Training in progress, step 2800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e2cdc75106d1ad5f42dc96e7ace20ebbd09c05bbb12e683edfe1e467ed2816
+oid sha256:2e24e09d9874cfe63e946a3885f4501b58eea3039e8d489d62c7a9c02175a6b0
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c76b030b5a876bdfcadcf5f497226e6adf7d57102b1edffdf58e5b318cf41c41
+oid sha256:38e4a629669fe4871341593d23ba93a00020483850008a05512c6a86a10d25ad
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0e1dc4e8513a0bba3d4b52d1e66539d1d92aa1df08b8a7f141be24c582260ed
+oid sha256:f9d6bd701fca6e19968b0e9d9d7fe0c31a82f71b8340d6006477f972d51d1483
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d747a341abc7681ba1384e20b96e3fad64e2a0f72aee64e5047f8f5bba229c8f
+oid sha256:79c08a7148c570c3d4c87a735e3acef3af52d256eb019f3a3f3feeab8a656949
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3713726997375488,
-  "best_model_checkpoint": "./outputs/checkpoint-2700",
-  "epoch": 1.9672131147540983,
+  "best_metric": 1.3606998920440674,
+  "best_model_checkpoint": "./outputs/checkpoint-2800",
+  "epoch": 2.040072859744991,
   "eval_steps": 100,
-  "global_step": 2700,
+  "global_step": 2800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -385,13 +385,27 @@
       "eval_samples_per_second": 43.585,
       "eval_steps_per_second": 5.453,
       "step": 2700
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 0.0002,
+      "loss": 1.3402,
+      "step": 2800
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 1.3606998920440674,
+      "eval_runtime": 144.0067,
+      "eval_samples_per_second": 43.567,
+      "eval_steps_per_second": 5.451,
+      "step": 2800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.6093831259072102e+17,
+  "total_flos": 1.6689897048172954e+17,
   "trial_name": null,
   "trial_params": null
 }