Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a545a2334935f0ceb44fd22576f243dfbfd282afb137f3852f6c8b158d7cdf0
+oid sha256:5ec4d6f70dfb8944d1bba1741f2a6dd100da2846e715de539eb14ceeef0aeb78
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db121c88e5d683427da5b417de88dc4e6caf0fd38255739d5034394bdb437ff
+oid sha256:c6359e9e33b6aa602baa48623acb51ef04f5c9a7d455e6797233361f60ff8afb
 size 63350356

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4af710ad4f274faa9b58f6cf20fac7055b576fc6d71184444a1ebd38ff3ab5cf
+oid sha256:8f950b0268010d104784b120cded4da9c670d6f266e714ca76f08fbfcb47fa9d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71f4cdd57db93caa0e11efdf70fa4ba465ba18c8a6ada689ee3d6ac9256e694
+oid sha256:26752e00ffcac10225a7efcf37955b0ad83d067cc5cc3f8f06c5725defc153ea
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008,
+  "epoch": 0.014,
   "eval_steps": 1000,
-  "global_step": 20,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -127,13 +127,103 @@
       "learning_rate": 0.00017687074829931973,
       "loss": 1.9084,
       "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017551020408163265,
+      "loss": 1.9708,
+      "step": 21
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001741496598639456,
+      "loss": 1.8567,
+      "step": 22
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0001727891156462585,
+      "loss": 1.5694,
+      "step": 23
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017142857142857143,
+      "loss": 1.8519,
+      "step": 24
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00017006802721088434,
+      "loss": 1.663,
+      "step": 25
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016870748299319729,
+      "loss": 1.9309,
+      "step": 26
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016734693877551023,
+      "loss": 1.551,
+      "step": 27
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016598639455782315,
+      "loss": 1.4782,
+      "step": 28
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016462585034013606,
+      "loss": 1.6643,
+      "step": 29
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016326530612244898,
+      "loss": 1.5571,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016190476190476192,
+      "loss": 1.6747,
+      "step": 31
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00016054421768707484,
+      "loss": 1.3539,
+      "step": 32
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015918367346938776,
+      "loss": 2.0579,
+      "step": 33
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015782312925170067,
+      "loss": 1.5418,
+      "step": 34
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.00015646258503401362,
+      "loss": 1.8159,
+      "step": 35
     }
   ],
   "logging_steps": 1,
   "max_steps": 150,
   "num_train_epochs": 1,
   "save_steps": 5,
-  "total_flos": 2841084152954880.0,
+  "total_flos": 4201718730424320.0,
   "trial_name": null,
   "trial_params": null
 }