demo
Browse files- result/checkpoint-11000/config.json +39 -0
- result/checkpoint-11000/generation_config.json +6 -0
- result/checkpoint-11000/optimizer.pt +3 -0
- result/checkpoint-11000/pytorch_model.bin +3 -0
- result/checkpoint-11000/rng_state.pth +3 -0
- result/checkpoint-11000/scheduler.pt +3 -0
- result/checkpoint-11000/trainer_state.json +151 -0
- result/checkpoint-11000/training_args.bin +3 -0
- result/config.json +39 -0
- result/generation_config.json +6 -0
- result/merges.txt +0 -0
- result/pytorch_model.bin +3 -0
- result/runs/Nov16_01-48-04_TORRE/events.out.tfevents.1700110084.TORRE.21416.0 +3 -0
- result/special_tokens_map.json +23 -0
- result/tokenizer_config.json +33 -0
- result/training_args.bin +3 -0
- result/vocab.json +0 -0
result/checkpoint-11000/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
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": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
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": "4.32.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
result/checkpoint-11000/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": "4.32.1"
|
6 |
+
}
|
result/checkpoint-11000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb53b4edb6a9148dfbdadbc2a5958acac7ff6059de4a2f09e1afca8aa6eed2dc
|
3 |
+
size 995642298
|
result/checkpoint-11000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7018f6be6786a099c378974e4f271404d930527b91e7d184c5130a8aa4853116
|
3 |
+
size 497807706
|
result/checkpoint-11000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c576aec34ae3702913f1ca3fc1d7d4cd0e3c358330d30641fe4fccd044e8d51d
|
3 |
+
size 14244
|
result/checkpoint-11000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dff580832c0430c0915e35cfde00f7805082e4e645c55b1651180d8af4811177
|
3 |
+
size 1064
|
result/checkpoint-11000/trainer_state.json
ADDED
@@ -0,0 +1,151 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.801396769969446,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 11000,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.22,
|
13 |
+
"learning_rate": 4.7817546922741165e-05,
|
14 |
+
"loss": 4.0109,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.44,
|
19 |
+
"learning_rate": 4.563509384548232e-05,
|
20 |
+
"loss": 3.3335,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.65,
|
25 |
+
"learning_rate": 4.3452640768223485e-05,
|
26 |
+
"loss": 3.0906,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.87,
|
31 |
+
"learning_rate": 4.127018769096465e-05,
|
32 |
+
"loss": 2.9653,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.09,
|
37 |
+
"learning_rate": 3.9087734613705804e-05,
|
38 |
+
"loss": 2.855,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.31,
|
43 |
+
"learning_rate": 3.690528153644697e-05,
|
44 |
+
"loss": 2.764,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.53,
|
49 |
+
"learning_rate": 3.472282845918813e-05,
|
50 |
+
"loss": 2.7204,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.75,
|
55 |
+
"learning_rate": 3.2540375381929286e-05,
|
56 |
+
"loss": 2.6883,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 1.96,
|
61 |
+
"learning_rate": 3.035792230467045e-05,
|
62 |
+
"loss": 2.6503,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.18,
|
67 |
+
"learning_rate": 2.817546922741161e-05,
|
68 |
+
"loss": 2.5871,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.4,
|
73 |
+
"learning_rate": 2.5993016150152772e-05,
|
74 |
+
"loss": 2.5675,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 2.62,
|
79 |
+
"learning_rate": 2.3810563072893935e-05,
|
80 |
+
"loss": 2.5442,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 2.84,
|
85 |
+
"learning_rate": 2.1628109995635095e-05,
|
86 |
+
"loss": 2.5271,
|
87 |
+
"step": 6500
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.06,
|
91 |
+
"learning_rate": 1.9445656918376258e-05,
|
92 |
+
"loss": 2.4952,
|
93 |
+
"step": 7000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.27,
|
97 |
+
"learning_rate": 1.7263203841117417e-05,
|
98 |
+
"loss": 2.4653,
|
99 |
+
"step": 7500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 3.49,
|
103 |
+
"learning_rate": 1.5080750763858579e-05,
|
104 |
+
"loss": 2.4566,
|
105 |
+
"step": 8000
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 3.71,
|
109 |
+
"learning_rate": 1.2898297686599738e-05,
|
110 |
+
"loss": 2.4551,
|
111 |
+
"step": 8500
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 3.93,
|
115 |
+
"learning_rate": 1.07158446093409e-05,
|
116 |
+
"loss": 2.4445,
|
117 |
+
"step": 9000
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 4.15,
|
121 |
+
"learning_rate": 8.533391532082061e-06,
|
122 |
+
"loss": 2.4247,
|
123 |
+
"step": 9500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 4.36,
|
127 |
+
"learning_rate": 6.3509384548232216e-06,
|
128 |
+
"loss": 2.4052,
|
129 |
+
"step": 10000
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 4.58,
|
133 |
+
"learning_rate": 4.168485377564382e-06,
|
134 |
+
"loss": 2.4033,
|
135 |
+
"step": 10500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 4.8,
|
139 |
+
"learning_rate": 1.9860323003055434e-06,
|
140 |
+
"loss": 2.3983,
|
141 |
+
"step": 11000
|
142 |
+
}
|
143 |
+
],
|
144 |
+
"logging_steps": 500,
|
145 |
+
"max_steps": 11455,
|
146 |
+
"num_train_epochs": 5,
|
147 |
+
"save_steps": 500,
|
148 |
+
"total_flos": 5747118243840000.0,
|
149 |
+
"trial_name": null,
|
150 |
+
"trial_params": null
|
151 |
+
}
|
result/checkpoint-11000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80e96e420e8512d7fb75dfda4774fa9c590ddbf2c70fe33e7c23bada5b6508af
|
3 |
+
size 4472
|
result/config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "gpt2",
|
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": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
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": "4.32.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
result/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": "4.32.1"
|
6 |
+
}
|
result/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
result/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0994830a2fa876ad2d97f9efa9cd8bbfac36a1a6414b863b6683987032c78cb
|
3 |
+
size 497807706
|
result/runs/Nov16_01-48-04_TORRE/events.out.tfevents.1700110084.TORRE.21416.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0cc73d6d183df6782e4660c908056a3559d2cdc1c25cebe038ffd925895154eb
|
3 |
+
size 8089
|
result/special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|endoftext|>",
|
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 |
+
"unk_token": {
|
17 |
+
"content": "<|endoftext|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
result/tokenizer_config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"bos_token": {
|
5 |
+
"__type": "AddedToken",
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"clean_up_tokenization_spaces": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 1024,
|
23 |
+
"pad_token": null,
|
24 |
+
"tokenizer_class": "GPT2Tokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
result/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80e96e420e8512d7fb75dfda4774fa9c590ddbf2c70fe33e7c23bada5b6508af
|
3 |
+
size 4472
|
result/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|