Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c68d59ab4d2c4b72a6891c3607ac02704e61812a273ff1be9becf10d57a12526
+oid sha256:2d63daef62dc77f1ba6f764f83f7b02999fff144c3b161ea32cef10d37c7ed4a
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5b99c1f41733e36dbf2b7cd8e6749d272cb1c678c0936764f8c77fbbaa4f31
+oid sha256:a75c69a5c2f8f95f9a8dd4e08c386857b1b16ba220d6c66832a60471fd5234df
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963109be152ba18d176455e8bf40578d153adfdff8104de1d72f96e3d3b82507
+oid sha256:744a5a6bba1f0aff99d5e21c41ab079ee18b65574a5f3f9abbf77c2cfb749393
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013011656275413392,
+  "epoch": 0.026023312550826783,
   "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": 4.748,
       "eval_steps_per_second": 2.38,
       "step": 3
+    },
+    {
+      "epoch": 0.01734887503388452,
+      "grad_norm": 234.3598175048828,
+      "learning_rate": 4e-05,
+      "loss": 129.1868,
+      "step": 4
+    },
+    {
+      "epoch": 0.021686093792355653,
+      "grad_norm": 219.65846252441406,
+      "learning_rate": 5e-05,
+      "loss": 121.4155,
+      "step": 5
+    },
+    {
+      "epoch": 0.026023312550826783,
+      "grad_norm": 224.65374755859375,
+      "learning_rate": 6e-05,
+      "loss": 114.3207,
+      "step": 6
+    },
+    {
+      "epoch": 0.026023312550826783,
+      "eval_loss": NaN,
+      "eval_runtime": 81.9854,
+      "eval_samples_per_second": 4.745,
+      "eval_steps_per_second": 2.378,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.744736565690368e+16,
+  "total_flos": 5.489473131380736e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null