Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d4b06137715f08cb1819a7e64ffe4867022fc98dd74c9620510568c2eb22551
+oid sha256:f721cdf8778daedd4a3ef794c51aa3b5e53e4fc05c6baa7d95be0804bfc53c0f
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362013b919620535789e01ddf8fe320a697c8e5c2c9149bb97ac9dce8d40cbf1
+oid sha256:12f065202ab17e7299c16d51e708d5eca87082441a934a30ded8d5549cba370b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f7d71d2520220b24b14e74f15b8fc66bb3fd91884b9f80b2d1815e9fc2c23c
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011825572801182557,
+  "epoch": 0.0023651145602365115,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,87 @@
       "eval_samples_per_second": 9.529,
       "eval_steps_per_second": 2.383,
       "step": 20
+    },
+    {
+      "epoch": 0.0012416851441241685,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014190687361419069,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014781966001478197,
+      "eval_loss": NaN,
+      "eval_runtime": 747.4269,
+      "eval_samples_per_second": 9.529,
+      "eval_steps_per_second": 2.383,
+      "step": 25
+    },
+    {
+      "epoch": 0.0015964523281596452,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017738359201773836,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0017738359201773836,
+      "eval_loss": NaN,
+      "eval_runtime": 747.2571,
+      "eval_samples_per_second": 9.531,
+      "eval_steps_per_second": 2.383,
+      "step": 30
+    },
+    {
+      "epoch": 0.001951219512195122,
+      "grad_norm": NaN,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.0020694752402069475,
+      "eval_loss": NaN,
+      "eval_runtime": 747.3957,
+      "eval_samples_per_second": 9.529,
+      "eval_steps_per_second": 2.383,
+      "step": 35
+    },
+    {
+      "epoch": 0.0021286031042128603,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.0023059866962305987,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0023651145602365115,
+      "eval_loss": NaN,
+      "eval_runtime": 747.4395,
+      "eval_samples_per_second": 9.529,
+      "eval_steps_per_second": 2.383,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -103,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.14364023570432e+16,
+  "total_flos": 2.28728047140864e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null