indiejoseph
commited on
Commit
•
b814aaf
1
Parent(s):
1388220
Model save
Browse files- README.md +5 -17
- all_results.json +13 -13
- config.json +1 -1
- eval_results.json +3 -8
- generation_config.json +1 -1
- model.safetensors +3 -0
- runs/Nov28_14-00-45_44d3998eda2b/events.out.tfevents.1701180578.44d3998eda2b.3099222.0 +3 -0
- runs/Nov28_14-24-09_44d3998eda2b/events.out.tfevents.1701183372.44d3998eda2b.3101657.0 +3 -0
- runs/Nov28_18-18-01_44d3998eda2b/events.out.tfevents.1701197416.44d3998eda2b.3136596.0 +3 -0
- runs/Nov28_19-12-15_44d3998eda2b/events.out.tfevents.1701200666.44d3998eda2b.3141349.0 +3 -0
- train_results.json +6 -6
- trainer_state.json +429 -81
- training_args.bin +2 -2
README.md
CHANGED
@@ -1,23 +1,9 @@
|
|
1 |
---
|
2 |
-
base_model: fnlp/bert-base-chinese
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
model-index:
|
6 |
- name: bart-base-cantonese
|
7 |
results: []
|
8 |
-
datasets:
|
9 |
-
- indiejoseph/wikipedia-zh-yue-filtered
|
10 |
-
- indiejoseph/cc100-yue
|
11 |
-
- indiejoseph/ted-transcriptions-cantonese
|
12 |
-
- indiejoseph/c4-cantonese-filtered
|
13 |
-
- mozilla-foundation/common_voice_13_0
|
14 |
-
- jed351/rthk_news
|
15 |
-
- jed351/shikoto_zh_hk
|
16 |
-
widget:
|
17 |
-
- text: "今日去咗旺角[MASK]"
|
18 |
-
example_title: "Mong Kok"
|
19 |
-
- text: "今時今日香港係一個[MASK]。"
|
20 |
-
example_title: "Hong Kong"
|
21 |
---
|
22 |
|
23 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -25,9 +11,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
25 |
|
26 |
# bart-base-cantonese
|
27 |
|
28 |
-
This model
|
29 |
|
30 |
-
|
|
|
|
|
31 |
|
32 |
## Intended uses & limitations
|
33 |
|
@@ -57,7 +45,7 @@ The following hyperparameters were used during training:
|
|
57 |
|
58 |
### Framework versions
|
59 |
|
60 |
-
- Transformers 4.35.
|
61 |
- Pytorch 2.1.1+cu121
|
62 |
- Datasets 2.14.6
|
63 |
- Tokenizers 0.14.1
|
|
|
1 |
---
|
|
|
2 |
tags:
|
3 |
- generated_from_trainer
|
4 |
model-index:
|
5 |
- name: bart-base-cantonese
|
6 |
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
---
|
8 |
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
11 |
|
12 |
# bart-base-cantonese
|
13 |
|
14 |
+
This model was trained from scratch on the None dataset.
|
15 |
|
16 |
+
## Model description
|
17 |
+
|
18 |
+
More information needed
|
19 |
|
20 |
## Intended uses & limitations
|
21 |
|
|
|
45 |
|
46 |
### Framework versions
|
47 |
|
48 |
+
- Transformers 4.35.2
|
49 |
- Pytorch 2.1.1+cu121
|
50 |
- Datasets 2.14.6
|
51 |
- Tokenizers 0.14.1
|
all_results.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"eval_accuracy": 0.
|
4 |
-
"eval_loss": 0.
|
5 |
-
"eval_runtime":
|
6 |
-
"eval_samples":
|
7 |
-
"eval_samples_per_second":
|
8 |
-
"eval_steps_per_second": 2.
|
9 |
-
"perplexity": 2.
|
10 |
-
"train_loss": 0.
|
11 |
-
"train_runtime":
|
12 |
-
"train_samples":
|
13 |
-
"train_samples_per_second": 19.
|
14 |
-
"train_steps_per_second": 1.
