Commit
•
529530e
1
Parent(s):
63f4935
add model
Browse files- .gitignore +1 -0
- README.md +74 -0
- all_results.json +16 -0
- config.json +35 -0
- eval_results.json +11 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +295 -0
- training_args.bin +3 -0
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
README.md
ADDED
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
language:
|
3 |
+
- en
|
4 |
+
license: apache-2.0
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
datasets:
|
8 |
+
- glue
|
9 |
+
metrics:
|
10 |
+
- accuracy
|
11 |
+
- f1
|
12 |
+
model_index:
|
13 |
+
- name: qqp
|
14 |
+
results:
|
15 |
+
- task:
|
16 |
+
name: Text Classification
|
17 |
+
type: text-classification
|
18 |
+
dataset:
|
19 |
+
name: GLUE QQP
|
20 |
+
type: glue
|
21 |
+
args: qqp
|
22 |
+
metric:
|
23 |
+
name: F1
|
24 |
+
type: f1
|
25 |
+
value: 0.8722569490623753
|
26 |
+
---
|
27 |
+
|
28 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
29 |
+
should probably proofread and complete it, then remove this comment. -->
|
30 |
+
|
31 |
+
# qqp
|
32 |
+
|
33 |
+
This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the GLUE QQP dataset.
|
34 |
+
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.3695
|
36 |
+
- Accuracy: 0.9050
|
37 |
+
- F1: 0.8723
|
38 |
+
- Combined Score: 0.8886
|
39 |
+
|
40 |
+
## Model description
|
41 |
+
|
42 |
+
More information needed
|
43 |
+
|
44 |
+
## Intended uses & limitations
|
45 |
+
|
46 |
+
More information needed
|
47 |
+
|
48 |
+
## Training and evaluation data
|
49 |
+
|
50 |
+
More information needed
|
51 |
+
|
52 |
+
## Training procedure
|
53 |
+
|
54 |
+
### Training hyperparameters
|
55 |
+
|
56 |
+
The following hyperparameters were used during training:
|
57 |
+
- learning_rate: 5e-05
|
58 |
+
- train_batch_size: 64
|
59 |
+
- eval_batch_size: 8
|
60 |
+
- seed: 42
|
61 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
62 |
+
- lr_scheduler_type: linear
|
63 |
+
- num_epochs: 4.0
|
64 |
+
|
65 |
+
### Training results
|
66 |
+
|
67 |
+
|
68 |
+
|
69 |
+
### Framework versions
|
70 |
+
|
71 |
+
- Transformers 4.9.1
|
72 |
+
- Pytorch 1.9.0+cu102
|
73 |
+
- Datasets 1.10.2
|
74 |
+
- Tokenizers 0.10.3
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9049715557754143,
|
4 |
+
"eval_combined_score": 0.8886142524188948,
|
5 |
+
"eval_f1": 0.8722569490623753,
|
6 |
+
"eval_loss": 0.3695096969604492,
|
7 |
+
"eval_runtime": 207.4157,
|
8 |
+
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 194.923,
|
10 |
+
"eval_steps_per_second": 24.367,
|
11 |
+
"train_loss": 0.1816996376236853,
|
12 |
+
"train_runtime": 16807.9309,
|
13 |
+
"train_samples": 363846,
|
14 |
+
"train_samples_per_second": 86.589,
|
15 |
+
"train_steps_per_second": 1.353
|
16 |
+
}
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
+
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"finetuning_task": "qqp",
|
13 |
+
"gap_size": 0,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_dropout_prob": 0,
|
16 |
+
"hidden_size": 768,
|
17 |
+
"initializer_range": 0.02,
|
18 |
+
"inner_group_num": 1,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"layer_norm_eps": 1e-12,
|
21 |
+
"max_position_embeddings": 512,
|
22 |
+
"model_type": "albert",
|
23 |
+
"net_structure_type": 0,
|
24 |
+
"num_attention_heads": 12,
|
25 |
+
"num_hidden_groups": 1,
|
26 |
+
"num_hidden_layers": 12,
|
27 |
+
"num_memory_blocks": 0,
|
28 |
+
"pad_token_id": 0,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
+
"problem_type": "single_label_classification",
|
31 |
+
"torch_dtype": "float32",
|
32 |
+
"transformers_version": "4.9.1",
|
33 |
+
"type_vocab_size": 2,
|
34 |
+
"vocab_size": 30000
|
35 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"eval_accuracy": 0.9049715557754143,
|
4 |
+
"eval_combined_score": 0.8886142524188948,
|
5 |
+
"eval_f1": 0.8722569490623753,
|
6 |
+
"eval_loss": 0.3695096969604492,
