Upload 10 files
Browse files- README.md +56 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
- train_results.json +7 -0
- trainer_state.json +394 -0
- training_args.bin +3 -0
README.md
CHANGED
@@ -1,3 +1,59 @@
|
|
1 |
---
|
2 |
license: llama2
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: llama2
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf
|
9 |
+
model-index:
|
10 |
+
- name: llama2_70b_aqlm_toolcall
|
11 |
+
results: []
|
12 |
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# llama2_70b_aqlm_toolcall
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf](https://huggingface.co/BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf) on the identity, the alpaca_gpt4_en and the glaive_toolcall datasets.
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 1
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 8
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 1.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.9.0
|
56 |
+
- Transformers 4.39.0.dev0
|
57 |
+
- Pytorch 2.2.1+cu121
|
58 |
+
- Datasets 2.15.0
|
59 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "BlackSamorez/Llama-2-70b-AQLM-2Bit-1x16-hf",
|
5 |
+
"bias": "none",
|
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 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16.0,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_dora": false,
|
27 |
+
"use_rslora": false
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a0d7e66ad280a63627676001c0311bf7504f553e70fc33ac43e7ca385255c6
|
3 |
+
size 65578776
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6279083029063726,
|
4 |
+
"train_runtime": 203702.1714,
|
5 |
+
"train_samples_per_second": 0.01,
|
6 |
+
"train_steps_per_second": 0.001
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"padding_side": "right",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "LlamaTokenizer",
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\\n' }}{% endif %}{% endfor %}",
|
44 |
+
"use_default_system_prompt": false
|
45 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.6279083029063726,
|
4 |
+
"train_runtime": 203702.1714,
|
5 |
+
"train_samples_per_second": 0.01,
|
6 |
+
"train_steps_per_second": 0.001
|
7 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,394 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9985652797704447,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 261,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"grad_norm": 0.45229363441467285,
|
14 |
+
"learning_rate": 9.990947518281311e-05,
|
15 |
+
"loss": 1.2293,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.04,
|
20 |
+
"grad_norm": 0.45895835757255554,
|
21 |
+
"learning_rate": 9.963822852095345e-05,
|
22 |
+
"loss": 1.0332,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.06,
|
27 |
+
"grad_norm": 1.148818850517273,
|
28 |
+
"learning_rate": 9.918724219660013e-05,
|
29 |
+
"loss": 1.1688,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.08,
|
34 |
+
"grad_norm": 0.6193984150886536,
|
35 |
+
"learning_rate": 9.855814922793582e-05,
|
36 |
+
"loss": 0.8491,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.1,
|
41 |
+
"grad_norm": 0.5973692536354065,
|
42 |
+
"learning_rate": 9.775322755599978e-05,
|
43 |
+
"loss": 0.8356,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.11,
|
48 |
+
"grad_norm": 0.471483439207077,
|
49 |
+
"learning_rate": 9.677539179628005e-05,
|
50 |
+
"loss": 0.782,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.13,
|
55 |
+
"grad_norm": 0.5395711660385132,
|
56 |
+
"learning_rate": 9.562818268491216e-05,
|
57 |
+
"loss": 0.7464,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.15,
|
62 |
+
"grad_norm": 0.7068768739700317,
|
63 |
+
"learning_rate": 9.431575425769938e-05,
|
64 |
+
"loss": 0.6813,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.17,
|
69 |
+
"grad_norm": 0.7348042130470276,
|
70 |
+
"learning_rate": 9.284285880837946e-05,
|
71 |
+
"loss": 0.6508,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.19,
|
76 |
+
"grad_norm": 1.763695478439331,
|
77 |
+
"learning_rate": 9.121482968060384e-05,
|
78 |
+
"loss": 0.7296,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.21,
|
83 |
+
"grad_norm": 0.7689581513404846,
|
84 |
+
"learning_rate": 8.943756195593916e-05,
|
85 |
+
"loss": 0.604,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.23,
