Training in progress, step 27, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d94de2d90888ff412be9030ba29b6ba01bbe7b6fc630ac425ff3dc994ec422d
+oid sha256:7e7876709536cc00039d760f19969d0d4cc00463afd7b9a639caf949d716e8d6
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:744f4b25d9d27786fbe13b26cfbe9f12e3cb849ad67e1877f33c639773c136fa
+oid sha256:daaca9b56f59ca5bc9c2416a658398e3bf50376464d364157ba9fde5c8d9e3a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
+oid sha256:f1f9e237c4e244cd6a21b3069d52ab1ce3e784c965dcb77abb8266616185916c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03262347077480743,
+  "epoch": 0.04893520616221115,
   "eval_steps": 9,
-  "global_step": 18,
+  "global_step": 27,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 284.299,
       "eval_steps_per_second": 35.646,
       "step": 18
+    },
+    {
+      "epoch": 0.03624830086089714,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.045310376076121435,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014855889603024227,
+      "loss": 0.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.04893520616221115,
+      "eval_loss": NaN,
+      "eval_runtime": 6.8843,
+      "eval_samples_per_second": 284.997,
+      "eval_steps_per_second": 35.734,
+      "step": 27
     }
   ],
   "logging_steps": 5,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 323567065497600.0,
+  "total_flos": 485350598246400.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null