|
7 |
+
"eval_runtime": 207.4157,
|
8 |
+
"eval_samples": 40430,
|
9 |
+
"eval_samples_per_second": 194.923,
|
10 |
+
"eval_steps_per_second": 24.367
|
11 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df9f08c944128cb32b79ad2cc8bc8caa69157df9717769d2aae093ade9849c25
|
3 |
+
size 46755537
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
|
3 |
+
size 760289
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"do_lower_case": true, "remove_space": true, "keep_accents": false, "bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "<unk>", "sep_token": "[SEP]", "pad_token": "<pad>", "cls_token": "[CLS]", "mask_token": {"content": "[MASK]", "single_word": false, "lstrip": true, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "albert-base-v2", "tokenizer_class": "AlbertTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.0,
|
3 |
+
"train_loss": 0.1816996376236853,
|
4 |
+
"train_runtime": 16807.9309,
|
5 |
+
"train_samples": 363846,
|
6 |
+
"train_samples_per_second": 86.589,
|
7 |
+
"train_steps_per_second": 1.353
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,295 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 22744,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.09,
|
12 |
+
"learning_rate": 4.890080900457263e-05,
|
13 |
+
"loss": 0.4414,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.18,
|
18 |
+
"learning_rate": 4.780161800914527e-05,
|
19 |
+
"loss": 0.3578,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.26,
|
24 |
+
"learning_rate": 4.6702427013717904e-05,
|
25 |
+
"loss": 0.3321,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.35,
|
30 |
+
"learning_rate": 4.560323601829054e-05,
|
31 |
+
"loss": 0.3132,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.44,
|
36 |
+
"learning_rate": 4.450404502286317e-05,
|
37 |
+
"loss": 0.3074,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.53,
|
42 |
+
"learning_rate": 4.3404854027435806e-05,
|
43 |
+
"loss": 0.2935,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.62,
|
48 |
+
"learning_rate": 4.230566303200844e-05,
|
49 |
+
"loss": 0.2856,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.7,
|
54 |
+
"learning_rate": 4.120647203658108e-05,
|
55 |
+
"loss": 0.2876,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.79,
|
60 |
+
"learning_rate": 4.010728104115371e-05,
|
61 |
+
"loss": 0.2751,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.88,
|
66 |
+
"learning_rate": 3.9008090045726345e-05,
|
67 |
+
"loss": 0.2709,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.97,
|
72 |
+
"learning_rate": 3.790889905029898e-05,
|
73 |
+
"loss": 0.266,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.06,
|
78 |
+
"learning_rate": 3.680970805487162e-05,
|
79 |
+
"loss": 0.2304,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.14,
|
84 |
+
"learning_rate": 3.571051705944425e-05,
|
85 |
+
"loss": 0.2132,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.23,
|
90 |
+
"learning_rate": 3.461132606401688e-05,
|
91 |
+
"loss": 0.2155,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.32,
|
96 |
+
"learning_rate": 3.351213506858952e-05,
|
97 |
+
"loss": 0.2111,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.41,
|
102 |
+
"learning_rate": 3.2412944073162155e-05,
|
103 |
+
"loss": 0.2164,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.49,
|
108 |
+
"learning_rate": 3.1313753077734785e-05,
|
109 |
+
"loss": 0.2107,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.58,
|
114 |
+
"learning_rate": 3.0214562082307425e-05,
|
115 |
+
"loss": 0.2149,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.67,
|
120 |
+
"learning_rate": 2.9115371086880054e-05,
|
121 |
+
"loss": 0.211,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.76,
|
126 |
+
"learning_rate": 2.8016180091452694e-05,
|
127 |
+
"loss": 0.2102,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.85,
|
132 |
+
"learning_rate": 2.6916989096025323e-05,
