Training in progress, step 1200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:157a409c2a3953e3585b6a9838d8867b4686af98e447a0ecc77f533bb6ac410c
+oid sha256:5518434d34b1084f69b5a344308504a438cd8b7fad7c6949e606673659ace3ca
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a1b60d94a37ad3cb1e04d44bc8e1fe984d21310128259de9fab294840e6257
+oid sha256:1e86acaeba2f8b0759512be4ed5b00a462ef8d52ef305f4bceafec6448abaf97
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf02797a956bbc09d23fc6a6c1f3c0b3a9c44933f60941f080cf8bb2f9d1331d
+oid sha256:67bc3393a9340b81770a2f56f26e7c6954acce785b42d5c7c1a980acfd38e481
 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": 2.36782169342041,
-  "best_model_checkpoint": "./outputs/checkpoint-1100",
-  "epoch": 0.8014571948998178,
+  "best_metric": 2.348783254623413,
+  "best_model_checkpoint": "./outputs/checkpoint-1200",
+  "epoch": 0.8743169398907104,
   "eval_steps": 100,
-  "global_step": 1100,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -161,13 +161,27 @@
       "eval_samples_per_second": 30.329,
       "eval_steps_per_second": 3.795,
       "step": 1100
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.0002,
+      "loss": 2.3384,
+      "step": 1200
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 2.348783254623413,
+      "eval_runtime": 206.6622,
+      "eval_samples_per_second": 30.359,
+      "eval_steps_per_second": 3.798,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.208363367473152e+16,
+  "total_flos": 3.500881324867584e+16,
   "trial_name": null,
   "trial_params": null
 }