Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bbf0a758679815da49219c49910c4f0d08b3e95598f1006e0536c21ac597284
+oid sha256:1263cfb0a5cbb250895383d1c540603d992511fb7c6bfb7133d1b9d81fd20d87
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4706f244e527807311dc947439f6497ab8ebfc0eb88b6dacadacdbf0327c44
+oid sha256:d2d417062abbaf7a8b2f3f4d99618349508a564be2ea7944c9b47e50a8a78a25
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afbf266a9b148760edf134e1852525c920aea14cf4004e12741c4e84517464ba
+oid sha256:8e2a97244d4c9e36a92ce9603501239216f8b35c73f1c473a49ecf7c2bcaecde
 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": 1.207801342010498,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.8666666666666667,
+  "best_metric": 1.2016816139221191,
+  "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": 4.222,
       "eval_steps_per_second": 0.529,
       "step": 1400
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0002,
+      "loss": 0.9807,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2016816139221191,
+      "eval_runtime": 457.4366,
+      "eval_samples_per_second": 4.219,
+      "eval_steps_per_second": 0.529,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.660632774947635e+16,
+  "total_flos": 4.991433715954483e+16,
   "trial_name": null,
   "trial_params": null
 }