Casper0508 commited on
Commit
336172d
1 Parent(s): 5fbf70f

End of training

Browse files
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: 0.7698
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
- | 3.7636 | 1.36 | 10 | 3.3566 |
68
- | 2.8254 | 2.71 | 20 | 2.0280 |
69
- | 1.5642 | 4.07 | 30 | 1.2681 |
70
- | 1.1877 | 5.42 | 40 | 1.1017 |
71
- | 1.0503 | 6.78 | 50 | 1.0240 |
72
- | 0.9732 | 8.14 | 60 | 0.9786 |
73
- | 0.9065 | 9.49 | 70 | 0.9394 |
74
- | 0.8513 | 10.85 | 80 | 0.9004 |
75
- | 0.7914 | 12.2 | 90 | 0.8791 |
76
- | 0.7408 | 13.56 | 100 | 0.8509 |
77
- | 0.6882 | 14.92 | 110 | 0.8191 |
78
- | 0.6389 | 16.27 | 120 | 0.7877 |
79
- | 0.5855 | 17.63 | 130 | 0.7748 |
80
- | 0.5293 | 18.98 | 140 | 0.7502 |
81
- | 0.4876 | 20.34 | 150 | 0.7337 |
82
- | 0.4619 | 21.69 | 160 | 0.7275 |
83
- | 0.4458 | 23.05 | 170 | 0.7315 |
84
- | 0.4287 | 24.41 | 180 | 0.7475 |
85
- | 0.434 | 25.76 | 190 | 0.7489 |
86
- | 0.4186 | 27.12 | 200 | 0.7573 |
87
- | 0.4158 | 28.47 | 210 | 0.7618 |
88
- | 0.4105 | 29.83 | 220 | 0.7719 |
89
- | 0.4039 | 31.19 | 230 | 0.7677 |
90
- | 0.4087 | 32.54 | 240 | 0.7692 |
91
- | 0.4078 | 33.9 | 250 | 0.7698 |
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 sha256:2396fd1095bb4c7827c0b91569b26ee5a0da7c1bc67d4316e1ed3125d0412e8c
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
- 2024-07-17T22:00:54,d57424a2-3051-45e7-aa21-4122e466d370,codecarbon,1337.6511194705963,0.0797943164549178,0.11872227543042274,United Kingdom,GBR,scotland,N,,
 
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": "<|end_of_text|>",
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": "<|end_of_text|>"
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": "<|end_of_text|>",
2055
  "model_input_names": [
2056
  "input_ids",
2057
  "attention_mask"
2058
  ],
2059
  "model_max_length": 1000000000000000019884624838656,
2060
- "pad_token": "<|end_of_text|>",
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 sha256:7c5748d207260224e60fd82bd6da0e65c6d55013cba7f3cac16494bfcf932da6
3
  size 4984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cef72bd14db9c868844ff3c9d70e303cc81b9c07a101d5f05f0fa45c6adaafe
3
  size 4984