Upload folder using huggingface_hub
Browse files- added_tokens.json +5 -0
- config.json +44 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +14 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- trainer_state.json +614 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Qwen/Qwen1.5-0.5B",
|
3 |
+
"architectures": [
|
4 |
+
"Qwen2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 151643,
|
8 |
+
"eos_token_id": 151643,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 1024,
|
11 |
+
"id2label": {
|
12 |
+
"0": "LABEL_0",
|
13 |
+
"1": "LABEL_1",
|
14 |
+
"2": "LABEL_2",
|
15 |
+
"3": "LABEL_3",
|
16 |
+
"4": "LABEL_4"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 2816,
|
20 |
+
"label2id": {
|
21 |
+
"LABEL_0": 0,
|
22 |
+
"LABEL_1": 1,
|
23 |
+
"LABEL_2": 2,
|
24 |
+
"LABEL_3": 3,
|
25 |
+
"LABEL_4": 4
|
26 |
+
},
|
27 |
+
"max_position_embeddings": 32768,
|
28 |
+
"max_window_layers": 21,
|
29 |
+
"model_type": "qwen2",
|
30 |
+
"num_attention_heads": 16,
|
31 |
+
"num_hidden_layers": 24,
|
32 |
+
"num_key_value_heads": 16,
|
33 |
+
"pad_token_id": 151643,
|
34 |
+
"problem_type": "single_label_classification",
|
35 |
+
"rms_norm_eps": 1e-06,
|
36 |
+
"rope_theta": 1000000.0,
|
37 |
+
"sliding_window": 32768,
|
38 |
+
"tie_word_embeddings": true,
|
39 |
+
"torch_dtype": "float32",
|
40 |
+
"transformers_version": "4.41.0",
|
41 |
+
"use_cache": true,
|
42 |
+
"use_sliding_window": false,
|
43 |
+
"vocab_size": 151936
|
44 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0462ee8274d9aab1297d68d7363e40940d90fd274cb2679c4790fdf4371f2808
|
3 |
+
size 1856004208
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6003ccee3fe43b2399026d95d5e6ba88a4b9aed79c91727d80210aecd67d195a
|
3 |
+
size 3712186874
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:13f452dd1f8e3ff166bd59d76a8c9a30be31a419255a241e157b8d598d37cfe0
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|endoftext|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": "<|endoftext|>"
|
14 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|endoftext|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 32768,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,614 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.217500628614534,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 41500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.06286145335680161,
|
13 |
+
"grad_norm": 2.0346406017779373e-06,
|
14 |
+
"learning_rate": 1.9820395847551996e-05,
|
15 |
+
"loss": 0.1532,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.12572290671360323,
|
20 |
+
"grad_norm": 3.3444328437326476e-05,
|
21 |
+
"learning_rate": 1.9640791695103994e-05,
|
22 |
+
"loss": 0.116,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.18858436007040483,
|
27 |
+
"grad_norm": 0.05133463069796562,
|
28 |
+
"learning_rate": 1.9461187542655988e-05,
|
29 |
+
"loss": 0.0844,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.25144581342720645,
|
34 |
+
"grad_norm": 6.244395626708865e-05,
|
35 |
+
"learning_rate": 1.9281583390207982e-05,
|
36 |
+
"loss": 0.0183,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.31430726678400805,
|
41 |
+
"grad_norm": 2.1667106011591386e-06,
|
42 |
+
"learning_rate": 1.9101979237759977e-05,
|
43 |
+
"loss": 0.0422,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.37716872014080965,
|
48 |
+
"grad_norm": 0.003454663557931781,
|
49 |
+
"learning_rate": 1.8922375085311975e-05,
|
50 |
+
"loss": 0.0682,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.44003017349761125,
|
55 |
+
"grad_norm": 9.719051740830764e-05,
|
56 |
+
"learning_rate": 1.874277093286397e-05,
|
57 |
+
"loss": 0.0394,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.5028916268544129,
|
62 |
+
"grad_norm": 557.3906860351562,
|
63 |
+
"learning_rate": 1.8563166780415963e-05,
|
64 |
+
"loss": 0.0471,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.5657530802112145,
|
69 |
+
"grad_norm": 0.07539618015289307,
|
