yongzx commited on
Commit
cbb039f
·
1 Parent(s): fb004f7

rm --cached *

Browse files
.gitattributes DELETED
@@ -1,33 +0,0 @@
1
- *.7z filter=lfs diff=lfs merge=lfs -text
2
- *.arrow filter=lfs diff=lfs merge=lfs -text
3
- *.bin filter=lfs diff=lfs merge=lfs -text
4
- *.bz2 filter=lfs diff=lfs merge=lfs -text
5
- *.ftz filter=lfs diff=lfs merge=lfs -text
6
- *.gz filter=lfs diff=lfs merge=lfs -text
7
- *.h5 filter=lfs diff=lfs merge=lfs -text
8
- *.joblib filter=lfs diff=lfs merge=lfs -text
9
- *.lfs.* filter=lfs diff=lfs merge=lfs -text
10
- *.mlmodel filter=lfs diff=lfs merge=lfs -text
11
- *.model filter=lfs diff=lfs merge=lfs -text
12
- *.msgpack filter=lfs diff=lfs merge=lfs -text
13
- *.npy filter=lfs diff=lfs merge=lfs -text
14
- *.npz filter=lfs diff=lfs merge=lfs -text
15
- *.onnx filter=lfs diff=lfs merge=lfs -text
16
- *.ot filter=lfs diff=lfs merge=lfs -text
17
- *.parquet filter=lfs diff=lfs merge=lfs -text
18
- *.pb filter=lfs diff=lfs merge=lfs -text
19
- *.pickle filter=lfs diff=lfs merge=lfs -text
20
- *.pkl filter=lfs diff=lfs merge=lfs -text
21
- *.pt filter=lfs diff=lfs merge=lfs -text
22
- *.pth filter=lfs diff=lfs merge=lfs -text
23
- *.rar filter=lfs diff=lfs merge=lfs -text
24
- saved_model/**/* filter=lfs diff=lfs merge=lfs -text
25
- *.tar.* filter=lfs diff=lfs merge=lfs -text
26
- *.tflite filter=lfs diff=lfs merge=lfs -text
27
- *.tgz filter=lfs diff=lfs merge=lfs -text
28
- *.wasm filter=lfs diff=lfs merge=lfs -text
29
- *.xz filter=lfs diff=lfs merge=lfs -text
30
- *.zip filter=lfs diff=lfs merge=lfs -text
31
- *.zst filter=lfs diff=lfs merge=lfs -text
32
- *tfevents* filter=lfs diff=lfs merge=lfs -text
33
- tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
.gitignore DELETED
@@ -1,15 +0,0 @@
1
- checkpoint-*/
2
- */pilot_*/
3
- pilot_*/
4
- checkpoint-*/
5
- */pilot_*/
6
- pilot_*/
7
- checkpoint-*/
8
- */pilot_*/
9
- pilot_*/
10
- checkpoint-*/
11
- */pilot_*/
12
- pilot_*/
13
- checkpoint-*/
14
- */pilot_*/
15
- pilot_*/
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
all_results.json DELETED
@@ -1,14 +0,0 @@
1
- {
2
- "epoch": 2.13,
3
- "eval_loss": 2.3144264221191406,
4
- "eval_runtime": 479.0156,
5
- "eval_samples": 4608,
6
- "eval_samples_per_second": 9.62,
7
- "eval_steps_per_second": 4.81,
8
- "perplexity": 10.119117152100543,
9
- "train_loss": 2.46404990234375,
10
- "train_runtime": 61043.1273,
11
- "train_samples": 94080,
12
- "train_samples_per_second": 3.276,
13
- "train_steps_per_second": 0.41
14
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,39 +0,0 @@
1
- {
2
- "_name_or_path": "bigscience/bloom-350m",
3
- "adapters": {
4
- "adapters": {},
5
- "config_map": {},
6
- "fusion_config_map": {},
7
- "fusions": {}
8
- },
9
- "apply_residual_connection_post_layernorm": false,
10
- "architectures": [
11
- "BloomForCausalLM"
12
- ],
13
- "attention_dropout": 0.0,
14
- "attention_softmax_in_fp32": true,
15
- "bias_dropout_fusion": true,
16
- "bos_token_id": 1,
17
- "eos_token_id": 2,
18
- "hidden_dropout": 0.0,
19
- "hidden_size": 1024,
20
- "initializer_range": 0.02,
21
- "layer_norm_epsilon": 1e-05,
22
- "masked_softmax_fusion": true,
23
- "model_type": "bloom",
24
- "n_head": 16,
25
- "n_inner": null,
26
- "n_layer": 24,
27
- "offset_alibi": 100,
28
- "pad_token_id": 3,
29
- "pretraining_tp": 1,
30
- "seq_length": 2048,
31
- "skip_bias_add": true,
32
- "skip_bias_add_qkv": false,
33
- "slow_but_exact": false,
34
- "torch_dtype": "float32",
35
- "transformers_version": "4.20.0.dev0",
36
- "unk_token_id": 0,
37
- "use_cache": true,
38
- "vocab_size": 250880
39
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eval_results.json DELETED
@@ -1,9 +0,0 @@
1
- {
2
- "epoch": 2.13,
3
- "eval_loss": 2.3144264221191406,
4
- "eval_runtime": 479.0156,
5
- "eval_samples": 4608,
6
- "eval_samples_per_second": 9.62,
7
- "eval_steps_per_second": 4.81,
8
- "perplexity": 10.119117152100543
9
- }
 