|
90 |
+
"grad_norm": 1.1951208114624023,
|
91 |
+
"learning_rate": 8.751749110782012e-05,
|
92 |
+
"loss": 0.594,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.25,
|
97 |
+
"grad_norm": 0.9435452818870544,
|
98 |
+
"learning_rate": 8.546156969874723e-05,
|
99 |
+
"loss": 0.6778,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.27,
|
104 |
+
"grad_norm": 0.8245531320571899,
|
105 |
+
"learning_rate": 8.327724220510873e-05,
|
106 |
+
"loss": 0.6173,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.29,
|
111 |
+
"grad_norm": 0.6063089966773987,
|
112 |
+
"learning_rate": 8.097241806078615e-05,
|
113 |
+
"loss": 0.7239,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.31,
|
118 |
+
"grad_norm": 0.4883978068828583,
|
119 |
+
"learning_rate": 7.855544301715203e-05,
|
120 |
+
"loss": 0.5158,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.33,
|
125 |
+
"grad_norm": 0.6936870217323303,
|
126 |
+
"learning_rate": 7.603506892316512e-05,
|
127 |
+
"loss": 0.5011,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.34,
|
132 |
+
"grad_norm": 2.553333282470703,
|
133 |
+
"learning_rate": 7.342042203498951e-05,
|
134 |
+
"loss": 0.6461,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.36,
|
139 |
+
"grad_norm": 0.9251458644866943,
|
140 |
+
"learning_rate": 7.07209699698876e-05,
|
141 |
+
"loss": 0.7273,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.38,
|
146 |
+
"grad_norm": 0.699193000793457,
|
147 |
+
"learning_rate": 6.79464874240473e-05,
|
148 |
+
"loss": 0.5878,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.4,
|
153 |
+
"grad_norm": 0.661618173122406,
|
154 |
+
"learning_rate": 6.510702077847863e-05,
|
155 |
+
"loss": 0.4787,
|
156 |
+
"step": 105
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.42,
|
160 |
+
"grad_norm": 0.4883117079734802,
|
161 |
+
"learning_rate": 6.221285172114157e-05,
|
162 |
+
"loss": 0.5766,
|
163 |
+
"step": 110
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.44,
|
167 |
+
"grad_norm": 2.715449810028076,
|
168 |
+
"learning_rate": 5.927446001702899e-05,
|
169 |
+
"loss": 0.5553,
|
170 |
+
"step": 115
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.46,
|
174 |
+
"grad_norm": 0.6433199644088745,
|
175 |
+
"learning_rate": 5.6302485561014475e-05,
|
176 |
+
"loss": 0.7007,
|
177 |
+
"step": 120
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.48,
|
181 |
+
"grad_norm": 1.7128715515136719,
|
182 |
+
"learning_rate": 5.330768985087059e-05,
|
183 |
+
"loss": 0.5773,
|
184 |
+
"step": 125
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.5,
|
188 |
+
"grad_norm": 0.7177631258964539,
|
189 |
+
"learning_rate": 5.030091701996428e-05,
|
190 |
+
"loss": 0.5787,
|
191 |
+
"step": 130
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.52,
|
195 |
+
"grad_norm": 0.6795344948768616,
|
196 |
+
"learning_rate": 4.729305457072913e-05,
|
197 |
+
"loss": 0.5013,
|
198 |
+
"step": 135
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.54,
|
202 |
+
"grad_norm": 1.1840591430664062,
|
203 |
+
"learning_rate": 4.429499395109877e-05,
|
204 |
+
"loss": 0.6419,
|
205 |
+
"step": 140
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.55,
|
209 |
+
"grad_norm": 0.7961875200271606,
|
210 |
+
"learning_rate": 4.131759111665349e-05,
|
211 |
+
"loss": 0.4529,
|
212 |
+
"step": 145
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.57,
|
216 |
+
"grad_norm": 0.7156918048858643,
|
217 |
+
"learning_rate": 3.8371627221284495e-05,
|
218 |
+
"loss": 0.5831,
|
219 |
+
"step": 150
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.59,
|
223 |
+
"grad_norm": 0.8424770832061768,
|
224 |
+
"learning_rate": 3.546776957871445e-05,
|
225 |
+
"loss": 0.6044,
|
226 |
+
"step": 155
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.61,
|
230 |
+
"grad_norm": 0.9914979338645935,
|
231 |
+
"learning_rate": 3.261653303623263e-05,
|
232 |
+
"loss": 0.5824,
|
233 |
+
"step": 160
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.63,
|
237 |
+
"grad_norm": 1.0051041841506958,
|
238 |
+
"learning_rate": 2.982824190050958e-05,
|
239 |
+
"loss": 0.4595,
|
240 |
+
"step": 165
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.65,
|
244 |
+
"grad_norm": 1.2977936267852783,
|
245 |
+
"learning_rate": 2.711299255335833e-05,
|
246 |
+
"loss": 0.544,
|
247 |
+
"step": 170
