Hugging Face's logo

SystemAdmin123
/
CodeLlama-7b-hf

Safetensors
llama
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
6fd7976
·
verified ·
1 Parent(s): b857fbe

Training in progress, step 200

Browse files
Files changed (5) hide show
  1. axolotl_config.yaml +5 -5
  2. model-00001-of-00003.safetensors +1 -1
  3. model-00002-of-00003.safetensors +1 -1
  4. model-00003-of-00003.safetensors +1 -1
  5. training_args.bin +1 -1
axolotl_config.yaml CHANGED
@@ -17,23 +17,23 @@ device_map: auto
17
  eval_sample_packing: false
18
  eval_steps: 200
19
  flash_attention: true
20
- gpu_memory_limit: 80GiB
21
  group_by_length: true
22
  hub_model_id: SystemAdmin123/CodeLlama-7b-hf
23
  hub_strategy: checkpoint
24
  learning_rate: 0.0002
25
  logging_steps: 10
26
  lr_scheduler: cosine
27
- max_steps: 2500
28
  micro_batch_size: 2
29
  model_type: AutoModelForCausalLM
30
  num_epochs: 100
31
  optimizer: adamw_bnb_8bit
32
- output_dir: /root/.sn56/axolotl/outputs/CodeLlama-7b-hf
33
  pad_to_sequence_len: true
34
  resize_token_embeddings_to_32x: false
35
- sample_packing: false
36
- save_steps: 400
37
  save_total_limit: 1
38
  sequence_len: 2048
39
  special_tokens:
 
17
  eval_sample_packing: false
18
  eval_steps: 200
19
  flash_attention: true
20
+ gradient_checkpointing: true
21
  group_by_length: true
22
  hub_model_id: SystemAdmin123/CodeLlama-7b-hf
23
  hub_strategy: checkpoint
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
31
  optimizer: adamw_bnb_8bit
32
+ output_dir: /root/.sn56/axolotl/tmp/CodeLlama-7b-hf
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
  special_tokens:
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96eefb2ab4b204e9308bae75f26755bc252532bdfce90c247e78733a4199e1e2
3
  size 4939116424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f1bd28175fd7513f12729e17ee3571da7edbf57f145604ce22771573d115cc5
3
  size 4939116424
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4096a8c7f67ddbd2910b504765f448908fdd008051d764d2428a8cf62c11b3d
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1e18b7d14aadcdd3ffd84212a90763f05677810d6606b0228ab48fc71aa8693
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c892e15db6ad07c12e5d0e95b0debfd095cf21e2bf401f6eca45fe7f25d85cb
3
  size 3590619888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74fed502be8e1cd05be29c5fb4cde46eadd9a078e63d9feccc111a8be0fd8b78
3
  size 3590619888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d8953c8f78e882c2468a8fd9123e7e01d1ba2fa70223c087509fa59b852ab047
3
  size 6840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7e4cc380bf07566f66cbd6e04a4bdc7a8bc1f51ced4f92d8dc2abee469a5015
3
  size 6840