add/repub model
Browse files- all_results.json +15 -0
- config.json +39 -0
- eval_results.json +10 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +181 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.42910256618275966,
|
4 |
+
"eval_loss": 3.251399040222168,
|
5 |
+
"eval_runtime": 155.7882,
|
6 |
+
"eval_samples": 20382,
|
7 |
+
"eval_samples_per_second": 130.832,
|
8 |
+
"eval_steps_per_second": 16.356,
|
9 |
+
"perplexity": 25.82644689174606,
|
10 |
+
"train_loss": 3.311987802313766,
|
11 |
+
"train_runtime": 196254.5716,
|
12 |
+
"train_samples": 1001102,
|
13 |
+
"train_samples_per_second": 51.01,
|
14 |
+
"train_steps_per_second": 2.125
|
15 |
+
}
|
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": "4.19.0.dev0",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"eval_accuracy": 0.42910256618275966,
|
4 |
+
"eval_loss": 3.251399040222168,
|
5 |
+
"eval_runtime": 155.7882,
|
6 |
+
"eval_samples": 20382,
|
7 |
+
"eval_samples_per_second": 130.832,
|
8 |
+
"eval_steps_per_second": 16.356,
|
9 |
+
"perplexity": 25.82644689174606
|
10 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efd585bfbc028086241f9137e801f8c3c5ded4c7e203cfd9c294cd63beae3498
|
3 |
+
size 510401019
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 10.0,
|
3 |
+
"train_loss": 3.311987802313766,
|
4 |
+
"train_runtime": 196254.5716,
|
5 |
+
"train_samples": 1001102,
|
6 |
+
"train_samples_per_second": 51.01,
|
7 |
+
"train_steps_per_second": 2.125
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 10.0,
|
5 |
+
"global_step": 417130,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.0,
|
12 |
+
"learning_rate": 4.999988013329178e-05,
|
13 |
+
"loss": 5.0345,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"learning_rate": 4.5e-05,
|
19 |
+
"loss": 3.5452,
|
20 |
+
"step": 41713
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 1.0,
|
24 |
+
"eval_accuracy": 0.4118760802529946,
|
25 |
+
"eval_loss": 3.3738181591033936,
|
26 |
+
"eval_runtime": 157.5504,
|
27 |
+
"eval_samples_per_second": 129.368,
|
28 |
+
"eval_steps_per_second": 16.173,
|
29 |
+
"step": 41713
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 2.0,
|
33 |
+
"learning_rate": 4e-05,
|
34 |
+
"loss": 3.4132,
|
35 |
+
"step": 83426
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.4179529258872079,
|
40 |
+
"eval_loss": 3.326674461364746,
|
41 |
+
"eval_runtime": 156.5806,
|
42 |
+
"eval_samples_per_second": 130.169,
|
43 |
+
"eval_steps_per_second": 16.273,
|
44 |
+
"step": 83426
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 3.0,
|
48 |
+
"learning_rate": 3.5e-05,
|
49 |
+
"loss": 3.3573,
|
50 |
+
"step": 125139
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 3.0,
|
54 |
+
"eval_accuracy": 0.4213834655713664,
|
55 |
+
"eval_loss": 3.3009300231933594,
|
56 |
+
"eval_runtime": 156.2147,
|
57 |
+
"eval_samples_per_second": 130.474,
|
58 |
+
"eval_steps_per_second": 16.311,
|
59 |
+
"step": 125139
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 4.0,
|
63 |
+
"learning_rate": 3e-05,
|
64 |
+
"loss": 3.3196,
|
65 |
+
"step": 166852
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"eval_accuracy": 0.42338731797471446,
|
70 |
+
"eval_loss": 3.2852749824523926,
|
71 |
+
"eval_runtime": 157.4446,
|
72 |
+
"eval_samples_per_second": 129.455,
|
73 |
+
"eval_steps_per_second": 16.183,
|
74 |
+
