End of training
Browse files- README.md +2 -1
- config.json +2 -1
- generation_config.json +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- runs/May17_22-02-54_node-0/events.out.tfevents.1715983376.node-0.16034.0 +3 -0
- training_args.bin +2 -2
README.md
CHANGED
@@ -15,6 +15,7 @@ model-index:
|
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
|
|
18 |
# Meta-Llama-3-8B-Instruct_fictional_arc_challenge_French_v2
|
19 |
|
20 |
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:
|
|
52 |
|
53 |
### Framework versions
|
54 |
|
55 |
-
- Transformers 4.
|
56 |
- Pytorch 2.1.0a0+32f93b1
|
57 |
- Datasets 2.19.1
|
58 |
- Tokenizers 0.19.1
|
|
|
15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
16 |
should probably proofread and complete it, then remove this comment. -->
|
17 |
|
18 |
+
[<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)
|
19 |
# Meta-Llama-3-8B-Instruct_fictional_arc_challenge_French_v2
|
20 |
|
21 |
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.
|
|
|
53 |
|
54 |
### Framework versions
|
55 |
|
56 |
+
- Transformers 4.41.0
|
57 |
- Pytorch 2.1.0a0+32f93b1
|
58 |
- Datasets 2.19.1
|
59 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -12,6 +12,7 @@
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
"max_position_embeddings": 8192,
|
|
|
15 |
"model_type": "llama",
|
16 |
"num_attention_heads": 32,
|
17 |
"num_hidden_layers": 32,
|
@@ -22,7 +23,7 @@
|
|
22 |
"rope_theta": 500000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
-
"transformers_version": "4.
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 128256
|
28 |
}
|
|
|
12 |
"initializer_range": 0.02,
|
13 |
"intermediate_size": 14336,
|
14 |
"max_position_embeddings": 8192,
|
15 |
+
"mlp_bias": false,
|
16 |
"model_type": "llama",
|
17 |
"num_attention_heads": 32,
|
18 |
"num_hidden_layers": 32,
|
|
|
23 |
"rope_theta": 500000.0,
|
24 |
"tie_word_embeddings": false,
|
25 |
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.41.0",
|
27 |
"use_cache": true,
|
28 |
"vocab_size": 128256
|
29 |
}
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
"max_length": 4096,
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
-
"transformers_version": "4.
|
12 |
}
|
|
|
8 |
"max_length": 4096,
|
9 |
"temperature": 0.6,
|
10 |
"top_p": 0.9,
|
11 |
+
"transformers_version": "4.41.0"
|
12 |
}
|
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4976698672
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d2ad0cabf0de9977611f74af0cb7cc7ceeb183e416bf7c747fb3699aa4c5fe4
|
3 |
size 4976698672
|
model-00002-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4999802720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d33e38e076b6f12168f46ab3341d48175944d811490343c4eb3a3393ab9b25e
|
3 |
size 4999802720
|
model-00003-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4915916176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8096630ff01896fef8769ce7d13b9f19268ad3906f76cd933f64533c0124a675
|
3 |
size 4915916176
|
model-00004-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1168138808
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcb746dffed7fa2e216f927256bf90f9531e774634011d8b2572d6d4edeeb3e5
|
3 |
size 1168138808
|
runs/May17_22-02-54_node-0/events.out.tfevents.1715983376.node-0.16034.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:edd6776b3693128394b112b55e7b69b3d57c85bfabff301dec15ec22c684a90d
|
3 |
+
size 5283
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:302fa83af8f9e0d30713718db624b60b6c035d1f8456653e484d572b54a101cc
|
3 |
+
size 5176
|