update from Yaxin
Browse files- README.md +68 -0
- all_results.json +15 -0
- config.json +28 -0
- eval_results.json +10 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +8 -0
- trainer_state.json +517 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- Yaxin/amazon_reviews_multi
|
7 |
+
metrics:
|
8 |
+
- accuracy
|
9 |
+
model-index:
|
10 |
+
- name: xlm-roberta-base-amazon-en-es-fr-mlm
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Masked Language Modeling
|
14 |
+
type: fill-mask
|
15 |
+
dataset:
|
16 |
+
name: Yaxin/amazon_reviews_multi
|
17 |
+
type: Yaxin/amazon_reviews_multi
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.6951035447140035
|
22 |
+
---
|
23 |
+
|
24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
25 |
+
should probably proofread and complete it, then remove this comment. -->
|
26 |
+
|
27 |
+
# xlm-roberta-base-amazon-en-es-fr-mlm
|
28 |
+
|
29 |
+
This model is a fine-tuned version of [xlm-roberta-base](https://huggingface.co/xlm-roberta-base) on the Yaxin/amazon_reviews_multi dataset.
|
30 |
+
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 1.3936
|
32 |
+
- Accuracy: 0.6951
|
33 |
+
|
34 |
+
## Model description
|
35 |
+
|
36 |
+
More information needed
|
37 |
+
|
38 |
+
## Intended uses & limitations
|
39 |
+
|
40 |
+
More information needed
|
41 |
+
|
42 |
+
## Training and evaluation data
|
43 |
+
|
44 |
+
More information needed
|
45 |
+
|
46 |
+
## Training procedure
|
47 |
+
|
48 |
+
### Training hyperparameters
|
49 |
+
|
50 |
+
The following hyperparameters were used during training:
|
51 |
+
- learning_rate: 5e-05
|
52 |
+
- train_batch_size: 6
|
53 |
+
- eval_batch_size: 6
|
54 |
+
- seed: 42
|
55 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
56 |
+
- lr_scheduler_type: linear
|
57 |
+
- num_epochs: 5.0
|
58 |
+
|
59 |
+
### Training results
|
60 |
+
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- Transformers 4.18.0.dev0
|
66 |
+
- Pytorch 1.11.0
|
67 |
+
- Datasets 2.0.0
|
68 |
+
- Tokenizers 0.11.6
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.6951035447140035,
|
4 |
+
"eval_loss": 1.39362370967865,
|
5 |
+
"eval_runtime": 37.186,
|
6 |
+
"eval_samples": 1232,
|
7 |
+
"eval_samples_per_second": 33.131,
|
8 |
+
"eval_steps_per_second": 5.54,
|
9 |
+
"perplexity": 4.029425095902525,
|
10 |
+
"train_loss": 1.5926296373474231,
|
11 |
+
"train_runtime": 22304.2482,
|
12 |
+
"train_samples": 49766,
|
13 |
+
"train_samples_per_second": 11.156,
|
14 |
+
"train_steps_per_second": 1.86
|
15 |
+
}
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForMaskedLM"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "xlm-roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.18.0.dev0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 250002
|
28 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"eval_accuracy": 0.6951035447140035,
|
4 |
+
"eval_loss": 1.39362370967865,
|
5 |
+
"eval_runtime": 37.186,
|
6 |
+
"eval_samples": 1232,
|
7 |
+
"eval_samples_per_second": 33.131,
|
8 |
+
"eval_steps_per_second": 5.54,
|
9 |
+
"perplexity": 4.029425095902525
|
10 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "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": "xlm-roberta-base", "tokenizer_class": "XLMRobertaTokenizer"}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 5.0,
|
3 |
+
"train_loss": 1.5926296373474231,
|
4 |
+
"train_runtime": 22304.2482,
|
5 |
+
"train_samples": 49766,
|
6 |
+
"train_samples_per_second": 11.156,
|
7 |
+
"train_steps_per_second": 1.86
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,517 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.0,
|
5 |
+
"global_step": 41475,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.06,
|
12 |
+
"learning_rate": 4.939722724532851e-05,
|
13 |
+
"loss": 2.1591,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.12,
|
18 |
+
"learning_rate": 4.8794454490657024e-05,
|
19 |
+
"loss": 1.9533,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.18,
|
24 |
+
"learning_rate": 4.8191681735985535e-05,
|
25 |
+
"loss": 1.8939,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.24,
|
30 |
+
"learning_rate": 4.7588908981314046e-05,
|
31 |
+
