End of training
Browse files- .gitattributes +1 -0
- .gitignore +1 -0
- all_results.json +22 -0
- config.json +32 -0
- eval_results.json +12 -0
- generated_predictions.txt +0 -0
- generation_config.json +6 -0
- predict_results.json +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +3 -0
- tokenizer_config.json +11 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
32 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
33 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
34 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
35 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.gitignore
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
checkpoint-*/
|
all_results.json
ADDED
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_gen_len": 65.14869050971558,
|
3 |
+
"eval_loss": 1.8010571002960205,
|
4 |
+
"eval_rouge1": 32.6372,
|
5 |
+
"eval_rouge2": 12.4352,
|
6 |
+
"eval_rougeL": 22.9598,
|
7 |
+
"eval_rougeLsum": 30.3946,
|
8 |
+
"eval_runtime": 167.4595,
|
9 |
+
"eval_samples": 3551,
|
10 |
+
"eval_samples_per_second": 21.205,
|
11 |
+
"eval_steps_per_second": 0.167,
|
12 |
+
"predict_gen_len": 67.65578424414478,
|
13 |
+
"predict_loss": 1.7709635496139526,
|
14 |
+
"predict_rouge1": 32.4648,
|
15 |
+
"predict_rouge2": 12.7718,
|
16 |
+
"predict_rougeL": 23.4671,
|
17 |
+
"predict_rougeLsum": 30.2757,
|
18 |
+
"predict_runtime": 275.8055,
|
19 |
+
"predict_samples": 5636,
|
20 |
+
"predict_samples_per_second": 20.435,
|
21 |
+
"predict_steps_per_second": 0.163
|
22 |
+
}
|
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-large-cnndaily/checkpoint-10318",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2816,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 1024,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
+
"dropout_rate": 0.1,
|
12 |
+
"eos_token_id": 1,
|
13 |
+
"feed_forward_proj": "gated-gelu",
|
14 |
+
"initializer_factor": 1.0,
|
15 |
+
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
+
"layer_norm_epsilon": 1e-06,
|
18 |
+
"model_type": "t5",
|
19 |
+
"num_decoder_layers": 24,
|
20 |
+
"num_heads": 16,
|
21 |
+
"num_layers": 24,
|
22 |
+
"output_past": true,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"tokenizer_class": "T5Tokenizer",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.27.0.dev0",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250112
|
32 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eval_gen_len": 65.14869050971558,
|
3 |
+
"eval_loss": 1.8010571002960205,
|
4 |
+
"eval_rouge1": 32.6372,
|
5 |
+
"eval_rouge2": 12.4352,
|
6 |
+
"eval_rougeL": 22.9598,
|
7 |
+
"eval_rougeLsum": 30.3946,
|
8 |
+
"eval_runtime": 167.4595,
|
9 |
+
"eval_samples": 3551,
|
10 |
+
"eval_samples_per_second": 21.205,
|
11 |
+
"eval_steps_per_second": 0.167
|
12 |
+
}
|
generated_predictions.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"decoder_start_token_id": 0,
|
3 |
+
"eos_token_id": 1,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.27.0.dev0"
|
6 |
+
}
|
predict_results.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"predict_gen_len": 67.65578424414478,
|
3 |
+
"predict_loss": 1.7709635496139526,
|
4 |
+
"predict_rouge1": 32.4648,
|
5 |
+
"predict_rouge2": 12.7718,
|
6 |
+
"predict_rougeL": 23.4671,
|
7 |
+
"predict_rougeLsum": 30.2757,
|
8 |
+
"predict_runtime": 275.8055,
|
9 |
+
"predict_samples": 5636,
|
10 |
+
"predict_samples_per_second": 20.435,
|
11 |
+
"predict_steps_per_second": 0.163
|
12 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c73bc1d3c697417ea522598e0261f2c2288e818f1d8d3806821981aee905215
|
3 |
+
size 4918519193
|
special_tokens_map.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
|
3 |
+
size 4309802
|
tokenizer.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6502d07619068a98aa2d3bb531332a694ffe108ca6c6fe62a467ccfe98d666b9
|
3 |
+
size 16315219
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"extra_ids": 0,
|
5 |
+
"model_max_length": 1000000000000000019884624838656,
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sp_model_kwargs": {},
|
8 |
+
"special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
|
9 |
+
"tokenizer_class": "T5Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:008c17e1097029732fc4cc281b0b270e53c1d2a495c524540908d79a67079359
|
3 |
+
size 3707
|