Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f25c608dae5960aa3157f959a318027fb24b56f2c22c2f00f2da12798dd2440
+oid sha256:f0cd9e63169a7693d893221d6d496c241b259ed265c4b3827680e851a49a36e6
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936078bd54aede1df1a013ccad470ef49b2af6814caa4e80a913b2cd22cafaf1
+oid sha256:1c912f99eba164ba548508da56ac857cacc1455d4da877841d53bc479eccc7e5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9264705882352942,
+  "epoch": 1.0588235294117647,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 6.865,
       "eval_steps_per_second": 0.895,
       "step": 63
+    },
+    {
+      "epoch": 0.9705882352941176,
+      "grad_norm": NaN,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 6.5478,
+      "step": 66
+    },
+    {
+      "epoch": 1.0147058823529411,
+      "grad_norm": NaN,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 3.7818,
+      "step": 69
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "grad_norm": NaN,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 17.1026,
+      "step": 72
+    },
+    {
+      "epoch": 1.0588235294117647,
+      "eval_loss": NaN,
+      "eval_runtime": 16.7798,
+      "eval_samples_per_second": 6.853,
+      "eval_steps_per_second": 0.894,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7915797435318272e+17,
+  "total_flos": 2.0412989438951424e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null