Training in progress, step 63, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec4bc64a2a4d3723ce8d6d8e746b2721c3ef5ae4d728a75f020af1330d6c66b9
+oid sha256:8f25c608dae5960aa3157f959a318027fb24b56f2c22c2f00f2da12798dd2440
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d981e986fc880ede433373fb3bed25f74e9754b75202cb893fc5c6a38d25f5e0
+oid sha256:936078bd54aede1df1a013ccad470ef49b2af6814caa4e80a913b2cd22cafaf1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7941176470588235,
+  "epoch": 0.9264705882352942,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 6.86,
       "eval_steps_per_second": 0.895,
       "step": 54
+    },
+    {
+      "epoch": 0.8382352941176471,
+      "grad_norm": NaN,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 0.0,
+      "step": 57
+    },
+    {
+      "epoch": 0.8823529411764706,
+      "grad_norm": NaN,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 22.9755,
+      "step": 60
+    },
+    {
+      "epoch": 0.9264705882352942,
+      "grad_norm": NaN,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 8.2233,
+      "step": 63
+    },
+    {
+      "epoch": 0.9264705882352942,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7523,
+      "eval_samples_per_second": 6.865,
+      "eval_steps_per_second": 0.895,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5356397801701376e+17,
+  "total_flos": 1.7915797435318272e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null