70 |
+
"learning_rate": 1.8383562627967958e-05,
|
71 |
+
"loss": 0.018,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.6286145335680161,
|
76 |
+
"grad_norm": 0.0003254573093727231,
|
77 |
+
"learning_rate": 1.8203958475519955e-05,
|
78 |
+
"loss": 0.0369,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.6914759869248177,
|
83 |
+
"grad_norm": 2.24390605580993e-05,
|
84 |
+
"learning_rate": 1.802435432307195e-05,
|
85 |
+
"loss": 0.0571,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.7543374402816193,
|
90 |
+
"grad_norm": 1.3767588825430721e-05,
|
91 |
+
"learning_rate": 1.7844750170623944e-05,
|
92 |
+
"loss": 0.0391,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.8171988936384209,
|
97 |
+
"grad_norm": 0.004321901593357325,
|
98 |
+
"learning_rate": 1.7665146018175942e-05,
|
99 |
+
"loss": 0.0186,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.8800603469952225,
|
104 |
+
"grad_norm": 2.2530954083777033e-05,
|
105 |
+
"learning_rate": 1.7485541865727936e-05,
|
106 |
+
"loss": 0.0138,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9429218003520241,
|
111 |
+
"grad_norm": 0.001634115818887949,
|
112 |
+
"learning_rate": 1.7305937713279934e-05,
|
113 |
+
"loss": 0.0164,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.0057832537088258,
|
118 |
+
"grad_norm": 3.9654673855693545e-06,
|
119 |
+
"learning_rate": 1.7126333560831928e-05,
|
120 |
+
"loss": 0.0266,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.0686447070656273,
|
125 |
+
"grad_norm": 1.5307747389670112e-06,
|
126 |
+
"learning_rate": 1.6946729408383923e-05,
|
127 |
+
"loss": 0.0064,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.131506160422429,
|
132 |
+
"grad_norm": 0.004159221425652504,
|
133 |
+
"learning_rate": 1.676712525593592e-05,
|
134 |
+
"loss": 0.0376,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.1943676137792305,
|
139 |
+
"grad_norm": 0.0006104345084168017,
|
140 |
+
"learning_rate": 1.6587521103487915e-05,
|
141 |
+
"loss": 0.0346,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.2572290671360322,
|
146 |
+
"grad_norm": 4.2246105294907466e-05,
|
147 |
+
"learning_rate": 1.640791695103991e-05,
|
148 |
+
"loss": 0.0219,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.3200905204928337,
|
153 |
+
"grad_norm": 4.186299065622734e-06,
|
154 |
+
"learning_rate": 1.6228312798591907e-05,
|
155 |
+
"loss": 0.0135,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 1.3829519738496354,
|
160 |
+
"grad_norm": 0.00025950674898922443,
|
161 |
+
"learning_rate": 1.60487086461439e-05,
|
162 |
+
"loss": 0.0324,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.4458134272064371,
|
167 |
+
"grad_norm": 5.111323480377905e-05,
|
168 |
+
"learning_rate": 1.5869104493695896e-05,
|
169 |
+
"loss": 0.0221,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.5086748805632386,
|
174 |
+
"grad_norm": 0.0006640023784711957,
|
175 |
+
"learning_rate": 1.5689500341247893e-05,
|
176 |
+
"loss": 0.019,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 1.57153633392004,
|
181 |
+
"grad_norm": 5.866236278961878e-06,
|
182 |
+
"learning_rate": 1.5509896188799888e-05,
|
183 |
+
"loss": 0.0243,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 1.6343977872768418,
|
188 |
+
"grad_norm": 5.0747665227390826e-05,
|
189 |
+
"learning_rate": 1.5330292036351882e-05,
|
190 |
+
"loss": 0.0199,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 1.6972592406336435,
|
195 |
+
"grad_norm": 0.0017497913213446736,
|
196 |
+
"learning_rate": 1.5150687883903876e-05,
|
197 |
+
"loss": 0.0142,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 1.760120693990445,
|
202 |
+
"grad_norm": 4.546816853689961e-05,
|
203 |
+
"learning_rate": 1.4971083731455874e-05,
|
204 |
+
"loss": 0.0336,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 1.8229821473472465,
|
209 |
+
"grad_norm": 0.005370904225856066,
|
210 |
+
"learning_rate": 1.4791479579007868e-05,
|
211 |
+
"loss": 0.0269,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.8858436007040482,
