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:e727323bdfa520289a8a2fcafdc26adf99fe346e3e4e6c67a66da55a141c4cc6
+oid sha256:244075e61cfba6fce1d39bcf9cb324d2c15855a85c8c9f070b1b02b583d79191
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94432f8e6db29ac2440ed1905d751ae5a85a222cbe97079923530b0f64df73b5
+oid sha256:14820837fa543088ed4263945cb71d78b076dc75cfbe8bb7b9d8cbc14d270e49
 size 39357765

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ef219513e71d8ab9cdbb2c25e6f2dd72b17893947136e50ff86a3f1b070d6b
+oid sha256:74da0cfd2909a0206b76154a6dfea7012609d0bc75531627f94fba04ca74d753
 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": 1.0926419496536255,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.0682977437973022,
+  "best_model_checkpoint": "./outputs/checkpoint-200",
+  "epoch": 0.26666666666666666,
   "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": 2.168,
       "eval_steps_per_second": 0.272,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 0.897,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.0682977437973022,
+      "eval_runtime": 890.4733,
+      "eval_samples_per_second": 2.167,
+      "eval_steps_per_second": 0.272,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.590619614224384e+16,
+  "total_flos": 5.173848389492736e+16,
   "trial_name": null,
   "trial_params": null
 }