Commit
•
907d4fc
1
Parent(s):
0bb4f9f
Training in progress, epoch 2
Browse files- model.safetensors +1 -1
- run-1/checkpoint-8420/config.json +25 -0
- run-1/checkpoint-8420/model.safetensors +3 -0
- run-1/checkpoint-8420/optimizer.pt +3 -0
- run-1/checkpoint-8420/rng_state.pth +3 -0
- run-1/checkpoint-8420/scheduler.pt +3 -0
- run-1/checkpoint-8420/special_tokens_map.json +7 -0
- run-1/checkpoint-8420/tokenizer.json +0 -0
- run-1/checkpoint-8420/tokenizer_config.json +55 -0
- run-1/checkpoint-8420/trainer_state.json +156 -0
- run-1/checkpoint-8420/training_args.bin +3 -0
- run-1/checkpoint-8420/vocab.txt +0 -0
- runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715697677.d0b6fd4b0e89.396.3 +2 -2
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267832560
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db29bc550c29b67ba33bf1510fd686d89e76b51a529616e9aa34a2a915e64a4c
|
3 |
size 267832560
|
run-1/checkpoint-8420/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilbert-base-uncased",
|
3 |
+
"activation": "gelu",
|
4 |
+
"architectures": [
|
5 |
+
"DistilBertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_dropout": 0.1,
|
8 |
+
"dim": 768,
|
9 |
+
"dropout": 0.1,
|
10 |
+
"hidden_dim": 3072,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"max_position_embeddings": 512,
|
13 |
+
"model_type": "distilbert",
|
14 |
+
"n_heads": 12,
|
15 |
+
"n_layers": 6,
|
16 |
+
"pad_token_id": 0,
|
17 |
+
"problem_type": "single_label_classification",
|
18 |
+
"qa_dropout": 0.1,
|
19 |
+
"seq_classif_dropout": 0.2,
|
20 |
+
"sinusoidal_pos_embds": false,
|
21 |
+
"tie_weights_": true,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.40.2",
|
24 |
+
"vocab_size": 30522
|
25 |
+
}
|
run-1/checkpoint-8420/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db29bc550c29b67ba33bf1510fd686d89e76b51a529616e9aa34a2a915e64a4c
|
3 |
+
size 267832560
|
run-1/checkpoint-8420/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58ce9238c96e271814fdff7c51f0afee37172bd996c80410687342418a4d7254
|
3 |
+
size 535727290
|
run-1/checkpoint-8420/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b6072e5519a25699c8c433f90cc84698ada8682ef972a22565664f18d6e9bcd
|
3 |
+
size 14244
|
run-1/checkpoint-8420/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f53c888981a56087762bc71d7ed3f200f7bfc191894d3ea4ca4aaff670f228f5
|
3 |
+
size 1064
|
run-1/checkpoint-8420/special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
run-1/checkpoint-8420/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
run-1/checkpoint-8420/tokenizer_config.json
ADDED
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"clean_up_tokenization_spaces": true,
|
45 |
+
"cls_token": "[CLS]",
|
46 |
+
"do_lower_case": true,
|
47 |
+
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 512,
|
49 |
+
"pad_token": "[PAD]",
|
50 |
+
"sep_token": "[SEP]",
|
51 |
+
"strip_accents": null,
|
52 |
+
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
run-1/checkpoint-8420/trainer_state.json
ADDED
@@ -0,0 +1,156 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.8979357798165137,
|
3 |
+
"best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-1/checkpoint-8420",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 8420,
|
7 |
+
"is_hyper_param_search": true,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1187648456057007,
|
13 |
+
"grad_norm": 10.556523323059082,
|
14 |
+
"learning_rate": 3.3640213484135133e-06,
|
15 |
+
"loss": 0.4628,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2375296912114014,
|
20 |
+
"grad_norm": 27.427276611328125,
|
21 |
+
"learning_rate": 3.261083118657898e-06,
|
22 |
+
"loss": 0.3038,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.35629453681710216,
|
27 |
+
"grad_norm": 10.17439079284668,
|
28 |
+
"learning_rate": 3.1581448889022824e-06,
|
29 |
+
"loss": 0.2837,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.4750593824228028,
|
34 |
+
"grad_norm": 13.1768159866333,
|
35 |
+
"learning_rate": 3.0552066591466673e-06,
