
+      "epoch": 27.692307692307693,
+      "grad_norm": 0.416015625,
+      "learning_rate": 7.54514512859201e-05,
+      "loss": 9.186,
+      "step": 360
+    },
+    {
+      "epoch": 28.46153846153846,
+      "grad_norm": 0.412109375,
+      "learning_rate": 7.014851889983057e-05,
+      "loss": 9.182,
+      "step": 370
+    },
+    {
+      "epoch": 29.23076923076923,
+      "grad_norm": 0.416015625,
+      "learning_rate": 6.493624448072457e-05,
+      "loss": 9.1823,
+      "step": 380
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 0.4140625,
+      "learning_rate": 5.983045753470308e-05,
+      "loss": 9.1806,
+      "step": 390
+    },
+    {
+      "epoch": 30.76923076923077,
+      "grad_norm": 0.419921875,
+      "learning_rate": 5.484666416891109e-05,
+      "loss": 9.18,
+      "step": 400
+    },
+    {
+      "epoch": 30.76923076923077,
+      "eval_loss": 9.195965766906738,
+      "eval_runtime": 5.2708,
+      "eval_samples_per_second": 284.775,
+      "eval_steps_per_second": 4.553,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -335,7 +378,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 143205492326400.0,
+  "total_flos": 163663419801600.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null