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"eval_accuracy": 0.8386325284846604,
|
4 |
+
"eval_loss": 0.8430067300796509,
|
5 |
+
"eval_runtime": 339.0879,
|
6 |
+
"eval_samples": 11278,
|
7 |
+
"eval_samples_per_second": 33.26,
|
8 |
+
"eval_steps_per_second": 2.079,
|
9 |
+
"perplexity": 2.3233421480194,
|
10 |
+
"train_loss": 0.787189019458772,
|
11 |
+
"train_runtime": 32945.1529,
|
12 |
+
"train_samples": 648171,
|
13 |
+
"train_samples_per_second": 19.674,
|
14 |
+
"train_steps_per_second": 1.23
|
15 |
}
|
config.json
CHANGED
@@ -69,7 +69,7 @@
|
|
69 |
},
|
70 |
"tokenizer_class": "BertTokenizer",
|
71 |
"torch_dtype": "float32",
|
72 |
-
"transformers_version": "4.35.
|
73 |
"use_cache": true,
|
74 |
"vocab_size": 51371
|
75 |
}
|
|
|
69 |
},
|
70 |
"tokenizer_class": "BertTokenizer",
|
71 |
"torch_dtype": "float32",
|
72 |
+
"transformers_version": "4.35.2",
|
73 |
"use_cache": true,
|
74 |
"vocab_size": 51371
|
75 |
}
|
eval_results.json
CHANGED
@@ -1,10 +1,5 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"eval_runtime": 188.7732,
|
6 |
-
"eval_samples": 6205,
|
7 |
-
"eval_samples_per_second": 32.87,
|
8 |
-
"eval_steps_per_second": 2.055,
|
9 |
-
"perplexity": 2.233884351646835
|
10 |
}
|
|
|
1 |
{
|
2 |
+
"eval_accuracy": 0.0,
|
3 |
+
"eval_loss": 11.697545369466146,
|
4 |
+
"eval_perplexity": 120276.11891132068
|
|
|
|
|
|
|
|
|
|
|
5 |
}
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
"no_repeat_ngram_size": 3,
|
9 |
"num_beams": 4,
|
10 |
"pad_token_id": 0,
|
11 |
-
"transformers_version": "4.35.
|
12 |
}
|
|
|
8 |
"no_repeat_ngram_size": 3,
|
9 |
"num_beams": 4,
|
10 |
"pad_token_id": 0,
|
11 |
+
"transformers_version": "4.35.2"
|
12 |
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cd8dc13b00393f4be5ae61eea43edb23b5f9cc6437f8979391a0a677f2519d1
|
3 |
+
size 561314676
|
runs/Nov28_14-00-45_44d3998eda2b/events.out.tfevents.1701180578.44d3998eda2b.3099222.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1de4ee578d88c3ccacef55afb9a31c2f9e2f78be1ae90047244709a6ff0520f9
|
3 |
+
size 5428
|
runs/Nov28_14-24-09_44d3998eda2b/events.out.tfevents.1701183372.44d3998eda2b.3101657.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:633b472eb60ffec309488358ef2154daac75bf51ebb63e5c5b0c9344d401dcb2
|
3 |
+
size 9981
|
runs/Nov28_18-18-01_44d3998eda2b/events.out.tfevents.1701197416.44d3998eda2b.3136596.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d870af4911b82236fc110d03aded1716e3e54bc74e8d10b3178bce21c0b6cfee
|
3 |
+
size 5899
|
runs/Nov28_19-12-15_44d3998eda2b/events.out.tfevents.1701200666.44d3998eda2b.3141349.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7dc98660544a599d020a0670457cdf57aa621524f6608c822116daeb79e6843f
|
3 |
+
size 18811
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss": 0.
|
4 |
-
"train_runtime":
|
5 |
-
"train_samples":
|
6 |
-
"train_samples_per_second": 19.
|
7 |
-
"train_steps_per_second": 1.
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 0.787189019458772,
|
4 |
+
"train_runtime": 32945.1529,
|
5 |
+
"train_samples": 648171,
|
6 |
+
"train_samples_per_second": 19.674,
|
7 |
+
"train_steps_per_second": 1.23
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,166 +1,514 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 2000.0,
|
6 |
-
"global_step":
|
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.
|
13 |
-
"learning_rate":
|
14 |
-
"loss": 1.
