Training in progress, step 20
Browse files- axolotl_config.yaml +4 -2
- model-00001-of-00003.safetensors +1 -1
- model-00002-of-00003.safetensors +1 -1
- model-00003-of-00003.safetensors +1 -1
- 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:
|
19 |
flash_attention: true
|
20 |
gradient_checkpointing: true
|
21 |
group_by_length: true
|
@@ -33,13 +33,15 @@ 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:
|
37 |
save_total_limit: 1
|
38 |
sequence_len: 2048
|
39 |
special_tokens:
|
40 |
pad_token: </s>
|
41 |
tokenizer_type: CodeLlamaTokenizerFast
|
42 |
torch_dtype: bf16
|
|
|
|
|
43 |
trust_remote_code: true
|
44 |
val_set_size: 0.1
|
45 |
wandb_entity: ''
|
|
|
15 |
system_prompt: ''
|
16 |
device_map: auto
|
17 |
eval_sample_packing: false
|
18 |
+
eval_steps: 20
|
19 |
flash_attention: true
|
20 |
gradient_checkpointing: true
|
21 |
group_by_length: true
|
|
|
33 |
pad_to_sequence_len: true
|
34 |
resize_token_embeddings_to_32x: false
|
35 |
sample_packing: true
|
36 |
+
save_steps: 20
|
37 |
save_total_limit: 1
|
38 |
sequence_len: 2048
|
39 |
special_tokens:
|
40 |
pad_token: </s>
|
41 |
tokenizer_type: CodeLlamaTokenizerFast
|
42 |
torch_dtype: bf16
|
43 |
+
training_args_kwargs:
|
44 |
+
hub_private_repo: true
|
45 |
trust_remote_code: true
|
46 |
val_set_size: 0.1
|
47 |
wandb_entity: ''
|
model-00001-of-00003.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4939116424
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebb73bcd3bf64d6b7f6c73f12411aa0002bd1ca75bb1ead942c50abb1c6a3d0c
|
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:
|
3 |
size 4947390880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c41f1c577edc81dfba0f3ff054e62abf8cd77b5e10c7889383f2a475a793632
|
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:
|
3 |
size 3590619888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05ee7c8fa42eb9f6e68261d8b7c688e67c38f688f5d787e776948b6b4d41c503
|
3 |
size 3590619888
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf9578eae927fa7e14b21d5ac2191f0f8c2650a9abe361eb798e45e9300ff09f
|
3 |
size 6840
|