Training in progress, step 320, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29dd7ebae639bd2d9820d94f55a7d57ed7d7e651db6caee9214dbc394d6d8a52
+oid sha256:dfd12fc64f06bad2fa92746516b8664309c4466b97e18621e506d23fda100aa8
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69d66ca304d85c0c98fb0bf09060960ca796eb9eb4224559d90c4ff9e6ce0ba7
+oid sha256:55c188f05db7cbc47d6d06e7ddb60737fba5819ce8ee84d17d80c52a5a576f38
 size 2423802

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23cf2bfaf6a90fad15e6cbfeee3986b0a34e7580afbe7ec2acc0dc8448accfb4
+oid sha256:04fce672895616ff879d43f4759ee203689dab1d6c33fbbeeae559d971ee1020
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bac6da347960aa710f0cf30015122a382ce8a8ef99042818f6297fe7974a65f2
+oid sha256:3572c26d973ddba0178cecd4abd00ac7ce2546e793a6c420879267916425a660
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00023347575354299455,
+  "epoch": 0.0002490408037791942,
   "eval_steps": 500,
-  "global_step": 300,
+  "global_step": 320,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -112,6 +112,13 @@
       "learning_rate": 4.9833333333333336e-05,
       "loss": 2.7932,
       "step": 300
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.788575172424316,
+      "learning_rate": 4.9999526661182696e-05,
+      "loss": 2.9341,
+      "step": 320
     }
   ],
   "logging_steps": 20,
@@ -119,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 1405893996822528.0,
+  "total_flos": 1489592759205888.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null