Training in progress, step 44, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699bfd4aca3d2e5c4e4cde8bfd7897c32108dbe7daf07b2c7d9432ca1b0543aa
+oid sha256:9545bc14be0e7babd203c01c8ca481ef646f996e3c0ed59dbce3cec9e4b51b84
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5a6242c7c02c25e5b316f544047c9044c9faa2fd1a8c1cfa264ca91871fe3a
+oid sha256:f7222a8bc78f2f195453d152b96260a204ab54c7585bb8a13af06def19205c49
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:7ed6431293c03d1e193e9501dc8ed4f4955bf079fba7f2c1c309a3efed166e50
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04338394793926247,
+  "epoch": 0.04772234273318872,
   "eval_steps": 4,
-  "global_step": 40,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,6 +375,42 @@
       "eval_samples_per_second": 7.658,
       "eval_steps_per_second": 3.839,
       "step": 40
+    },
+    {
+      "epoch": 0.044468546637744036,
+      "grad_norm": NaN,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.0455531453362256,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.046637744034707156,
+      "grad_norm": NaN,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 0.04772234273318872,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 0.04772234273318872,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8611,
+      "eval_samples_per_second": 7.648,
+      "eval_steps_per_second": 3.834,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -394,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.117937171693568e+16,
+  "total_flos": 1.2297308888629248e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null