Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:307db22548bb8efce244d1693d3d6bf218dddd86c9cfe375fb388e767c463354
+oid sha256:4c2c11dc9609637e2c0194db83e6a5ef6364fa742cce6e53c085366e64b7becc
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fae587b490d10ee1d9d0572f9974990e29e67b407d7d1a60dfacb6e03ca97b45
+oid sha256:d93c155a2f08d4854751b4c380883cd7a540e2503f59610b907be61301487777
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
+oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5546995377503852,
+  "epoch": 0.6101694915254238,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 61.19,
       "eval_steps_per_second": 15.633,
       "step": 90
+    },
+    {
+      "epoch": 0.5731895223420647,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.5916795069337443,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "eval_loss": NaN,
+      "eval_runtime": 2.2387,
+      "eval_samples_per_second": 61.197,
+      "eval_steps_per_second": 15.634,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3545441315586048.0,
+  "total_flos": 3893223025016832.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null