Training in progress, step 9380, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce3133fc8023dc9fec5e655ff4095b17d357c0b7879a0cb32cee9112f5995b98
+oid sha256:0bec6bca3c48b3e9f7ec1a052500985b06b331ed7b76a2c7795a8ebc958fc6fb
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cc9cb8b2654a9d8d631a10c10e390e4fcaec9c1afb800e42a2d87bc9203baf
+oid sha256:1ca5553eb1deb65392427bfb5f3e004d9236ac9eeebf32208464d046a530ffce
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:326613a61f7ba42eb9028eedd563cedc07a0da8a535fbe448e54c2eb7d1c1b65
+oid sha256:f652f4e3db4d7a26e9dba2e7386e5cf6c51fb000752a737298ff24d1508a8460
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719ba58f8d34bc5a5298f55e15bc61b57310339d8425df02e38a130cb9f3b6fa
+oid sha256:ca42f36f25082c2beb3fc00186e8ed8c12110e85da52d110e31ee1b1dc6e0295
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7488,
+  "epoch": 0.7504,
   "eval_steps": 500,
-  "global_step": 9360,
+  "global_step": 9380,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3283,6 +3283,13 @@
       "learning_rate": 1.7274514748802418e-05,
       "loss": 3.4322,
       "step": 9360
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 29.3850040435791,
+      "learning_rate": 1.7226483336120707e-05,
+      "loss": 3.443,
+      "step": 9380
     }
   ],
   "logging_steps": 20,
@@ -3290,7 +3297,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.212768645024973e+16,
+  "total_flos": 2.217039974842368e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null