|
216 |
+
"grad_norm": 0.0037405244074761868,
|
217 |
+
"learning_rate": 1.4611875426559863e-05,
|
218 |
+
"loss": 0.009,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.94870505406085,
|
223 |
+
"grad_norm": 0.003770838025957346,
|
224 |
+
"learning_rate": 1.4432271274111857e-05,
|
225 |
+
"loss": 0.0115,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 2.0115665074176516,
|
230 |
+
"grad_norm": 0.10231239348649979,
|
231 |
+
"learning_rate": 1.4252667121663855e-05,
|
232 |
+
"loss": 0.0155,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.074427960774453,
|
237 |
+
"grad_norm": 0.00043545279186218977,
|
238 |
+
"learning_rate": 1.407306296921585e-05,
|
239 |
+
"loss": 0.0161,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 2.1372894141312546,
|
244 |
+
"grad_norm": 0.0013906797394156456,
|
245 |
+
"learning_rate": 1.3893458816767844e-05,
|
246 |
+
"loss": 0.0111,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 2.2001508674880563,
|
251 |
+
"grad_norm": 0.03360624238848686,
|
252 |
+
"learning_rate": 1.3713854664319841e-05,
|
253 |
+
"loss": 0.0043,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.263012320844858,
|
258 |
+
"grad_norm": 2.512960600142833e-05,
|
259 |
+
"learning_rate": 1.3534250511871836e-05,
|
260 |
+
"loss": 0.0075,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 2.3258737742016597,
|
265 |
+
"grad_norm": 0.0004499895148910582,
|
266 |
+
"learning_rate": 1.335464635942383e-05,
|
267 |
+
"loss": 0.0021,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 2.388735227558461,
|
272 |
+
"grad_norm": 0.00035007469705305994,
|
273 |
+
"learning_rate": 1.3175042206975826e-05,
|
274 |
+
"loss": 0.0093,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 2.4515966809152627,
|
279 |
+
"grad_norm": 0.001043146476149559,
|
280 |
+
"learning_rate": 1.2995438054527822e-05,
|
281 |
+
"loss": 0.0098,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 2.5144581342720644,
|
286 |
+
"grad_norm": 0.0009557796292938292,
|
287 |
+
"learning_rate": 1.2815833902079816e-05,
|
288 |
+
"loss": 0.0111,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 2.5773195876288657,
|
293 |
+
"grad_norm": 0.00020876774215139449,
|
294 |
+
"learning_rate": 1.2636229749631813e-05,
|
295 |
+
"loss": 0.0,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.6401810409856674,
|
300 |
+
"grad_norm": 0.00011447193537605926,
|
301 |
+
"learning_rate": 1.2456625597183807e-05,
|
302 |
+
"loss": 0.0119,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 2.703042494342469,
|
307 |
+
"grad_norm": 0.00028604810358956456,
|
308 |
+
"learning_rate": 1.2277021444735805e-05,
|
309 |
+
"loss": 0.0112,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 2.765903947699271,
|
314 |
+
"grad_norm": 2.5067993192351423e-05,
|
315 |
+
"learning_rate": 1.2097417292287799e-05,
|
316 |
+
"loss": 0.0094,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 2.8287654010560725,
|
321 |
+
"grad_norm": 0.00034995036548934877,
|
322 |
+
"learning_rate": 1.1917813139839793e-05,
|
323 |
+
"loss": 0.0088,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 2.8916268544128743,
|
328 |
+
"grad_norm": 1.091743524739286e-05,
|
329 |
+
"learning_rate": 1.1738208987391791e-05,
|
330 |
+
"loss": 0.0,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 2.9544883077696755,
|
335 |
+
"grad_norm": 0.00016331751248799264,
|
336 |
+
"learning_rate": 1.1558604834943785e-05,
|
337 |
+
"loss": 0.0161,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.0173497611264772,
|
342 |
+
"grad_norm": 4.763499600812793e-05,
|
343 |
+
"learning_rate": 1.137900068249578e-05,
|
344 |
+
"loss": 0.005,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 3.080211214483279,
|
349 |
+
"grad_norm": 0.00027739102370105684,
|
350 |
+
"learning_rate": 1.1199396530047774e-05,
|
351 |
+
"loss": 0.008,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 3.1430726678400807,
|
356 |
+
"grad_norm": 0.001488861278630793,
