Spaces:
Sleeping
Sleeping
Commit
·
8175cd8
1
Parent(s):
008ebb9
deployment qa
Browse files- app/pyfiles/gpt2_qa_model/config.json +39 -0
- app/pyfiles/gpt2_qa_model/generation_config.json +6 -0
- app/pyfiles/gpt2_qa_model/model.safetensors +3 -0
- app/pyfiles/gpt2_qa_model/optimizer.pt +3 -0
- app/pyfiles/gpt2_qa_model/rng_state.pth +3 -0
- app/pyfiles/gpt2_qa_model/scheduler.pt +3 -0
- app/pyfiles/gpt2_qa_model/trainer_state.json +177 -0
- app/pyfiles/gpt2_qa_model/training_args.bin +3 -0
app/pyfiles/gpt2_qa_model/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": "4.37.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50258
|
39 |
+
}
|
app/pyfiles/gpt2_qa_model/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": "4.37.1"
|
6 |
+
}
|
app/pyfiles/gpt2_qa_model/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97c58cfcd6f3183c6bd368cd2d249c0c5cb8b4cc3e2e63dbed19f827a63595bd
|
3 |
+
size 497777280
|
app/pyfiles/gpt2_qa_model/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51e2d573dc0eaad6ed266613452b53c52fc0314974bbce6399425579de77be7c
|
3 |
+
size 995648005
|
app/pyfiles/gpt2_qa_model/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f70b22c76ffeb1a54dfea5e46ff4357813e4530099effda5ded403a5b6bad573
|
3 |
+
size 14575
|
app/pyfiles/gpt2_qa_model/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e1896dd01641cd5530a62fe19c8f250a473551bdb7196d9b92e1afcb65f1b0b
|
3 |
+
size 627
|
app/pyfiles/gpt2_qa_model/trainer_state.json
ADDED
@@ -0,0 +1,177 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 12.0,
|
5 |
+
"eval_steps": 1000,
|
6 |
+
"global_step": 6624,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.91,
|
13 |
+
"learning_rate": 9.245169082125605e-06,
|
14 |
+
"loss": 5.1379,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 1.81,
|
19 |
+
"learning_rate": 8.490338164251208e-06,
|
20 |
+
"loss": 2.6021,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.81,
|
25 |
+
"eval_R1": 0.4801,
|
26 |
+
"eval_R2": 0.2007,
|
27 |
+
"eval_RL": 0.3755,
|
28 |
+
"eval_RLsum": 0.375,
|
29 |
+
"eval_bleu": 24.4945,
|
30 |
+
"eval_loss": 3.176283836364746,
|
31 |
+
"eval_runtime": 4.6319,
|
32 |
+
"eval_samples_per_second": 31.305,
|
33 |
+
"eval_steps_per_second": 31.305,
|
34 |
+
"step": 1000
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 2.72,
|
38 |
+
"learning_rate": 7.735507246376812e-06,
|
39 |
+
"loss": 2.442,
|
40 |
+
"step": 1500
|
41 |
+
},
|
42 |
+
{
|
43 |
+
"epoch": 3.62,
|
44 |
+
"learning_rate": 6.980676328502416e-06,
|
45 |
+
"loss": 2.3457,
|
46 |
+
"step": 2000
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 3.62,
|
50 |
+
"eval_R1": 0.4863,
|
51 |
+
"eval_R2": 0.2078,
|
52 |
+
"eval_RL": 0.3799,
|
53 |
+
"eval_RLsum": 0.3793,
|
54 |
+
"eval_bleu": 25.6685,
|
55 |
+
"eval_loss": 3.01701021194458,
|
56 |
+
"eval_runtime": 4.4695,
|
57 |
+
"eval_samples_per_second": 32.442,
|
58 |
+
"eval_steps_per_second": 32.442,
|
59 |
+
"step": 2000
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.53,
|
63 |
+
"learning_rate": 6.22584541062802e-06,
|
64 |
+
"loss": 2.2664,
|
65 |
+
"step": 2500
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 5.43,
|
69 |
+
"learning_rate": 5.471014492753623e-06,
|
70 |
