Hugging Face's logo

willtensora
/
123e4567-e89b-12d3-a456-426614174000

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
willtensora commited on
Commit
23d48b4
·
verified ·
1 Parent(s): d47019b

End of training

Browse files
Files changed (2) hide show
  1. README.md +8 -8
  2. adapter_model.bin +1 -1
README.md CHANGED
@@ -38,12 +38,12 @@ deepspeed: null
38
  early_stopping_patience: null
39
  eval_max_new_tokens: 128
40
  eval_table_size: null
41
- evals_per_epoch: 4
42
  flash_attention: false
43
  fp16: null
44
  fsdp: null
45
  fsdp_config: null
46
- gradient_accumulation_steps: 4
47
  gradient_checkpointing: false
48
  group_by_length: false
49
  hub_model_id: willtensora/123e4567-e89b-12d3-a456-426614174000
@@ -62,8 +62,8 @@ lora_model_dir: null
62
  lora_r: 8
63
  lora_target_linear: true
64
  lr_scheduler: cosine
65
- max_steps: 10
66
- micro_batch_size: 2
67
  mlflow_experiment_name: argilla/databricks-dolly-15k-curated-en
68
  model_type: AutoModelForCausalLM
69
  num_epochs: 1
@@ -73,21 +73,21 @@ pad_to_sequence_len: true
73
  resume_from_checkpoint: null
74
  s2_attention: null
75
  sample_packing: false
76
- saves_per_epoch: 4
77
- sequence_len: 512
78
  strict: false
79
  tf32: false
80
  tokenizer_type: AutoTokenizer
81
  train_on_inputs: false
82
  trust_remote_code: true
83
- val_set_size: 0.05
84
  wandb_entity: null
85
  wandb_mode: online
86
  wandb_name: 123e4567-e89b-12d3-a456-426614174000
87
  wandb_project: Gradients-On-Demand
88
  wandb_run: your_name
89
  wandb_runid: 123e4567-e89b-12d3-a456-426614174000
90
- warmup_steps: 10
91
  weight_decay: 0.0
92
  xformers_attention: null
93
 
 
38
  early_stopping_patience: null
39
  eval_max_new_tokens: 128
40
  eval_table_size: null
41
+ evals_per_epoch: 1
42
  flash_attention: false
43
  fp16: null
44
  fsdp: null
45
  fsdp_config: null
46
+ gradient_accumulation_steps: 1
47
  gradient_checkpointing: false
48
  group_by_length: false
49
  hub_model_id: willtensora/123e4567-e89b-12d3-a456-426614174000
 
62
  lora_r: 8
63
  lora_target_linear: true
64
  lr_scheduler: cosine
65
+ max_steps: 2
66
+ micro_batch_size: 1
67
  mlflow_experiment_name: argilla/databricks-dolly-15k-curated-en
68
  model_type: AutoModelForCausalLM
69
  num_epochs: 1
 
73
  resume_from_checkpoint: null
74
  s2_attention: null
75
  sample_packing: false
76
+ saves_per_epoch: 1
77
+ sequence_len: 128
78
  strict: false
79
  tf32: false
80
  tokenizer_type: AutoTokenizer
81
  train_on_inputs: false
82
  trust_remote_code: true
83
+ val_set_size: 0.01
84
  wandb_entity: null
85
  wandb_mode: online
86
  wandb_name: 123e4567-e89b-12d3-a456-426614174000
87
  wandb_project: Gradients-On-Demand
88
  wandb_run: your_name
89
  wandb_runid: 123e4567-e89b-12d3-a456-426614174000
90
+ warmup_steps: 2
91
  weight_decay: 0.0
92
  xformers_attention: null
93
 
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:303537388eb66b48b782b3fed48631e5410960672a9aaacfbd58653b6b7510df
3
  size 80115210
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a59373a974866d944d76f095a936779dd70b9ca43d96196d5e05e9668d5584d7
3
  size 80115210