Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:083558a113db9efb2cf479f3d7de4395a6e412d5fdfa2d4acf791f1c858b34ed
+oid sha256:7151fe7fcb33826563b5ed5fcb17f7a06d826580b4d45f91810fa5004e6109ed
 size 463916180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141fe731c27da354e082db328d428f949999b83b115b46b9ef67c59bbcdc3469
+oid sha256:5ef5917c07e516c225171717991df903e6a8126613e1066d0d6d0daeb6ad0c24
 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": 0.5187319884726225,
+  "epoch": 0.5706051873198847,
   "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": 9.49,
       "eval_steps_per_second": 1.198,
       "step": 90
+    },
+    {
+      "epoch": 0.5360230547550432,
+      "grad_norm": NaN,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.553314121037464,
+      "grad_norm": NaN,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.5706051873198847,
+      "grad_norm": NaN,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.5706051873198847,
+      "eval_loss": NaN,
+      "eval_runtime": 30.8968,
+      "eval_samples_per_second": 9.483,
+      "eval_steps_per_second": 1.198,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1120281594560512e+17,
+  "total_flos": 2.3267123404996608e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null