Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f45da18ffe6a87eec948702c550eb89629bb19b370b9203cabcf65a1e7a0f995
+oid sha256:6999c99eea0b0266a2ac7dcbaddb81c62a52a7e6e4a53bcdfc61d88e64dafb3e
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d64953f2e9fcada48106b0ad051c6bb12e4e7fe1c3f5c7aceb52311967353d2
+oid sha256:3c1a4926822db30f09f4bbd86995ac88e3a184071e334d5409d35d505e654066
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a2b95a554f478964b177ad3584df1edb2740b9bf0b38dfedd8dd3ec77bf608
+oid sha256:cfaa4886ed0ea6607b80dc19768b13929cd61db49ca5da535bb81315a547e2d0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e28956bcd22cce157bbc51b2792ecea0f5758f658ecdb7e2f6f44bf0a8eb437
+oid sha256:727ba7417be9bf55486018db0bce299e5f30a0929b57ebeb211860d94b8f688e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa7369be71488b3930265a27fef5a0c7339be82a8750ca1eac7c1e8b9538cf4a
+oid sha256:14aa7e4285ecbf100d4080f2325c15105b90cc4db299cabd9399cadfa04d8fd2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3416370106761566,
+  "epoch": 0.35587188612099646,
   "eval_steps": 4,
-  "global_step": 48,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,20 @@
       "eval_samples_per_second": 32.938,
       "eval_steps_per_second": 4.169,
       "step": 48
+    },
+    {
+      "epoch": 0.3487544483985765,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.35587188612099646,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -461,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4244235844360602e+17,
+  "total_flos": 1.483774567120896e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null