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:b0ad383ff5c1ca432c7eb7f004459e86ec446f6336bbe22f7837fbc1622283e0
+oid sha256:1c145c57781431c7ea3ab34d9ece0d9db7741f412082d016f3b05e990f012324
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbf975638616e1ce382f110c7bfdff8bbebaa42a491f319760ed57a5f0dda2df
+oid sha256:288f5747825c1c9f6a40aae2c568a2cad6e2b3b2285c2da2321bf1db84163476
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6921adec0cc9a9c9df2dc7b65fb0eb0e5c535cd65447579a8ab1f2c8e71d1dd4
+oid sha256:65a2ceac8780befc0683f9bef6e870ca84bd737e8a83c0f5eee58e03df31124f
 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": 1.9745317697525024,
-  "best_model_checkpoint": "./outputs/checkpoint-1900",
-  "epoch": 2.6988636363636362,
+  "best_metric": 1.9676258563995361,
+  "best_model_checkpoint": "./outputs/checkpoint-2000",
+  "epoch": 2.840909090909091,
   "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": 28.673,
       "eval_steps_per_second": 3.594,
       "step": 1900
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 0.0002,
+      "loss": 2.0839,
+      "step": 2000
+    },
+    {
+      "epoch": 2.84,
+      "eval_loss": 1.9676258563995361,
+      "eval_runtime": 52.0774,
+      "eval_samples_per_second": 28.65,
+      "eval_steps_per_second": 3.591,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.51482666140672e+16,
+  "total_flos": 5.804658999724032e+16,
   "trial_name": null,
   "trial_params": null
 }