Upload 11 files
Browse files- config.json +59 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +187 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "castorini/monot5-base-msmarco",
|
3 |
+
"_num_labels": 2,
|
4 |
+
"architectures": [
|
5 |
+
"T5ForConditionalGeneration"
|
6 |
+
],
|
7 |
+
"d_ff": 3072,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "relu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"layer_norm_epsilon": 1e-06,
|
17 |
+
"model_type": "t5",
|
18 |
+
"n_positions": 512,
|
19 |
+
"num_decoder_layers": 12,
|
20 |
+
"num_heads": 12,
|
21 |
+
"num_layers": 12,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"task_specific_params": {
|
27 |
+
"summarization": {
|
28 |
+
"early_stopping": true,
|
29 |
+
"length_penalty": 2.0,
|
30 |
+
"max_length": 200,
|
31 |
+
"min_length": 30,
|
32 |
+
"no_repeat_ngram_size": 3,
|
33 |
+
"num_beams": 4,
|
34 |
+
"prefix": "summarize: "
|
35 |
+
},
|
36 |
+
"translation_en_to_de": {
|
37 |
+
"early_stopping": true,
|
38 |
+
"max_length": 300,
|
39 |
+
"num_beams": 4,
|
40 |
+
"prefix": "translate English to German: "
|
41 |
+
},
|
42 |
+
"translation_en_to_fr": {
|
43 |
+
"early_stopping": true,
|
44 |
+
"max_length": 300,
|
45 |
+
"num_beams": 4,
|
46 |
+
"prefix": "translate English to French: "
|
47 |
+
},
|
48 |
+
"translation_en_to_ro": {
|
49 |
+
"early_stopping": true,
|
50 |
+
"max_length": 300,
|
51 |
+
"num_beams": 4,
|
52 |
+
"prefix": "translate English to Romanian: "
|
53 |
+
}
|
54 |
+
},
|
55 |
+
"torch_dtype": "float32",
|
56 |
+
"transformers_version": "4.18.0",
|
57 |
+
"use_cache": true,
|
58 |
+
"vocab_size": 32128
|
59 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4268d3d4b7ddae5d778ff3cb90a8afaf719d05b3cfdadfaca6b4accfc549404f
|
3 |
+
size 1783379133
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8c067ba989e86ee85daa0c4d38634680ab09253f61214ebfc0c6116490f93f44
|
3 |
+
size 891700799
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ec6eae7d484df8e18d2da01f05e865edd82600891c87924e1e107d78746088b
|
3 |
+
size 14503
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7760edc16b231ce3f016d6733d8decfc4d3adf52e4a97dbc6f8b0cbb28ac7e2d
|
3 |
+
size 623
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "castorini/monot5-base-msmarco", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
trainer_state.json
ADDED
@@ -0,0 +1,187 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.285884141921997,
|
3 |
+
"best_model_checkpoint": "monot5-base-msmarco-finetuned-monoQA-rep-HDN-CONVDR-Question-Answering-100sample/checkpoint-3941",
|
4 |
+
"epoch": 9.0,
|
5 |
+
"global_step": 35469,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 1.0,
|
12 |
+
"learning_rate": 1.8e-05,
|
13 |
+
"loss": 0.2134,
|
14 |
+
"step": 3941
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_Rel Acc": 65.42,
|
19 |
+
"eval_loss": 1.285884141921997,
|
20 |
+
"eval_rouge1": 10.8,
|
21 |
+
"eval_rouge2": 6.16,
|
22 |
+
"eval_rougeL": 9.97,
|
23 |
+
"eval_rougeLsum": 10.02,
|
24 |
+
"eval_runtime": 586.4065,
|
25 |
+
"eval_samples_per_second": 4.823,
|
26 |
+
"eval_steps_per_second": 0.302,
|
27 |
+
"step": 3941
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 2.0,
|
31 |
+
"learning_rate": 1.6000000000000003e-05,
|
32 |
+
"loss": 0.051,
|
33 |
+
"step": 7882
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 2.0,
|
37 |
+
"eval_Rel Acc": 43.53,
|
38 |
+
"eval_loss": 1.3421778678894043,
|
39 |
+
"eval_rouge1": 10.09,
|
40 |
+
"eval_rouge2": 6.8,
|
41 |
+
"eval_rougeL": 9.49,
|
42 |
+
"eval_rougeLsum": 9.5,
|
43 |
+
"eval_runtime": 584.9981,
|
44 |
+
"eval_samples_per_second": 4.834,
|
45 |
+
"eval_steps_per_second": 0.303,
|
46 |
+
"step": 7882
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 3.0,
|
50 |
+
"learning_rate": 1.4e-05,
|
51 |
+
"loss": 0.0461,
|
52 |
+
"step": 11823
|
53 |
+
},
|
54 |
+
{
|
55 |
+
"epoch": 3.0,
|
56 |
+
"eval_Rel Acc": 34.94,
|
57 |
+
"eval_loss": 1.4272361993789673,
