Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a870e1c4663c7b346f7c28740905d6735c9efb02a7467f900ac8bbe2ef56d13
+oid sha256:82268eb4ebc284da022ba2a9876cc8ca39128b9fb076a2ff162338b619ffedb7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:595282d5c0bc1890eec6a56cb6d4822e889c54ad99cb82e23d9a68d582d25475
+oid sha256:a712b99c069e5d84e2999ce04a3787ef3a8c95f730e89e8e74262bdde18bc9ca
 size 160172858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e2355e43fd44f1d9860c59f45b4d1039afaad0a42f79d076c0667863cd27cb0
+oid sha256:73aa535a34327d8ff7e12fc9f716f24d876cbdb9f9fc9bc13d972c1b7c68dd32
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0013207131851199648,
+  "epoch": 0.0026414263702399295,
   "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": 15.111,
       "eval_steps_per_second": 15.111,
       "step": 3
+    },
+    {
+      "epoch": 0.0017609509134932863,
+      "grad_norm": 5.33453893661499,
+      "learning_rate": 6e-05,
+      "loss": 11.7484,
+      "step": 4
+    },
+    {
+      "epoch": 0.002201188641866608,
+      "grad_norm": 5.404849052429199,
+      "learning_rate": 8e-05,
+      "loss": 13.2869,
+      "step": 5
+    },
+    {
+      "epoch": 0.0026414263702399295,
+      "grad_norm": 6.6339240074157715,
+      "learning_rate": 0.0001,
+      "loss": 12.8958,
+      "step": 6
+    },
+    {
+      "epoch": 0.0026414263702399295,
+      "eval_loss": 12.353913307189941,
+      "eval_runtime": 32.0275,
+      "eval_samples_per_second": 14.956,
+      "eval_steps_per_second": 14.956,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 492949267808256.0,
+  "total_flos": 985898535616512.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null