Training in progress, step 72, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:560328ad1ead82256b7dd494b6819dd6ffa7f9002401cfebbad9117059fb87d8
+oid sha256:7fc409f0cd4922b48234cc46633800eb915f58fb50d607b96a99d2abf746ba4f
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc9120ba08562e298368a02d3bb5097b22537f427b96b3a071e6c5a8b4dba68e
+oid sha256:963103910acf3003b8f4035e02dee57e8e13bbe04dcb03283c8c89f04827e98f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b2d2818ab3151c9ed744a4cb682fe1730b800005846a54cc3da941ac8ce20d
+oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022747275066007717,
+  "epoch": 0.025996885789723107,
   "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": 4.549,
       "eval_steps_per_second": 2.275,
       "step": 63
+    },
+    {
+      "epoch": 0.023830478640579515,
+      "grad_norm": NaN,
+      "learning_rate": 7.66554636144095e-05,
+      "loss": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.02491368221515131,
+      "grad_norm": NaN,
+      "learning_rate": 6.538829429225069e-05,
+      "loss": 0.0,
+      "step": 69
+    },
+    {
+      "epoch": 0.025996885789723107,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 72
+    },
+    {
+      "epoch": 0.025996885789723107,
+      "eval_loss": NaN,
+      "eval_runtime": 2143.6207,
+      "eval_samples_per_second": 4.352,
+      "eval_steps_per_second": 2.176,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.342329086444831e+17,
+  "total_flos": 3.819804670222664e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null