Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f12d59d9eda5ce3a7a5c06a22c0ea3f0790d059dd154c77e8cad1df04b7777a
+oid sha256:48ff2fb04423828044b233b95ffadbfb1c2c3bde1bb32b2d59f6677d3fed0243
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8c5309ea7d3e405b007bf21f952f6db4aef04195279c19e91cffe3ac4c44ee
+oid sha256:4bad32bf022a1a6b71c28d75d441a0630bc4bb6fb59aee68fea16a9fbf135daf
 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": 0.015737704918032787,
+  "epoch": 0.02360655737704918,
   "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": 70.49,
       "eval_steps_per_second": 35.464,
       "step": 6
+    },
+    {
+      "epoch": 0.018360655737704918,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.02098360655737705,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.02360655737704918,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.02360655737704918,
+      "eval_loss": NaN,
+      "eval_runtime": 2.3678,
+      "eval_samples_per_second": 67.996,
+      "eval_steps_per_second": 34.209,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 144327309262848.0,
+  "total_flos": 216490963894272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null