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:e76c97b27b51d837fe269cdda525be6be9c4d7a31602f78d2f350e2e4c055475
+oid sha256:226eac9da1d16dfae98e9742092d3db5948d02bcd6fdf015f9f6259d978c6328
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4104c3726537a5faa74893845e9bfab56b36655aba99fddca711a343e68399f2
+oid sha256:cf3c99c313c8ca88ec9e080f7d3ed1d80f489d4c73366c1ba8dfa6f2f610e154
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e579106e8f865507506805b7ed42146d38e63f436a4089773e539eb4028c15
+oid sha256:208b65f2b4ae56cb8de73a85ca91a54774b9f0b3186f1fa88165117387fd53e3
 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": 1.8999686241149902,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.9886363636363638,
+  "best_metric": 1.895570158958435,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 2.1306818181818183,
   "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": 19.836,
       "eval_steps_per_second": 2.486,
       "step": 1400
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 0.0002,
+      "loss": 1.9962,
+      "step": 1500
+    },
+    {
+      "epoch": 2.13,
+      "eval_loss": 1.895570158958435,
+      "eval_runtime": 74.7767,
+      "eval_samples_per_second": 19.953,
+      "eval_steps_per_second": 2.501,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
@@ -210,7 +224,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.261985771323392e+16,
+  "total_flos": 4.570396780271616e+16,
   "trial_name": null,
   "trial_params": null
 }