Training in progress, step 2700, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e174e4e94a899beafa9c1bbe86f01c4feab4ec1f0be307efd28dfa83cacde37c
+oid sha256:e15f6f8a1c74ee1c50a533e91f8dc55aab33781475907e3cfd29cfe229cdc393
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1d62ecbae204cca549314b1554c884304e78cc17e04037de064f77595c5ae7c
+oid sha256:22a8b6522d298f5a1edc763ecc5ed68639b683c8dbf4708ab9dda9db901124e0
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ed2e6e7194b18dd2ea9c5a73ce05b0eb8f0d9fc4df120db907ba6de9186dc94
+oid sha256:852c3549f3820e15177f2fb596f07ccf8f099f9430fc2054948ec692e9be0b1a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7c5d3b3c2a8d9b140a1a8519d056f5ffffcb2bb6ee7238329a9e6866488adf2
+oid sha256:6c717fe9cf16244515cfd5ef71c3568c9f4f82b198f2a2eda00b7b6d3dadae13
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.490273118019104,
-  "best_model_checkpoint": "./outputs/checkpoint-2600",
-  "epoch": 1.8943533697632058,
+  "best_metric": 1.4760063886642456,
+  "best_model_checkpoint": "./outputs/checkpoint-2700",
+  "epoch": 1.9672131147540983,
   "eval_steps": 100,
-  "global_step": 2600,
+  "global_step": 2700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,13 +371,27 @@
       "eval_samples_per_second": 43.695,
       "eval_steps_per_second": 5.467,
       "step": 2600
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0002,
+      "loss": 1.4731,
+      "step": 2700
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 1.4760063886642456,
+      "eval_runtime": 143.5661,
+      "eval_samples_per_second": 43.701,
+      "eval_steps_per_second": 5.468,
+      "step": 2700
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.5480351852702106e+17,
+  "total_flos": 1.6076866793843098e+17,
   "trial_name": null,
   "trial_params": null
 }