Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae119f341e84b366dd2ab4e1a59e100469a5de2a1e27012bbeaf763ff2fcd67a
+oid sha256:59c010fef0ffc6ed6428a23a7e8f2eea45bc8ab1e032bff0fb9d3af862d6273d
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6f68db41ae05e4fd61bc0a423f43413fd1059772aa4b829d12fe86154e429e
+oid sha256:df8304a1b6caf559d349ffc15246f73f97b2e77436833ef04589d16dde40a62a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006783493499152063,
+  "epoch": 0.013566986998304126,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 8.867,
       "eval_steps_per_second": 4.457,
       "step": 3
+    },
+    {
+      "epoch": 0.009044657998869417,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.011305822498586773,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.013566986998304126,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 0.013566986998304126,
+      "eval_loss": NaN,
+      "eval_runtime": 21.0654,
+      "eval_samples_per_second": 8.877,
+      "eval_steps_per_second": 4.462,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 988845956923392.0,
+  "total_flos": 1977691913846784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null