Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1631171f6439b6a14b2e153dcf540167f86737bb2c711c2b140dea1fe25d6b1
+oid sha256:0b2c5bc1a76f4fbdd072da55811ba8b559e7f35d8cd10d44b30780d70158a606
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7260ad99737e832312585651bb9f4fa31542e715dde742931df691aee36b0dc5
+oid sha256:99cab54530b04c4e337e61b78568629b37a2bc3ea33be1090a731ebf5954117e
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eb03dd380d1de2cd7fa7a5f5e88bd2d0511a2b1ef619fa3362c6bbf618b480e
+oid sha256:5f1ca28b12f1b42177acf034b5d821b827e3ac2972087ad885819b0f3cdde924
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0351811b292a925d9e90fecda402ef74b5027ecf82c420e29489a6a985de561
+oid sha256:49529a8a08195bb413b67911c12112ee8fc35503e6add1381465d2e9e7251e57
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0002830335536277826,
+  "epoch": 0.0005660671072555652,
   "eval_steps": 500,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,6 +14,13 @@
       "learning_rate": 1.6666666666666667e-06,
       "loss": 4.5462,
       "step": 20
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 51.19196319580078,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 4.6693,
+      "step": 40
     }
   ],
   "logging_steps": 20,
@@ -21,7 +28,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 41401061670912.0,
+  "total_flos": 84409613058048.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null