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
-
"epoch": 0.
|
19 |
-
"learning_rate":
|
20 |
-
"loss": 1.
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
-
"epoch": 0.
|
25 |
-
"learning_rate":
|
26 |
-
"loss":
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
-
"epoch": 0.
|
31 |
-
"learning_rate":
|
32 |
-
"loss":
|
33 |
"step": 2000
|
34 |
},
|
35 |
{
|
36 |
-
"epoch": 0.
|
37 |
-
"learning_rate":
|
38 |
-
"loss":
|
39 |
"step": 2500
|
40 |
},
|
41 |
{
|
42 |
-
"epoch": 0.
|
43 |
-
"learning_rate":
|
44 |
-
"loss": 0.
|
45 |
"step": 3000
|
46 |
},
|
47 |
{
|
48 |
-
"epoch": 0.
|
49 |
-
"learning_rate":
|
50 |
-
"loss": 0.
|
51 |
"step": 3500
|
52 |
},
|
53 |
{
|
54 |
-
"epoch": 1
|
55 |
-
"learning_rate":
|
56 |
-
"loss": 0.
|
57 |
"step": 4000
|
58 |
},
|
59 |
{
|
60 |
-
"epoch":
|
61 |
-
"learning_rate":
|
62 |
-
"loss": 0.
|
63 |
"step": 4500
|
64 |
},
|
65 |
{
|
66 |
-
"epoch":
|
67 |
-
"learning_rate":
|
68 |
-
"loss": 0.
|
69 |
"step": 5000
|
70 |
},
|
71 |
{
|
72 |
-
"epoch":
|
73 |
-
"learning_rate":
|
74 |
-
"loss": 0.
|
75 |
"step": 5500
|
76 |
},
|
77 |
{
|
78 |
-
"epoch":
|
79 |
-
"learning_rate":
|
80 |
-
"loss": 0.
|
81 |
"step": 6000
|
82 |
},
|
83 |
{
|
84 |
-
"epoch":
|
85 |
-
"learning_rate":
|
86 |
-
"loss": 0.
|
87 |
"step": 6500
|
88 |
},
|
89 |
{
|
90 |
-
"epoch":
|
91 |
-
"learning_rate": 4.
|
92 |
-
"loss": 0.
|
93 |
"step": 7000
|
94 |
},
|
95 |
{
|
96 |
-
"epoch":
|
97 |
-
"learning_rate": 4.
|
98 |
-
"loss": 0.
|
99 |
"step": 7500
|
100 |
},
|
101 |
{
|
102 |
-
"epoch": 2
|
103 |
-
"learning_rate":
|
104 |
-
"loss": 0.
|
105 |
"step": 8000
|
106 |
},
|
107 |
{
|
108 |
-
"epoch":
|
109 |
-
"learning_rate":
|
110 |
-
"loss": 0.
|
111 |
"step": 8500
|
112 |
},
|
113 |
{
|
114 |
-
"epoch":
|
115 |
-
"learning_rate":
|
116 |
-
"loss": 0.
|
117 |
"step": 9000
|
118 |
},
|
119 |
{
|
120 |
-
"epoch":
|
121 |
-
"learning_rate":
|
122 |
-
"loss": 0.
|
123 |
"step": 9500
|
124 |
},
|
125 |
{
|
126 |
-
"epoch":
|
127 |
-
"learning_rate":
|
128 |
-
"loss": 0.
|
129 |
"step": 10000
|
130 |
},
|
131 |
{
|
132 |
-
"epoch":
|
133 |
-
"learning_rate":
|
134 |
-
"loss": 0.
|
135 |
"step": 10500
|
136 |
},
|
137 |
{
|
138 |
-
"epoch":
|
139 |
-
"learning_rate":
|
140 |
-
"loss": 0.
|
141 |
"step": 11000
|
142 |
},
|
143 |
{
|
144 |
-
"epoch":
|
145 |
-
"learning_rate": 3.
|
146 |
-
"loss": 0.
