Training in progress, step 840, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c685aafc65181370b17db36243c0d171817f938725ed77fa0a1e03b53e030014
+oid sha256:110e40ef4e3b35e43c4b8e29cc4d8dacba6d280f69bc8a29bf2ea57136d99510
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:036773597bfd897fa517e6ad196b274fca905a2d4b3b02935e43e14210ec8f79
+oid sha256:f714a7f3ccb21a9df52dd325a7b732a1a6695dc5d620393c7f1ac8fb9f416e45
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ad9df02f521bb1e4003457689d3b3dba0522b12dae9613bb1e420ae84cb87c5
+oid sha256:f65c5ab9da6e46829bd259bc0530be4e36f97ecb7b4f497275a1a99eb3a6c3bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d3370081bd8faebed56ed9d5e5383e284bccc346e41b56e56c69c853ca9ca1
+oid sha256:8606193994762bc6fbc4224c0c881800eb5d3299a457924ce427b06d77b4771d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0656,
+  "epoch": 0.0672,
   "eval_steps": 500,
-  "global_step": 820,
+  "global_step": 840,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -294,6 +294,13 @@
       "learning_rate": 2.9990481752904566e-05,
       "loss": 3.6855,
       "step": 820
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 46.554874420166016,
+      "learning_rate": 2.9988672727066197e-05,
+      "loss": 3.7201,
+      "step": 840
     }
   ],
   "logging_steps": 20,
@@ -301,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 1942798948663296.0,
+  "total_flos": 1985676276400128.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null