Training in progress, epoch 9
Browse files- checkpoint-1215/added_tokens.json +1 -0
- checkpoint-1215/config.json +28 -0
- checkpoint-1215/optimizer.pt +3 -0
- checkpoint-1215/pytorch_model.bin +3 -0
- checkpoint-1215/rng_state.pth +3 -0
- checkpoint-1215/scaler.pt +3 -0
- checkpoint-1215/scheduler.pt +3 -0
- checkpoint-1215/special_tokens_map.json +1 -0
- checkpoint-1215/spiece.model +3 -0
- checkpoint-1215/tokenizer.json +0 -0
- checkpoint-1215/tokenizer_config.json +1 -0
- checkpoint-1215/trainer_state.json +142 -0
- checkpoint-1215/training_args.bin +3 -0
- checkpoint-1350/added_tokens.json +1 -0
- checkpoint-1350/config.json +28 -0
- checkpoint-1350/optimizer.pt +3 -0
- checkpoint-1350/pytorch_model.bin +3 -0
- checkpoint-1350/rng_state.pth +3 -0
- checkpoint-1350/scaler.pt +3 -0
- checkpoint-1350/scheduler.pt +3 -0
- checkpoint-1350/special_tokens_map.json +1 -0
- checkpoint-1350/spiece.model +3 -0
- checkpoint-1350/tokenizer.json +0 -0
- checkpoint-1350/tokenizer_config.json +1 -0
- checkpoint-1350/trainer_state.json +156 -0
- checkpoint-1350/training_args.bin +3 -0
- pytorch_model.bin +1 -1
checkpoint-1215/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<CSD>": 32100}
|
checkpoint-1215/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/t5-v1_1-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
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": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"num_decoder_layers": 12,
|
18 |
+
"num_heads": 12,
|
19 |
+
"num_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"relative_attention_num_buckets": 32,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.16.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32101
|
28 |
+
}
|
checkpoint-1215/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d2418dc2866f0faf28ee63408ddac48ba809c36793baf2015edd73b7c879324
|
3 |
+
size 1980455257
|
checkpoint-1215/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b3754caed6a5e92adbf19c94addf2ea4520f93dbb5cc8ebe6124561e15230ec
|
3 |
+
size 990272461
|
checkpoint-1215/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:542baa314e1713521c4d7a09fbbb906bf33fa6e22bb670a6d0bb139c40d471d0
|
3 |
+
size 14503
|
checkpoint-1215/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ee64f81e11fb4023ccce5a8bcfb0e976197229db0e4af837461055e0a9d041
|
3 |
+
size 559
|
checkpoint-1215/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:124e123bacd421f8436683b2136339433bc2069c1bc5dbf733c5278f6e00a37e
|
3 |
+
size 623
|
checkpoint-1215/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-1215/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-1215/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1215/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, "name_or_path": "google/t5-v1_1-base", "special_tokens_map_file": "/home/chris-zeng/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
checkpoint-1215/trainer_state.json
ADDED
@@ -0,0 +1,142 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.22521649301052094,
|
3 |
+
"best_model_checkpoint": "outputs/t5-v1_1-base-detox/checkpoint-1080",
|
4 |
+
"epoch": 8.995391705069125,
|
5 |
+
"global_step": 1215,
|
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": 8.9719,
|
14 |
+
"step": 135
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.031940221786499,
|
19 |
+
"eval_runtime": 22.7196,
|
20 |
+
"eval_samples_per_second": 136.446,
|
21 |
+
"eval_steps_per_second": 17.078,
|
22 |
+
"step": 135
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8e-05,
|
27 |
+
"loss": 1.9438,
|
28 |
+
"step": 270
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.6424035429954529,
|
33 |
+
"eval_runtime": 22.8507,
|
34 |
+
"eval_samples_per_second": 135.663,
|
35 |
+
"eval_steps_per_second": 16.98,
|
36 |
+
"step": 270
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 7e-05,
|
41 |
+
"loss": 0.8941,
|
42 |
+
"step": 405
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.43842175602912903,
|
47 |
+
"eval_runtime": 22.8845,
|
48 |
+
"eval_samples_per_second": 135.463,
|
49 |
+
"eval_steps_per_second": 16.955,
|
50 |
+
"step": 405
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 6e-05,
|
55 |
+
"loss": 0.6694,
|
56 |
+
"step": 540
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 0.3455743193626404,
|
61 |
+
"eval_runtime": 22.9242,
|
62 |
+
"eval_samples_per_second": 135.228,
|
63 |
+
