Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00520c6b5ae5a29a1a2087de54b8069da8f84b97f5d3effb49ce1cca9aabf035
+oid sha256:95b987300ed3bf1eabefdcf46c561f7da4872cca39645cb9d5b662921dee7e38
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b37796b30487c5d4558761e294fdfa206090263e6dc98adb4ec379fe4f88a62
+oid sha256:f9662648e8ff68edf557966408fa4f52086bc2cd000e7752c95a7844a5c294d8
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d476c32fceaf15672f38d44739e4c35ea25e02b48054c6ba3d611f9a7e809820
+oid sha256:6a459123c36ae0df8f68f5770d79b0ab359abbfdd421de1deab88f1fca75f214
 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": 1.4659545421600342,
-  "best_model_checkpoint": "./outputs/checkpoint-100",
-  "epoch": 0.13333333333333333,
+  "best_metric": 1.4343539476394653,
+  "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": 12.62,
       "eval_steps_per_second": 1.583,
       "step": 100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0002,
+      "loss": 1.1954,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.4343539476394653,
+      "eval_runtime": 112.6008,
+      "eval_samples_per_second": 12.886,
+      "eval_steps_per_second": 1.616,
+      "step": 200
     }
   ],
   "logging_steps": 100,
@@ -28,7 +42,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6338028270551040.0,
+  "total_flos": 1.272610076000256e+16,
   "trial_name": null,
   "trial_params": null
 }