Training in progress, step 450, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e5d1b25f242c4059e38af761fe20109094cf4ff071e1b42eae5fe27d3898d9
+oid sha256:2a72c7122e01b7a3c69dbf48689b25e3f1a1ea9b39c9477bbcce48aa824ebd75
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3a2fe70770abb05b9a17211f4d92b1c5c9b9326c74929f9fd7a6b607ab5e01
+oid sha256:bdfb9a962054085d51f65b07ec7ce6efdce52c9f1305a80120bfc71525e5d53b
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8de433ccc2eb550cd1203215b586d51ab7806aea1bd10df48f783bc82071b584
+oid sha256:cae951ad6b64c1ca00eac3b94f71a01edaadd9f074943dac7c98b25779eacbdd
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2af68b5e1729c4169c5bcdf83d662c94d2aac05a4d0e5f5a1fd64f69c1c27280
+oid sha256:f80182874a8dae6d37ca411908d4270925dd00a648a54c2f458ca439f7a0f4f2
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4c78e85c4ba926d25150d4aaddeaf5728dcb066f4afc01202e3e56f29a5487
+oid sha256:09cdb762729be962079ece7b2f698502a2f7c6e43bcd7a4d08e2ef5354e88da2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 30.76923076923077,
+  "epoch": 34.61538461538461,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 284.775,
       "eval_steps_per_second": 4.553,
       "step": 400
+    },
+    {
+      "epoch": 31.53846153846154,
+      "grad_norm": 0.4140625,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 9.1787,
+      "step": 410
+    },
+    {
+      "epoch": 32.30769230769231,
+      "grad_norm": 0.419921875,
+      "learning_rate": 4.530518418775733e-05,
+      "loss": 9.1782,
+      "step": 420
+    },
+    {
+      "epoch": 33.07692307692308,
+      "grad_norm": 0.41796875,
+      "learning_rate": 4.077647473350201e-05,
+      "loss": 9.1776,
+      "step": 430
+    },
+    {
+      "epoch": 33.84615384615385,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.642762517900322e-05,
+      "loss": 9.1787,
+      "step": 440
+    },
+    {
+      "epoch": 34.61538461538461,
+      "grad_norm": 0.416015625,
+      "learning_rate": 3.227184283742591e-05,
+      "loss": 9.1777,
+      "step": 450
+    },
+    {
+      "epoch": 34.61538461538461,
+      "eval_loss": 9.195714950561523,
+      "eval_runtime": 5.2816,
+      "eval_samples_per_second": 284.194,
+      "eval_steps_per_second": 4.544,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -378,7 +421,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 163663419801600.0,
+  "total_flos": 184121347276800.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null