Upload folder using huggingface_hub
Browse files- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- tokenizer_config.json +1 -1
- trainer_state.json +75 -0
- training_args.bin +1 -1
adapter_config.json
CHANGED
@@ -20,10 +20,10 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"qkv_proj",
|
24 |
-
"down_proj",
|
25 |
"o_proj",
|
26 |
-
"gate_up_proj"
|
|
|
|
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
|
|
|
|
23 |
"o_proj",
|
24 |
+
"gate_up_proj",
|
25 |
+
"down_proj",
|
26 |
+
"qkv_proj"
|
27 |
],
|
28 |
"task_type": "CAUSAL_LM",
|
29 |
"use_dora": false,
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 805341552
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c95750cf4269c771496c20d64ad1715c9bd0a8f9e99be1a0b6ed7c7822aa123
|
3 |
size 805341552
|
tokenizer_config.json
CHANGED
@@ -117,7 +117,7 @@
|
|
117 |
}
|
118 |
},
|
119 |
"bos_token": "<s>",
|
120 |
-
"chat_template": "{
|
121 |
"clean_up_tokenization_spaces": false,
|
122 |
"eos_token": "<|end|>",
|
123 |
"legacy": false,
|
|
|
117 |
}
|
118 |
},
|
119 |
"bos_token": "<s>",
|
120 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|system|>\n' + system_message + '<|end|>\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|user|>\n' + content + '<|end|>\n<|assistant|>\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|end|>' + '\n' }}{% endif %}{% endfor %}",
|
121 |
"clean_up_tokenization_spaces": false,
|
122 |
"eos_token": "<|end|>",
|
123 |
"legacy": false,
|
trainer_state.json
ADDED
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 24,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.4166666666666667,
|
13 |
+
"grad_norm": 0.33834290504455566,
|
14 |
+
"learning_rate": 8.966766701456177e-05,
|
15 |
+
"loss": 0.5297,
|
16 |
+
"num_input_tokens_seen": 81920,
|
17 |
+
"step": 5
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.8333333333333334,
|
21 |
+
"grad_norm": 0.35304397344589233,
|
22 |
+
"learning_rate": 6.294095225512603e-05,
|
23 |
+
"loss": 0.4377,
|
24 |
+
"num_input_tokens_seen": 159872,
|
25 |
+
"step": 10
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 1.25,
|
29 |
+
"grad_norm": 0.21805448830127716,
|
30 |
+
"learning_rate": 3.086582838174551e-05,
|
31 |
+
"loss": 0.3134,
|
32 |
+
"num_input_tokens_seen": 241792,
|
33 |
+
"step": 15
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.6666666666666665,
|
37 |
+
"grad_norm": 0.21976211667060852,
|
38 |
+
"learning_rate": 6.698729810778065e-06,
|
39 |
+
"loss": 0.3175,
|
40 |
+
"num_input_tokens_seen": 323712,
|
41 |
+
"step": 20
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.0,
|
45 |
+
"num_input_tokens_seen": 389248,
|
46 |
+
"step": 24,
|
47 |
+
"total_flos": 9164234264936448.0,
|
48 |
+
"train_loss": 0.3852280577023824,
|
49 |
+
"train_runtime": 121.43,
|
50 |
+
"train_samples_per_second": 2.965,
|
51 |
+
"train_steps_per_second": 0.198
|
52 |
+
}
|
53 |
+
],
|
54 |
+
"logging_steps": 5,
|
55 |
+
"max_steps": 24,
|
56 |
+
"num_input_tokens_seen": 389248,
|
57 |
+
"num_train_epochs": 2,
|
58 |
+
"save_steps": 500,
|
59 |
+
"stateful_callbacks": {
|
60 |
+
"TrainerControl": {
|
61 |
+
"args": {
|
62 |
+
"should_epoch_stop": false,
|
63 |
+
"should_evaluate": false,
|
64 |
+
"should_log": false,
|
65 |
+
"should_save": true,
|
66 |
+
"should_training_stop": true
|
67 |
+
},
|
68 |
+
"attributes": {}
|
69 |
+
}
|
70 |
+
},
|
71 |
+
"total_flos": 9164234264936448.0,
|
72 |
+
"train_batch_size": 8,
|
73 |
+
"trial_name": null,
|
74 |
+
"trial_params": null
|
75 |
+
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3597165398adfe7bab467032b5785b6270a5d7c565c51ea6dddeb0892408df34
|
3 |
size 5432
|