Training in progress, step 8, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da9ca59cda04a48a7bc13f8f064118e5e390a24fbf9a17d3b21de5b8d0c169c5
+oid sha256:ff33993c83db654924ab85ac1155bf79ecd4ba80222ed0113f3865437c2cd23d
 size 147781268

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1807731d788099118091845b07fc2a28def49c3ade7b082b6ef3b856f918715
+oid sha256:06ded0f3db3370155cf83e972d92995dd98a90bf7b3580e316ce3a6a5e6d81cf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
+oid sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.015820698747528016,
+  "epoch": 0.02109426499670402,
   "eval_steps": 1,
-  "global_step": 6,
+  "global_step": 8,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -97,6 +97,36 @@
       "eval_samples_per_second": 7.618,
       "eval_steps_per_second": 3.809,
       "step": 6
+    },
+    {
+      "epoch": 0.01845748187211602,
+      "grad_norm": NaN,
+      "learning_rate": 7e-05,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.01845748187211602,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0252,
+      "eval_samples_per_second": 7.61,
+      "eval_steps_per_second": 3.805,
+      "step": 7
+    },
+    {
+      "epoch": 0.02109426499670402,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.02109426499670402,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0431,
+      "eval_samples_per_second": 7.603,
+      "eval_steps_per_second": 3.802,
+      "step": 8
     }
   ],
   "logging_steps": 1,
@@ -116,7 +146,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3897168934993920.0,
+  "total_flos": 5196225246658560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null