Views
No views yet
0.3.01base_model: phi-600M-cont/checkpoint-5000
2model_type: AutoModelForCausalLM
3tokenizer_type: AutoTokenizer
4trust_remote_code: true
5
6load_in_8bit: false
7load_in_4bit: false
8strict: false
9
10# max_steps: 8000
11#pretraining_dataset: nampdn-ai/tiny-strange-textbooks
12datasets:
13 - path: math-ai/StackMathQA
14 name: stackmathqa100k
15 type:
16 system_prompt: ""
17 field_system: system
18 field_instruction: Q
19 field_output: A
20 format: "[INST] {instruction} [/INST]"
21 no_input_format: "[INST] {instruction} [/INST]"
22 train_on_split: train[:10%]
23 - path: SciPhi/textbooks-are-all-you-need-lite
24 type: completion
25 field: completion
26 train_on_split: train[:10%]
27
28
29dataset_prepared_path:
30val_set_size: 0.001
31output_dir: ./phi-600M-mix
32
33sequence_len: 2048
34sample_packing: true # currently unsupported
35pad_to_sequence_len:
36
37adapter:
38lora_model_dir:
39lora_r:
40lora_alpha:
41lora_dropout:
42lora_target_linear:
43lora_fan_in_fan_out:
44lora_modules_to_save:
45
46wandb_project: phine
47wandb_entity: willfulbytes
48wandb_watch:
49wandb_name:
50wandb_log_model:
51
52gradient_accumulation_steps: 4
53micro_batch_size: 1
54num_epochs: 1
55optimizer: paged_adamw_8bit
56adam_beta2: 0.98
57adam_epsilon: 0.0000001
58max_grad_norm: 1.0
59lr_scheduler: cosine
60learning_rate: 1e-4
61cosine_min_lr_ratio: 0.2
62
63train_on_inputs: false
64group_by_length: false
65bf16: true
66fp16: false
67tf32: true
68
69gradient_checkpointing: true
70early_stopping_patience: false
71resume_from_checkpoint:
72local_rank:
73logging_steps: 1
74xformers_attention:
75flash_attention: true
76
77warmup_steps: 0
78evals_per_epoch: 100
79saves_per_epoch: 10
80save_steps:
81debug:
82deepspeed:
83weight_decay: 0.1
84fsdp:
85fsdp_config:
86resize_token_embeddings_to_32x: true
87special_tokens:
88 pad_token: "<|endoftext|>"
89| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.366 | 0.0 | 1 | 3.3037 |
| 2.5809 | 0.01 | 84 | 2.5172 |
| 2.5684 | 0.02 | 168 | 2.3902 |
| 2.6054 | 0.03 | 252 | 2.3144 |
| 2.2944 | 0.04 | 336 | 2.2658 |
| 2.2836 | 0.05 | 420 | 2.2178 |
| 2.4438 | 0.06 | 504 | 2.1837 |
| 2.1093 | 0.07 | 588 | 2.1460 |
| 2.1831 | 0.08 | 672 | 2.1220 |
| 2.3081 | 0.09 | 756 | 2.0990 |
| 1.9909 | 0.1 | 840 | 2.0850 |
| 2.114 | 0.11 | 924 | 2.0550 |
| 1.8529 | 0.12 | 1008 | 2.0410 |
| 2.1594 | 0.13 | 1092 | 2.0215 |
| 2.0632 | 0.14 | 1176 | 2.0035 |
| 1.9221 | 0.15 | 1260 | 1.9906 |
| 2.0664 | 0.16 | 1344 | 1.9861 |
| 1.931 | 0.17 | 1428 | 1.9708 |
| 1.9948 | 0.18 | 1512 | 1.9533 |
| 1.9229 | 0.19 | 1596 | 1.9464 |
| 2.0231 | 0.2 | 1680 | 1.9332 |