"eval_steps_per_second": 16.925,
|
64 |
+
"step": 540
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"learning_rate": 5e-05,
|
69 |
+
"loss": 0.5336,
|
70 |
+
"step": 675
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 0.2819174826145172,
|
75 |
+
"eval_runtime": 23.1392,
|
76 |
+
"eval_samples_per_second": 133.972,
|
77 |
+
"eval_steps_per_second": 16.768,
|
78 |
+
"step": 675
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 4e-05,
|
83 |
+
"loss": 0.4519,
|
84 |
+
"step": 810
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 0.24306097626686096,
|
89 |
+
"eval_runtime": 22.7762,
|
90 |
+
"eval_samples_per_second": 136.107,
|
91 |
+
"eval_steps_per_second": 17.035,
|
92 |
+
"step": 810
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 0.4006,
|
98 |
+
"step": 945
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 0.23186618089675903,
|
103 |
+
"eval_runtime": 23.1423,
|
104 |
+
"eval_samples_per_second": 133.954,
|
105 |
+
"eval_steps_per_second": 16.766,
|
106 |
+
"step": 945
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 8.0,
|
110 |
+
"learning_rate": 2e-05,
|
111 |
+
"loss": 0.3771,
|
112 |
+
"step": 1080
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 8.0,
|
116 |
+
"eval_loss": 0.22521649301052094,
|
117 |
+
"eval_runtime": 22.8858,
|
118 |
+
"eval_samples_per_second": 135.455,
|
119 |
+
"eval_steps_per_second": 16.954,
|
120 |
+
"step": 1080
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 9.0,
|
124 |
+
"learning_rate": 1e-05,
|
125 |
+
"loss": 0.3646,
|
126 |
+
"step": 1215
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 9.0,
|
130 |
+
"eval_loss": 0.22711366415023804,
|
131 |
+
"eval_runtime": 23.0199,
|
132 |
+
"eval_samples_per_second": 134.666,
|
133 |
+
"eval_steps_per_second": 16.855,
|
134 |
+
"step": 1215
|
135 |
+
}
|
136 |
+
],
|
137 |
+
"max_steps": 1350,
|
138 |
+
"num_train_epochs": 10,
|
139 |
+
"total_flos": 1.1828425175728128e+16,
|
140 |
+
"trial_name": null,
|
141 |
+
"trial_params": null
|
142 |
+
}
|
checkpoint-1215/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:839084c79c487b59c2c5870b0257ed8fb82211fae1f0295222d556827c5f599c
|
3 |
+
size 3247
|
checkpoint-1350/added_tokens.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"<CSD>": 32100}
|
checkpoint-1350/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/t5-v1_1-base",
|
3 |
+
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"d_ff": 2048,
|
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": "gated-gelu",
|
13 |
+
"initializer_factor": 1.0,
|
14 |
+
"is_encoder_decoder": true,
|
15 |
+
"layer_norm_epsilon": 1e-06,
|
16 |
+
"model_type": "t5",
|
17 |
+
"num_decoder_layers": 12,
|
18 |
+
"num_heads": 12,
|
19 |
+
"num_layers": 12,
|
20 |
+
"output_past": true,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"relative_attention_num_buckets": 32,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.16.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32101
|
28 |
+
}
|
checkpoint-1350/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a102657c8abcee83a727a69bd19037aaf7d086a789e1ed3636e17ca71cccce1c
|
3 |
+
size 1980455257
|
checkpoint-1350/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b96f85935381aa728a8408d2b058937fa87bb407e7b2b45da5292d662a8717
|
3 |
+
size 990272461
|
checkpoint-1350/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a962512227aebbde2d2be290e39986c046f6f9afa677c57d50e43a997d7927d
|
3 |
+
size 14503
|
checkpoint-1350/scaler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38c8383aa55713a5718c61e5991e5ced733d4d656374b83a5ea439678861908a
|
3 |
+
size 559
|
checkpoint-1350/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b5ef616b9ca994fc4bcdf514c869f8427d5e4c7b958be5f5d9883a7ed601683
|
3 |
+
size 623
|
checkpoint-1350/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-1350/spiece.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
3 |
+
size 791656
|
checkpoint-1350/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1350/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, "name_or_path": "google/t5-v1_1-base", "special_tokens_map_file": "/home/chris-zeng/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
|
checkpoint-1350/trainer_state.json
ADDED
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.22521649301052094,
|
3 |
+
"best_model_checkpoint": "outputs/t5-v1_1-base-detox/checkpoint-1080",
|
4 |
+