|
357 |
+
"learning_rate": 1.1019792377599772e-05,
|
358 |
+
"loss": 0.0047,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 3.205934121196882,
|
363 |
+
"grad_norm": 0.00010821361502166837,
|
364 |
+
"learning_rate": 1.0840188225151766e-05,
|
365 |
+
"loss": 0.001,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 3.2687955745536836,
|
370 |
+
"grad_norm": 7.778286089887843e-05,
|
371 |
+
"learning_rate": 1.066058407270376e-05,
|
372 |
+
"loss": 0.006,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 3.3316570279104853,
|
377 |
+
"grad_norm": 0.003971356898546219,
|
378 |
+
"learning_rate": 1.0480979920255758e-05,
|
379 |
+
"loss": 0.0037,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 3.394518481267287,
|
384 |
+
"grad_norm": 0.0018279771320521832,
|
385 |
+
"learning_rate": 1.0301375767807753e-05,
|
386 |
+
"loss": 0.007,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 3.4573799346240883,
|
391 |
+
"grad_norm": 2.947276516351849e-05,
|
392 |
+
"learning_rate": 1.0121771615359747e-05,
|
393 |
+
"loss": 0.0033,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 3.52024138798089,
|
398 |
+
"grad_norm": 0.0054627698846161366,
|
399 |
+
"learning_rate": 9.942167462911743e-06,
|
400 |
+
"loss": 0.0029,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 3.5831028413376917,
|
405 |
+
"grad_norm": 6.94687114446424e-05,
|
406 |
+
"learning_rate": 9.762563310463739e-06,
|
407 |
+
"loss": 0.0023,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 3.6459642946944935,
|
412 |
+
"grad_norm": 2.092416980303824e-05,
|
413 |
+
"learning_rate": 9.582959158015735e-06,
|
414 |
+
"loss": 0.0043,
|
415 |
+
"step": 29000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 3.7088257480512947,
|
419 |
+
"grad_norm": 0.00010166186257265508,
|
420 |
+
"learning_rate": 9.40335500556773e-06,
|
421 |
+
"loss": 0.0067,
|
422 |
+
"step": 29500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 3.7716872014080964,
|
426 |
+
"grad_norm": 2.6766716473503038e-05,
|
427 |
+
"learning_rate": 9.223750853119726e-06,
|
428 |
+
"loss": 0.0052,
|
429 |
+
"step": 30000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 3.834548654764898,
|
433 |
+
"grad_norm": 2.3570633857161738e-05,
|
434 |
+
"learning_rate": 9.04414670067172e-06,
|
435 |
+
"loss": 0.0026,
|
436 |
+
"step": 30500
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 3.8974101081217,
|
440 |
+
"grad_norm": 0.00028839215519838035,
|
441 |
+
"learning_rate": 8.864542548223716e-06,
|
442 |
+
"loss": 0.015,
|
443 |
+
"step": 31000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 3.9602715614785016,
|
447 |
+
"grad_norm": 5.503819693331025e-07,
|
448 |
+
"learning_rate": 8.68493839577571e-06,
|
449 |
+
"loss": 0.0032,
|
450 |
+
"step": 31500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 4.023133014835303,
|
454 |
+
"grad_norm": 0.019892163574695587,
|
455 |
+
"learning_rate": 8.505334243327706e-06,
|
456 |
+
"loss": 0.0068,
|
457 |
+
"step": 32000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 4.085994468192105,
|
461 |
+
"grad_norm": 9.153469727607444e-05,
|
462 |
+
"learning_rate": 8.325730090879702e-06,
|
463 |
+
"loss": 0.0047,
|
464 |
+
"step": 32500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 4.148855921548906,
|
468 |
+
"grad_norm": 0.0040658023208379745,
|
469 |
+
"learning_rate": 8.146125938431697e-06,
|
470 |
+
"loss": 0.0019,
|
471 |
+
"step": 33000
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 4.2117173749057075,
|
475 |
+
"grad_norm": 2.282762579852715e-05,
|
476 |
+
"learning_rate": 7.966521785983693e-06,
|
477 |
+
"loss": 0.0035,
|
478 |
+
"step": 33500
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 4.274578828262509,
|
482 |
+
"grad_norm": 5.513780706678517e-06,
|
483 |
+
"learning_rate": 7.786917633535687e-06,
|
484 |
+
"loss": 0.005,
|
485 |
+
"step": 34000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 4.337440281619311,
|
489 |
+
"grad_norm": 0.008914977312088013,
|
490 |