|
36 |
+
"loss": 0.2588,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.5938242280285035,
|
41 |
+
"grad_norm": 7.38680362701416,
|
42 |
+
"learning_rate": 2.952268429391051e-06,
|
43 |
+
"loss": 0.2554,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.7125890736342043,
|
48 |
+
"grad_norm": 13.285799980163574,
|
49 |
+
"learning_rate": 2.849330199635436e-06,
|
50 |
+
"loss": 0.2433,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.831353919239905,
|
55 |
+
"grad_norm": 10.867403984069824,
|
56 |
+
"learning_rate": 2.7463919698798204e-06,
|
57 |
+
"loss": 0.2491,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.9501187648456056,
|
62 |
+
"grad_norm": 8.815483093261719,
|
63 |
+
"learning_rate": 2.643453740124205e-06,
|
64 |
+
"loss": 0.232,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.0,
|
69 |
+
"eval_accuracy": 0.8944954128440367,
|
70 |
+
"eval_loss": 0.2890743613243103,
|
71 |
+
"eval_runtime": 1.2151,
|
72 |
+
"eval_samples_per_second": 717.616,
|
73 |
+
"eval_steps_per_second": 45.262,
|
74 |
+
"step": 4210
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.0688836104513064,
|
78 |
+
"grad_norm": 16.8696231842041,
|
79 |
+
"learning_rate": 2.5405155103685896e-06,
|
80 |
+
"loss": 0.2066,
|
81 |
+
"step": 4500
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 1.187648456057007,
|
85 |
+
"grad_norm": 6.819976329803467,
|
86 |
+
"learning_rate": 2.4375772806129744e-06,
|
87 |
+
"loss": 0.1874,
|
88 |
+
"step": 5000
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 1.3064133016627077,
|
92 |
+
"grad_norm": 4.169142246246338,
|
93 |
+
"learning_rate": 2.3346390508573587e-06,
|
94 |
+
"loss": 0.1915,
|
95 |
+
"step": 5500
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 1.4251781472684084,
|
99 |
+
"grad_norm": 18.407304763793945,
|
100 |
+
"learning_rate": 2.2317008211017436e-06,
|
101 |
+
"loss": 0.2073,
|
102 |
+
"step": 6000
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 1.5439429928741093,
|
106 |
+
"grad_norm": 7.375812530517578,
|
107 |
+
"learning_rate": 2.128762591346128e-06,
|
108 |
+
"loss": 0.2011,
|
109 |
+
"step": 6500
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 1.66270783847981,
|
113 |
+
"grad_norm": 5.930243968963623,
|
114 |
+
"learning_rate": 2.0258243615905123e-06,
|
115 |
+
"loss": 0.2006,
|
116 |
+
"step": 7000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.7814726840855108,
|
120 |
+
"grad_norm": 4.470451831817627,
|
121 |
+
"learning_rate": 1.9228861318348967e-06,
|
122 |
+
"loss": 0.1969,
|
123 |
+
"step": 7500
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 1.9002375296912115,
|
127 |
+
"grad_norm": 11.651495933532715,
|
128 |
+
"learning_rate": 1.8199479020792813e-06,
|
129 |
+
"loss": 0.1855,
|
130 |
+
"step": 8000
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 2.0,
|
134 |
+
"eval_accuracy": 0.8979357798165137,
|
135 |
+
"eval_loss": 0.321312814950943,
|
136 |
+
"eval_runtime": 1.2118,
|
137 |
+
"eval_samples_per_second": 719.61,
|
138 |
+
"eval_steps_per_second": 45.388,
|
139 |
+
"step": 8420
|
140 |
+
}
|
141 |
+
],
|
142 |
+
"logging_steps": 500,
|
143 |
+
"max_steps": 16840,
|
144 |
+
"num_input_tokens_seen": 0,
|
145 |
+
"num_train_epochs": 4,
|
146 |
+
"save_steps": 500,
|
147 |
+
"total_flos": 1163165956727940.0,
|
148 |
+
"train_batch_size": 16,
|
149 |
+
"trial_name": null,
|
150 |
+
"trial_params": {
|
151 |
+
"learning_rate": 3.466959578169129e-06,
|
152 |
+
"num_train_epochs": 4,
|
153 |
+
"per_device_train_batch_size": 16,
|
154 |
+
"seed": 22
|
155 |
+
}
|
156 |
+
}
|
run-1/checkpoint-8420/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4981b833ec6213c008f66b30a316660ab04fb07a2c3971bfc74c2eb43819a780
|
3 |
+
size 5048
|
run-1/checkpoint-8420/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715697677.d0b6fd4b0e89.396.3
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 sha256:242e3fea628da28431b1f75611a6c8062e8868b0c23bc93c486fae1e8f979378
|
3 |
+
size 8871
|