 
 
 
 
 
 
 
 
 
pytorch_diff.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b9081e8d526052a2528e8a17e3c6531dacf48a3bd0c6531c254df54d3a55aeb
3
- size 22511165
 
 
 
 
pytorch_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:10508d1e416b6ef8eccdd237279b4bee7afcf9a6e4f1262a81bfbcf005c8b8ea
3
- size 2236955191
 
 
 
 
special_tokens_map.json DELETED
@@ -1 +0,0 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}
 
 
tatoeba-az-en-results.txt DELETED
@@ -1,7 +0,0 @@
1
- ==================================================
2
- Tatoeba Results (200 pairs of az-en)
3
- ==================================================
4
- Model: /users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_sft_100000samples_-1vocab_original-frozen
5
- [tensor(0.)]
6
- 0.00 ± 0.00
7
- ==================================================
 
 
 
 
 
 
 
 
tokenizer.json DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
3
- size 14500443
 
 
 
 
tokenizer_config.json DELETED
@@ -1 +0,0 @@
1
- {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "add_prefix_space": false, "name_or_path": "bigscience/bloom-350m", "special_tokens_map_file": null, "padding_side": "left", "tokenizer_class": "BloomTokenizer"}
 
 
train_results.json DELETED
@@ -1,8 +0,0 @@
1
- {
2
- "epoch": 2.13,
3
- "train_loss": 2.46404990234375,
4
- "train_runtime": 61043.1273,
5
- "train_samples": 94080,
6
- "train_samples_per_second": 3.276,
7
- "train_steps_per_second": 0.41
8
- }
 
 
 
 
 
 
 
 
 