|
147 |
"step": 11500
|
148 |
},
|
149 |
{
|
150 |
-
"epoch": 3
|
151 |
-
"
|
152 |
-
"
|
153 |
-
"
|
154 |
-
|
155 |
-
|
156 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
}
|
158 |
],
|
159 |
"logging_steps": 500,
|
160 |
-
"max_steps":
|
161 |
-
"num_train_epochs":
|
162 |
"save_steps": 2000,
|
163 |
-
"total_flos":
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|
166 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 2000.0,
|
6 |
+
"global_step": 40511,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 6.16979269496545e-06,
|
14 |
+
"loss": 1.3917,
|
15 |
"step": 500
|
16 |
},
|
17 |
{
|
18 |
+
"epoch": 0.02,
|
19 |
+
"learning_rate": 1.23395853899309e-05,
|
20 |
+
"loss": 1.0351,
|
21 |
"step": 1000
|
22 |
},
|
23 |
{
|
24 |
+
"epoch": 0.04,
|
25 |
+
"learning_rate": 1.8509378084896346e-05,
|
26 |
+
"loss": 0.9747,
|
27 |
"step": 1500
|
28 |
},
|
29 |
{
|
30 |
+
"epoch": 0.05,
|
31 |
+
"learning_rate": 2.46791707798618e-05,
|
32 |
+
"loss": 0.9373,
|
33 |
"step": 2000
|
34 |
},
|
35 |
{
|
36 |
+
"epoch": 0.06,
|
37 |
+
"learning_rate": 3.084896347482725e-05,
|
38 |
+
"loss": 0.9124,
|
39 |
"step": 2500
|
40 |
},
|
41 |
{
|
42 |
+
"epoch": 0.07,
|
43 |
+
"learning_rate": 3.701875616979269e-05,
|
44 |
+
"loss": 0.8946,
|
45 |
"step": 3000
|
46 |
},
|
47 |
{
|
48 |
+
"epoch": 0.09,
|
49 |
+
"learning_rate": 4.318854886475814e-05,
|
50 |
+
"loss": 0.8819,
|
51 |
"step": 3500
|
52 |
},
|
53 |
{
|
54 |
+
"epoch": 0.1,
|
55 |
+
"learning_rate": 4.93583415597236e-05,
|
56 |
+
"loss": 0.8723,
|
57 |
"step": 4000
|
58 |
},
|
59 |
{
|
60 |
+
"epoch": 0.11,
|
61 |
+
"learning_rate": 4.9385611234537426e-05,
|
62 |
+
"loss": 0.8615,
|
63 |
"step": 4500
|
64 |
},
|
65 |
{
|
66 |
+
"epoch": 0.12,
|
67 |
+
"learning_rate": 4.869990948736938e-05,
|
68 |
+
"loss": 0.8553,
|
69 |
"step": 5000
|
70 |
},
|
71 |
{
|
72 |
+
"epoch": 0.14,
|
73 |
+
"learning_rate": 4.801420774020132e-05,
|
74 |
+
"loss": 0.8466,
|
75 |
"step": 5500
|
76 |
},
|
77 |
{
|
78 |
+
"epoch": 0.15,
|
79 |
+
"learning_rate": 4.732850599303327e-05,
|
80 |
+
"loss": 0.8412,
|
81 |
"step": 6000
|
82 |
},
|
83 |
{
|
84 |
+
"epoch": 0.16,
|
85 |
+
"learning_rate": 4.6642804245865215e-05,
|
86 |
+
"loss": 0.8331,
|
87 |
"step": 6500
|
88 |
},
|
89 |
{
|
90 |
+
"epoch": 0.17,
|
91 |
+
"learning_rate": 4.5957102498697166e-05,
|
92 |
+
"loss": 0.8252,
|
93 |
"step": 7000
|
94 |
},
|
95 |
{
|
96 |
+
"epoch": 0.19,
|
97 |
+
"learning_rate": 4.527140075152912e-05,
|
98 |
+
"loss": 0.8164,
|
99 |
"step": 7500
|
100 |
},
|
101 |
{
|
102 |
+
"epoch": 0.2,
|
103 |
+
"learning_rate": 4.458569900436107e-05,
|
104 |
+
"loss": 0.8139,
|
105 |
"step": 8000
|
106 |
},
|
107 |
{
|
108 |
+
"epoch": 0.21,
|
109 |
+
"learning_rate": 4.389999725719302e-05,
|
110 |
+
"loss": 0.8072,
|
111 |
"step": 8500
|
112 |
},
|
113 |
{
|
114 |
+
"epoch": 0.22,
|
115 |
+
"learning_rate": 4.321429551002496e-05,
|
116 |
+
"loss": 0.8096,
|
117 |
"step": 9000
|
118 |
},
|
119 |
{
|
120 |
+
"epoch": 0.23,
|
121 |
+
"learning_rate": 4.252859376285691e-05,
|
122 |
+
"loss": 0.8026,
|
123 |
"step": 9500
|
124 |
},
|
125 |
{
|
126 |
+
"epoch": 0.25,
|
127 |
+
"learning_rate": 4.1842892015688856e-05,
|
128 |
+
"loss": 0.8027,
|
129 |
"step": 10000
|
130 |
},
|
131 |
{
|
132 |
+
"epoch": 0.26,
|
133 |
+
"learning_rate": 4.115719026852081e-05,
|
134 |
+
"loss": 0.7952,
|
135 |
"step": 10500
|
