Training in progress, step 32, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2195117d41b17e4fe58cca08787f019143407a6dab60695c3c4ba2233a5692f
+oid sha256:d79035a77b8af93ed625dddbdf69f7b138f37f11242f6e892460a33847f7fc32
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d476b0b3563b1fa3d4de8be22a666cbc835905a62f1f401aa3aa58a55379251
+oid sha256:68726575bc3953efd1f0f03d12422c84092fd0f66b74c5722849bdea24401053
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff994fffd2fb6fe21545e6fbc55baa2a1474438a89b2d40605678f7de701427c
+oid sha256:06c69db2db6de56f38ba12b474a491d20087e27dc2893a95d6ac7716476ca645
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03036876355748373,
+  "epoch": 0.03470715835140998,
   "eval_steps": 4,
-  "global_step": 28,
+  "global_step": 32,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,42 @@
       "eval_samples_per_second": 3.63,
       "eval_steps_per_second": 1.82,
       "step": 28
+    },
+    {
+      "epoch": 0.031453362255965296,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001078459095727845,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.03253796095444685,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.033622559652928416,
+      "grad_norm": NaN,
+      "learning_rate": 9.215409042721552e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 0.03470715835140998,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 0.03470715835140998,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8923,
+      "eval_samples_per_second": 7.644,
+      "eval_steps_per_second": 3.832,
+      "step": 32
     }
   ],
   "logging_steps": 1,
@@ -286,7 +322,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7825560201854976.0,
+  "total_flos": 8943497373548544.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null