Training in progress, step 117, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db53d6e20ce5b276c29b77d163bd02156b7147537fbe7c49225e999d43969323
+oid sha256:2cab66a9ac6a7915e9514675876bc4722ab7dda5a154da7acb92ef39161c1b30
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d2c7b52816077146c7dceed94c13544f09e525e066cdac16695dfabd5a8807
+oid sha256:0cb88087a989efdb67ff97d3da25401e541aeeb31f6e8cdd767f7fb901fb5acc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c89b61481eb2980a04190d12a0165f95c9fc0a4db20ad8cc3d895835eac42f68
+oid sha256:49a9f08177ba433a82ec0fa599b737a453ff55e83dd9d31c6fddaf5bc4b0a0b3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0612244897959184,
+  "epoch": 1.193877551020408,
   "eval_steps": 13,
-  "global_step": 104,
+  "global_step": 117,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,49 @@
       "eval_samples_per_second": 36.458,
       "eval_steps_per_second": 4.64,
       "step": 104
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": NaN,
+      "learning_rate": 2.3398396174233178e-05,
+      "loss": 0.0,
+      "step": 105
+    },
+    {
+      "epoch": 1.1020408163265305,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 108
+    },
+    {
+      "epoch": 1.1326530612244898,
+      "grad_norm": NaN,
+      "learning_rate": 1.7956219300748793e-05,
+      "loss": 0.0,
+      "step": 111
+    },
+    {
+      "epoch": 1.163265306122449,
+      "grad_norm": NaN,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 0.0,
+      "step": 114
+    },
+    {
+      "epoch": 1.193877551020408,
+      "grad_norm": NaN,
+      "learning_rate": 1.3094050125632972e-05,
+      "loss": 0.0,
+      "step": 117
+    },
+    {
+      "epoch": 1.193877551020408,
+      "eval_loss": NaN,
+      "eval_runtime": 4.5276,
+      "eval_samples_per_second": 36.443,
+      "eval_steps_per_second": 4.638,
+      "step": 117
     }
   ],
   "logging_steps": 3,
@@ -336,7 +379,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.829454746845184e+16,
+  "total_flos": 3.183242896736256e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null