Hugging Face's logo

SystemAdmin123
/
Qwen2-7B-Instruct

Safetensors
qwen2
Model card Files Community
SystemAdmin123 commited on
Commit
eed8544
·
verified ·
1 Parent(s): fb262e8

Training in progress, step 200

Browse files
Files changed (6) hide show
  1. axolotl_config.yaml +6 -4
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. training_args.bin +1 -1
axolotl_config.yaml CHANGED
@@ -15,7 +15,7 @@ datasets:
15
  system_prompt: ''
16
  device_map: auto
17
  eval_sample_packing: false
18
- eval_steps: 50
19
  flash_attention: true
20
  gradient_checkpointing: true
21
  group_by_length: true
@@ -24,7 +24,7 @@ hub_strategy: checkpoint
24
  learning_rate: 0.0002
25
  logging_steps: 10
26
  lr_scheduler: cosine
27
- max_steps: 5000
28
  micro_batch_size: 2
29
  model_type: AutoModelForCausalLM
30
  num_epochs: 100
@@ -33,11 +33,13 @@ output_dir: /root/.sn56/axolotl/tmp/Qwen2-7B-Instruct
33
  pad_to_sequence_len: true
34
  resize_token_embeddings_to_32x: false
35
  sample_packing: true
36
- save_steps: 50
37
- save_total_limit: 2
38
  sequence_len: 2048
39
  tokenizer_type: Qwen2TokenizerFast
40
  torch_dtype: bf16
 
 
41
  trust_remote_code: true
42
  val_set_size: 0.1
43
  wandb_entity: ''
 
15
  system_prompt: ''
16
  device_map: auto
17
  eval_sample_packing: false
18
+ eval_steps: 200
19
  flash_attention: true
20
  gradient_checkpointing: true
21
  group_by_length: true
 
24
  learning_rate: 0.0002
25
  logging_steps: 10
26
  lr_scheduler: cosine
27
+ max_steps: 10000
28
  micro_batch_size: 2
29
  model_type: AutoModelForCausalLM
30
  num_epochs: 100
 
33
  pad_to_sequence_len: true
34
  resize_token_embeddings_to_32x: false
35
  sample_packing: true
36
+ save_steps: 200
37
+ save_total_limit: 1
38
  sequence_len: 2048
39
  tokenizer_type: Qwen2TokenizerFast
40
  torch_dtype: bf16
41
+ training_args_kwargs:
42
+ hub_private_repo: true
43
  trust_remote_code: true
44
  val_set_size: 0.1
45
  wandb_entity: ''
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42c0e60d02078c5df49b184b5207a976737868513b16290824ce27ee54f58f88
3
  size 4874664552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b69510103c86ab6c7d79f2705fcd3bc77def1938ff647a7523546cfaa6d7eb1
3
  size 4874664552
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:336b403138c01e5ac747451b875ef0f98f60a47e84e1d500278074060de44438
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f48df3f5accdfbdae4f827024db4d1dabfa7cf1d3dd237e8d4c6cbab835ee5
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:519e7722a9b117a48704c83b8fc1ec28a8f1e8e375a9f6626fcf5d5d9c8160c3
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:464a609182441fb88482d5a7a508cf91905e87e8d57b74fbf74ed4610d98783e
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2d0ac70726380aba81367b3bf7d78acaf8e27ea4a4a759c4b90b787f44c121f
3
  size 1086998656
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58e53b04f20e02489ca57de06513f0a94a759f82223847010fa4abd53f07e10b
3
  size 1086998656
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32a7a8613e5fa3317cdc198f56f6d0577b15eb3e0cf0efd4aa72ac710a8260e0
3
  size 6968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d11551a59df892a04244070ff3f59b02e2dcaa3eb1aab844864a42113437689
3
  size 6968