Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0de4208c8778429ac6b5f80ce878731493c8b2216d4019454e93ec500763601
+oid sha256:8fe26216da1bb3ebaab64bfdb360c9aaadefeb27a569d66bae7e6cb2e242a6d1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a06a1c37100e16fd1ab7afe8d6bc229150bb98862afa2726a42490a2a521834d
-size 84580566
+oid sha256:3323fc1a621e1a5fbb6a729145d2305369dd78e4a6afb19820024f3325e85179
+size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61eec90c503ad61fc666dce3815e956968ca41328f56c2c01270ec9dcb92b8df
+oid sha256:1cfd6051928a8e961ef995d4d43e26d5715feab4fcd701563228166343bafae5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de8ba3ee82628953ab67efb1ce3da28f2928aa0319dd164d0c752f92d7ef5e9
+oid sha256:481f596060c3212f56594c5c4670b5c573732140807b73f1dd3dd781bdd56d29
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00014873261222805173,
+  "epoch": 0.00029746522445610346,
   "eval_steps": 2000,
-  "global_step": 200,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 1.9999999959757473e-05,
       "loss": 1.835,
       "step": 200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.7373883724212646,
+      "learning_rate": 1.9999999832252933e-05,
+      "loss": 1.6278,
+      "step": 400
     }
   ],
   "logging_steps": 200,
@@ -21,7 +28,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 2438121270509568.0,
+  "total_flos": 4910339289341952.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null