|
133 |
+
"loss": 0.2099,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.93,
|
138 |
+
"learning_rate": 2.5817798100597963e-05,
|
139 |
+
"loss": 0.2047,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 2.02,
|
144 |
+
"learning_rate": 2.4718607105170596e-05,
|
145 |
+
"loss": 0.1848,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 2.11,
|
150 |
+
"learning_rate": 2.3619416109743232e-05,
|
151 |
+
"loss": 0.1338,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 2.2,
|
156 |
+
"learning_rate": 2.2520225114315865e-05,
|
157 |
+
"loss": 0.1315,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 2.29,
|
162 |
+
"learning_rate": 2.14210341188885e-05,
|
163 |
+
"loss": 0.1354,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 2.37,
|
168 |
+
"learning_rate": 2.0321843123461134e-05,
|
169 |
+
"loss": 0.1422,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.46,
|
174 |
+
"learning_rate": 1.922265212803377e-05,
|
175 |
+
"loss": 0.1354,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 2.55,
|
180 |
+
"learning_rate": 1.8123461132606403e-05,
|
181 |
+
"loss": 0.1353,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.64,
|
186 |
+
"learning_rate": 1.702427013717904e-05,
|
187 |
+
"loss": 0.1352,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.73,
|
192 |
+
"learning_rate": 1.5925079141751672e-05,
|
193 |
+
"loss": 0.1315,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.81,
|
198 |
+
"learning_rate": 1.4825888146324307e-05,
|
199 |
+
"loss": 0.134,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.9,
|
204 |
+
"learning_rate": 1.3726697150896941e-05,
|
205 |
+
"loss": 0.1347,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.99,
|
210 |
+
"learning_rate": 1.2627506155469576e-05,
|
211 |
+
"loss": 0.1329,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3.08,
|
216 |
+
"learning_rate": 1.1528315160042209e-05,
|
217 |
+
"loss": 0.085,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 3.17,
|
222 |
+
"learning_rate": 1.0429124164614843e-05,
|
223 |
+
"loss": 0.0735,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 3.25,
|
228 |
+
"learning_rate": 9.329933169187478e-06,
|
229 |
+
"loss": 0.0739,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 3.34,
|
234 |
+
"learning_rate": 8.230742173760112e-06,
|
235 |
+
"loss": 0.0735,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 3.43,
|
240 |
+
"learning_rate": 7.131551178332748e-06,
|
241 |
+
"loss": 0.0718,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 3.52,
|
246 |
+
"learning_rate": 6.032360182905382e-06,
|
247 |
+
"loss": 0.0708,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 3.61,
|
252 |
+
"learning_rate": 4.933169187478016e-06,
|
253 |
+
"loss": 0.0706,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.69,
|
258 |
+
"learning_rate": 3.833978192050651e-06,
|
259 |
+
"loss": 0.0658,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 3.78,
|
264 |
+
"learning_rate": 2.7347871966232856e-06,
|
265 |
+
"loss": 0.0705,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.87,
|
270 |
+
"learning_rate": 1.63559620119592e-06,
|
271 |
+
"loss": 0.0692,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.96,
|
276 |
+
"learning_rate": 5.364052057685544e-07,
|
277 |
+
"loss": 0.0641,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 4.0,
|
282 |
+
"step": 22744,
|
283 |
+
"total_flos": 8695228732968960.0,
|
284 |
+
"train_loss": 0.1816996376236853,
|
285 |
+
"train_runtime": 16807.9309,
|
286 |
+
"train_samples_per_second": 86.589,
|
287 |
+
"train_steps_per_second": 1.353
|
288 |
+
}
|
289 |
+
],
|
290 |
+
"max_steps": 22744,
|
291 |
+
"num_train_epochs": 4,
|
292 |
+
"total_flos": 8695228732968960.0,
|
293 |
+
"trial_name": null,
|
294 |
+
"trial_params": null
|
295 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab74ea35cc43df1d47a80758bac1f3d772f30e225e40ab61a8208fa4557c908e
|
3 |
+
size 2607
|