136 |
},
|
137 |
{
|
138 |
+
"epoch": 0.27,
|
139 |
+
"learning_rate": 4.047148852135275e-05,
|
140 |
+
"loss": 0.7936,
|
141 |
"step": 11000
|
142 |
},
|
143 |
{
|
144 |
+
"epoch": 0.28,
|
145 |
+
"learning_rate": 3.97857867741847e-05,
|
146 |
+
"loss": 0.7913,
|
147 |
"step": 11500
|
148 |
},
|
149 |
{
|
150 |
+
"epoch": 0.3,
|
151 |
+
"learning_rate": 3.910008502701665e-05,
|
152 |
+
"loss": 0.7896,
|
153 |
+
"step": 12000
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.31,
|
157 |
+
"learning_rate": 3.8414383279848596e-05,
|
158 |
+
"loss": 0.7857,
|
159 |
+
"step": 12500
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.32,
|
163 |
+
"learning_rate": 3.7728681532680547e-05,
|
164 |
+
"loss": 0.7842,
|
165 |
+
"step": 13000
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.33,
|
169 |
+
"learning_rate": 3.70429797855125e-05,
|
170 |
+
"loss": 0.7813,
|
171 |
+
"step": 13500
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.35,
|
175 |
+
"learning_rate": 3.635727803834445e-05,
|
176 |
+
"loss": 0.7812,
|
177 |
+
"step": 14000
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.36,
|
181 |
+
"learning_rate": 3.567157629117639e-05,
|
182 |
+
"loss": 0.7793,
|
183 |
+
"step": 14500
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.37,
|
187 |
+
"learning_rate": 3.498587454400834e-05,
|
188 |
+
"loss": 0.7721,
|
189 |
+
"step": 15000
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.38,
|
193 |
+
"learning_rate": 3.4300172796840286e-05,
|
194 |
+
"loss": 0.7726,
|
195 |
+
"step": 15500
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.39,
|
199 |
+
"learning_rate": 3.361447104967224e-05,
|
200 |
+
"loss": 0.7714,
|
201 |
+
"step": 16000
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.41,
|
205 |
+
"learning_rate": 3.292876930250419e-05,
|
206 |
+
"loss": 0.7737,
|
207 |
+
"step": 16500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.42,
|
211 |
+
"learning_rate": 3.224306755533613e-05,
|
212 |
+
"loss": 0.7661,
|
213 |
+
"step": 17000
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.43,
|
217 |
+
"learning_rate": 3.155736580816808e-05,
|
218 |
+
"loss": 0.7675,
|
219 |
+
"step": 17500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.44,
|
223 |
+
"learning_rate": 3.0871664061000026e-05,
|
224 |
+
"loss": 0.7688,
|
225 |
+
"step": 18000
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.46,
|
229 |
+
"learning_rate": 3.0185962313831976e-05,
|
230 |
+
"loss": 0.7637,
|
231 |
+
"step": 18500
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.47,
|
235 |
+
"learning_rate": 2.9500260566663924e-05,
|
236 |
+
"loss": 0.7644,
|
237 |
+
"step": 19000
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.48,
|
241 |
+
"learning_rate": 2.8814558819495874e-05,
|
242 |
+
"loss": 0.7632,
|
243 |
+
"step": 19500
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.49,
|
247 |
+
"learning_rate": 2.8128857072327825e-05,
|
248 |
+
"loss": 0.7607,
|
249 |
+
"step": 20000
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.51,
|
253 |
+
"learning_rate": 2.744315532515977e-05,
|
254 |
+
"loss": 0.7614,
|
255 |
+
"step": 20500
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.52,
|
259 |
+
"learning_rate": 2.675745357799172e-05,
|
260 |
+
"loss": 0.7602,
|
261 |
+
"step": 21000
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.53,
|
265 |
+
"learning_rate": 2.6071751830823667e-05,
