nttx commited on
Commit
9496ec3
·
verified ·
1 Parent(s): af5b94c

End of training

Browse files
README.md ADDED
@@ -0,0 +1,158 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: unsloth/SmolLM2-360M-Instruct
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: 7d9818af-c17a-4a29-95e0-1716cdd406cb
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ [<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
17
+ <details><summary>See axolotl config</summary>
18
+
19
+ axolotl version: `0.4.1`
20
+ ```yaml
21
+ adapter: lora
22
+ base_model: unsloth/SmolLM2-360M-Instruct
23
+ bf16: auto
24
+ chat_template: llama3
25
+ data_processes: 16
26
+ dataset_prepared_path: null
27
+ datasets:
28
+ - data_files:
29
+ - 404e644c8bd2ea66_train_data.json
30
+ ds_type: json
31
+ format: custom
32
+ path: /workspace/input_data/404e644c8bd2ea66_train_data.json
33
+ type:
34
+ field_input: sentence
35
+ field_instruction: prompt
36
+ field_output: summary
37
+ format: '{instruction} {input}'
38
+ no_input_format: '{instruction}'
39
+ system_format: '{system}'
40
+ system_prompt: ''
41
+ debug: null
42
+ deepspeed: null
43
+ device_map: auto
44
+ do_eval: true
45
+ early_stopping_patience: null
46
+ eval_batch_size: 4
47
+ eval_max_new_tokens: 128
48
+ eval_steps: null
49
+ eval_table_size: null
50
+ evals_per_epoch: null
51
+ flash_attention: true
52
+ fp16: null
53
+ fsdp: null
54
+ fsdp_config: null
55
+ gradient_accumulation_steps: 4
56
+ gradient_checkpointing: true
57
+ group_by_length: true
58
+ hub_model_id: nttx/7d9818af-c17a-4a29-95e0-1716cdd406cb
59
+ hub_repo: null
60
+ hub_strategy: end
61
+ hub_token: null
62
+ learning_rate: 0.0001
63
+ load_in_4bit: false
64
+ load_in_8bit: false
65
+ local_rank: null
66
+ logging_steps: 1
67
+ lora_alpha: 16
68
+ lora_dropout: 0.05
69
+ lora_fan_in_fan_out: null
70
+ lora_model_dir: null
71
+ lora_r: 8
72
+ lora_target_linear: true
73
+ lr_scheduler: cosine
74
+ max_grad_norm: 1.0
75
+ max_memory:
76
+ 0: 75GB
77
+ max_steps: 200
78
+ micro_batch_size: 4
79
+ mlflow_experiment_name: /tmp/404e644c8bd2ea66_train_data.json
80
+ model_type: AutoModelForCausalLM
81
+ num_epochs: 1
82
+ optimizer: adamw_bnb_8bit
83
+ output_dir: miner_id_24
84
+ pad_to_sequence_len: true
85
+ resume_from_checkpoint: null
86
+ s2_attention: null
87
+ sample_packing: false
88
+ save_steps: null
89
+ saves_per_epoch: null
90
+ sequence_len: 1024
91
+ strict: false
92
+ tf32: true
93
+ tokenizer_type: AutoTokenizer
94
+ train_on_inputs: false
95
+ trust_remote_code: true
96
+ val_set_size: 0.05
97
+ wandb_entity: null
98
+ wandb_mode: online
99
+ wandb_name: 62984f97-5702-495e-bb17-35a4b91707e6
100
+ wandb_project: Gradients-On-Demand
101
+ wandb_run: your_name
102
+ wandb_runid: 62984f97-5702-495e-bb17-35a4b91707e6
103
+ warmup_steps: 5
104
+ weight_decay: 0.0
105
+ xformers_attention: null
106
+
107
+ ```
108
+
109
+ </details><br>
110
+
111
+ # 7d9818af-c17a-4a29-95e0-1716cdd406cb
112
+
113
+ This model is a fine-tuned version of [unsloth/SmolLM2-360M-Instruct](https://huggingface.co/unsloth/SmolLM2-360M-Instruct) on the None dataset.
