Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfed874c1198ec47f693a78f84623349783ec912c533f92284cb6be95857cc1a
+oid sha256:f3ab3ed9d9a9328d836e02e368f382ee66936af3adecf6cacf12c3d5f5f37b64
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22dd9d8a3a3a43362e98f3a584e3df34a48d815ce70df67c325918db31a036e8
+oid sha256:54d04bfb7aa3c282c988c95c52c118eeebdd77bc9f43dc2d03b8d6e17835e6fe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017772998815873953,
+  "epoch": 0.0035545997631747906,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 6.021,
       "eval_steps_per_second": 6.021,
       "step": 25
+    },
+    {
+      "epoch": 0.0021327598579048744,
+      "grad_norm": NaN,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.0024882198342223534,
+      "grad_norm": NaN,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 0.0028436798105398327,
+      "grad_norm": NaN,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0031991397868573117,
+      "grad_norm": NaN,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.0035545997631747906,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.0035545997631747906,
+      "eval_loss": NaN,
+      "eval_runtime": 14158.1679,
+      "eval_samples_per_second": 3.533,
+      "eval_steps_per_second": 3.533,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.30626883682304e+16,
+  "total_flos": 2.61253767364608e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null