Upload 12 files
Browse files- added_tokens.json +4 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer_config.json +38 -0
- trainer_state.json +600 -0
- training_args.bin +3 -0
- vocab.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|pad|>": 50258,
|
3 |
+
"<|startoftext|>": 50257
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hidude562/OpenMusenet-2.11-3M",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 128,
|
15 |
+
"n_embd": 64,
|
16 |
+
"n_head": 8,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 6,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.41.2",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50259
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.41.2"
|
6 |
+
}
|
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:fd320b1a325a6e1829cc07c68280ac8663b3636ebc3663d09f06285007113608
|
3 |
+
size 14335776
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5840ee5e44814d018ec698db4d0fc87a06dd062bef49906bb14bacb9804ccebe
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76ae6ade3e120f66721d39d1b02e598af5c4d6c964414d7265bfef637900aa7b
|
3 |
+
size 1064
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": "<|pad|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<|startoftext|>",
|
31 |
+
"clean_up_tokenization_spaces": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 1024,
|
35 |
+
"pad_token": "<|pad|>",
|
36 |
+
"tokenizer_class": "GPT2Tokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,600 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9977335435553804,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 40500,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.012317698068584943,
|
13 |
+
"grad_norm": 2.049720048904419,
|
14 |
+
"learning_rate": 4.938534686637761e-05,
|
15 |
+
"loss": 1.4868,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.024635396137169887,
|
20 |
+
"grad_norm": 1.9058018922805786,
|
21 |
+
"learning_rate": 4.8769461962948364e-05,
|
22 |
+
"loss": 1.1702,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.03695309420575483,
|
27 |
+
"grad_norm": 1.4330534934997559,
|
28 |
+
"learning_rate": 4.815357705951912e-05,
|
29 |
+
"loss": 1.0684,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.049270792274339774,
|
34 |
+
"grad_norm": 2.9333412647247314,
|
35 |
+
"learning_rate": 4.753769215608987e-05,
|
36 |
+
"loss": 1.0331,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.06158849034292471,
|
41 |
+
"grad_norm": 1.674055576324463,
|
42 |
+
"learning_rate": 4.6921807252660625e-05,
|
43 |
+
"loss": 1.0139,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.07390618841150966,
|
48 |
+
"grad_norm": 1.7064428329467773,
|
49 |
+
"learning_rate": 4.630592234923138e-05,
|
50 |
+
"loss": 0.987,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0862238864800946,
|
55 |
+
"grad_norm": 1.4718812704086304,
|
56 |
+
"learning_rate": 4.569003744580213e-05,
|
57 |
+
"loss": 0.9881,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.09854158454867955,
|
62 |
+
"grad_norm": 1.326068639755249,
|
63 |
+
"learning_rate": 4.507415254237288e-05,
|
64 |
+
"loss": 0.9511,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.11085928261726448,
|
69 |
+
"grad_norm": 1.724241852760315,
|
70 |
+
"learning_rate": 4.4458267638943634e-05,
|
71 |
+
"loss": 0.952,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.12317698068584942,
|
76 |
+
"grad_norm": 0.20040610432624817,
|
77 |
+
"learning_rate": 4.384361450532125e-05,
|
78 |
+
"loss": 0.9575,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.13549467875443438,
|
83 |
+
"grad_norm": 1.6827597618103027,
|
84 |
+
"learning_rate": 4.3227729601892e-05,
|
85 |
+
"loss": 0.9589,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.14781237682301931,
|
90 |
+
"grad_norm": 0.9528223276138306,
|
91 |
+
"learning_rate": 4.2611844698462756e-05,
|
92 |
+
