nbninh commited on
Commit
3c07192
1 Parent(s): fed7a74

End of training

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,148 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: bigscience-bloom-rail-1.0
4
+ base_model: bigscience/bloomz-560m
5
+ tags:
6
+ - axolotl
7
+ - generated_from_trainer
8
+ model-index:
9
+ - name: c10e5a21-b288-425e-9c45-cc5c06b616a9
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: bigscience/bloomz-560m
23
+ bf16: auto
24
+ chat_template: llama3
25
+ dataset_prepared_path: null
26
+ datasets:
27
+ - data_files:
28
+ - 39a10c1f992e800d_train_data.json
29
+ ds_type: json
30
+ format: custom
31
+ path: /workspace/input_data/39a10c1f992e800d_train_data.json
32
+ type:
33
+ field_input: sentence2
34
+ field_instruction: sentence1
35
+ field_output: lang
36
+ format: '{instruction} {input}'
37
+ no_input_format: '{instruction}'
38
+ system_format: '{system}'
39
+ system_prompt: ''
40
+ debug: null
41
+ deepspeed: null
42
+ early_stopping_patience: null
43
+ eval_max_new_tokens: 128
44
+ eval_table_size: null
45
+ evals_per_epoch: 1
46
+ flash_attention: false
47
+ fp16: null
48
+ fsdp: null
49
+ fsdp_config: null
50
+ gradient_accumulation_steps: 1
51
+ gradient_checkpointing: true
52
+ gradient_clipping: 1.0
53
+ group_by_length: false
54
+ hub_model_id: nbninh/c10e5a21-b288-425e-9c45-cc5c06b616a9
55
+ hub_repo: null
56
+ hub_strategy: end
57
+ hub_token: null
58
+ learning_rate: 0.0001
59
+ load_in_4bit: true
60
+ load_in_8bit: true
61
+ local_rank: null
62
+ logging_steps: 1
63
+ lora_alpha: 32
64
+ lora_dropout: 0.1
65
+ lora_fan_in_fan_out: null
66
+ lora_model_dir: null
67
+ lora_r: 16
68
+ lora_target_linear: true
69
+ lr_scheduler: cosine
70
+ max_steps: 50
71
+ micro_batch_size: 1
72
+ mlflow_experiment_name: /tmp/39a10c1f992e800d_train_data.json
73
+ model_type: AutoModelForCausalLM
74
+ num_epochs: 1
75
+ optimizer: adamw_bnb_8bit
76
+ output_dir: miner_id_24
77
+ pad_to_sequence_len: true
78
+ resume_from_checkpoint: null
79
+ s2_attention: null
80
+ sample_packing: false
81
+ saves_per_epoch: 1
82
+ sequence_len: 2048
83
+ strict: false
84
+ tf32: false
85
+ tokenizer_type: AutoTokenizer
86
+ train_on_inputs: false
87
+ trust_remote_code: true
88
+ val_set_size: 0.05
89
+ wandb_entity: null
90
+ wandb_mode: online
91
+ wandb_name: c10e5a21-b288-425e-9c45-cc5c06b616a9
92
+ wandb_project: Gradients-On-Demand
93
+ wandb_run: your_name
94
+ wandb_runid: c10e5a21-b288-425e-9c45-cc5c06b616a9
95
+ warmup_steps: 10
96
+ weight_decay: 0.01
97
+ xformers_attention: true
98
+
99
+ ```
100
+
101
+ </details><br>
102
+
103
+ # c10e5a21-b288-425e-9c45-cc5c06b616a9
104
+
105
+ This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on the None dataset.
