Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a48e0e5bde33bb82c52da7473d5f0b81aa3ad4d16f1b412eac2591e9ab1a27e1
+oid sha256:2146169b4fb1058d0986a3326fd72dc0dfe47b976290869ebf399fddbb50c31f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ad78154fee72f2aca6fca0e93077aac0cc3d7717cd9c9ea57c8c724ce6383b
+oid sha256:c049a1a89951687ef2f25fd4c200917ca7b44158d62446e72c444137f6d51aea
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43b3279df66a37918fc86e90e9c6a8fa486ff8c675a0a5adbdb77a496e973bf1
+oid sha256:849c2735d9f3711d3b45cd02f417d920a694e6d10391da18f0c884120cdb6f60
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
+oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.11466121673584,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.14204545454545456,
+  "best_metric": 2.072767734527588,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.2840909090909091,
   "eval_steps": 100,
-  "global_step": 100,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,20 @@
       "eval_samples_per_second": 26.458,
       "eval_steps_per_second": 3.316,
       "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002,
+      "loss": 2.253,
+      "step": 200
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 2.072767734527588,
+      "eval_runtime": 54.1215,
+      "eval_samples_per_second": 27.568,
+      "eval_steps_per_second": 3.455,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3017571420487680.0,
+  "total_flos": 6049717237186560.0,
   "trial_name": null,
   "trial_params": null
 }