Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:434e9148a55d7de38db07465532dbaab0cdcfec5676d112c61532c1b6dbdca8d
+oid sha256:27c29bc43948c63a0f226cc87ab0660cea4ab6cd6ae33f4b3a1386449f13e33c
 size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0acaa33677f5b343e216066837b318cd2dc361ba008f7a6195aeade17a72da0
+oid sha256:ac748cfb6f2f2d9146a22f9e90943f89a69ac611b4ace36f0cd0825509a80ec0
 size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b250d2763d35faebbdd3f9ef34837fd6af467c994efa1d3cf9d8c38a46fa8c98
+oid sha256:bd836bde9e7de00360c353ed3595fa24ed6d63347354818295fc73e9837134fc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02758e7835c7a932b7dc5b6b1f15336e44a2ac260859979939ab13fea0a3b332
+oid sha256:6977daaeb422e8aea5fd23309b89c0087d980bd2e3b8f44821aa562f12801c8d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.782525118099818e-05,
+  "epoch": 9.339030141719783e-05,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -42,6 +42,13 @@
       "learning_rate": 1.65e-05,
       "loss": 3.3337,
       "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 4.047863006591797,
+      "learning_rate": 1.9833333333333335e-05,
+      "loss": 3.1903,
+      "step": 120
     }
   ],
   "logging_steps": 20,
@@ -49,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 543796744273920.0,
+  "total_flos": 637410213568512.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null