|
266 |
+
"loss": 0.7564,
|
267 |
+
"step": 21500
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.54,
|
271 |
+
"learning_rate": 2.5386050083655617e-05,
|
272 |
+
"loss": 0.7574,
|
273 |
+
"step": 22000
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.56,
|
277 |
+
"learning_rate": 2.4700348336487565e-05,
|
278 |
+
"loss": 0.7534,
|
279 |
+
"step": 22500
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.57,
|
283 |
+
"learning_rate": 2.4014646589319512e-05,
|
284 |
+
"loss": 0.7567,
|
285 |
+
"step": 23000
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.58,
|
289 |
+
"learning_rate": 2.332894484215146e-05,
|
290 |
+
"loss": 0.7534,
|
291 |
+
"step": 23500
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.59,
|
295 |
+
"learning_rate": 2.2643243094983406e-05,
|
296 |
+
"loss": 0.7555,
|
297 |
+
"step": 24000
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.6,
|
301 |
+
"learning_rate": 2.1957541347815357e-05,
|
302 |
+
"loss": 0.7534,
|
303 |
+
"step": 24500
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.62,
|
307 |
+
"learning_rate": 2.1271839600647304e-05,
|
308 |
+
"loss": 0.7475,
|
309 |
+
"step": 25000
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.63,
|
313 |
+
"learning_rate": 2.058613785347925e-05,
|
314 |
+
"loss": 0.7482,
|
315 |
+
"step": 25500
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.64,
|
319 |
+
"learning_rate": 1.99004361063112e-05,
|
320 |
+
"loss": 0.7475,
|
321 |
+
"step": 26000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.65,
|
325 |
+
"learning_rate": 1.9214734359143146e-05,
|
326 |
+
"loss": 0.7479,
|
327 |
+
"step": 26500
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.67,
|
331 |
+
"learning_rate": 1.8529032611975096e-05,
|
332 |
+
"loss": 0.7433,
|
333 |
+
"step": 27000
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.68,
|
337 |
+
"learning_rate": 1.7843330864807044e-05,
|
338 |
+
"loss": 0.7473,
|
339 |
+
"step": 27500
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.69,
|
343 |
+
"learning_rate": 1.7157629117638994e-05,
|
344 |
+
"loss": 0.7439,
|
345 |
+
"step": 28000
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.7,
|
349 |
+
"learning_rate": 1.647192737047094e-05,
|
350 |
+
"loss": 0.7423,
|
351 |
+
"step": 28500
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.72,
|
355 |
+
"learning_rate": 1.578622562330289e-05,
|
356 |
+
"loss": 0.7429,
|
357 |
+
"step": 29000
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.73,
|
361 |
+
"learning_rate": 1.5100523876134836e-05,
|
362 |
+
"loss": 0.7424,
|
363 |
+
"step": 29500
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.74,
|
367 |
+
"learning_rate": 1.4414822128966785e-05,
|
368 |
+
"loss": 0.7408,
|
369 |
+
"step": 30000
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.75,
|
373 |
+
"learning_rate": 1.3729120381798732e-05,
|
374 |
+
"loss": 0.7402,
|
375 |
+
"step": 30500
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.77,
|
379 |
+
"learning_rate": 1.3043418634630683e-05,
|
380 |
+
"loss": 0.7376,
|
381 |
+
"step": 31000
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.78,
|
385 |
+
"learning_rate": 1.235771688746263e-05,
|
386 |
+
"loss": 0.7371,
|
387 |
+
"step": 31500
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.79,
|
391 |
+
"learning_rate": 1.1672015140294577e-05,
|
392 |
+
"loss": 0.741,
|
393 |
+
"step": 32000
