Training in progress, step 500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a72c7122e01b7a3c69dbf48689b25e3f1a1ea9b39c9477bbcce48aa824ebd75
+oid sha256:457ea60d64db7108be0259f24e397d19fe5ff7dc5efa5e76d938a0c21604a326
 size 2066752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdfb9a962054085d51f65b07ec7ce6efdce52c9f1305a80120bfc71525e5d53b
+oid sha256:d90884f4c593fcabac0b3930a1fc340afcd016fedb3640704d17b8ab041a1059
 size 2162798

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cae951ad6b64c1ca00eac3b94f71a01edaadd9f074943dac7c98b25779eacbdd
+oid sha256:e9e00cf017b71358b07c8c2c8b20cbd10a881dae50181b31232805c6f5faced7
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80182874a8dae6d37ca411908d4270925dd00a648a54c2f458ca439f7a0f4f2
+oid sha256:77b5493d245f39afc7c313900f9bd075608d678324a8dee69773a4ada7717fca
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09cdb762729be962079ece7b2f698502a2f7c6e43bcd7a4d08e2ef5354e88da2
+oid sha256:628e045b78e5d559e9fcef6658ed03e911773af6f7354bf6b3b679b0ff34bfdb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 34.61538461538461,
+  "epoch": 38.46153846153846,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 284.194,
       "eval_steps_per_second": 4.544,
       "step": 450
+    },
+    {
+      "epoch": 35.38461538461539,
+      "grad_norm": 0.4140625,
+      "learning_rate": 2.8321748683154893e-05,
+      "loss": 9.1782,
+      "step": 460
+    },
+    {
+      "epoch": 36.15384615384615,
+      "grad_norm": 0.419921875,
+      "learning_rate": 2.4589339022310386e-05,
+      "loss": 9.1783,
+      "step": 470
+    },
+    {
+      "epoch": 36.92307692307692,
+      "grad_norm": 0.416015625,
+      "learning_rate": 2.1085949060360654e-05,
+      "loss": 9.1769,
+      "step": 480
+    },
+    {
+      "epoch": 37.69230769230769,
+      "grad_norm": 0.4140625,
+      "learning_rate": 1.7822218477475494e-05,
+      "loss": 9.1779,
+      "step": 490
+    },
+    {
+      "epoch": 38.46153846153846,
+      "grad_norm": 0.419921875,
+      "learning_rate": 1.4808059116167305e-05,
+      "loss": 9.1781,
+      "step": 500
+    },
+    {
+      "epoch": 38.46153846153846,
+      "eval_loss": 9.193068504333496,
+      "eval_runtime": 5.6598,
+      "eval_samples_per_second": 265.206,
+      "eval_steps_per_second": 4.24,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -421,7 +464,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 184121347276800.0,
+  "total_flos": 204579274752000.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null