Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ef53ef5d0dca1b659a9e42edbd29e501fd6b2e3e351fb934083deb75ee3211
+oid sha256:fb5d9be0c5d559f23742ab958ed7b2b40e5d0e7499e22b9c05afe7c8d903d767
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f44422a433ce81a89551cd1cc0ce2c0494dc1515a0610a53dfff333adbf8842
+oid sha256:0b68b5ba54bdbf8baa3d26a7490acac1193a5b5381d147f873c74e6bb65e1a01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1911764705882353,
+  "epoch": 1.3235294117647058,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 6.819,
       "eval_steps_per_second": 0.889,
       "step": 81
+    },
+    {
+      "epoch": 1.2352941176470589,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 15.8322,
+      "step": 84
+    },
+    {
+      "epoch": 1.2794117647058822,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 22.2182,
+      "step": 87
+    },
+    {
+      "epoch": 1.3235294117647058,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 8.1206,
+      "step": 90
+    },
+    {
+      "epoch": 1.3235294117647058,
+      "eval_loss": NaN,
+      "eval_runtime": 16.849,
+      "eval_samples_per_second": 6.825,
+      "eval_steps_per_second": 0.89,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.297238907256832e+17,
+  "total_flos": 2.5531788706185216e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null