"loss": 0.9464,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.16013007489160425,
|
97 |
+
"grad_norm": 1.1192400455474854,
|
98 |
+
"learning_rate": 4.199595979503351e-05,
|
99 |
+
"loss": 0.9395,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.1724477729601892,
|
104 |
+
"grad_norm": 1.5803415775299072,
|
105 |
+
"learning_rate": 4.138007489160426e-05,
|
106 |
+
"loss": 0.9376,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.18476547102877414,
|
111 |
+
"grad_norm": 1.0329970121383667,
|
112 |
+
"learning_rate": 4.076542175798187e-05,
|
113 |
+
"loss": 0.9247,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.1970831690973591,
|
118 |
+
"grad_norm": 1.0181173086166382,
|
119 |
+
"learning_rate": 4.014953685455262e-05,
|
120 |
+
"loss": 0.9469,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.20940086716594403,
|
125 |
+
"grad_norm": 0.837753176689148,
|
126 |
+
"learning_rate": 3.953365195112337e-05,
|
127 |
+
"loss": 0.9017,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.22171856523452896,
|
132 |
+
"grad_norm": 1.228780746459961,
|
133 |
+
"learning_rate": 3.891776704769413e-05,
|
134 |
+
"loss": 0.9006,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.23403626330311392,
|
139 |
+
"grad_norm": 1.6748690605163574,
|
140 |
+
"learning_rate": 3.830188214426488e-05,
|
141 |
+
"loss": 0.9312,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.24635396137169885,
|
146 |
+
"grad_norm": 2.5065925121307373,
|
147 |
+
"learning_rate": 3.7687229010642495e-05,
|
148 |
+
"loss": 0.9102,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.2586716594402838,
|
153 |
+
"grad_norm": 0.4429062008857727,
|
154 |
+
"learning_rate": 3.70725758770201e-05,
|
155 |
+
"loss": 0.9185,
|
156 |
+
"step": 10500
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.27098935750886877,
|
160 |
+
"grad_norm": 0.8518178462982178,
|
161 |
+
"learning_rate": 3.6456690973590856e-05,
|
162 |
+
"loss": 0.9158,
|
163 |
+
"step": 11000
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.28330705557745367,
|
167 |
+
"grad_norm": 1.952348232269287,
|
168 |
+
"learning_rate": 3.584080607016161e-05,
|
169 |
+
"loss": 0.8735,
|
170 |
+
"step": 11500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.29562475364603863,
|
174 |
+
"grad_norm": 0.9509502053260803,
|
175 |
+
"learning_rate": 3.5224921166732364e-05,
|
176 |
+
"loss": 0.8721,
|
177 |
+
"step": 12000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.3079424517146236,
|
181 |
+
"grad_norm": 0.9900819659233093,
|
182 |
+
"learning_rate": 3.460903626330311e-05,
|
183 |
+
"loss": 0.9015,
|
184 |
+
"step": 12500
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.3202601497832085,
|
188 |
+
"grad_norm": 1.6706575155258179,
|
189 |
+
"learning_rate": 3.399315135987387e-05,
|
190 |
+
"loss": 0.9053,
|
191 |
+
"step": 13000
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.33257784785179345,
|
195 |
+
"grad_norm": 2.245882272720337,
|
196 |
+
"learning_rate": 3.3377266456444625e-05,
|
197 |
+
"loss": 0.9008,
|
198 |
+
"step": 13500
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.3448955459203784,
|
202 |
+
"grad_norm": 1.2105801105499268,
|
203 |
+
"learning_rate": 3.276138155301537e-05,
|
204 |
+
"loss": 0.8859,
|
205 |
+
"step": 14000
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.35721324398896337,
|
209 |
+
"grad_norm": 1.136516809463501,
|
210 |
+
"learning_rate": 3.214672841939299e-05,
|
211 |
+
"loss": 0.8922,
|
212 |
+
"step": 14500
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.3695309420575483,
|
216 |
+
"grad_norm": 1.4451056718826294,
|
217 |
+
"learning_rate": 3.1530843515963734e-05,
|
218 |
+
"loss": 0.8907,
|
219 |
+
"step": 15000
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.38184864012613323,
|
223 |
+
"grad_norm": 0.8413623571395874,
|
224 |
+
"learning_rate": 3.091495861253449e-05,
|
225 |
+
"loss": 0.8929,
|
226 |
+
"step": 15500