"loss": 1.8664,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.3,
|
36 |
+
"learning_rate": 4.6986136226642556e-05,
|
37 |
+
"loss": 1.8392,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.36,
|
42 |
+
"learning_rate": 4.638336347197107e-05,
|
43 |
+
"loss": 1.8177,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.42,
|
48 |
+
"learning_rate": 4.5780590717299585e-05,
|
49 |
+
"loss": 1.7998,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.48,
|
54 |
+
"learning_rate": 4.5177817962628096e-05,
|
55 |
+
"loss": 1.7895,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.54,
|
60 |
+
"learning_rate": 4.45750452079566e-05,
|
61 |
+
"loss": 1.7798,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.6,
|
66 |
+
"learning_rate": 4.397227245328511e-05,
|
67 |
+
"loss": 1.7647,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.66,
|
72 |
+
"learning_rate": 4.336949969861363e-05,
|
73 |
+
"loss": 1.7568,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.72,
|
78 |
+
"learning_rate": 4.276672694394214e-05,
|
79 |
+
"loss": 1.7502,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.78,
|
84 |
+
"learning_rate": 4.216395418927065e-05,
|
85 |
+
"loss": 1.7346,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.84,
|
90 |
+
"learning_rate": 4.1561181434599153e-05,
|
91 |
+
"loss": 1.7177,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.9,
|
96 |
+
"learning_rate": 4.095840867992767e-05,
|
97 |
+
"loss": 1.7246,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.96,
|
102 |
+
"learning_rate": 4.035563592525618e-05,
|
103 |
+
"loss": 1.7119,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.02,
|
108 |
+
"learning_rate": 3.975286317058469e-05,
|
109 |
+
"loss": 1.7028,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.08,
|
114 |
+
"learning_rate": 3.9150090415913203e-05,
|
115 |
+
"loss": 1.685,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.15,
|
120 |
+
"learning_rate": 3.8547317661241714e-05,
|
121 |
+
"loss": 1.6779,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.21,
|
126 |
+
"learning_rate": 3.7944544906570225e-05,
|
127 |
+
"loss": 1.6613,
|
128 |
+
"step": 10000
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.27,
|
132 |
+
"learning_rate": 3.7341772151898736e-05,
|
133 |
+
"loss": 1.6646,
|
134 |
+
"step": 10500
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.33,
|
138 |
+
"learning_rate": 3.6738999397227247e-05,
|
139 |
+
"loss": 1.6491,
|
140 |
+
"step": 11000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.39,
|
144 |
+
"learning_rate": 3.613622664255576e-05,
|
145 |
+
"loss": 1.6525,
|
146 |
+
"step": 11500
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.45,
|
150 |
+
"learning_rate": 3.553345388788427e-05,
|
151 |
+
"loss": 1.648,
|
152 |
+
"step": 12000
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.51,
|
156 |
+
"learning_rate": 3.493068113321278e-05,
|
157 |
+
"loss": 1.6482,
|
158 |
+
"step": 12500
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.57,
|
162 |
+
"learning_rate": 3.432790837854129e-05,
|
163 |
+
"loss": 1.6386,
|
164 |
+
"step": 13000
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.63,
|
168 |
+
"learning_rate": 3.37251356238698e-05,
|
169 |
+
"loss": 1.6421,
|
170 |
+
"step": 13500
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.69,
|
174 |
+
"learning_rate": 3.312236286919831e-05,
|
175 |
+
"loss": 1.6305,
|
176 |
+
"step": 14000
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.75,
|
180 |
+
"learning_rate": 3.251959011452683e-05,
|
181 |
+
"loss": 1.6255,
|
182 |
+
"step": 14500
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 1.81,
|
186 |
+
"learning_rate": 3.191681735985534e-05,
|
187 |
+
"loss": 1.6254,
|
188 |
+
"step": 15000
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.87,
|
192 |
+
"learning_rate": 3.1314044605183844e-05,
|
193 |
+
"loss": 1.6217,
|
194 |
+
"step": 15500
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 1.93,
|
198 |
+
"learning_rate": 3.0711271850512355e-05,
|
199 |
+
"loss": 1.6082,
|
200 |
+
"step": 16000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 1.99,
|
204 |
+
"learning_rate": 3.010849909584087e-05,
|
205 |
+
"loss": 1.6026,
|
206 |
+
"step": 16500
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.05,
