Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8355842eaaea4ad648b1185be8e59943fbef2b5c148636242e862a9bbd6be82
+oid sha256:14d78da68a3cd7c8507ded2a06d3dc0ae1bb125cd9dc2d93be1232584af4f93b
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9abc5be02d6818ada0a46267e1ad7acb6ec38aef01cc20ce9268dfc145060865
+oid sha256:31d78ee47b7325a3fe3c9292fec1428718dbfde329f578ab0236f92537ee5db9
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8eabc4c6534ef93123c1386a68bfedd2b9d4f40032f88ace4c9615f83893ae17
+oid sha256:0f00fc8a02d93d39594f8723df4519e49ea33868de4de4aca98b1b742a0f6838
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005682563273156445,
+  "epoch": 0.001136512654631289,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 8.991,
       "eval_steps_per_second": 4.496,
       "step": 10
+    },
+    {
+      "epoch": 0.0006556803776718975,
+      "grad_norm": 5.863097190856934,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.0983,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008742405035625301,
+      "grad_norm": 5.090754985809326,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1696,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008742405035625301,
+      "eval_loss": 0.4852387309074402,
+      "eval_runtime": 1072.4751,
+      "eval_samples_per_second": 8.982,
+      "eval_steps_per_second": 4.491,
+      "step": 20
+    },
+    {
+      "epoch": 0.0010928006294531627,
+      "grad_norm": 4.771880626678467,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9564,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4162595523133440.0,
+  "total_flos": 8500458226188288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null