Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f225d8ae8f69d55bf001f6132d299f58dc2026159676b83b56cd491cbf09165
+oid sha256:26f344f50a80a0bc0dc011cd9c3d2d6045b4bd1803a855ea0066bedb9d678139
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9a9196e18f947229f8d19996e0b02da11c24b427a684e279b592d59d0c94ba
+oid sha256:7db39a09db19a5a861fcc8d9325620db973b11e445fa9f8f0c5639c5a066f9be
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d55838b2a5d2cc02e664d55f8af0bd999b1640f076d9cd2e5f34a26e5a2e02
+oid sha256:9385acd159a025ccd0b5a01c24aef0bbaaa79b38d5e205d834949d4c26aa1a4c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aa2c8b84e17817e6a4dcba5955fca913e266fdcd47f5594a29933ebd4972a01
+oid sha256:c3e02e4b8a74e841ee5a1ce8c453a9becb15f5be6cbcdd100b814e93235dab36
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4663879871368408,
-  "best_model_checkpoint": "./outputs/checkpoint-200",
-  "epoch": 0.26666666666666666,
+  "best_metric": 1.4471981525421143,
+  "best_model_checkpoint": "./outputs/checkpoint-300",
+  "epoch": 0.4,
   "eval_steps": 100,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -35,6 +35,20 @@
       "eval_samples_per_second": 30.75,
       "eval_steps_per_second": 3.857,
       "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0002,
+      "loss": 1.5693,
+      "step": 300
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 1.4471981525421143,
+      "eval_runtime": 47.1683,
+      "eval_samples_per_second": 30.762,
+      "eval_steps_per_second": 3.859,
+      "step": 300
     }
   ],
   "logging_steps": 100,
@@ -42,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6707497402368000.0,
+  "total_flos": 1.0061246103552e+16,
   "trial_name": null,
   "trial_params": null
 }