Training in progress, step 3000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb110544751599c957e4ec900fd2bc3a6fd62da2ac029bd4078a8954ca7480b
+oid sha256:90969e1f4631d6a4750f1033ee78267e41e1eae527d369876513577947b3b01c
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25deb4b33095e0124e0d2c0a9488366f70b518a9b351967dc14aff6ad6b992ac
+oid sha256:45e42be7b6b073634e42924885559e62287f26b05e2afff19ac0a413d83b5f1d
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b597608731e9fda30cc7f58f49388742efa2b4e42761755355b7e670b12c553c
+oid sha256:dc2e1786069cc9ad07bacad5e810a6188c96dc94ad35674990c2c336dd1da97c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097f95efaf3ced711759e9e49c3b8b3ef906ff28483e958d227db85b3ea360b9
+oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.074641227722168,
-  "best_model_checkpoint": "./outputs/checkpoint-2900",
-  "epoch": 2.1129326047358834,
+  "best_metric": 2.0661864280700684,
+  "best_model_checkpoint": "./outputs/checkpoint-3000",
+  "epoch": 2.185792349726776,
   "eval_steps": 100,
-  "global_step": 2900,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -413,13 +413,27 @@
       "eval_samples_per_second": 30.4,
       "eval_steps_per_second": 3.804,
       "step": 2900
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.0002,
+      "loss": 2.0386,
+      "step": 3000
+    },
+    {
+      "epoch": 2.19,
+      "eval_loss": 2.0661864280700684,
+      "eval_runtime": 206.2191,
+      "eval_samples_per_second": 30.424,
+      "eval_steps_per_second": 3.807,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.514013463617536e+16,
+  "total_flos": 8.8094446626816e+16,
   "trial_name": null,
   "trial_params": null
 }