Training in progress, step 120, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79d9c815d4c43548c4c0ce822c3f1c0ee1bdede2f9fab3ab3cfa6a4b4da825c8
+oid sha256:c38bdb0979c928e502c97dd82b769114b80aa32487f2fa00dc25b698969b75a2
 size 8077608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3869c96ebfba4f36b625f829a247602f184bab0bda88f860ef66d890bb9851f
+oid sha256:2ebcaa011427412ab8e2fea63b8c8e971f5197b41f6e48c45c3d73093532d3f8
 size 4052500

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f32c34e49a5be573fa37f12748aab7e78650fd25c6cf007f14b7927a9f8cf3fb
+oid sha256:e768a159af022ca8d40d66c6ad973ca9bd9af8b77073a0bd9deb9b53bc1bafcb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002,
+  "epoch": 0.0024,
   "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": 4.9999999999999996e-06,
       "loss": 4.7237,
       "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 115.61023712158203,
+      "learning_rate": 6e-06,
+      "loss": 4.4426,
+      "step": 120
     }
   ],
   "logging_steps": 20,
@@ -49,7 +56,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 34052722827264.0,
+  "total_flos": 42048279232512.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null