Training in progress, epoch 0
Browse files
adapter_config.json
CHANGED
@@ -6,24 +6,18 @@
|
|
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": 16,
|
14 |
"lora_dropout": 0.05,
|
15 |
-
"megatron_config": null,
|
16 |
-
"megatron_core": "megatron.core",
|
17 |
"modules_to_save": null,
|
18 |
"peft_type": "LORA",
|
19 |
"r": 16,
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
-
"task_type": "CAUSAL_LM"
|
27 |
-
"use_dora": false,
|
28 |
-
"use_rslora": false
|
29 |
}
|
|
|
6 |
"fan_in_fan_out": false,
|
7 |
"inference_mode": true,
|
8 |
"init_lora_weights": true,
|
|
|
9 |
"layers_pattern": null,
|
10 |
"layers_to_transform": null,
|
|
|
11 |
"lora_alpha": 16,
|
12 |
"lora_dropout": 0.05,
|
|
|
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 16,
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"q_proj",
|
20 |
+
"v_proj"
|
21 |
],
|
22 |
+
"task_type": "CAUSAL_LM"
|
|
|
|
|
23 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9022864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25a2710e0d4284fad1ce9dbe15095b84a272ff38140547a82daadb6c8ac9097f
|
3 |
size 9022864
|
runs/May26_14-31-28_nc383ar3my/events.out.tfevents.1716733889.nc383ar3my.76.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a837162abded76c3d745f7b7b54236221f820e955bf7305987dcb6bc192b28dd
|
3 |
+
size 5294
|
tokenizer.json
CHANGED
@@ -139,7 +139,6 @@
|
|
139 |
"end_of_word_suffix": null,
|
140 |
"fuse_unk": true,
|
141 |
"byte_fallback": true,
|
142 |
-
"ignore_merges": false,
|
143 |
"vocab": {
|
144 |
"<unk>": 0,
|
145 |
"<s>": 1,
|
|
|
139 |
"end_of_word_suffix": null,
|
140 |
"fuse_unk": true,
|
141 |
"byte_fallback": true,
|
|
|
142 |
"vocab": {
|
143 |
"<unk>": 0,
|
144 |
"<s>": 1,
|
tokenizer_config.json
CHANGED
@@ -1,6 +1,4 @@
|
|
1 |
{
|
2 |
-
"add_bos_token": true,
|
3 |
-
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
@@ -31,6 +29,7 @@
|
|
31 |
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
"eos_token": "</s>",
|
|
|
34 |
"model_max_length": 2048,
|
35 |
"pad_token": "</s>",
|
36 |
"padding_side": "right",
|
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
|
|
29 |
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
30 |
"clean_up_tokenization_spaces": false,
|
31 |
"eos_token": "</s>",
|
32 |
+
"legacy": false,
|
33 |
"model_max_length": 2048,
|
34 |
"pad_token": "</s>",
|
35 |
"padding_side": "right",
|
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:a0b2d6d7a74acb20027b4245ba06849210082b9a1965ffec1a8c7af3d1ca78aa
|
3 |
+
size 4600
|