Hugging Face's logo

zeeshan73
/
Text2SQL_mistral_7b_cosine_lr

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
zeeshan73 commited on
Commit
a9d2dcd
•
1 Parent(s): 01cd5ed

Training in progress, step 10

Browse files
Files changed (11) hide show
  1. adapter_config.json +34 -0
  2. adapter_model.safetensors +3 -0
  3. added_tokens.json +4 -0
  4. logs/events.out.tfevents.1730036942.APSISCSDT-3690.2174405.0 +3 -0
  5. logs/events.out.tfevents.1730037746.APSISCSDT-3690.2176097.0 +3 -0
  6. logs/events.out.tfevents.1730045591.APSISCSDT-3690.2201692.0 +3 -0
  7. special_tokens_map.json +28 -0
  8. tokenizer.json +0 -0
  9. tokenizer.model +3 -0
  10. tokenizer_config.json +0 -0
  11. training_args.bin +3 -0
adapter_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 128,
14
+ "lora_dropout": 0.07,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 256,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "down_proj",
24
+ "q_proj",
25
+ "v_proj",
26
+ "up_proj",
27
+ "k_proj",
28
+ "gate_proj",
29
+ "o_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM",
32
+ "use_dora": false,
33
+ "use_rslora": false
34
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933d4915bc38e7b62db7ea78e7ab0739ad446107811f04404713046c09d5ccda
3
+ size 3221320120
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<|im_end|>": 32769,
3
+ "<|im_start|>": 32768
4
+ }
logs/events.out.tfevents.1730036942.APSISCSDT-3690.2174405.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a9736a5ee26ee8b5525dcf0db1e796c0b819c327d7c14ad85d1766b526f8b41
3
+ size 6546
logs/events.out.tfevents.1730037746.APSISCSDT-3690.2176097.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2f9593f2717cfc4063a5ba9c504b3474bb5d1f24f8cf8ea72c3a6da4e958dca
3
+ size 6073
logs/events.out.tfevents.1730045591.APSISCSDT-3690.2201692.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1930d940033272b6f4e61f6d11b2c30e9239bf3bf3d9b8e29119542a6a31136b
3
+ size 6545
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<unk>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
3
+ size 587404
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e42a4f929633e2908f87147050b6f87b7355a16cae9da773ee6aabc75af3ac1a
3
+ size 5624