114
+ It achieves the following results on the evaluation set:
115
+ - Loss: 2.2233
116
+
117
+ ## Model description
118
+
119
+ More information needed
120
+
121
+ ## Intended uses & limitations
122
+
123
+ More information needed
124
+
125
+ ## Training and evaluation data
126
+
127
+ More information needed
128
+
129
+ ## Training procedure
130
+
131
+ ### Training hyperparameters
132
+
133
+ The following hyperparameters were used during training:
134
+ - learning_rate: 0.0001
135
+ - train_batch_size: 4
136
+ - eval_batch_size: 4
137
+ - seed: 42
138
+ - gradient_accumulation_steps: 4
139
+ - total_train_batch_size: 16
140
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
141
+ - lr_scheduler_type: cosine
142
+ - lr_scheduler_warmup_steps: 5
143
+ - training_steps: 111
144
+
145
+ ### Training results
146
+
147
+ | Training Loss | Epoch | Step | Validation Loss |
148
+ |:-------------:|:-----:|:----:|:---------------:|
149
+ | 2.501 | 1.0 | 111 | 2.2233 |
150
+
151
+
152
+ ### Framework versions
153
+
154
+ - PEFT 0.13.2
155
+ - Transformers 4.46.0
156
+ - Pytorch 2.5.0+cu124
157
+ - Datasets 3.0.1
158
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "unsloth/SmolLM2-360M-Instruct",
5
+ "bias": "none",
6
+ "fan_in_fan_out": null,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.05,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "up_proj",
24
+ "gate_proj",
25
+ "q_proj",
26
+ "k_proj",
27
+ "o_proj",
28
+ "down_proj",
29
+ "v_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edc246c16621cb1bfdfed10c6160819b39a3b6f38e05f24f15e2989ac141672
3
+ size 17528138
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e26a945aa6c1de7ae4abfa8795d8d080853106eb140f06b4cdcd735278d2036f
3
+ size 17425352
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<|PAD_TOKEN|>": 49152
3
+ }
config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "unsloth/SmolLM2-360M-Instruct",
4
+ "architectures": [
5
+ "LlamaForCausalLM"
6
+ ],
7
+ "attention_bias": false,
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "head_dim": 64,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 960,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 2560,
16
+ "is_llama_config": true,
17
+ "max_position_embeddings": 8192,
18
+ "mlp_bias": false,
19
+ "model_type": "llama",
20
+ "num_attention_heads": 15,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 5,
23
+ "pad_token_id": 49152,
24
+ "pretraining_tp": 1,
25
+ "rms_norm_eps": 1e-05,
26
+ "rope_interleaved": false,
27
+ "rope_scaling": null,
28
+ "rope_theta": 100000,
29
+ "tie_word_embeddings": true,
30
+ "torch_dtype": "bfloat16",
31
+ "transformers.js_config": {
32
+ "kv_cache_dtype": {
33
+ "fp16": "float16",
34
+ "q4f16": "float16"
35
+ }
36
+ },
37
+ "transformers_version": "4.46.0",
38
+ "use_cache": false,
39
+ "vocab_size": 49153
40
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|im_start|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|im_end|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|PAD_TOKEN|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "unk_token": "�"
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "24211": {
141
+ "content": "�",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49152": {
149
+ "content": "<|PAD_TOKEN|>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ }
156
+ },
157
+ "additional_special_tokens": [
158
+ "<|im_start|>",
159
+ "<|im_end|>"
160
+ ],
161
+ "bos_token": "<|im_start|>",
162
+ "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% 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 %}",
163
+ "clean_up_tokenization_spaces": false,
164
+ "eos_token": "<|im_end|>",
165
+ "model_max_length": 2048,
166
+ "pad_token": "<|PAD_TOKEN|>",
167
+ "padding_side": "left",
168
+ "tokenizer_class": "GPT2Tokenizer",
169
+ "unk_token": "�",
170
+ "vocab_size": 49152
171
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b35fcc4542e6957d18b0e13b061f1cd691e2cd74ace08ded8d07942e8c7616c5
3
+ size 6776
vocab.json ADDED
The diff for this file is too large to render. See raw diff