Training in progress, step 3400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffa24c6d65d6ebe046b12c298cf4ae161aa8f7a73a62399ba6434af84128daa
+oid sha256:88adee23a7e35b2cf4aebcd8c81faec7b932abea1a3d19cf7a8d36adbdbc169d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecd655e3d91e89f6e1fa258974b79bf0d215f8ace68f3d365b99110b5abe49ce
+oid sha256:73c08ba3cc41f312df74a4897f9862543590396f79d1f28fccf1aaa0e2d0a62e
 size 84581014

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c5ce141a264dd8520f51f3b5490a7f5208fde47774153324df63d2668f9a7d7
+oid sha256:8533a46f2820d296dd8dd66497b3038b4c8cd3388b495350dff5037c2a4c3482
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0770650b062be7cee981b3da10cdf7010bb9457e5bd03d190388904fc6d3b7aa
+oid sha256:715607d045c48cb60eaa3afa895318c1f98eb549c11762cb3cadd29ed207b42b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0023797217956488276,
+  "epoch": 0.0025284544078768793,
   "eval_steps": 2000,
-  "global_step": 3200,
+  "global_step": 3400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,13 @@
       "learning_rate": 1.9999988884312347e-05,
       "loss": 1.6221,
       "step": 3200
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 2.5657193660736084,
+      "learning_rate": 1.9999987447266877e-05,
+      "loss": 1.5533,
+      "step": 3400
     }
   ],
   "logging_steps": 200,
@@ -126,7 +133,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5,
   "save_steps": 200,
-  "total_flos": 4.180089275793408e+16,
+  "total_flos": 4.438400445092659e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null