Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f25312d1e55d963392faae14984bde8883ac5ed45521d95a5ba3117c044d577
+oid sha256:7fd837a5590edd92029db548fe3c5c440905e517bc803ca576abb91035efe586
 size 128584660

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:139902d6f1c5ecb87ebd67e8bc0b0f5c60f709abf28f12ffe9c8398dabb0497f
+oid sha256:787672b76393ad80c7004ec715772706d091c91cf1cb475edc6cd466b470af71
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
+oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02450379808870375,
+  "epoch": 0.0490075961774075,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 22.33,
       "eval_steps_per_second": 11.165,
       "step": 50
+    },
+    {
+      "epoch": 0.029404557706444498,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.03430531732418525,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.1023,
+      "step": 70
+    },
+    {
+      "epoch": 0.039206076941926,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 2.9289,
+      "step": 80
+    },
+    {
+      "epoch": 0.04410683655966675,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.0490075961774075,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.0490075961774075,
+      "eval_loss": NaN,
+      "eval_runtime": 19.2916,
+      "eval_samples_per_second": 22.29,
+      "eval_steps_per_second": 11.145,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -77,7 +120,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6551577506611200.0,
+  "total_flos": 1.3234186563354624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null