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.3941663381947182,
|
230 |
+
"grad_norm": 1.7711334228515625,
|
231 |
+
"learning_rate": 3.029907370910524e-05,
|
232 |
+
"loss": 0.8792,
|
233 |
+
"step": 16000
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.4064840362633031,
|
237 |
+
"grad_norm": 1.3520532846450806,
|
238 |
+
"learning_rate": 2.9683188805676e-05,
|
239 |
+
"loss": 0.8809,
|
240 |
+
"step": 16500
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 0.41880173433188805,
|
244 |
+
"grad_norm": 1.8900405168533325,
|
245 |
+
"learning_rate": 2.906853567205361e-05,
|
246 |
+
"loss": 0.8834,
|
247 |
+
"step": 17000
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 0.431119432400473,
|
251 |
+
"grad_norm": 1.377387523651123,
|
252 |
+
"learning_rate": 2.845265076862436e-05,
|
253 |
+
"loss": 0.8902,
|
254 |
+
"step": 17500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.4434371304690579,
|
258 |
+
"grad_norm": 1.2132008075714111,
|
259 |
+
"learning_rate": 2.7836765865195114e-05,
|
260 |
+
"loss": 0.8607,
|
261 |
+
"step": 18000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.4557548285376429,
|
265 |
+
"grad_norm": 0.94814532995224,
|
266 |
+
"learning_rate": 2.7220880961765865e-05,
|
267 |
+
"loss": 0.88,
|
268 |
+
"step": 18500
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 0.46807252660622783,
|
272 |
+
"grad_norm": 0.8629463315010071,
|
273 |
+
"learning_rate": 2.6606227828143476e-05,
|
274 |
+
"loss": 0.8609,
|
275 |
+
"step": 19000
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 0.4803902246748128,
|
279 |
+
"grad_norm": 1.1995203495025635,
|
280 |
+
"learning_rate": 2.599034292471423e-05,
|
281 |
+
"loss": 0.8778,
|
282 |
+
"step": 19500
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.4927079227433977,
|
286 |
+
"grad_norm": 1.2757550477981567,
|
287 |
+
"learning_rate": 2.5374458021284987e-05,
|
288 |
+
"loss": 0.853,
|
289 |
+
"step": 20000
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.5050256208119827,
|
293 |
+
"grad_norm": 1.4950288534164429,
|
294 |
+
"learning_rate": 2.4758573117855734e-05,
|
295 |
+
"loss": 0.8688,
|
296 |
+
"step": 20500
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 0.5173433188805676,
|
300 |
+
"grad_norm": 0.997870147228241,
|
301 |
+
"learning_rate": 2.4143919984233348e-05,
|
302 |
+
"loss": 0.8738,
|
303 |
+
"step": 21000
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.5296610169491526,
|
307 |
+
"grad_norm": 1.2419720888137817,
|
308 |
+
"learning_rate": 2.3528035080804102e-05,
|
309 |
+
"loss": 0.8929,
|
310 |
+
"step": 21500
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 0.5419787150177375,
|
314 |
+
"grad_norm": 1.197637915611267,
|
315 |
+
"learning_rate": 2.2912150177374853e-05,
|
316 |
+
"loss": 0.8848,
|
317 |
+
"step": 22000
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 0.5542964130863224,
|
321 |
+
"grad_norm": 1.501338005065918,
|
322 |
+
"learning_rate": 2.2296265273945606e-05,
|
323 |
+
"loss": 0.8543,
|
324 |
+
"step": 22500
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 0.5666141111549073,
|
328 |
+
"grad_norm": 1.2377902269363403,
|
329 |
+
"learning_rate": 2.1681612140323217e-05,
|
330 |
+
"loss": 0.8402,
|
331 |
+
"step": 23000
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.5789318092234923,
|
335 |
+
"grad_norm": 0.6151154637336731,
|
336 |
+
"learning_rate": 2.106572723689397e-05,
|
337 |
+
"loss": 0.872,
|
338 |
+
"step": 23500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.5912495072920773,
|
342 |
+
"grad_norm": 0.8272470235824585,
|
343 |
+
"learning_rate": 2.044984233346472e-05,
|
344 |
+
"loss": 0.8524,
|
345 |
+
"step": 24000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.6035672053606622,
|
349 |
+
"grad_norm": 1.718947410583496,
|
350 |
+
"learning_rate": 1.9833957430035476e-05,
|
351 |
+
"loss": 0.8404,
|
352 |
+
"step": 24500
