Training in progress, step 2000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ea48fedf3567693a233ab696e87e4079cef59dd7754ef804b70a8cf2b4c4c93
+oid sha256:2ec9581db0bafcc251909e89dd1e8ce2d337df14761350644f9a26f3151b49a5
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc28a28ffdba7ebaaddae9978b7c6f60a379dfd0b5e9be3ffa8617c8ace143d
+oid sha256:204f4f933229e5656d8bdc3f32f78531154973a23ab0b0dfd2de55c8ba4afb03
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ad88a6bfc78cc2d96c86e9869672dcdb69503f9c79a03551b693ef534be373
+oid sha256:fb50e2bd42723bb54172691df4d73f85a33829b8a1f4dc1ca27fee83c3724b7c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
+oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.371971845626831,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.533333333333333,
+  "best_metric": 1.3672411441802979,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.6666666666666665,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 15.569,
       "eval_steps_per_second": 1.953,
       "step": 1900
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 0.0002,
+      "loss": 1.1351,
+      "step": 2000
+    },
+    {
+      "epoch": 2.67,
+      "eval_loss": 1.3672411441802979,
+      "eval_runtime": 93.2635,
+      "eval_samples_per_second": 15.558,
+      "eval_steps_per_second": 1.951,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.110771231510528e+17,
+  "total_flos": 1.1694767356919808e+17,
   "trial_name": null,
   "trial_params": null
 }