Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38a69eea60ae2c511a6a8a453007dc0ae54463f09a21478cf573a6cb04903739
+oid sha256:3cea84735b20860df07e99c5d032c755433782ce57a7cebf8eb1b1f833e67ae5
 size 160284754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0c99adfd3842a16f78adc954f43d1319a31e4bf74797a8fd450f6ab3f8c288b
+oid sha256:0c325a5b88aa7600e783ee566917eff9758a4ec707c33c129463258bf687aee2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:842484d97bbf42f9f92b7e7c8dcf4fda5e0b0607fec45e60ed168e6d3a7f3132
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.028735632183908046,
+  "epoch": 0.038314176245210725,
   "eval_steps": 3,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,49 @@
       "eval_samples_per_second": 8.902,
       "eval_steps_per_second": 4.451,
       "step": 15
+    },
+    {
+      "epoch": 0.03065134099616858,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.032567049808429116,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 17
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 18
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "eval_loss": NaN,
+      "eval_runtime": 24.7147,
+      "eval_samples_per_second": 8.902,
+      "eval_steps_per_second": 4.451,
+      "step": 18
+    },
+    {
+      "epoch": 0.03639846743295019,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 19
+    },
+    {
+      "epoch": 0.038314176245210725,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -179,7 +222,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4929492678082560.0,
+  "total_flos": 6572656904110080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null