Casper0508
commited on
Commit
•
336172d
1
Parent(s):
5fbf70f
End of training
Browse files- README.md +28 -28
- adapter_config.json +1 -1
- adapter_model.safetensors +1 -1
- emissions.csv +1 -1
- runs/Jul18_15-08-23_msc-modeltrain-pod/events.out.tfevents.1721315307.msc-modeltrain-pod.8697.0 +3 -0
- special_tokens_map.json +2 -2
- tokenizer_config.json +3 -2
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
license: llama3
|
3 |
-
base_model: meta-llama/Meta-Llama-3-8B
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -14,9 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# MSc_llama3_finetuned_model_secondData
|
16 |
|
17 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -64,31 +64,31 @@ The following hyperparameters were used during training:
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
-
| 3.
|
68 |
-
| 2.
|
69 |
-
| 1.
|
70 |
-
| 1.
|
71 |
-
| 1.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.
|
78 |
-
| 0.
|
79 |
-
| 0.
|
80 |
-
| 0.
|
81 |
-
| 0.
|
82 |
-
| 0.
|
83 |
-
| 0.
|
84 |
-
| 0.
|
85 |
-
| 0.
|
86 |
-
| 0.
|
87 |
-
| 0.
|
88 |
-
| 0.
|
89 |
-
| 0.
|
90 |
-
| 0.
|
91 |
-
| 0.
|
92 |
|
93 |
|
94 |
### Framework versions
|
|
|
1 |
---
|
2 |
license: llama3
|
3 |
+
base_model: meta-llama/Meta-Llama-3-8B-Instruct
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
14 |
|
15 |
# MSc_llama3_finetuned_model_secondData
|
16 |
|
17 |
+
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 None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.7658
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
64 |
|
65 |
| Training Loss | Epoch | Step | Validation Loss |
|
66 |
|:-------------:|:-----:|:----:|:---------------:|
|
67 |
+
| 3.7986 | 1.36 | 10 | 3.3486 |
|
68 |
+
| 2.781 | 2.71 | 20 | 1.9851 |
|
69 |
+
| 1.6096 | 4.07 | 30 | 1.3075 |
|
70 |
+
| 1.2107 | 5.42 | 40 | 1.1210 |
|
71 |
+
| 1.0597 | 6.78 | 50 | 1.0222 |
|
72 |
+
| 0.9672 | 8.14 | 60 | 0.9562 |
|
73 |
+
| 0.8924 | 9.49 | 70 | 0.9131 |
|
74 |
+
| 0.8189 | 10.85 | 80 | 0.8582 |
|
75 |
+
| 0.7393 | 12.2 | 90 | 0.7907 |
|
76 |
+
| 0.6355 | 13.56 | 100 | 0.7136 |
|
77 |
+
| 0.5683 | 14.92 | 110 | 0.7013 |
|
78 |
+
| 0.533 | 16.27 | 120 | 0.7011 |
|
79 |
+
| 0.5155 | 17.63 | 130 | 0.7049 |
|
80 |
+
| 0.4965 | 18.98 | 140 | 0.7194 |
|
81 |
+
| 0.4826 | 20.34 | 150 | 0.7222 |
|
82 |
+
| 0.4617 | 21.69 | 160 | 0.7294 |
|
83 |
+
| 0.453 | 23.05 | 170 | 0.7347 |
|
84 |
+
| 0.439 | 24.41 | 180 | 0.7418 |
|
85 |
+
| 0.4333 | 25.76 | 190 | 0.7473 |
|
86 |
+
| 0.4261 | 27.12 | 200 | 0.7600 |
|
87 |
+
| 0.4238 | 28.47 | 210 | 0.7580 |
|
88 |
+
| 0.4163 | 29.83 | 220 | 0.7646 |
|
89 |
+
| 0.4158 | 31.19 | 230 | 0.7659 |
|
90 |
+
| 0.4137 | 32.54 | 240 | 0.7662 |
|
91 |
+
| 0.4131 | 33.9 | 250 | 0.7658 |
|
92 |
|
93 |
|
94 |
### Framework versions
|
adapter_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
-
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
|
|
1 |
{
|
2 |
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B-Instruct",
|
4 |
"bias": "none",
|
5 |
"fan_in_fan_out": false,
|
6 |
"inference_mode": true,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 75523312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c79b518cd11b8a6534588d5307e8de14d00c864982e240d6fbb4a42c5c073fee
|
3 |
size 75523312
|
emissions.csv
CHANGED
@@ -1,2 +1,2 @@
|
|
1 |
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
-
2024-07-
|
|
|
1 |
timestamp,experiment_id,project_name,duration,emissions,energy_consumed,country_name,country_iso_code,region,on_cloud,cloud_provider,cloud_region
|
2 |
+
2024-07-18T15:29:54,95beb92d-f3cb-419a-bd73-35f2aa8381d9,codecarbon,1287.520273923874,0.07720597406987714,0.11487120042662032,United Kingdom,GBR,scotland,N,,
|
runs/Jul18_15-08-23_msc-modeltrain-pod/events.out.tfevents.1721315307.msc-modeltrain-pod.8697.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef88e6c9665715bc56653441f60d18830ed4e43c531b772dad650939be6f2548
|
3 |
+
size 17476
|
special_tokens_map.json
CHANGED
@@ -7,11 +7,11 @@
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
-
"content": "<|
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "<|
|
17 |
}
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "<|eot_id|>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|eot_id|>"
|
17 |
}
|
tokenizer_config.json
CHANGED
@@ -2050,13 +2050,14 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
-
"eos_token": "<|
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
2058 |
],
|
2059 |
"model_max_length": 1000000000000000019884624838656,
|
2060 |
-
"pad_token": "<|
|
2061 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2062 |
}
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|
2059 |
],
|
2060 |
"model_max_length": 1000000000000000019884624838656,
|
2061 |
+
"pad_token": "<|eot_id|>",
|
2062 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
2063 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5cef72bd14db9c868844ff3c9d70e303cc81b9c07a101d5f05f0fa45c6adaafe
|
3 |
size 4984
|