Training in progress, epoch 6
Browse files- checkpoint-810/added_tokens.json +1 -0
- checkpoint-810/config.json +57 -0
- checkpoint-810/optimizer.pt +3 -0
- checkpoint-810/pytorch_model.bin +3 -0
- checkpoint-810/rng_state.pth +3 -0
- checkpoint-810/scaler.pt +3 -0
- checkpoint-810/scheduler.pt +3 -0
- checkpoint-810/special_tokens_map.json +1 -0
- checkpoint-810/spiece.model +3 -0
- checkpoint-810/tokenizer.json +0 -0
- checkpoint-810/tokenizer_config.json +1 -0
- checkpoint-810/trainer_state.json +100 -0
- checkpoint-810/training_args.bin +3 -0
- checkpoint-945/added_tokens.json +1 -0
- checkpoint-945/config.json +57 -0
- checkpoint-945/optimizer.pt +3 -0
- checkpoint-945/pytorch_model.bin +3 -0
- checkpoint-945/rng_state.pth +3 -0
- checkpoint-945/scaler.pt +3 -0
- checkpoint-945/scheduler.pt +3 -0
- checkpoint-945/special_tokens_map.json +1 -0
- checkpoint-945/spiece.model +3 -0
- checkpoint-945/tokenizer.json +0 -0
- checkpoint-945/tokenizer_config.json +1 -0
- checkpoint-945/trainer_state.json +114 -0
- checkpoint-945/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-810/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<CSD>": 32100}
|
checkpoint-810/config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 2.0,
|
28 |
+
"max_length": 200,
|
29 |
+
"min_length": 30,
|
30 |
+
"no_repeat_ngram_size": 3,
|
31 |
+
"num_beams": 4,
|
32 |
+
"prefix": "summarize: "
|
33 |
+
},
|
34 |
+
"translation_en_to_de": {
|
35 |
+
"early_stopping": true,
|
36 |
+
"max_length": 300,
|
37 |
+
"num_beams": 4,
|
38 |
+
"prefix": "translate English to German: "
|
39 |
+
},
|
40 |
+
"translation_en_to_fr": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"max_length": 300,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "translate English to French: "
|
45 |
+
},
|
46 |
+
"translation_en_to_ro": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to Romanian: "
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.16.2",
|
55 |
+
"use_cache": false,
|
56 |
+
"vocab_size": 32101
|
57 |
+
}
|
checkpoint-810/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c68dc3399cd5d67c84eb0eae158b25497293ee2b83e29e90764362b5ce5fe6c3
|
3 |
+
size 1783211965
|
checkpoint-810/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:65c25c76978d5c9fd5c7a34677a4923608a98c7ee8213d69bff405ef4bcc2ad9
|
3 |
+
size 891647935
|
checkpoint-810/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37befb2975ab1063cb14cf3ea1b5b8d190fb7489c39eba7084a8e8df1dd5d78e
|
3 |
+
size 14503
|
checkpoint-810/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d9a3a2afd74254bd8754a814e3ae3960b01c9386cad98a313ce986dd9c592a1
|
3 |
+
size 559
|
checkpoint-810/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02a193f86a70dd6e41d4704f196fab6aa7b25db1c4b75aff259d2831c3929dde
|
3 |
+
size 623
|
checkpoint-810/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
checkpoint-810/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-810/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-810/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
|
checkpoint-810/trainer_state.json
ADDED
@@ -0,0 +1,100 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2737014591693878,
|
3 |
+
"best_model_checkpoint": "outputs/t5-base-detox/checkpoint-810",
|
4 |
+
"epoch": 5.9953917050691246,
|
5 |
+
"global_step": 810,
|
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 |
+
"learning_rate": 9e-05,
|
13 |
+
"loss": 1.337,
|
14 |
+
"step": 135
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.48098286986351013,
|
19 |
+
"eval_runtime": 18.2812,
|
20 |
+
"eval_samples_per_second": 169.573,
|
21 |
+
"eval_steps_per_second": 21.224,
|
22 |
+
"step": 135
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8e-05,
|
27 |
+
"loss": 0.5238,
|
28 |
+
"step": 270
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.38857772946357727,
