Training in progress, step 960, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9ff2623ebc59ce1f05948fb7f333347562f31720ea83bd9c654d07132bc456
+oid sha256:cd6935101c95c7a3fcf35393fcef907ca744d140d002e80f3e1ab8bc68740781
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5979893651a6ad117a2ca79acc918df76f51b5615316af74b15fc3790d5db672
+oid sha256:efbc01513003cd4778a5d7c40f35733a97acc954ec9ed9a205fe5bb1048cad2d
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:175dfe02b8f41adb5d4468faa982ed5a51b1c1cd012483cfc61f70c9241471b4
+oid sha256:a60dce02b424b527030edce82260ee74eebf81dd57466a5e2b83b22d49a22b4a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1c7c4b3a6117ae282f791966d823034e6914b8063785569ba52a491b2ee826
+oid sha256:b961e5bd3f5ce2b76de5850c52ad545f91b84e33c7fc906eadd1fa38681efcd4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0752,
+  "epoch": 0.0768,
   "eval_steps": 500,
-  "global_step": 940,
+  "global_step": 960,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -336,6 +336,13 @@
       "learning_rate": 2.9977269673842554e-05,
       "loss": 3.6172,
       "step": 940
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 58.2718620300293,
+      "learning_rate": 2.997451764584951e-05,
+      "loss": 3.7494,
+      "step": 960
     }
   ],
   "logging_steps": 20,
@@ -343,7 +350,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2230933278818304.0,
+  "total_flos": 2278337822490624.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null