Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59c010fef0ffc6ed6428a23a7e8f2eea45bc8ab1e032bff0fb9d3af862d6273d
+oid sha256:bc9f95e4bdbec0ae6395d61733fcfb06307ca3439f74672bf6a8fcac2ac8c7a4
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8304a1b6caf559d349ffc15246f73f97b2e77436833ef04589d16dde40a62a
+oid sha256:3a863630364a7135b46ef32308a2fa185916dd292a6377f2cb605faf2f8420f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013566986998304126,
+  "epoch": 0.02035048049745619,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 8.877,
       "eval_steps_per_second": 4.462,
       "step": 6
+    },
+    {
+      "epoch": 0.01582815149802148,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.018089315997738834,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.02035048049745619,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.02035048049745619,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0564,
+      "eval_samples_per_second": 8.881,
+      "eval_steps_per_second": 4.464,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1977691913846784.0,
+  "total_flos": 2966537870770176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null