|
33 |
+
"eval_runtime": 18.7764,
|
34 |
+
"eval_samples_per_second": 165.101,
|
35 |
+
"eval_steps_per_second": 20.664,
|
36 |
+
"step": 270
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 7e-05,
|
41 |
+
"loss": 0.4301,
|
42 |
+
"step": 405
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.33775028586387634,
|
47 |
+
"eval_runtime": 18.505,
|
48 |
+
"eval_samples_per_second": 167.522,
|
49 |
+
"eval_steps_per_second": 20.967,
|
50 |
+
"step": 405
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 6e-05,
|
55 |
+
"loss": 0.3755,
|
56 |
+
"step": 540
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 0.31217730045318604,
|
61 |
+
"eval_runtime": 18.8887,
|
62 |
+
"eval_samples_per_second": 164.119,
|
63 |
+
"eval_steps_per_second": 20.541,
|
64 |
+
"step": 540
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"learning_rate": 5e-05,
|
69 |
+
"loss": 0.3359,
|
70 |
+
"step": 675
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 0.2910080552101135,
|
75 |
+
"eval_runtime": 18.2985,
|
76 |
+
"eval_samples_per_second": 169.413,
|
77 |
+
"eval_steps_per_second": 21.204,
|
78 |
+
"step": 675
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 4e-05,
|
83 |
+
"loss": 0.3068,
|
84 |
+
"step": 810
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 0.2737014591693878,
|
89 |
+
"eval_runtime": 18.6417,
|
90 |
+
"eval_samples_per_second": 166.294,
|
91 |
+
"eval_steps_per_second": 20.814,
|
92 |
+
"step": 810
|
93 |
+
}
|
94 |
+
],
|
95 |
+
"max_steps": 1350,
|
96 |
+
"num_train_epochs": 10,
|
97 |
+
"total_flos": 7009438344192000.0,
|
98 |
+
"trial_name": null,
|
99 |
+
"trial_params": null
|
100 |
+
}
|
checkpoint-810/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ceb7f0869ed2740615ac6ff98c0dd315d6a44ecbb6fe70eac15c7cbab0a4b65
|
3 |
+
size 3183
|
checkpoint-945/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<CSD>": 32100}
|
checkpoint-945/config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "t5-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 3072,
|
7 |
+
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
+
"decoder_start_token_id": 0,
|
10 |
+
"dropout_rate": 0.1,
|
11 |
+
"eos_token_id": 1,
|
12 |
+
"feed_forward_proj": "relu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"n_positions": 512,
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
+
"pad_token_id": 0,
|
23 |
+
"relative_attention_num_buckets": 32,
|
24 |
+
"task_specific_params": {
|
25 |
+
"summarization": {
|
26 |
+
"early_stopping": true,
|
27 |
+
"length_penalty": 2.0,
|
28 |
+
"max_length": 200,
|
29 |
+
"min_length": 30,
|
30 |
+
"no_repeat_ngram_size": 3,
|
31 |
+
"num_beams": 4,
|
32 |
+
"prefix": "summarize: "
|
33 |
+
},
|
34 |
+
"translation_en_to_de": {
|
35 |
+
"early_stopping": true,
|
36 |
+
"max_length": 300,
|
37 |
+
"num_beams": 4,
|
38 |
+
"prefix": "translate English to German: "
|
39 |
+
},
|
40 |
+
"translation_en_to_fr": {
|
41 |
+
"early_stopping": true,
|
42 |
+
"max_length": 300,
|
43 |
+
"num_beams": 4,
|
44 |
+
"prefix": "translate English to French: "
|
45 |
+
},
|
46 |
+
"translation_en_to_ro": {
|
47 |
+
"early_stopping": true,
|
48 |
+
"max_length": 300,
|
49 |
+
"num_beams": 4,
|
50 |
+
"prefix": "translate English to Romanian: "
|
51 |
+
}
|
52 |
+
},
|
53 |
+
"torch_dtype": "float32",
|
54 |
+
"transformers_version": "4.16.2",
|
55 |
+
"use_cache": false,
|
56 |
+
"vocab_size": 32101
|
57 |
+
}
|
checkpoint-945/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:078251830536d22699ace8454aa021d5a9871f90317f9796554fef2782d72f43
|
3 |
+
size 1783211965
|
checkpoint-945/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048c3d40567f94ccf1868541ecba24f916c86643833dec36cd5189710c80a2ef
|
3 |
+
size 891647935
|