"step": 166852
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 5.0,
|
78 |
+
"learning_rate": 2.5e-05,
|
79 |
+
"loss": 3.2912,
|
80 |
+
"step": 208565
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 5.0,
|
84 |
+
"eval_accuracy": 0.42540662325952266,
|
85 |
+
"eval_loss": 3.2730937004089355,
|
86 |
+
"eval_runtime": 155.9547,
|
87 |
+
"eval_samples_per_second": 130.692,
|
88 |
+
"eval_steps_per_second": 16.338,
|
89 |
+
"step": 208565
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 6.0,
|
93 |
+
"learning_rate": 2e-05,
|
94 |
+
"loss": 3.2688,
|
95 |
+
"step": 250278
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 6.0,
|
99 |
+
"eval_accuracy": 0.42657331580976576,
|
100 |
+
"eval_loss": 3.265730857849121,
|
101 |
+
"eval_runtime": 157.36,
|
102 |
+
"eval_samples_per_second": 129.525,
|
103 |
+
"eval_steps_per_second": 16.192,
|
104 |
+
"step": 250278
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 7.0,
|
108 |
+
"learning_rate": 1.5e-05,
|
109 |
+
"loss": 3.2506,
|
110 |
+
"step": 291991
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 7.0,
|
114 |
+
"eval_accuracy": 0.4276302929016416,
|
115 |
+
"eval_loss": 3.25875186920166,
|
116 |
+
"eval_runtime": 157.1763,
|
117 |
+
"eval_samples_per_second": 129.676,
|
118 |
+
"eval_steps_per_second": 16.211,
|
119 |
+
"step": 291991
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 8.0,
|
123 |
+
"learning_rate": 1e-05,
|
124 |
+
"loss": 3.2358,
|
125 |
+
"step": 333704
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 8.0,
|
129 |
+
"eval_accuracy": 0.4284013916865043,
|
130 |
+
"eval_loss": 3.2545275688171387,
|
131 |
+
"eval_runtime": 155.6431,
|
132 |
+
"eval_samples_per_second": 130.953,
|
133 |
+
"eval_steps_per_second": 16.371,
|
134 |
+
"step": 333704
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 9.0,
|
138 |
+
"learning_rate": 5e-06,
|
139 |
+
"loss": 3.2237,
|
140 |
+
"step": 375417
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 9.0,
|
144 |
+
"eval_accuracy": 0.4288819762999157,
|
145 |
+
"eval_loss": 3.2520158290863037,
|
146 |
+
"eval_runtime": 156.3518,
|
147 |
+
"eval_samples_per_second": 130.36,
|
148 |
+
"eval_steps_per_second": 16.297,
|
149 |
+
"step": 375417
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 10.0,
|
153 |
+
"learning_rate": 0.0,
|
154 |
+
"loss": 3.2144,
|
155 |
+
"step": 417130
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 10.0,
|
159 |
+
"eval_accuracy": 0.42910256618275966,
|
160 |
+
"eval_loss": 3.251399040222168,
|
161 |
+
"eval_runtime": 154.5215,
|
162 |
+
"eval_samples_per_second": 131.904,
|
163 |
+
"eval_steps_per_second": 16.49,
|
164 |
+
"step": 417130
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 10.0,
|
168 |
+
"step": 417130,
|
169 |
+
"total_flos": 6.5394993954816e+17,
|
170 |
+
"train_loss": 3.311987802313766,
|
171 |
+
"train_runtime": 196254.5716,
|
172 |
+
"train_samples_per_second": 51.01,
|
173 |
+
"train_steps_per_second": 2.125
|
174 |
+
}
|
175 |
+
],
|
176 |
+
"max_steps": 417130,
|
177 |
+
"num_train_epochs": 10,
|
178 |
+
"total_flos": 6.5394993954816e+17,
|
179 |
+
"trial_name": null,
|
180 |
+
"trial_params": null
|
181 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7ab9b8fafe400ca6338bee04bac62cf40e4b9eaa08d4fd3ea678157325342fa
|
3 |
+
size 3119
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|