Hugging Face's logo

SystemAdmin123
/
codellama-7b

Safetensors
llama
Model card Files
xet
Community
SystemAdmin123 commited on
Commit
8e513d2
·
verified ·
1 Parent(s): 1adb409

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
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
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
  tokenizer_type: CodeLlamaTokenizerFast
 
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
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
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: CodeLlamaTokenizerFast
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb968af799165acf1cfa9ded37b1ef66cc0c047f680efd9d3f9e0669cb5f0c1
3
  size 4939116424
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80719f65a4c76f5f9549a9ff6b40c12ab753baa9b2dede5200e8eaf0ee485610
3
  size 4939116424
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52fe44bbdbc149f43a4a3f05f9cfada2db0985da8fa1554981ed6616e0a9c909
3
  size 4947390880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93baeb991618ed9cb503e7afa440c283da11219662d8b7e72afa7c5cdb049e3e
3
  size 4947390880
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5abe838d9f785fd0a874716143de87fdbdc4b78e71af4464450a4d88e1861857
3
  size 3590619888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8870def62712246e10267b52717c3817d3f0bf0bebf0ca06ac04e24b91d2483
3
  size 3590619888
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2bf6f06544da4fe32a2b63dd4d1f2f74f2cd1ba39da1c617fe85338c0397a8ef
3
  size 6840
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba673725c24b475995eb203939e8d5642b3dae413ae05b5e3595152a67bc2b87
3
  size 6840