Commit
·
de7c1d4
1
Parent(s):
6ff6c23
Upload 12 files
Browse files- config.json +1 -1
- generation_config.json +7 -0
- optimizer.pt +3 -0
- pytorch_model.bin +1 -1
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- tokenizer_config.json +1 -2
- trainer_state.json +38 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -25,7 +25,7 @@
|
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "float32",
|
28 |
-
"transformers_version": "4.
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 32100
|
31 |
}
|
|
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"tie_word_embeddings": false,
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.28.1",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 32100
|
31 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"decoder_start_token_id": 0,
|
4 |
+
"eos_token_id": 1,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.1"
|
7 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:456d3711287986b7f27929fe0fbded05bcbbd98387a92740b9b1ef56ad894477
|
3 |
+
size 1980446085
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990236853
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d675b65f1f4cba3406b8bd9e9ff2625f9581e68665bc3e274b79770e475cac62
|
3 |
size 990236853
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df27e633b2b4506b18a5a41802d52e86fe621a88e79819863260ed69ac7f9335
|
3 |
+
size 14575
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:867316fc27f84daa9fb93f7705f521aa73cb5355d4500dd63c428294ee5115c9
|
3 |
+
size 627
|
tokenizer_config.json
CHANGED
@@ -101,13 +101,12 @@
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
|
|
104 |
"eos_token": "</s>",
|
105 |
"extra_ids": 100,
|
106 |
"model_max_length": 512,
|
107 |
-
"name_or_path": "allenai/tk-instruct-base-def-pos",
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
110 |
-
"special_tokens_map_file": "/home/patrick/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46",
|
111 |
"tokenizer_class": "T5Tokenizer",
|
112 |
"unk_token": "<unk>"
|
113 |
}
|
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
+
"clean_up_tokenization_spaces": true,
|
105 |
"eos_token": "</s>",
|
106 |
"extra_ids": 100,
|
107 |
"model_max_length": 512,
|
|
|
108 |
"pad_token": "<pad>",
|
109 |
"sp_model_kwargs": {},
|
|
|
110 |
"tokenizer_class": "T5Tokenizer",
|
111 |
"unk_token": "<unk>"
|
112 |
}
|
trainer_state.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.0,
|
5 |
+
"global_step": 580,
|
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 |
+
"eval_loss": 0.3067856431007385,
|
13 |
+
"eval_runtime": 17.8304,
|
14 |
+
"eval_samples_per_second": 35.782,
|
15 |
+
"eval_steps_per_second": 2.243,
|
16 |
+
"step": 290
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.72,
|
20 |
+
"learning_rate": 3.508587904974522e-05,
|
21 |
+
"loss": 0.3404,
|
22 |
+
"step": 500
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"eval_loss": 0.27310052514076233,
|
27 |
+
"eval_runtime": 17.9797,
|
28 |
+
"eval_samples_per_second": 35.485,
|
29 |
+
"eval_steps_per_second": 2.225,
|
30 |
+
"step": 580
|
31 |
+
}
|
32 |
+
],
|
33 |
+
"max_steps": 1160,
|
34 |
+
"num_train_epochs": 4,
|
35 |
+
"total_flos": 2050812231828480.0,
|
36 |
+
"trial_name": null,
|
37 |
+
"trial_params": null
|
38 |
+
}
|
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 sha256:500d4126a7ddd04082bf4f576e30f8a87b3d0d59fcf6c4a5c2a2fc51a5e0ac8a
|
3 |
+
size 3835
|