Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee965144516b4e149f02338575d3819d2bc87be913df116f67c3bcadb67b4931
+oid sha256:c67a6d5516396247f78e672019632cb827d8fb2b5c48dafb5278175502cf0edc
 size 20814996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f6b216af514ae2829132776730c75f6fcabc4f6aafe115b0e300d42921890bf
+oid sha256:c367f329ae6cb5bb8e3e64fd29746c6490651d10a102be67dd7605dc7a667ed5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013676382596803146,
+  "epoch": 0.002735276519360629,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 6.939,
       "eval_steps_per_second": 6.939,
       "step": 2
+    },
+    {
+      "epoch": 0.002051457389520472,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 5.5757,
+      "step": 3
+    },
+    {
+      "epoch": 0.002735276519360629,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 6.9588,
+      "step": 4
+    },
+    {
+      "epoch": 0.002735276519360629,
+      "eval_loss": NaN,
+      "eval_runtime": 88.9657,
+      "eval_samples_per_second": 6.924,
+      "eval_steps_per_second": 6.924,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 193120507527168.0,
+  "total_flos": 416733726769152.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null