Training in progress, step 3100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:255f5c63a7fde9d2dc9858daf509f801b4915dc1e8299dedfd3f822f42f1b50a
+oid sha256:ba434e596e78e24fd65758fc552892a2e3440d2c23cf133cf526374a2891baca
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8c68b621ae78ea36555b8e95cd54e0b5b666bcd3477fd48b336a3dd32db9d50
+oid sha256:54a46fed62f3db70ebd24cccea6cc3ffb0525475da2d3cefea886e3a1a297fc9
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc2e1786069cc9ad07bacad5e810a6188c96dc94ad35674990c2c336dd1da97c
+oid sha256:90991c2ad675e02574fbc94f99c043b9b88b65b41849dc17999930cdb657da15
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb57538b0fddb988f32d5e33311bcf25efee1aa4001ec3e33ef4a2dd884d77d3
+oid sha256:0f4766a50a63740d51a19c983a4de442d7f62ff1e951fc016c44cc6c58fb9db1
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.063817024230957,
-  "best_model_checkpoint": "./outputs/checkpoint-3000",
-  "epoch": 2.185792349726776,
+  "best_metric": 2.0530624389648438,
+  "best_model_checkpoint": "./outputs/checkpoint-3100",
+  "epoch": 2.2586520947176685,
   "eval_steps": 100,
-  "global_step": 3000,
+  "global_step": 3100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,13 +427,27 @@
       "eval_samples_per_second": 30.424,
       "eval_steps_per_second": 3.807,
       "step": 3000
+    },
+    {
+      "epoch": 2.26,
+      "learning_rate": 0.0002,
+      "loss": 2.0054,
+      "step": 3100
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 2.0530624389648438,
+      "eval_runtime": 206.2013,
+      "eval_samples_per_second": 30.427,
+      "eval_steps_per_second": 3.807,
+      "step": 3100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 8.8094446626816e+16,
+  "total_flos": 9.104980666392576e+16,
   "trial_name": null,
   "trial_params": null
 }