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 0.6158849034292472,
|
356 |
+
"grad_norm": 1.5924681425094604,
|
357 |
+
"learning_rate": 1.921807252660623e-05,
|
358 |
+
"loss": 0.868,
|
359 |
+
"step": 25000
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 0.6282026014978321,
|
363 |
+
"grad_norm": 1.3491289615631104,
|
364 |
+
"learning_rate": 1.860341939298384e-05,
|
365 |
+
"loss": 0.8521,
|
366 |
+
"step": 25500
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 0.640520299566417,
|
370 |
+
"grad_norm": 1.2171722650527954,
|
371 |
+
"learning_rate": 1.798753448955459e-05,
|
372 |
+
"loss": 0.8312,
|
373 |
+
"step": 26000
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.6528379976350019,
|
377 |
+
"grad_norm": 1.0879688262939453,
|
378 |
+
"learning_rate": 1.7371649586125348e-05,
|
379 |
+
"loss": 0.8471,
|
380 |
+
"step": 26500
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 0.6651556957035869,
|
384 |
+
"grad_norm": 0.9785297513008118,
|
385 |
+
"learning_rate": 1.67557646826961e-05,
|
386 |
+
"loss": 0.8571,
|
387 |
+
"step": 27000
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.6774733937721719,
|
391 |
+
"grad_norm": 2.27364444732666,
|
392 |
+
"learning_rate": 1.614111154907371e-05,
|
393 |
+
"loss": 0.8548,
|
394 |
+
"step": 27500
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.6897910918407568,
|
398 |
+
"grad_norm": 1.1297192573547363,
|
399 |
+
"learning_rate": 1.552645841545132e-05,
|
400 |
+
"loss": 0.8662,
|
401 |
+
"step": 28000
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 0.7021087899093418,
|
405 |
+
"grad_norm": 1.4344604015350342,
|
406 |
+
"learning_rate": 1.4910573512022074e-05,
|
407 |
+
"loss": 0.8609,
|
408 |
+
"step": 28500
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 0.7144264879779267,
|
412 |
+
"grad_norm": 0.8162903189659119,
|
413 |
+
"learning_rate": 1.4294688608592826e-05,
|
414 |
+
"loss": 0.8519,
|
415 |
+
"step": 29000
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 0.7267441860465116,
|
419 |
+
"grad_norm": 1.4598755836486816,
|
420 |
+
"learning_rate": 1.3678803705163579e-05,
|
421 |
+
"loss": 0.8376,
|
422 |
+
"step": 29500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 0.7390618841150965,
|
426 |
+
"grad_norm": 0.9850552082061768,
|
427 |
+
"learning_rate": 1.3062918801734334e-05,
|
428 |
+
"loss": 0.842,
|
429 |
+
"step": 30000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.7513795821836815,
|
433 |
+
"grad_norm": 1.2781943082809448,
|
434 |
+
"learning_rate": 1.2447033898305085e-05,
|
435 |
+
"loss": 0.8539,
|
436 |
+
"step": 30500
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 0.7636972802522665,
|
440 |
+
"grad_norm": 0.9877688884735107,
|
441 |
+
"learning_rate": 1.1831148994875837e-05,
|
442 |
+
"loss": 0.8439,
|
443 |
+
"step": 31000
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 0.7760149783208514,
|
447 |
+
"grad_norm": 1.0702171325683594,
|
448 |
+
"learning_rate": 1.121526409144659e-05,
|
449 |
+
"loss": 0.8492,
|
450 |
+
"step": 31500
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.7883326763894364,
|
454 |
+
"grad_norm": 1.0662543773651123,
|
455 |
+
"learning_rate": 1.0600610957824203e-05,
|
456 |
+
"loss": 0.8572,
|
457 |
+
"step": 32000
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 0.8006503744580212,
|
461 |
+
"grad_norm": 1.029024600982666,
|
462 |
+
"learning_rate": 9.985957824201814e-06,
|
463 |
+
"loss": 0.8347,
|
464 |
+
"step": 32500
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 0.8129680725266062,
|
468 |
+
"grad_norm": 0.965148389339447,
|
469 |
+
"learning_rate": 9.370072920772566e-06,
|
470 |
+
"loss": 0.8408,
|
471 |
+
"step": 33000
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.8252857705951911,
|
475 |
+
"grad_norm": 1.441133975982666,
|
476 |
+
"learning_rate": 8.754188017343319e-06,
|
477 |
+
"loss": 0.8385,
|
478 |
