JacksonBrune commited on
Commit
ecfbecd
·
verified ·
1 Parent(s): a4f716e

End of training

Browse files
Files changed (1) hide show
  1. README.md +0 -176
README.md CHANGED
@@ -13,101 +13,6 @@ model-index:
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: facebook/opt-125m
23
- bf16: auto
24
- chat_template: llama3
25
- dataset_prepared_path: null
26
- datasets:
27
- - data_files:
28
- - e9426b45bbc30495_train_data.json
29
- ds_type: json
30
- format: custom
31
- path: /workspace/input_data/e9426b45bbc30495_train_data.json
32
- type:
33
- field_input: original_version
34
- field_instruction: title
35
- field_output: french_version
36
- format: '{instruction} {input}'
37
- no_input_format: '{instruction}'
38
- system_format: '{system}'
39
- system_prompt: ''
40
- debug: null
41
- deepspeed: null
42
- device_map: auto
43
- do_eval: true
44
- early_stopping_patience: 3
45
- eval_batch_size: 4
46
- eval_max_new_tokens: 128
47
- eval_steps: 300
48
- eval_table_size: null
49
- evals_per_epoch: null
50
- flash_attention: true
51
- fp16: false
52
- fsdp: null
53
- fsdp_config: null
54
- gradient_accumulation_steps: 4
55
- gradient_checkpointing: false
56
- group_by_length: true
57
- hub_model_id: JacksonBrune/646255e0-25a0-42b8-b4bd-76e703084fb9
58
- hub_strategy: end
59
- learning_rate: 0.0002
60
- load_in_4bit: false
61
- load_in_8bit: false
62
- local_rank: null
63
- logging_steps: 50
64
- lora_alpha: 64
65
- lora_dropout: 0.05
66
- lora_fan_in_fan_out: null
67
- lora_model_dir: null
68
- lora_r: 32
69
- lora_target_linear: true
70
- lr_scheduler: constant
71
- max_grad_norm: 1.0
72
- max_memory:
73
- 0: 75GB
74
- max_steps: 20953
75
- micro_batch_size: 4
76
- mlflow_experiment_name: /tmp/e9426b45bbc30495_train_data.json
77
- model_type: AutoModelForCausalLM
78
- num_epochs: 10
79
- optim_args:
80
- adam_beta1: 0.9
81
- adam_beta2: 0.95
82
- adam_epsilon: 1e-5
83
- optimizer: adamw_bnb_8bit
84
- output_dir: miner_id_24
85
- pad_to_sequence_len: true
86
- resume_from_checkpoint: null
87
- s2_attention: null
88
- sample_packing: false
89
- save_steps: 300
90
- saves_per_epoch: null
91
- sequence_len: 512
92
- strict: false
93
- tf32: true
94
- tokenizer_type: AutoTokenizer
95
- train_on_inputs: false
96
- trust_remote_code: true
97
- val_set_size: 0.05
98
- wandb_entity: null
99
- wandb_mode: online
100
- wandb_name: 4dbfff5d-e150-40fd-bcd9-78e926ac420c
101
- wandb_project: SN56-18
102
- wandb_run: your_name
103
- wandb_runid: 4dbfff5d-e150-40fd-bcd9-78e926ac420c
104
- warmup_steps: 50
105
- weight_decay: 0.0
106
- xformers_attention: null
107
-
108
- ```
109
-
110
- </details><br>
111
 
112
  # 646255e0-25a0-42b8-b4bd-76e703084fb9
113
 
@@ -127,87 +32,6 @@ More information needed
127
 
128
  More information needed
129
 
130
- ## Training procedure
131
-
132
- ### Training hyperparameters
133
-
134
- The following hyperparameters were used during training:
135
- - learning_rate: 0.0002
136
- - train_batch_size: 4
137
- - eval_batch_size: 4
138
- - seed: 42
139
- - gradient_accumulation_steps: 4
140
- - total_train_batch_size: 16
141
- - optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=adam_beta1=0.9,adam_beta2=0.95,adam_epsilon=1e-5
142
- - lr_scheduler_type: constant
143
- - lr_scheduler_warmup_steps: 50
144
- - training_steps: 20953
145
-
146
- ### Training results
147
-
148
- | Training Loss | Epoch | Step | Validation Loss |
149
- |:-------------:|:------:|:-----:|:---------------:|
150
- | No log | 0.0002 | 1 | 2.5731 |
151
- | 8.1083 | 0.0510 | 300 | 1.9096 |
152
- | 7.1078 | 0.1021 | 600 | 1.6839 |
153
- | 6.6696 | 0.1531 | 900 | 1.5693 |
154
- | 6.2632 | 0.2042 | 1200 | 1.5010 |
155
- | 6.0785 | 0.2552 | 1500 | 1.4457 |
156
- | 5.8829 | 0.3063 | 1800 | 1.4097 |
157
- | 5.6869 | 0.3573 | 2100 | 1.3755 |
158
- | 5.5791 | 0.4083 | 2400 | 1.3511 |
159
- | 5.7238 | 0.4594 | 2700 | 1.3324 |
160
- | 5.5444 | 0.5104 | 3000 | 1.3186 |
161
- | 5.648 | 0.5615 | 3300 | 1.2941 |
162
- | 5.5452 | 0.6125 | 3600 | 1.2857 |
163
- | 5.3401 | 0.6635 | 3900 | 1.2733 |
164
- | 5.345 | 0.7146 | 4200 | 1.2610 |
165
- | 5.2741 | 0.7656 | 4500 | 1.2497 |
166
- | 5.1186 | 0.8167 | 4800 | 1.2454 |
167
- | 5.2047 | 0.8677 | 5100 | 1.2338 |
168
- | 5.3053 | 0.9188 | 5400 | 1.2297 |
169
- | 5.2865 | 0.9698 | 5700 | 1.2233 |
170
- | 5.2367 | 1.0208 | 6000 | 1.2095 |
171
- | 5.2783 | 1.0719 | 6300 | 1.2095 |
172
- | 5.0683 | 1.1229 | 6600 | 1.2021 |
173
- | 5.0163 | 1.1740 | 6900 | 1.1992 |
174
- | 4.896 | 1.2250 | 7200 | 1.1973 |
175
- | 4.8037 | 1.2761 | 7500 | 1.1908 |
176
- | 4.9946 | 1.3271 | 7800 | 1.1821 |
177
- | 5.08 | 1.3781 | 8100 | 1.1812 |
178
- | 5.0091 | 1.4292 | 8400 | 1.1765 |
179
- | 4.9605 | 1.4802 | 8700 | 1.1745 |
180
- | 5.1488 | 1.5313 | 9000 | 1.1679 |
181
- | 4.7554 | 1.5823 | 9300 | 1.1685 |
182
- | 5.0706 | 1.6333 | 9600 | 1.1651 |
183
- | 4.8837 | 1.6844 | 9900 | 1.1624 |
184
- | 4.8728 | 1.7354 | 10200 | 1.1567 |
185
- | 4.8636 | 1.7865 | 10500 | 1.1549 |
186
- | 4.8859 | 1.8375 | 10800 | 1.1524 |
187
- | 4.9733 | 1.8886 | 11100 | 1.1537 |
188
- | 4.6105 | 1.9396 | 11400 | 1.1523 |
189
- | 4.9071 | 1.9906 | 11700 | 1.1477 |
190
- | 4.8601 | 2.0417 | 12000 | 1.1421 |
191
- | 4.7578 | 2.0927 | 12300 | 1.1450 |
192
- | 4.7045 | 2.1438 | 12600 | 1.1386 |
193
- | 4.7653 | 2.1948 | 12900 | 1.1393 |
194
- | 4.9627 | 2.2459 | 13200 | 1.1378 |
195
- | 4.5644 | 2.2969 | 13500 | 1.1343 |
196
- | 4.6682 | 2.3479 | 13800 | 1.1316 |
197
- | 4.8793 | 2.3990 | 14100 | 1.1303 |
198
- | 4.5809 | 2.4500 | 14400 | 1.1302 |
199
- | 4.7643 | 2.5011 | 14700 | 1.1256 |
200
- | 4.6261 | 2.5521 | 15000 | 1.1251 |
201
- | 4.7251 | 2.6031 | 15300 | 1.1243 |
202
- | 4.7382 | 2.6542 | 15600 | 1.1213 |
203
- | 4.9042 | 2.7052 | 15900 | 1.1206 |
204
- | 4.8754 | 2.7563 | 16200 | 1.1232 |
205
- | 4.552 | 2.8073 | 16500 | 1.1160 |
206
- | 4.6477 | 2.8584 | 16800 | 1.1167 |
207
- | 4.7991 | 2.9094 | 17100 | 1.1170 |
208
- | 4.6374 | 2.9604 | 17400 | 1.1171 |
209
-
210
-
211
  ### Framework versions
212
 
213
  - PEFT 0.13.2
 
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
 
17
  # 646255e0-25a0-42b8-b4bd-76e703084fb9
18
 
 
32
 
33
  More information needed
34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35
  ### Framework versions
36
 
37
  - PEFT 0.13.2