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.67,
|
251 |
+
"grad_norm": 0.5247394442558289,
|
252 |
+
"learning_rate": 2.4480616892809594e-05,
|
253 |
+
"loss": 0.5458,
|
254 |
+
"step": 175
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.69,
|
258 |
+
"grad_norm": 0.9446833729743958,
|
259 |
+
"learning_rate": 2.194064673188089e-05,
|
260 |
+
"loss": 0.5625,
|
261 |
+
"step": 180
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.71,
|
265 |
+
"grad_norm": 0.9111084938049316,
|
266 |
+
"learning_rate": 1.9502279283951364e-05,
|
267 |
+
"loss": 0.5163,
|
268 |
+
"step": 185
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.73,
|
272 |
+
"grad_norm": 0.9301843643188477,
|
273 |
+
"learning_rate": 1.7174343859719333e-05,
|
274 |
+
"loss": 0.5594,
|
275 |
+
"step": 190
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.75,
|
279 |
+
"grad_norm": 1.5420268774032593,
|
280 |
+
"learning_rate": 1.4965269896332885e-05,
|
281 |
+
"loss": 0.4737,
|
282 |
+
"step": 195
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.77,
|
286 |
+
"grad_norm": 0.866782546043396,
|
287 |
+
"learning_rate": 1.2883056434459506e-05,
|
288 |
+
"loss": 0.5539,
|
289 |
+
"step": 200
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.78,
|
293 |
+
"grad_norm": 1.928578495979309,
|
294 |
+
"learning_rate": 1.0935243153818436e-05,
|
295 |
+
"loss": 0.5426,
|
296 |
+
"step": 205
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.8,
|
300 |
+
"grad_norm": 0.5703736543655396,
|
301 |
+
"learning_rate": 9.12888307205541e-06,
|
302 |
+
"loss": 0.5781,
|
303 |
+
"step": 210
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.82,
|
307 |
+
"grad_norm": 1.3220263719558716,
|
308 |
+
"learning_rate": 7.470517005817474e-06,
|
309 |
+
"loss": 0.6523,
|
310 |
+
"step": 215
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.84,
|
314 |
+
"grad_norm": 4.24189567565918,
|
315 |
+
"learning_rate": 5.966149886503614e-06,
|
316 |
+
"loss": 0.5199,
|
317 |
+
"step": 220
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.86,
|
321 |
+
"grad_norm": 0.606140673160553,
|
322 |
+
"learning_rate": 4.621229016452156e-06,
|
323 |
+
"loss": 0.487,
|
324 |
+
"step": 225
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.88,
|
328 |
+
"grad_norm": 0.7255881428718567,
|
329 |
+
"learning_rate": 3.4406243442987764e-06,
|
330 |
+
"loss": 0.5654,
|
331 |
+
"step": 230
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.9,
|
335 |
+
"grad_norm": 0.7342286705970764,
|
336 |
+
"learning_rate": 2.428610830928152e-06,
|
337 |
+
"loss": 0.5211,
|
338 |
+
"step": 235
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.92,
|
342 |
+
"grad_norm": 1.0628710985183716,
|
343 |
+
"learning_rate": 1.5888529698718346e-06,
|
344 |
+
"loss": 0.5965,
|
345 |
+
"step": 240
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.94,
|
349 |
+
"grad_norm": 0.6802533268928528,
|
350 |
+
"learning_rate": 9.243915182039431e-07,
|
351 |
+
"loss": 0.542,
|
352 |
+
"step": 245
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.96,
|
356 |
+
"grad_norm": 2.282472610473633,
|
357 |
+
"learning_rate": 4.376324859820924e-07,
|
358 |
+
"loss": 0.5677,
|
359 |
+
"step": 250
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.98,
|
363 |
+
"grad_norm": 2.717949628829956,
|
364 |
+
"learning_rate": 1.3033842410251075e-07,
|
365 |
+
"loss": 0.4775,
|
366 |
+
"step": 255
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.99,
|
370 |
+
"grad_norm": 1.769280195236206,
|
371 |
+
"learning_rate": 3.622042116169233e-09,
|
372 |
+
"loss": 0.6862,
|
373 |
+
"step": 260
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 1.0,
|
377 |
+
"step": 261,
|
378 |
+
"total_flos": 3.809983450683802e+16,
|
379 |
+
"train_loss": 0.6279083029063726,
|
380 |
+
"train_runtime": 203702.1714,
|
381 |
+
"train_samples_per_second": 0.01,
|
382 |
+
"train_steps_per_second": 0.001
|
383 |
+
}
|
384 |
+
],
|
385 |
+
"logging_steps": 5,
|
386 |
+
"max_steps": 261,
|
387 |
+
"num_input_tokens_seen": 0,
|
388 |
+
"num_train_epochs": 1,
|
389 |
+
"save_steps": 100,
|
390 |
+
"total_flos": 3.809983450683802e+16,
|
391 |
+
"train_batch_size": 1,
|
392 |
+
"trial_name": null,
|
393 |
+
"trial_params": null
|
394 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf8955447713682dea96b55ed6553542f208fe798191ff47e302b2670f37f689
|
3 |
+
size 5112
|