+
"loss": 2.2153,
|
71 |
+
"step": 3000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 5.43,
|
75 |
+
"eval_R1": 0.4856,
|
76 |
+
"eval_R2": 0.2091,
|
77 |
+
"eval_RL": 0.3822,
|
78 |
+
"eval_RLsum": 0.3816,
|
79 |
+
"eval_bleu": 25.6215,
|
80 |
+
"eval_loss": 2.978219747543335,
|
81 |
+
"eval_runtime": 4.507,
|
82 |
+
"eval_samples_per_second": 32.172,
|
83 |
+
"eval_steps_per_second": 32.172,
|
84 |
+
"step": 3000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.34,
|
88 |
+
"learning_rate": 4.716183574879228e-06,
|
89 |
+
"loss": 2.1315,
|
90 |
+
"step": 3500
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 7.25,
|
94 |
+
"learning_rate": 3.961352657004831e-06,
|
95 |
+
"loss": 2.1401,
|
96 |
+
"step": 4000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 7.25,
|
100 |
+
"eval_R1": 0.4855,
|
101 |
+
"eval_R2": 0.206,
|
102 |
+
"eval_RL": 0.385,
|
103 |
+
"eval_RLsum": 0.3847,
|
104 |
+
"eval_bleu": 25.5534,
|
105 |
+
"eval_loss": 2.978952646255493,
|
106 |
+
"eval_runtime": 4.5866,
|
107 |
+
"eval_samples_per_second": 31.614,
|
108 |
+
"eval_steps_per_second": 31.614,
|
109 |
+
"step": 4000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 8.15,
|
113 |
+
"learning_rate": 3.206521739130435e-06,
|
114 |
+
"loss": 2.0507,
|
115 |
+
"step": 4500
|
116 |
+
},
|
117 |
+
{
|
118 |
+
"epoch": 9.06,
|
119 |
+
"learning_rate": 2.451690821256039e-06,
|
120 |
+
"loss": 2.021,
|
121 |
+
"step": 5000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 9.06,
|
125 |
+
"eval_R1": 0.4835,
|
126 |
+
"eval_R2": 0.2053,
|
127 |
+
"eval_RL": 0.384,
|
128 |
+
"eval_RLsum": 0.3834,
|
129 |
+
"eval_bleu": 25.5813,
|
130 |
+
"eval_loss": 2.980417013168335,
|
131 |
+
"eval_runtime": 4.6238,
|
132 |
+
"eval_samples_per_second": 31.36,
|
133 |
+
"eval_steps_per_second": 31.36,
|
134 |
+
"step": 5000
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.96,
|
138 |
+
"learning_rate": 1.6968599033816427e-06,
|
139 |
+
"loss": 2.0242,
|
140 |
+
"step": 5500
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.87,
|
144 |
+
"learning_rate": 9.420289855072465e-07,
|
145 |
+
"loss": 2.0082,
|
146 |
+
"step": 6000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 10.87,
|
150 |
+
"eval_R1": 0.4861,
|
151 |
+
"eval_R2": 0.2068,
|
152 |
+
"eval_RL": 0.3845,
|
153 |
+
"eval_RLsum": 0.384,
|
154 |
+
"eval_bleu": 25.5723,
|
155 |
+
"eval_loss": 2.9800899028778076,
|
156 |
+
"eval_runtime": 4.497,
|
157 |
+
"eval_samples_per_second": 32.244,
|
158 |
+
"eval_steps_per_second": 32.244,
|
159 |
+
"step": 6000
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 11.78,
|
163 |
+
"learning_rate": 1.8719806763285025e-07,
|
164 |
+
"loss": 1.974,
|
165 |
+
"step": 6500
|
166 |
+
}
|
167 |
+
],
|
168 |
+
"logging_steps": 500,
|
169 |
+
"max_steps": 6624,
|
170 |
+
"num_input_tokens_seen": 0,
|
171 |
+
"num_train_epochs": 12,
|
172 |
+
"save_steps": 500,
|
173 |
+
"total_flos": 825101038080000.0,
|
174 |
+
"train_batch_size": 2,
|
175 |
+
"trial_name": null,
|
176 |
+
"trial_params": null
|
177 |
+
}
|
app/pyfiles/gpt2_qa_model/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:277200f397cb704f1248c12d2812c5cb6ac52e08e7839e1c742dc2ba2e986b16
|
3 |
+
size 4283
|