Training in progress, step 500
Browse files- adapter_config.json +11 -7
- adapter_model.safetensors +2 -2
- tokenizer_config.json +0 -1
- training_args.bin +2 -2
adapter_config.json
CHANGED
@@ -3,6 +3,9 @@
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "unsloth/SmolLM-135M",
|
5 |
"bias": "none",
|
|
|
|
|
|
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
@@ -11,26 +14,27 @@
|
|
11 |
"layers_to_transform": null,
|
12 |
"loftq_config": {},
|
13 |
"lora_alpha": 256,
|
|
|
14 |
"lora_dropout": 0.1,
|
15 |
"megatron_config": null,
|
16 |
"megatron_core": "megatron.core",
|
17 |
-
"modules_to_save":
|
18 |
-
"lm_head"
|
19 |
-
],
|
20 |
"peft_type": "LORA",
|
21 |
"r": 128,
|
22 |
"rank_pattern": {},
|
23 |
"revision": null,
|
24 |
"target_modules": [
|
25 |
-
"v_proj",
|
26 |
-
"up_proj",
|
27 |
"gate_proj",
|
28 |
-
"
|
29 |
"q_proj",
|
|
|
|
|
30 |
"o_proj",
|
31 |
-
"
|
|
|
32 |
],
|
33 |
"task_type": "CAUSAL_LM",
|
|
|
34 |
"use_dora": false,
|
35 |
"use_rslora": false
|
36 |
}
|
|
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "unsloth/SmolLM-135M",
|
5 |
"bias": "none",
|
6 |
+
"corda_config": null,
|
7 |
+
"eva_config": null,
|
8 |
+
"exclude_modules": null,
|
9 |
"fan_in_fan_out": false,
|
10 |
"inference_mode": true,
|
11 |
"init_lora_weights": true,
|
|
|
14 |
"layers_to_transform": null,
|
15 |
"loftq_config": {},
|
16 |
"lora_alpha": 256,
|
17 |
+
"lora_bias": false,
|
18 |
"lora_dropout": 0.1,
|
19 |
"megatron_config": null,
|
20 |
"megatron_core": "megatron.core",
|
21 |
+
"modules_to_save": null,
|
|
|
|
|
22 |
"peft_type": "LORA",
|
23 |
"r": 128,
|
24 |
"rank_pattern": {},
|
25 |
"revision": null,
|
26 |
"target_modules": [
|
|
|
|
|
27 |
"gate_proj",
|
28 |
+
"v_proj",
|
29 |
"q_proj",
|
30 |
+
"k_proj",
|
31 |
+
"down_proj",
|
32 |
"o_proj",
|
33 |
+
"lm_head",
|
34 |
+
"up_proj"
|
35 |
],
|
36 |
"task_type": "CAUSAL_LM",
|
37 |
+
"trainable_token_indices": null,
|
38 |
"use_dora": false,
|
39 |
"use_rslora": false
|
40 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f091d40d50198e530f01b9a25487cd690a670b42ab8b3fa59ef973cece5faa3
|
3 |
+
size 238444008
|
tokenizer_config.json
CHANGED
@@ -158,7 +158,6 @@
|
|
158 |
"<empty_output>"
|
159 |
],
|
160 |
"bos_token": "<|endoftext|>",
|
161 |
-
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
162 |
"clean_up_tokenization_spaces": false,
|
163 |
"eos_token": "<|endoftext|>",
|
164 |
"extra_special_tokens": {},
|
|
|
158 |
"<empty_output>"
|
159 |
],
|
160 |
"bos_token": "<|endoftext|>",
|
|
|
161 |
"clean_up_tokenization_spaces": false,
|
162 |
"eos_token": "<|endoftext|>",
|
163 |
"extra_special_tokens": {},
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f846d36aae485459ed98faa0c0b1bdadf6bf66458553293b2754e96264b2078
|
3 |
+
size 5752
|