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.8,
|
397 |
+
"learning_rate": 1.0986313393126526e-05,
|
398 |
+
"loss": 0.7354,
|
399 |
+
"step": 32500
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.81,
|
403 |
+
"learning_rate": 1.0300611645958475e-05,
|
404 |
+
"loss": 0.7343,
|
405 |
+
"step": 33000
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.83,
|
409 |
+
"learning_rate": 9.614909898790423e-06,
|
410 |
+
"loss": 0.7357,
|
411 |
+
"step": 33500
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.84,
|
415 |
+
"learning_rate": 8.92920815162237e-06,
|
416 |
+
"loss": 0.7319,
|
417 |
+
"step": 34000
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.85,
|
421 |
+
"learning_rate": 8.243506404454319e-06,
|
422 |
+
"loss": 0.7339,
|
423 |
+
"step": 34500
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.86,
|
427 |
+
"learning_rate": 7.557804657286268e-06,
|
428 |
+
"loss": 0.732,
|
429 |
+
"step": 35000
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.88,
|
433 |
+
"learning_rate": 6.872102910118215e-06,
|
434 |
+
"loss": 0.7352,
|
435 |
+
"step": 35500
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.89,
|
439 |
+
"learning_rate": 6.186401162950164e-06,
|
440 |
+
"loss": 0.7364,
|
441 |
+
"step": 36000
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.9,
|
445 |
+
"learning_rate": 5.500699415782112e-06,
|
446 |
+
"loss": 0.733,
|
447 |
+
"step": 36500
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.91,
|
451 |
+
"learning_rate": 4.814997668614059e-06,
|
452 |
+
"loss": 0.7318,
|
453 |
+
"step": 37000
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.93,
|
457 |
+
"learning_rate": 4.129295921446008e-06,
|
458 |
+
"loss": 0.7333,
|
459 |
+
"step": 37500
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.94,
|
463 |
+
"learning_rate": 3.4435941742779558e-06,
|
464 |
+
"loss": 0.7358,
|
465 |
+
"step": 38000
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.95,
|
469 |
+
"learning_rate": 2.7578924271099047e-06,
|
470 |
+
"loss": 0.7332,
|
471 |
+
"step": 38500
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.96,
|
475 |
+
"learning_rate": 2.0721906799418528e-06,
|
476 |
+
"loss": 0.7325,
|
477 |
+
"step": 39000
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.98,
|
481 |
+
"learning_rate": 1.3864889327738007e-06,
|
482 |
+
"loss": 0.7282,
|
483 |
+
"step": 39500
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.99,
|
487 |
+
"learning_rate": 7.00787185605749e-07,
|
488 |
+
"loss": 0.731,
|
489 |
+
"step": 40000
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.0,
|
493 |
+
"learning_rate": 1.508543843769714e-08,
|
494 |
+
"loss": 0.7318,
|
495 |
+
"step": 40500
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 1.0,
|
499 |
+
"step": 40511,
|
500 |
+
"total_flos": 1.9760674493693952e+17,
|
501 |
+
"train_loss": 0.787189019458772,
|
502 |
+
"train_runtime": 32945.1529,
|
503 |
+
"train_samples_per_second": 19.674,
|
504 |
+
"train_steps_per_second": 1.23
|
505 |
}
|
506 |
],
|
507 |
"logging_steps": 500,
|
508 |
+
"max_steps": 40511,
|
509 |
+
"num_train_epochs": 1,
|
510 |
"save_steps": 2000,
|
511 |
+
"total_flos": 1.9760674493693952e+17,
|
512 |
"trial_name": null,
|
513 |
"trial_params": null
|
514 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f321738d7dc9125e15c79e15f46839e735df9d313bee21b88fbd1a2628cf64c1
|
3 |
+
size 4664
|