"epoch": 9.995391705069125,
|
5 |
+
"global_step": 1350,
|
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": 8.9719,
|
14 |
+
"step": 135
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 1.0,
|
18 |
+
"eval_loss": 2.031940221786499,
|
19 |
+
"eval_runtime": 22.7196,
|
20 |
+
"eval_samples_per_second": 136.446,
|
21 |
+
"eval_steps_per_second": 17.078,
|
22 |
+
"step": 135
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"epoch": 2.0,
|
26 |
+
"learning_rate": 8e-05,
|
27 |
+
"loss": 1.9438,
|
28 |
+
"step": 270
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"eval_loss": 0.6424035429954529,
|
33 |
+
"eval_runtime": 22.8507,
|
34 |
+
"eval_samples_per_second": 135.663,
|
35 |
+
"eval_steps_per_second": 16.98,
|
36 |
+
"step": 270
|
37 |
+
},
|
38 |
+
{
|
39 |
+
"epoch": 3.0,
|
40 |
+
"learning_rate": 7e-05,
|
41 |
+
"loss": 0.8941,
|
42 |
+
"step": 405
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 3.0,
|
46 |
+
"eval_loss": 0.43842175602912903,
|
47 |
+
"eval_runtime": 22.8845,
|
48 |
+
"eval_samples_per_second": 135.463,
|
49 |
+
"eval_steps_per_second": 16.955,
|
50 |
+
"step": 405
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 4.0,
|
54 |
+
"learning_rate": 6e-05,
|
55 |
+
"loss": 0.6694,
|
56 |
+
"step": 540
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 4.0,
|
60 |
+
"eval_loss": 0.3455743193626404,
|
61 |
+
"eval_runtime": 22.9242,
|
62 |
+
"eval_samples_per_second": 135.228,
|
63 |
+
"eval_steps_per_second": 16.925,
|
64 |
+
"step": 540
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 5.0,
|
68 |
+
"learning_rate": 5e-05,
|
69 |
+
"loss": 0.5336,
|
70 |
+
"step": 675
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 5.0,
|
74 |
+
"eval_loss": 0.2819174826145172,
|
75 |
+
"eval_runtime": 23.1392,
|
76 |
+
"eval_samples_per_second": 133.972,
|
77 |
+
"eval_steps_per_second": 16.768,
|
78 |
+
"step": 675
|
79 |
+
},
|
80 |
+
{
|
81 |
+
"epoch": 6.0,
|
82 |
+
"learning_rate": 4e-05,
|
83 |
+
"loss": 0.4519,
|
84 |
+
"step": 810
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 6.0,
|
88 |
+
"eval_loss": 0.24306097626686096,
|
89 |
+
"eval_runtime": 22.7762,
|
90 |
+
"eval_samples_per_second": 136.107,
|
91 |
+
"eval_steps_per_second": 17.035,
|
92 |
+
"step": 810
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 7.0,
|
96 |
+
"learning_rate": 3e-05,
|
97 |
+
"loss": 0.4006,
|
98 |
+
"step": 945
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 7.0,
|
102 |
+
"eval_loss": 0.23186618089675903,
|
103 |
+
"eval_runtime": 23.1423,
|
104 |
+
"eval_samples_per_second": 133.954,
|
105 |
+
"eval_steps_per_second": 16.766,
|
106 |
+
"step": 945
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 8.0,
|
110 |
+
"learning_rate": 2e-05,
|
111 |
+
"loss": 0.3771,
|
112 |
+
"step": 1080
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 8.0,
|
116 |
+
"eval_loss": 0.22521649301052094,
|
117 |
+
"eval_runtime": 22.8858,
|
118 |
+
"eval_samples_per_second": 135.455,
|
119 |
+
"eval_steps_per_second": 16.954,
|
120 |
+
"step": 1080
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 9.0,
|
124 |
+
"learning_rate": 1e-05,
|
125 |
+
"loss": 0.3646,
|
126 |
+
"step": 1215
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 9.0,
|
130 |
+
"eval_loss": 0.22711366415023804,
|
131 |
+
"eval_runtime": 23.0199,
|
132 |
+
"eval_samples_per_second": 134.666,
|
133 |
+
"eval_steps_per_second": 16.855,
|
134 |
+
"step": 1215
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 10.0,
|
138 |
+
"learning_rate": 0.0,
|
139 |
+
"loss": 0.3578,
|
140 |
+
"step": 1350
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 10.0,
|
144 |
+
"eval_loss": 0.22696341574192047,
|
145 |
+
"eval_runtime": 22.8653,
|
146 |
+
"eval_samples_per_second": 135.576,
|
147 |
+
"eval_steps_per_second": 16.969,
|
148 |
+
"step": 1350
|
149 |
+
}
|
150 |
+
],
|
151 |
+
"max_steps": 1350,
|
152 |
+
"num_train_epochs": 10,
|
153 |
+
"total_flos": 1.3138971617968128e+16,
|
154 |
+
"trial_name": null,
|
155 |
+
"trial_params": null
|
156 |
+
}
|
checkpoint-1350/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:839084c79c487b59c2c5870b0257ed8fb82211fae1f0295222d556827c5f599c
|
3 |
+
size 3247
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 990272461
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b96f85935381aa728a8408d2b058937fa87bb407e7b2b45da5292d662a8717
|
3 |
size 990272461
|