+
"learning_rate": 7.607313481087683e-06,
|
491 |
+
"loss": 0.0045,
|
492 |
+
"step": 34500
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 4.400301734976113,
|
496 |
+
"grad_norm": 6.84509941493161e-05,
|
497 |
+
"learning_rate": 7.4277093286396784e-06,
|
498 |
+
"loss": 0.0003,
|
499 |
+
"step": 35000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 4.463163188332914,
|
503 |
+
"grad_norm": 1.599622737558093e-05,
|
504 |
+
"learning_rate": 7.2481051761916745e-06,
|
505 |
+
"loss": 0.0,
|
506 |
+
"step": 35500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 4.526024641689716,
|
510 |
+
"grad_norm": 1.801977305149194e-05,
|
511 |
+
"learning_rate": 7.068501023743669e-06,
|
512 |
+
"loss": 0.0,
|
513 |
+
"step": 36000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 4.588886095046518,
|
517 |
+
"grad_norm": 1.085722124116728e-05,
|
518 |
+
"learning_rate": 6.888896871295665e-06,
|
519 |
+
"loss": 0.0044,
|
520 |
+
"step": 36500
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 4.6517475484033195,
|
524 |
+
"grad_norm": 2.5041081244125962e-05,
|
525 |
+
"learning_rate": 6.70929271884766e-06,
|
526 |
+
"loss": 0.0087,
|
527 |
+
"step": 37000
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 4.71460900176012,
|
531 |
+
"grad_norm": 0.0013843434862792492,
|
532 |
+
"learning_rate": 6.529688566399655e-06,
|
533 |
+
"loss": 0.0052,
|
534 |
+
"step": 37500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 4.777470455116922,
|
538 |
+
"grad_norm": 0.00015471581718884408,
|
539 |
+
"learning_rate": 6.350084413951651e-06,
|
540 |
+
"loss": 0.0015,
|
541 |
+
"step": 38000
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 4.840331908473724,
|
545 |
+
"grad_norm": 0.00010056547034764662,
|
546 |
+
"learning_rate": 6.1704802615036465e-06,
|
547 |
+
"loss": 0.0001,
|
548 |
+
"step": 38500
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 4.9031933618305255,
|
552 |
+
"grad_norm": 2.1669136913260445e-05,
|
553 |
+
"learning_rate": 5.990876109055643e-06,
|
554 |
+
"loss": 0.0,
|
555 |
+
"step": 39000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 4.966054815187327,
|
559 |
+
"grad_norm": 3.164667577948421e-05,
|
560 |
+
"learning_rate": 5.811271956607637e-06,
|
561 |
+
"loss": 0.0,
|
562 |
+
"step": 39500
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 5.028916268544129,
|
566 |
+
"grad_norm": 3.5525452403817326e-05,
|
567 |
+
"learning_rate": 5.631667804159633e-06,
|
568 |
+
"loss": 0.0,
|
569 |
+
"step": 40000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 5.091777721900931,
|
573 |
+
"grad_norm": 1.85646513273241e-05,
|
574 |
+
"learning_rate": 5.452063651711627e-06,
|
575 |
+
"loss": 0.0,
|
576 |
+
"step": 40500
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 5.154639175257732,
|
580 |
+
"grad_norm": 1.2565506040118635e-05,
|
581 |
+
"learning_rate": 5.272459499263623e-06,
|
582 |
+
"loss": 0.0,
|
583 |
+
"step": 41000
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 5.217500628614534,
|
587 |
+
"grad_norm": 3.7605339002766414e-06,
|
588 |
+
"learning_rate": 5.092855346815619e-06,
|
589 |
+
"loss": 0.0,
|
590 |
+
"step": 41500
|
591 |
+
}
|
592 |
+
],
|
593 |
+
"logging_steps": 500,
|
594 |
+
"max_steps": 55678,
|
595 |
+
"num_input_tokens_seen": 0,
|
596 |
+
"num_train_epochs": 7,
|
597 |
+
"save_steps": 500,
|
598 |
+
"stateful_callbacks": {
|
599 |
+
"TrainerControl": {
|
600 |
+
"args": {
|
601 |
+
"should_epoch_stop": false,
|
602 |
+
"should_evaluate": false,
|
603 |
+
"should_log": false,
|
604 |
+
"should_save": true,
|
605 |
+
"should_training_stop": false
|
606 |
+
},
|
607 |
+
"attributes": {}
|
608 |
+
}
|
609 |
+
},
|
610 |
+
"total_flos": 2.3565764455911014e+17,
|
611 |
+
"train_batch_size": 6,
|
612 |
+
"trial_name": null,
|
613 |
+
"trial_params": null
|
614 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:415ba9208ec02de9364b44e3499014dd8bea5b9cbf75e732e4a58d5767df9fa8
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|