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/7283970144.51595-887226ef-9076-4284-993d-3e22f4763aa6)
 # Meta-Llama-3-8B-Instruct_fictional_arc_challenge_Italian_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 sha256:6478e8d3392ecb7cfe8ff69662ef094542f8847ff3f3ff54c39241c53043678b
+oid sha256:f200372ab9d4d9b7b338eaa3c631945f56193c8ae202484e93c7be41d506513a
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a4b34db73db3bf5d71995af172a66b411881d484a442268e047f82e063be5eb
+oid sha256:2e7387d448c402f1ca610556c1fb3029285775c3f5137532bd6702e1768f9d60
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f56875d1b9deb12497831833ab26c128c28dbf472a0aa14b7972ea2f39c24ab0
+oid sha256:f39800c153fdd2b8fb5d6b05c1ba66e7ca97f04bac0004120d55828987c63d05
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025ac67de6f9d1d0b3df835e4c06c1bba5dc97a729eaddf676189e002c89a5d8
+oid sha256:742388115e15cb657522dcfdb9ca2c42a71f07154b9c9ea2f8d37c313f8fe3c0
 size 1168138808

runs/May18_07-05-47_node-0/events.out.tfevents.1716015949.node-0.28736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57218ee9944b0ba82ffe75d8de9606ac76aeef87280d07d66bd02e5202607eac
+size 5293

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03d6370fd44f7e1569bf814a77af4bc14bcb9112901b048fa31ef30921d9de9
-size 5048
+oid sha256:faaf7f53e56d6e20fd96086f8191b4e1d4fe2ef644797a39d3eff73196a731f6
+size 5176