+
"step": 33500
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 0.8376034686637761,
|
482 |
+
"grad_norm": 1.6267979145050049,
|
483 |
+
"learning_rate": 8.138303113914072e-06,
|
484 |
+
"loss": 0.8426,
|
485 |
+
"step": 34000
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 0.8499211667323611,
|
489 |
+
"grad_norm": 1.0745171308517456,
|
490 |
+
"learning_rate": 7.522418210484825e-06,
|
491 |
+
"loss": 0.8509,
|
492 |
+
"step": 34500
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 0.862238864800946,
|
496 |
+
"grad_norm": 1.2497833967208862,
|
497 |
+
"learning_rate": 6.906533307055578e-06,
|
498 |
+
"loss": 0.868,
|
499 |
+
"step": 35000
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 0.874556562869531,
|
503 |
+
"grad_norm": 1.1674834489822388,
|
504 |
+
"learning_rate": 6.2918801734331886e-06,
|
505 |
+
"loss": 0.8548,
|
506 |
+
"step": 35500
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.8868742609381158,
|
510 |
+
"grad_norm": 1.369992733001709,
|
511 |
+
"learning_rate": 5.6759952700039425e-06,
|
512 |
+
"loss": 0.8662,
|
513 |
+
"step": 36000
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.8991919590067008,
|
517 |
+
"grad_norm": 2.269826889038086,
|
518 |
+
"learning_rate": 5.060110366574695e-06,
|
519 |
+
"loss": 0.8518,
|
520 |
+
"step": 36500
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 0.9115096570752858,
|
524 |
+
"grad_norm": 1.3908036947250366,
|
525 |
+
"learning_rate": 4.444225463145448e-06,
|
526 |
+
"loss": 0.8583,
|
527 |
+
"step": 37000
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.9238273551438707,
|
531 |
+
"grad_norm": 0.907351553440094,
|
532 |
+
"learning_rate": 3.8283405597162e-06,
|
533 |
+
"loss": 0.8568,
|
534 |
+
"step": 37500
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 0.9361450532124557,
|
538 |
+
"grad_norm": 1.2205787897109985,
|
539 |
+
"learning_rate": 3.2124556562869534e-06,
|
540 |
+
"loss": 0.86,
|
541 |
+
"step": 38000
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 0.9484627512810406,
|
545 |
+
"grad_norm": 0.8388875722885132,
|
546 |
+
"learning_rate": 2.596570752857706e-06,
|
547 |
+
"loss": 0.8228,
|
548 |
+
"step": 38500
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 0.9607804493496256,
|
552 |
+
"grad_norm": 1.2039369344711304,
|
553 |
+
"learning_rate": 1.980685849428459e-06,
|
554 |
+
"loss": 0.8462,
|
555 |
+
"step": 39000
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.9730981474182104,
|
559 |
+
"grad_norm": 1.1439008712768555,
|
560 |
+
"learning_rate": 1.3660327158060701e-06,
|
561 |
+
"loss": 0.8669,
|
562 |
+
"step": 39500
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.9854158454867954,
|
566 |
+
"grad_norm": 1.5806646347045898,
|
567 |
+
"learning_rate": 7.50147812376823e-07,
|
568 |
+
"loss": 0.8306,
|
569 |
+
"step": 40000
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.9977335435553804,
|
573 |
+
"grad_norm": 0.8370537757873535,
|
574 |
+
"learning_rate": 1.342629089475759e-07,
|
575 |
+
"loss": 0.8485,
|
576 |
+
"step": 40500
|
577 |
+
}
|
578 |
+
],
|
579 |
+
"logging_steps": 500,
|
580 |
+
"max_steps": 40592,
|
581 |
+
"num_input_tokens_seen": 0,
|
582 |
+
"num_train_epochs": 1,
|
583 |
+
"save_steps": 500,
|
584 |
+
"stateful_callbacks": {
|
585 |
+
"TrainerControl": {
|
586 |
+
"args": {
|
587 |
+
"should_epoch_stop": false,
|
588 |
+
"should_evaluate": false,
|
589 |
+
"should_log": false,
|
590 |
+
"should_save": true,
|
591 |
+
"should_training_stop": false
|
592 |
+
},
|
593 |
+
"attributes": {}
|
594 |
+
}
|
595 |
+
},
|
596 |
+
"total_flos": 74657562624000.0,
|
597 |
+
"train_batch_size": 1,
|
598 |
+
"trial_name": null,
|
599 |
+
"trial_params": null
|
600 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee7f2ff58aa9d77ebddf572edfd330081a38bf2c16caaac7d474b17edcb68d67
|
3 |
+
size 5048
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|