|
210 |
+
"learning_rate": 2.9505726341169383e-05,
|
211 |
+
"loss": 1.5867,
|
212 |
+
"step": 17000
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.11,
|
216 |
+
"learning_rate": 2.8902953586497894e-05,
|
217 |
+
"loss": 1.5732,
|
218 |
+
"step": 17500
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.17,
|
222 |
+
"learning_rate": 2.83001808318264e-05,
|
223 |
+
"loss": 1.5877,
|
224 |
+
"step": 18000
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.23,
|
228 |
+
"learning_rate": 2.7697408077154912e-05,
|
229 |
+
"loss": 1.5735,
|
230 |
+
"step": 18500
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.29,
|
234 |
+
"learning_rate": 2.7094635322483426e-05,
|
235 |
+
"loss": 1.5707,
|
236 |
+
"step": 19000
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.35,
|
240 |
+
"learning_rate": 2.6491862567811937e-05,
|
241 |
+
"loss": 1.5633,
|
242 |
+
"step": 19500
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.41,
|
246 |
+
"learning_rate": 2.5889089813140448e-05,
|
247 |
+
"loss": 1.5716,
|
248 |
+
"step": 20000
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.47,
|
252 |
+
"learning_rate": 2.5286317058468955e-05,
|
253 |
+
"loss": 1.5516,
|
254 |
+
"step": 20500
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.53,
|
258 |
+
"learning_rate": 2.468354430379747e-05,
|
259 |
+
"loss": 1.5582,
|
260 |
+
"step": 21000
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.59,
|
264 |
+
"learning_rate": 2.408077154912598e-05,
|
265 |
+
"loss": 1.5618,
|
266 |
+
"step": 21500
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 2.65,
|
270 |
+
"learning_rate": 2.347799879445449e-05,
|
271 |
+
"loss": 1.545,
|
272 |
+
"step": 22000
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 2.71,
|
276 |
+
"learning_rate": 2.2875226039783005e-05,
|
277 |
+
"loss": 1.5472,
|
278 |
+
"step": 22500
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 2.77,
|
282 |
+
"learning_rate": 2.2272453285111512e-05,
|
283 |
+
"loss": 1.5445,
|
284 |
+
"step": 23000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 2.83,
|
288 |
+
"learning_rate": 2.1669680530440027e-05,
|
289 |
+
"loss": 1.5458,
|
290 |
+
"step": 23500
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 2.89,
|
294 |
+
"learning_rate": 2.1066907775768534e-05,
|
295 |
+
"loss": 1.5449,
|
296 |
+
"step": 24000
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 2.95,
|
300 |
+
"learning_rate": 2.0464135021097048e-05,
|
301 |
+
"loss": 1.5378,
|
302 |
+
"step": 24500
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.01,
|
306 |
+
"learning_rate": 1.986136226642556e-05,
|
307 |
+
"loss": 1.5272,
|
308 |
+
"step": 25000
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.07,
|
312 |
+
"learning_rate": 1.925858951175407e-05,
|
313 |
+
"loss": 1.5207,
|
314 |
+
"step": 25500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.13,
|
318 |
+
"learning_rate": 1.865581675708258e-05,
|
319 |
+
"loss": 1.5153,
|
320 |
+
"step": 26000
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.19,
|
324 |
+
"learning_rate": 1.8053044002411095e-05,
|
325 |
+
"loss": 1.5062,
|
326 |
+
"step": 26500
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 3.25,
|
330 |
+
"learning_rate": 1.7450271247739602e-05,
|
331 |
+
"loss": 1.5083,
|
332 |
+
"step": 27000
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 3.32,
|
336 |
+
"learning_rate": 1.6847498493068113e-05,
|
337 |
+
"loss": 1.5091,
|
338 |
+
"step": 27500
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.38,
|
342 |
+
"learning_rate": 1.6244725738396624e-05,
|
343 |
+
"loss": 1.4977,
|
344 |
+
"step": 28000
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 3.44,
|
348 |
+
"learning_rate": 1.5641952983725134e-05,
|
349 |
+
"loss": 1.4937,
|
350 |
+
"step": 28500
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 3.5,
|
354 |
+
"learning_rate": 1.5039180229053649e-05,
|
355 |
+
"loss": 1.5031,
|
356 |
+
"step": 29000
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 3.56,
|
360 |
+
"learning_rate": 1.4436407474382158e-05,
|
361 |
+
"loss": 1.5006,
|
362 |
+
"step": 29500
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 3.62,
|
366 |
+
"learning_rate": 1.383363471971067e-05,
