Training in progress, step 500

README.md

@@ -27,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alexkroman-alex-kroman/tiny-audio-lm-stage1/runs/jaez9aux) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/alexkroman-alex-kroman/tiny-audio-lm-stage1/runs/zgex76y0) 
 
 
 This model was trained with SFT.

config.json

@@ -55,9 +55,9 @@
     "rope_type": "default"
   },
   "sliding_window": null,
-  "tie_word_embeddings": true,
+  "tie_word_embeddings": false,
   "transformers_version": "5.0.0",
   "use_cache": false,
   "use_sliding_window": false,
-  "vocab_size": 217213
+  "vocab_size": 217207
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb5b9383a9224b76ceb9195b6bb6d184e3bf5fafb539f2809b655d6f260f1ce
-size 1325822488
+oid sha256:d6db175b69832b3e24dfb550c8c996319ce1ce89a25c7ce81daf2fdb47e79aae
+size 1325810200

tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94481d9500423064efa27f6dec6b82a61eb28b9c4f1ce8ed956433190b6b5d79
-size 23733882
+oid sha256:6ab10322c3436a84b2fd70c01fc7ccca19b7fad2b218ad7249fd3bf08dc54711
+size 23732690

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c11043dc5e5907a73d966f5a50170f7294a569e1a25584944bf6b61f1d05f3e
-size 5713
+oid sha256:fbd493e1def4f2f074cb53960bf03044aa3f5dc556904cafe84d9f21bbc971f6
+size 5649