Training in progress, step 1500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:331ae41f446d9853796b411bdfafd0b9a732ac28d6b08e7818e1408864ebff89
+oid sha256:edd613c9ebde393fdab8e20d8204e4d152cf35089660f145f4dbef78cfb6b4f1
 size 31466288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ac473e3bd3cdc5172ed91f763a96f13cc8a67d453c9675bbb47dd050f881b55
+oid sha256:9b628c7d707cfbb5143e133f23b9af2d0e02f5ef84cc25b954d4553b44098aa6
 size 62950917

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0280e7fd33d37b1aeeef3952241543aba36153b8c4239484d3e5400cbb9284c8
+oid sha256:ef917bf1bec8cffeebbc0401af79a27e3570d44ae491f055da1b000fa1464589
 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": 1.691584587097168,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 1.6627237796783447,
+  "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": 11.321,
       "eval_steps_per_second": 1.416,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 1.6213,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 1.6627237796783447,
+      "eval_runtime": 554.2183,
+      "eval_samples_per_second": 11.32,
+      "eval_steps_per_second": 1.416,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.651229330252923e+17,
+  "total_flos": 3.912157345269842e+17,
   "trial_name": null,
   "trial_params": null
 }