Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1082455398449d12ac8bbbfa6d63e461bfdbe800fbfb9316824abc14bad2c7a
+oid sha256:f404772dbfc6484d56cf268fff416e4d99e924bf618a5f6fd70db14e446a6cb7
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90a5b6114bb835045b6ff37c42c41b54034ec598465948be93bd14aa9dd98e52
+oid sha256:36e4af8591c9cb3e6471099476e46f360f01ef2b76ecc78b87b06ab70991b090
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa4be861121341cc53f3c40e98a1feeecc92876a32bb3dc6eb154e58726a8e8
+oid sha256:33e9f79b5682cc7de6c19637ae4bc96dff9f33f94a98cd0c93f9b811cc4e7411
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3997007608413696,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 1.3967318534851074,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.0,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,6 +203,20 @@
       "eval_samples_per_second": 15.539,
       "eval_steps_per_second": 1.949,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 1.1695,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.3967318534851074,
+      "eval_runtime": 93.2877,
+      "eval_samples_per_second": 15.554,
+      "eval_steps_per_second": 1.951,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.182893825921024e+16,
+  "total_flos": 8.770169121251328e+16,
   "trial_name": null,
   "trial_params": null
 }