checkpoint-945/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a1fa8002459afa3f79668beb0bc688306f986d89967257f5dd0b9a2f09aab61d
|
3 |
+
size 14503
|
checkpoint-945/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea5966bf2c38c09348d1c2d132a2be680c83b44ac5a594dcceaa8e159901261c
|
3 |
+
size 559
|
checkpoint-945/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9c748038eff3e5be92dc865799f4158603df312178abea08300d2f1a78c62c1
|
3 |
+
size 623
|
checkpoint-945/special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
|
checkpoint-945/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-945/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-945/tokenizer_config.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-base", "tokenizer_class": "T5Tokenizer"}
|
checkpoint-945/trainer_state.json
ADDED
@@ -0,0 +1,114 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2709713876247406,
|
3 |
+
"best_model_checkpoint": "outputs/t5-base-detox/checkpoint-945",
|
4 |
+
"epoch": 6.9953917050691246,
|
5 |
+
"global_step": 945,
|
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 |
+
"learning_rate": 9e-05,
|
13 |
+
"loss": 1.337,
|
14 |
+
"step": 135
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 0.48098286986351013,
|
19 |
+
"eval_runtime": 18.2812,
|
20 |
+
"eval_samples_per_second": 169.573,
|
21 |
+
"eval_steps_per_second": 21.224,
|
22 |
+
"step": 135
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8e-05,
|
27 |
+
"loss": 0.5238,
|
28 |
+
"step": 270
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.38857772946357727,
|
33 |
+
"eval_runtime": 18.7764,
|
34 |
+
"eval_samples_per_second": 165.101,
|
35 |
+
"eval_steps_per_second": 20.664,
|
36 |
+
"step": 270
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 7e-05,
|
41 |
+
"loss": 0.4301,
|
42 |
+
"step": 405
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.33775028586387634,
|
47 |
+
"eval_runtime": 18.505,
|
48 |
+
"eval_samples_per_second": 167.522,
|
49 |
+
"eval_steps_per_second": 20.967,
|
50 |
+
"step": 405
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 6e-05,
|
55 |
+
"loss": 0.3755,
|
56 |
+
"step": 540
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 0.31217730045318604,
|
61 |
+
"eval_runtime": 18.8887,
|
62 |
+
"eval_samples_per_second": 164.119,
|
63 |
+
"eval_steps_per_second": 20.541,
|
64 |
+
"step": 540
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"learning_rate": 5e-05,
|
69 |
+
"loss": 0.3359,
|
70 |
+
"step": 675
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 0.2910080552101135,
|
75 |
+
"eval_runtime": 18.2985,
|
76 |
+
"eval_samples_per_second": 169.413,
|
77 |
+
"eval_steps_per_second": 21.204,
|
78 |
+
"step": 675
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 4e-05,
|
83 |
+
"loss": 0.3068,
|
84 |
+
"step": 810
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 0.2737014591693878,
|
89 |
+
"eval_runtime": 18.6417,
|
90 |
+
"eval_samples_per_second": 166.294,
|
91 |
+
"eval_steps_per_second": 20.814,
|
92 |
+
"step": 810
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 0.2861,
|
98 |
+
"step": 945
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 0.2709713876247406,
|
103 |
+
"eval_runtime": 18.2786,
|
104 |
+
"eval_samples_per_second": 169.597,
|
105 |
+
"eval_steps_per_second": 21.227,
|
106 |
+
"step": 945
|
107 |
+
}
|
108 |
+
],
|
109 |
+
"max_steps": 1350,
|
110 |
+
"num_train_epochs": 10,
|
111 |
+
"total_flos": 8181729858355200.0,
|
112 |
+
"trial_name": null,
|
113 |
+
"trial_params": null
|
114 |
+
}
|
checkpoint-945/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ceb7f0869ed2740615ac6ff98c0dd315d6a44ecbb6fe70eac15c7cbab0a4b65
|
3 |
+
size 3183
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 891647935
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048c3d40567f94ccf1868541ecba24f916c86643833dec36cd5189710c80a2ef
|
3 |
size 891647935
|