Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:209a24c1da8a93ac16367365eec1fae0adaa3a62bfd35bbeaed228d1e940dcba
+oid sha256:b4da1d93de07f6426eb36dad5df4d9f864458ec2b3b7300d7784eb0d32cb9c28
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f90ff78eb336ca2a0d175b16a248ed1a5ba3c8c8e3686c58f7b1676d16c99c58
+oid sha256:7c28cec03ab6548c85e674a5d153e3f9905a52c90df2dffc1b873e7a943b4409
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c40dab02973b1cc46cf9629cd02e8f44b9b493929030f20bf23390e0e7e4d8
+oid sha256:ffde39b50896bc17b78a0302958b86632bce20c81789b1dc8c76995d55dbbd05
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
+oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1310428380966187,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 1.4666666666666668,
+  "best_metric": 1.1256643533706665,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 1.6,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,6 +161,20 @@
       "eval_samples_per_second": 10.879,
       "eval_steps_per_second": 1.364,
       "step": 1100
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 0.0002,
+      "loss": 0.9277,
+      "step": 1200
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 1.1256643533706665,
+      "eval_runtime": 177.3878,
+      "eval_samples_per_second": 10.88,
+      "eval_steps_per_second": 1.364,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -168,7 +182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.219848108179456e+16,
+  "total_flos": 8.96699552329728e+16,
   "trial_name": null,
   "trial_params": null
 }