106
+ It achieves the following results on the evaluation set:
107
+ - Loss: nan
108
+
109
+ ## Model description
110
+
111
+ More information needed
112
+
113
+ ## Intended uses & limitations
114
+
115
+ More information needed
116
+
117
+ ## Training and evaluation data
118
+
119
+ More information needed
120
+
121
+ ## Training procedure
122
+
123
+ ### Training hyperparameters
124
+
125
+ The following hyperparameters were used during training:
126
+ - learning_rate: 0.0001
127
+ - train_batch_size: 1
128
+ - eval_batch_size: 1
129
+ - seed: 42
130
+ - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
131
+ - lr_scheduler_type: cosine
132
+ - lr_scheduler_warmup_steps: 10
133
+ - training_steps: 50
134
+
135
+ ### Training results
136
+
137
+ | Training Loss | Epoch | Step | Validation Loss |
138
+ |:-------------:|:------:|:----:|:---------------:|
139
+ | 0.0 | 0.1429 | 50 | nan |
140
+
141
+
142
+ ### Framework versions
143
+
144
+ - PEFT 0.13.2
145
+ - Transformers 4.46.0
146
+ - Pytorch 2.5.0+cu124
147
+ - Datasets 3.0.1
148
+ - Tokenizers 0.20.1
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "bigscience/bloomz-560m",
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": 32,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "dense",
24
+ "query_key_value",
25
+ "dense_4h_to_h",
26
+ "dense_h_to_4h"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2eeda0fd473d3df19efdf6ac2ef70c064acbbce7257b2bb8fe6f3d8ec8b95f8
3
+ size 25236362
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09e2a40b7952008237976490546913e0ce4041a46ecaba68cbfaeb20b288b77f
3
+ size 25192688
config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": true,
3
+ "_name_or_path": "bigscience/bloomz-560m",
4
+ "apply_residual_connection_post_layernorm": false,
5
+ "architectures": [
6
+ "BloomForCausalLM"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "attention_softmax_in_fp32": true,
10
+ "bias_dropout_fusion": true,
11
+ "bos_token_id": 1,
12
+ "eos_token_id": 2,
13
+ "hidden_dropout": 0.0,
14
+ "hidden_size": 1024,
15
+ "initializer_range": 0.02,
16
+ "layer_norm_epsilon": 1e-05,
17
+ "masked_softmax_fusion": true,
18
+ "model_type": "bloom",
19
+ "n_head": 16,
20
+ "n_inner": null,
21
+ "n_layer": 24,
22
+ "offset_alibi": 100,
23
+ "pad_token_id": 3,
24
+ "pretraining_tp": 1,
25
+ "quantization_config": {
26
+ "_load_in_4bit": false,
27
+ "_load_in_8bit": true,
28
+ "bnb_4bit_compute_dtype": "float32",
29
+ "bnb_4bit_quant_storage": "uint8",
30
+ "bnb_4bit_quant_type": "fp4",
31
+ "bnb_4bit_use_double_quant": false,
32
+ "llm_int8_enable_fp32_cpu_offload": false,
33
+ "llm_int8_has_fp16_weight": false,
34
+ "llm_int8_skip_modules": null,
35
+ "llm_int8_threshold": 6.0,
36
+ "load_in_4bit": false,
37
+ "load_in_8bit": true,
38
+ "quant_method": "bitsandbytes"
39
+ },
40
+ "seq_length": 2048,
41
+ "skip_bias_add": true,
42
+ "skip_bias_add_qkv": false,
43
+ "slow_but_exact": false,
44
+ "transformers_version": "4.46.0",
45
+ "unk_token_id": 0,
46
+ "use_cache": false,
47
+ "vocab_size": 250880
48
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<pad>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d963066d6adae5034a1dc114c3ac444512de09928cf14ed4562ba94d9a440e66
3
+ size 21763085
tokenizer_config.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<unk>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<pad>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ }
36
+ },
37
+ "bos_token": "<s>",
38
+ "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 %}",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "merges_file": null,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "<pad>",
44
+ "padding_side": "left",
45
+ "tokenizer_class": "BloomTokenizer",
46
+ "unk_token": "<unk>",
47
+ "vocab_file": null
48
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8787372375453a5d678e10ae3f1b8d1e07a3cee93c3e218494547510aa4cd6c7
3
+ size 6776