End of training

README.md

@@ -15,6 +15,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/yufanz/autotree/runs/7283996822.14762-2aed876c-4ecf-4452-813a-ccbb31504c90)
 # Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Korean_v2
 
 This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the generator dataset.
@@ -52,7 +53,7 @@ The following hyperparameters were used during training:
 
 ### Framework versions
 
-- Transformers 4.40.2
+- Transformers 4.41.0
 - Pytorch 2.1.0a0+32f93b1
 - Datasets 2.19.1
 - Tokenizers 0.19.1

config.json

@@ -12,6 +12,7 @@
   "initializer_range": 0.02,
   "intermediate_size": 14336,
   "max_position_embeddings": 8192,
+  "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 32,
   "num_hidden_layers": 32,
@@ -22,7 +23,7 @@
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.40.2",
+  "transformers_version": "4.41.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json

@@ -8,5 +8,5 @@
   "max_length": 4096,
   "temperature": 0.6,
   "top_p": 0.9,
-  "transformers_version": "4.40.2"
+  "transformers_version": "4.41.0"
 }

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a95355f64e3361ca35e0ca94feac64bb66b8a19c487a933b562211cc7ce69316
+oid sha256:794281548d93d6dfcc0a941f6be4d0e457953faa443e5e99ca8e7f96baaa25f2
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1774df226864caf24f075a9720ea1f63e2abd24bc81319d77b2c226195e5f2
+oid sha256:5221d0b0e981db96a68cf71002998f1c5289b4f6c45d08de5179efc7f00c6348
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:864f70ba380725ede59e8b60f52f23bd245acecf2c4cddab160463708b04075a
+oid sha256:a496a7c9028dfe001b4909559ba5af9140e82904b07c96a0add33638a1a9a383
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7824e0405100827dc7624c19bdbb4416d8e40258608cf8c6e672ee99c6f726
+oid sha256:32f9ada921c5558096dc7aa723d394cbe7d562f461b38fdd68e299f5fa9f31e6
 size 1168138808

runs/May17_21-26-44_node-0/events.out.tfevents.1715981208.node-0.11119.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84ef6baddfff11d353f09d38c01260ac5d972d5e9c28dddd1cc9d3e7b51d35c6
+size 5289

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f2dfef2b21e596047293f19f231478132fcf7da1a2f8a9f4ab21cc441d5e102
-size 5048
+oid sha256:ea43e1b8e36b946fd2659086f16eb6c36092f909d8878b99361fa339c72c7f92
+size 5176