|
367 |
+
"loss": 1.4899,
|
368 |
+
"step": 30000
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 3.68,
|
372 |
+
"learning_rate": 1.3230861965039181e-05,
|
373 |
+
"loss": 1.4942,
|
374 |
+
"step": 30500
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 3.74,
|
378 |
+
"learning_rate": 1.2628089210367692e-05,
|
379 |
+
"loss": 1.48,
|
380 |
+
"step": 31000
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 3.8,
|
384 |
+
"learning_rate": 1.2025316455696203e-05,
|
385 |
+
"loss": 1.4784,
|
386 |
+
"step": 31500
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 3.86,
|
390 |
+
"learning_rate": 1.1422543701024713e-05,
|
391 |
+
"loss": 1.4768,
|
392 |
+
"step": 32000
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 3.92,
|
396 |
+
"learning_rate": 1.0819770946353224e-05,
|
397 |
+
"loss": 1.4776,
|
398 |
+
"step": 32500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 3.98,
|
402 |
+
"learning_rate": 1.0216998191681737e-05,
|
403 |
+
"loss": 1.4759,
|
404 |
+
"step": 33000
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.04,
|
408 |
+
"learning_rate": 9.614225437010247e-06,
|
409 |
+
"loss": 1.4794,
|
410 |
+
"step": 33500
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 4.1,
|
414 |
+
"learning_rate": 9.011452682338758e-06,
|
415 |
+
"loss": 1.4614,
|
416 |
+
"step": 34000
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 4.16,
|
420 |
+
"learning_rate": 8.408679927667269e-06,
|
421 |
+
"loss": 1.4605,
|
422 |
+
"step": 34500
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.22,
|
426 |
+
"learning_rate": 7.805907172995782e-06,
|
427 |
+
"loss": 1.4724,
|
428 |
+
"step": 35000
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 4.28,
|
432 |
+
"learning_rate": 7.203134418324292e-06,
|
433 |
+
"loss": 1.4625,
|
434 |
+
"step": 35500
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 4.34,
|
438 |
+
"learning_rate": 6.600361663652803e-06,
|
439 |
+
"loss": 1.4623,
|
440 |
+
"step": 36000
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 4.4,
|
444 |
+
"learning_rate": 5.997588908981315e-06,
|
445 |
+
"loss": 1.4485,
|
446 |
+
"step": 36500
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 4.46,
|
450 |
+
"learning_rate": 5.3948161543098255e-06,
|
451 |
+
"loss": 1.4532,
|
452 |
+
"step": 37000
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 4.52,
|
456 |
+
"learning_rate": 4.792043399638336e-06,
|
457 |
+
"loss": 1.4435,
|
458 |
+
"step": 37500
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 4.58,
|
462 |
+
"learning_rate": 4.189270644966848e-06,
|
463 |
+
"loss": 1.4503,
|
464 |
+
"step": 38000
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 4.64,
|
468 |
+
"learning_rate": 3.5864978902953588e-06,
|
469 |
+
"loss": 1.4512,
|
470 |
+
"step": 38500
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 4.7,
|
474 |
+
"learning_rate": 2.98372513562387e-06,
|
475 |
+
"loss": 1.4388,
|
476 |
+
"step": 39000
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 4.76,
|
480 |
+
"learning_rate": 2.3809523809523808e-06,
|
481 |
+
"loss": 1.4554,
|
482 |
+
"step": 39500
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 4.82,
|
486 |
+
"learning_rate": 1.778179626280892e-06,
|
487 |
+
"loss": 1.4481,
|
488 |
+
"step": 40000
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 4.88,
|
492 |
+
"learning_rate": 1.1754068716094034e-06,
|
493 |
+
"loss": 1.4525,
|
494 |
+
"step": 40500
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 4.94,
|
498 |
+
"learning_rate": 5.726341169379144e-07,
|
499 |
+
"loss": 1.4436,
|
500 |
+
"step": 41000
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 5.0,
|
504 |
+
"step": 41475,
|
505 |
+
"total_flos": 6.56610253452288e+16,
|
506 |
+
"train_loss": 1.5926296373474231,
|
507 |
+
"train_runtime": 22304.2482,
|
508 |
+
"train_samples_per_second": 11.156,
|
509 |
+
"train_steps_per_second": 1.86
|
510 |
+
}
|
511 |
+
],
|
512 |
+
"max_steps": 41475,
|
513 |
+
"num_train_epochs": 5,
|
514 |
+
"total_flos": 6.56610253452288e+16,
|
515 |
+
"trial_name": null,
|
516 |
+
"trial_params": null
|
517 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc82095cabb03b6c96c035b9eb208a6ba56bb90071f2c33b9cc830b82aa1fdd4
|
3 |
+
size 3055
|