| 2.2535 | 0.21 | 1764 | 1.9232 |
| 1.8994 | 0.22 | 1848 | 1.9140 |
| 1.9913 | 0.23 | 1932 | 1.8935 |
| 1.8613 | 0.24 | 2016 | 1.8916 |
| 1.9724 | 0.25 | 2100 | 1.8790 |
| 1.9965 | 0.26 | 2184 | 1.8653 |
| 2.0012 | 0.27 | 2268 | 1.8648 |
| 1.9752 | 0.28 | 2352 | 1.8572 |
| 1.9709 | 0.29 | 2436 | 1.8504 |
| 1.7314 | 0.3 | 2520 | 1.8432 |
| 1.7373 | 0.31 | 2604 | 1.8470 |
| 1.93 | 0.32 | 2688 | 1.8353 |
| 1.7185 | 0.33 | 2772 | 1.8210 |
| 1.8435 | 0.34 | 2856 | 1.8201 |
| 1.8117 | 0.35 | 2940 | 1.8118 |
| 2.1292 | 0.36 | 3024 | 1.8095 |
| 1.7536 | 0.37 | 3108 | 1.8023 |
| 1.7596 | 0.38 | 3192 | 1.7956 |
| 1.9481 | 0.39 | 3276 | 1.7890 |
| 1.7915 | 0.4 | 3360 | 1.7872 |
| 1.8639 | 0.41 | 3444 | 1.7782 |
| 1.6688 | 0.42 | 3528 | 1.7754 |
| 1.6312 | 0.43 | 3612 | 1.7669 |
| 1.8053 | 0.45 | 3696 | 1.7602 |
| 1.8867 | 0.46 | 3780 | 1.7544 |
| 1.9305 | 0.47 | 3864 | 1.7546 |
| 1.7926 | 0.48 | 3948 | 1.7496 |
| 1.8326 | 0.49 | 4032 | 1.7436 |
| 1.7334 | 0.5 | 4116 | 1.7437 |
| 1.6552 | 0.51 | 4200 | 1.7348 |
| 1.6622 | 0.52 | 4284 | 1.7330 |
| 1.9858 | 0.53 | 4368 | 1.7303 |
| 1.7784 | 0.54 | 4452 | 1.7271 |
| 1.8752 | 0.55 | 4536 | 1.7222 |
| 1.5931 | 0.56 | 4620 | 1.7186 |
| 1.6785 | 0.57 | 4704 | 1.7131 |
| 1.8382 | 0.58 | 4788 | 1.7101 |
| 1.5888 | 0.59 | 4872 | 1.7081 |
| 1.8055 | 0.6 | 4956 | 1.7062 |
| 1.6869 | 0.61 | 5040 | 1.7021 |
| 1.8096 | 0.62 | 5124 | 1.6999 |
| 1.9318 | 0.63 | 5208 | 1.6980 |
| 1.6153 | 0.64 | 5292 | 1.6963 |
| 1.6556 | 0.65 | 5376 | 1.6924 |
| 1.4087 | 0.66 | 5460 | 1.6908 |
| 1.7946 | 0.67 | 5544 | 1.6881 |
| 1.6097 | 0.68 | 5628 | 1.6867 |
| 1.6397 | 0.69 | 5712 | 1.6847 |
| 1.7799 | 0.7 | 5796 | 1.6828 |
| 1.6216 | 0.71 | 5880 | 1.6809 |
| 1.5052 | 0.72 | 5964 | 1.6790 |
| 1.6931 | 0.73 | 6048 | 1.6773 |
| 1.5936 | 0.74 | 6132 | 1.6762 |
| 1.803 | 0.75 | 6216 | 1.6737 |
| 1.5175 | 0.76 | 6300 | 1.6719 |
| 1.6305 | 0.77 | 6384 | 1.6711 |
| 1.715 | 0.78 | 6468 | 1.6698 |
| 1.8779 | 0.79 | 6552 | 1.6686 |
| 1.6844 | 0.8 | 6636 | 1.6669 |
| 1.3624 | 0.81 | 6720 | 1.6658 |
| 1.5534 | 0.82 | 6804 | 1.6650 |
| 1.8579 | 0.83 | 6888 | 1.6648 |
| 1.6093 | 0.84 | 6972 | 1.6632 |
| 1.5325 | 0.85 | 7056 | 1.6618 |
| 1.6753 | 0.86 | 7140 | 1.6619 |
| 1.3612 | 0.87 | 7224 | 1.6611 |
| 1.4817 | 0.88 | 7308 | 1.6606 |
| 1.7252 | 0.89 | 7392 | 1.6599 |
| 1.7463 | 0.9 | 7476 | 1.6586 |
| 1.8894 | 0.91 | 7560 | 1.6581 |
| 1.545 | 0.92 | 7644 | 1.6575 |
| 1.7251 | 0.93 | 7728 | 1.6572 |
| 1.7265 | 0.94 | 7812 | 1.6572 |
| 1.7813 | 0.95 | 7896 | 1.6564 |
| 1.7005 | 0.96 | 7980 | 1.6560 |
| 1.6444 | 0.97 | 8064 | 1.6555 |
| 1.5202 | 0.98 | 8148 | 1.6552 |
| 1.8648 | 0.99 | 8232 | 1.6549 |