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_French_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 sha256:8b45188354c158b74c0122555be8b758d5da69320de635af6ced6c3f0832b2cb
+oid sha256:2d2ad0cabf0de9977611f74af0cb7cc7ceeb183e416bf7c747fb3699aa4c5fe4
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c949b64c0ec2f69f44b33436e33ef37ff8766540175f133f516139dfb6f8b789
+oid sha256:2d33e38e076b6f12168f46ab3341d48175944d811490343c4eb3a3393ab9b25e
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b57383160bc36ad655af6faf41e5cbccac63479df2c0790dfe6c584b6cc2583
+oid sha256:8096630ff01896fef8769ce7d13b9f19268ad3906f76cd933f64533c0124a675
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06bc905c4a11482e6b02dedecd310ef913ad3eadb95fd34b6d9d305237971b69
+oid sha256:dcb746dffed7fa2e216f927256bf90f9531e774634011d8b2572d6d4edeeb3e5
 size 1168138808

runs/May17_22-02-54_node-0/events.out.tfevents.1715983376.node-0.16034.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd6776b3693128394b112b55e7b69b3d57c85bfabff301dec15ec22c684a90d
+size 5283

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b63c6e185e4ee31aa005087249378faa42a800d711a15f1ffff1ff1ec72b654d
-size 5048
+oid sha256:302fa83af8f9e0d30713718db624b60b6c035d1f8456653e484d572b54a101cc
+size 5176