trainer_state.json DELETED
@@ -1,135 +0,0 @@
1
- {
2
- "best_metric": 2.3144264221191406,
3
- "best_model_checkpoint": "/users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_sft_100000samples_-1vocab_original-frozen/checkpoint-25000",
4
- "epoch": 2.1258503401360542,
5
- "global_step": 25000,
6
- "is_hyper_param_search": false,
7
- "is_local_process_zero": true,
8
- "is_world_process_zero": true,
9
- "log_history": [
10
- {
11
- "epoch": 0.21,
12
- "l1_reg_loss": 0.0,
13
- "learning_rate": 9e-05,
14
- "loss": 3.1768,
15
- "step": 2500
16
- },
17
- {
18
- "epoch": 0.43,
19
- "l1_reg_loss": 0.0,
20
- "learning_rate": 8e-05,
21
- "loss": 2.6549,
22
- "step": 5000
23
- },
24
- {
25
- "epoch": 0.43,
26
- "eval_loss": 2.602942943572998,
27
- "eval_runtime": 480.7936,
28
- "eval_samples_per_second": 9.584,
29
- "eval_steps_per_second": 4.792,
30
- "step": 5000
31
- },
32
- {
33
- "epoch": 0.64,
34
- "l1_reg_loss": 0.0001,
35
- "learning_rate": 7e-05,
36
- "loss": 2.5072,
37
- "step": 7500
38
- },
39
- {
40
- "epoch": 0.85,
41
- "l1_reg_loss": 0.0001,
42
- "learning_rate": 6e-05,
43
- "loss": 2.4336,
44
- "step": 10000
45
- },
46
- {
47
- "epoch": 0.85,
48
- "eval_loss": 2.436041831970215,
49
- "eval_runtime": 480.6448,
50
- "eval_samples_per_second": 9.587,
51
- "eval_steps_per_second": 4.794,
52
- "step": 10000
53
- },
54
- {
55
- "epoch": 1.06,
56
- "l1_reg_loss": 0.0001,
57
- "learning_rate": 5e-05,
58
- "loss": 2.3747,
59
- "step": 12500
60
- },
61
- {
62
- "epoch": 1.28,
63
- "l1_reg_loss": 0.0001,
64
- "learning_rate": 4e-05,
65
- "loss": 2.332,
66
- "step": 15000
67
- },
68
- {
69
- "epoch": 1.28,
70
- "eval_loss": 2.36257266998291,
71
- "eval_runtime": 480.5182,
72
- "eval_samples_per_second": 9.59,
73
- "eval_steps_per_second": 4.795,
74
- "step": 15000
75
- },
76
- {
77
- "epoch": 1.49,
78
- "l1_reg_loss": 0.0001,
79
- "learning_rate": 3e-05,
80
- "loss": 2.3094,
81
- "step": 17500
82
- },
83
- {
84
- "epoch": 1.7,
85
- "l1_reg_loss": 0.0001,
86
- "learning_rate": 2e-05,
87
- "loss": 2.2923,
88
- "step": 20000
89
- },
90
- {
91
- "epoch": 1.7,
92
- "eval_loss": 2.326047658920288,
93
- "eval_runtime": 480.5697,
94
- "eval_samples_per_second": 9.589,
95
- "eval_steps_per_second": 4.794,
96
- "step": 20000
97
- },
98
- {
99
- "epoch": 1.91,
100
- "l1_reg_loss": 0.0001,
101
- "learning_rate": 1e-05,
102
- "loss": 2.2803,
103
- "step": 22500
104
- },
105
- {
106
- "epoch": 2.13,
107
- "l1_reg_loss": 0.0001,
108
- "learning_rate": 0.0,
109
- "loss": 2.2793,
110
- "step": 25000
111
- },
112
- {
113
- "epoch": 2.13,
114
- "eval_loss": 2.3144264221191406,
115
- "eval_runtime": 478.8598,
116
- "eval_samples_per_second": 9.623,
117
- "eval_steps_per_second": 4.811,
118
- "step": 25000
119
- },
120
- {
121
- "epoch": 2.13,
122
- "step": 25000,
123
- "total_flos": 3.714827943936e+17,
124
- "train_loss": 2.46404990234375,
125
- "train_runtime": 61043.1273,
126
- "train_samples_per_second": 3.276,
127
- "train_steps_per_second": 0.41
128
- }
129
- ],
130
- "max_steps": 25000,
131
- "num_train_epochs": 3,
132
- "total_flos": 3.714827943936e+17,
133
- "trial_name": null,
134
- "trial_params": null
135
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d9909364f1ae5e4a5a6d466bee22638c6f7675ee9ac21ef20ca13f0d207ecb8
3
- size 3375
 
 
 
 
wikiann-az-results.txt DELETED
@@ -1,8 +0,0 @@
1
- ==================================================
2
- Results WikiANN-az
3
- ==================================================
4
- Model: /users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_sft_100000samples_-1vocab_original-frozen/
5
- [0.1048873019415309, 0.13495469718645686, 0.11973180076628352, 0.09593421653723161, 0.11878319652341865]
6
- 11.49
7
- 1.34
8
- ==================================================
 
 
 
 
 
 
 
 
 
word_embeddings.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:174ed618237771e5906be0e8d70c568de63633f3bb5e8a1e303bbdbaeaedc1ca
3
- size 1027605867
 
 
 
 
word_embeddings_layernorm.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:10917f86841a4f322406bd72ba2e4ae8e4780aaf462c98a76eca01e0c5fbc893
3
- size 9703