Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77f916cd72838e5a74c887b0f8491d580af88041208a33bf73a82f96ad192193
+oid sha256:12d8d44bc5cb2da5a6d0f0bed03a7d35ba3cdd92cafdcfaa45ecaaa43a8f91ea
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c537483cedf4bf0185066bae5c81ff2e0992e039da70cb627db8437720c24997
+oid sha256:5a9b3b3d6d175b27a5188b9184a30feb2c0b407580b749e4b283f6a22ae6e60b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55a434fa2478e58592908e5f1cc53dc10fd07fe28ea2b87f64160779bd08c4a0
+oid sha256:ade3539adbe7197226065a369a265f6f0f1e7d107ccc3030d3acbbd888426eb0
 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": 2.2812631130218506,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 2.2644264698028564,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 30.493,
       "eval_steps_per_second": 3.815,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 2.2397,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.2644264698028564,
+      "eval_runtime": 206.0922,
+      "eval_samples_per_second": 30.443,
+      "eval_steps_per_second": 3.809,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.118366969063424e+16,
+  "total_flos": 4.412678068463616e+16,
   "trial_name": null,
   "trial_params": null
 }