|
58 |
+
"eval_rouge1": 8.96,
|
59 |
+
"eval_rouge2": 6.5,
|
60 |
+
"eval_rougeL": 8.56,
|
61 |
+
"eval_rougeLsum": 8.56,
|
62 |
+
"eval_runtime": 577.0374,
|
63 |
+
"eval_samples_per_second": 4.901,
|
64 |
+
"eval_steps_per_second": 0.307,
|
65 |
+
"step": 11823
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 4.0,
|
69 |
+
"learning_rate": 1.2e-05,
|
70 |
+
"loss": 0.0425,
|
71 |
+
"step": 15764
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 4.0,
|
75 |
+
"eval_Rel Acc": 34.69,
|
76 |
+
"eval_loss": 1.5165988206863403,
|
77 |
+
"eval_rouge1": 9.76,
|
78 |
+
"eval_rouge2": 7.04,
|
79 |
+
"eval_rougeL": 9.31,
|
80 |
+
"eval_rougeLsum": 9.31,
|
81 |
+
"eval_runtime": 70.6183,
|
82 |
+
"eval_samples_per_second": 40.046,
|
83 |
+
"eval_steps_per_second": 2.506,
|
84 |
+
"step": 15764
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 5.0,
|
88 |
+
"learning_rate": 1e-05,
|
89 |
+
"loss": 0.0401,
|
90 |
+
"step": 19705
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 5.0,
|
94 |
+
"eval_Rel Acc": 33.7,
|
95 |
+
"eval_loss": 1.5656001567840576,
|
96 |
+
"eval_rouge1": 9.42,
|
97 |
+
"eval_rouge2": 7.06,
|
98 |
+
"eval_rougeL": 9.03,
|
99 |
+
"eval_rougeLsum": 9.04,
|
100 |
+
"eval_runtime": 70.3483,
|
101 |
+
"eval_samples_per_second": 40.2,
|
102 |
+
"eval_steps_per_second": 2.516,
|
103 |
+
"step": 19705
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 6.0,
|
107 |
+
"learning_rate": 8.000000000000001e-06,
|
108 |
+
"loss": 0.038,
|
109 |
+
"step": 23646
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 6.0,
|
113 |
+
"eval_Rel Acc": 33.84,
|
114 |
+
"eval_loss": 1.5563075542449951,
|
115 |
+
"eval_rouge1": 9.21,
|
116 |
+
"eval_rouge2": 6.96,
|
117 |
+
"eval_rougeL": 8.83,
|
118 |
+
"eval_rougeLsum": 8.82,
|
119 |
+
"eval_runtime": 70.1794,
|
120 |
+
"eval_samples_per_second": 40.297,
|
121 |
+
"eval_steps_per_second": 2.522,
|
122 |
+
"step": 23646
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 7.0,
|
126 |
+
"learning_rate": 6e-06,
|
127 |
+
"loss": 0.0364,
|
128 |
+
"step": 27587
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 7.0,
|
132 |
+
"eval_Rel Acc": 31.58,
|
133 |
+
"eval_loss": 1.6121798753738403,
|
134 |
+
"eval_rouge1": 9.42,
|
135 |
+
"eval_rouge2": 7.19,
|
136 |
+
"eval_rougeL": 9.06,
|
137 |
+
"eval_rougeLsum": 9.07,
|
138 |
+
"eval_runtime": 70.6676,
|
139 |
+
"eval_samples_per_second": 40.018,
|
140 |
+
"eval_steps_per_second": 2.505,
|
141 |
+
"step": 27587
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 8.0,
|
145 |
+
"learning_rate": 4.000000000000001e-06,
|
146 |
+
"loss": 0.0353,
|
147 |
+
"step": 31528
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 8.0,
|
151 |
+
"eval_Rel Acc": 32.32,
|
152 |
+
"eval_loss": 1.6281025409698486,
|
153 |
+
"eval_rouge1": 9.84,
|
154 |
+
"eval_rouge2": 7.47,
|
155 |
+
"eval_rougeL": 9.46,
|
156 |
+
"eval_rougeLsum": 9.43,
|
157 |
+
"eval_runtime": 70.4202,
|
158 |
+
"eval_samples_per_second": 40.159,
|
159 |
+
"eval_steps_per_second": 2.513,
|
160 |
+
"step": 31528
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 9.0,
|
164 |
+
"learning_rate": 2.0000000000000003e-06,
|
165 |
+
"loss": 0.0342,
|
166 |
+
"step": 35469
|
167 |
+
},
|
168 |
+
{
|
169 |
+
"epoch": 9.0,
|
170 |
+
"eval_Rel Acc": 32.07,
|
171 |
+
"eval_loss": 1.6341171264648438,
|
172 |
+
"eval_rouge1": 9.77,
|
173 |
+
"eval_rouge2": 7.43,
|
174 |
+
"eval_rougeL": 9.42,
|
175 |
+
"eval_rougeLsum": 9.4,
|
176 |
+
"eval_runtime": 70.4771,
|
177 |
+
"eval_samples_per_second": 40.127,
|
178 |
+
"eval_steps_per_second": 2.511,
|
179 |
+
"step": 35469
|
180 |
+
}
|
181 |
+
],
|
182 |
+
"max_steps": 39410,
|
183 |
+
"num_train_epochs": 10,
|
184 |
+
"total_flos": 3.455584072600781e+17,
|
185 |
+
"trial_name": null,
|
186 |
+
"trial_params": null
|
187 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8ec8bb27e34e3c3f99c5c16bcec5b42e2ea8f7c2af917dd13205d69429017cf
|
3 |
+
size 3247
|