Training in progress, step 340, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfd12fc64f06bad2fa92746516b8664309c4466b97e18621e506d23fda100aa8
+oid sha256:7a2031f1e6cfe542aa6f89f6acad2e6e61e5eccb774c028eacc849acf7dc731e
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55c188f05db7cbc47d6d06e7ddb60737fba5819ce8ee84d17d80c52a5a576f38
+oid sha256:a30a2f52f2a1b0e6af1f396a27551dee57d0a8a9bc75f3983a9f22ff5a3791fb
 size 2423802

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fce672895616ff879d43f4759ee203689dab1d6c33fbbeeae559d971ee1020
+oid sha256:9d6a661ce10cf6ec0952952c89c18c5adfff1f458e16ee8c25253323214e7629
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3572c26d973ddba0178cecd4abd00ac7ce2546e793a6c420879267916425a660
+oid sha256:958b2ef2ec14693170ade17a6d7d18d3a64014324c4ca5063751e5c7d0563ec3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002490408037791942,
+  "epoch": 0.00026460585401539384,
   "eval_steps": 500,
-  "global_step": 320,
+  "global_step": 340,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,13 @@
       "learning_rate": 4.9999526661182696e-05,
       "loss": 2.9341,
       "step": 320
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 7.716049671173096,
+      "learning_rate": 4.999800570348766e-05,
+      "loss": 2.5987,
+      "step": 340
     }
   ],
   "logging_steps": 20,
@@ -126,7 +133,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1489592759205888.0,
+  "total_flos": 1573291521589248.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null