Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe26216da1bb3ebaab64bfdb360c9aaadefeb27a569d66bae7e6cb2e242a6d1
+oid sha256:dbc59f60f0b03fc7d848bb49dd337a2c313e7da3137d63d5330c2fd0bf931778
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3323fc1a621e1a5fbb6a729145d2305369dd78e4a6afb19820024f3325e85179
+oid sha256:674fd7d1b2da8e8b572dcd8c5c60764fe92b223569cb37500fc42668fb9f866e
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cfd6051928a8e961ef995d4d43e26d5715feab4fcd701563228166343bafae5
+oid sha256:b38798aed442913f3edb40ed2e6dd248c47415757a186238aa4d86325b07c484
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481f596060c3212f56594c5c4670b5c573732140807b73f1dd3dd781bdd56d29
+oid sha256:f02eb1d87c6e64756c982d23c5194d17c9b128eb05ac315db5c766e38219aacd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00029746522445610346,
+  "epoch": 0.00044619783668415513,
   "eval_steps": 2000,
-  "global_step": 400,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -21,6 +21,13 @@
       "learning_rate": 1.9999999832252933e-05,
       "loss": 1.6278,
       "step": 400
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 3.7490854263305664,
+      "learning_rate": 1.9999999617416517e-05,
+      "loss": 1.6314,
+      "step": 600
     }
   ],
   "logging_steps": 200,
@@ -28,7 +35,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4910339289341952.0,
+  "total_flos": 7590307482550272.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null