Upload folder using huggingface_hub
Browse files- README.md +36 -0
- checkpoint-204/config.json +38 -0
- checkpoint-204/model.safetensors +3 -0
- checkpoint-204/optimizer.pt +3 -0
- checkpoint-204/rng_state.pth +3 -0
- checkpoint-204/scheduler.pt +3 -0
- checkpoint-204/trainer_state.json +572 -0
- checkpoint-204/training_args.bin +3 -0
- config.json +38 -0
- model.safetensors +3 -0
- runs/Nov21_14-36-08_r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d/events.out.tfevents.1732199772.r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d.440.0 +2 -2
- runs/Nov21_14-36-08_r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d/events.out.tfevents.1732206073.r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d.440.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
- training_args.bin +3 -0
- training_params.json +30 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
---
|
3 |
+
tags:
|
4 |
+
- autotrain
|
5 |
+
- text-classification
|
6 |
+
base_model: google-bert/bert-base-uncased
|
7 |
+
widget:
|
8 |
+
- text: "I love AutoTrain"
|
9 |
+
---
|
10 |
+
|
11 |
+
# Model Trained Using AutoTrain
|
12 |
+
|
13 |
+
- Problem type: Text Classification
|
14 |
+
|
15 |
+
## Validation Metrics
|
16 |
+
loss: 0.7707859873771667
|
17 |
+
|
18 |
+
f1_macro: 0.6722359201219389
|
19 |
+
|
20 |
+
f1_micro: 0.674074074074074
|
21 |
+
|
22 |
+
f1_weighted: 0.6722359201219389
|
23 |
+
|
24 |
+
precision_macro: 0.6750194250194249
|
25 |
+
|
26 |
+
precision_micro: 0.674074074074074
|
27 |
+
|
28 |
+
precision_weighted: 0.675019425019425
|
29 |
+
|
30 |
+
recall_macro: 0.674074074074074
|
31 |
+
|
32 |
+
recall_micro: 0.674074074074074
|
33 |
+
|
34 |
+
recall_weighted: 0.674074074074074
|
35 |
+
|
36 |
+
accuracy: 0.674074074074074
|
checkpoint-204/config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "negative",
|
15 |
+
"1": "neutral",
|
16 |
+
"2": "positive"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"negative": 0,
|
22 |
+
"neutral": 1,
|
23 |
+
"positive": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.46.2",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 30522
|
38 |
+
}
|
checkpoint-204/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4bbbe5875da93c0545e4b00e4c26a9ba77e95c072477d03317c7a23345145b3
|
3 |
+
size 437961724
|
checkpoint-204/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfd8cdb4ae47fe07c28971c363a41fbe7ae31118517ce302b824e249ab6b6bb0
|
3 |
+
size 876038906
|
checkpoint-204/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2bfb2d5c2058da8c76eb6401abd436c15cbe14373e4ad2efc681ad00f70b81e4
|
3 |
+
size 13990
|
checkpoint-204/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:acb8fe1e5d004b5d71099900aaa993567c53230962d397347705b3c8afb593bd
|
3 |
+
size 1064
|
checkpoint-204/trainer_state.json
ADDED
@@ -0,0 +1,572 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7707859873771667,
|
3 |
+
"best_model_checkpoint": "bert-balanced-v1/checkpoint-204",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 204,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.04411764705882353,
|
13 |
+
"grad_norm": 11.873502731323242,
|
14 |
+
"learning_rate": 7.142857142857143e-06,
|
15 |
+
"loss": 1.1054,
|
16 |
+
"step": 3
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.08823529411764706,
|
20 |
+
"grad_norm": 6.837568283081055,
|
21 |
+
"learning_rate": 1.4285714285714285e-05,
|
22 |
+
"loss": 1.1623,
|
23 |
+
"step": 6
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.1323529411764706,
|
27 |
+
"grad_norm": 6.079131126403809,
|
28 |
+
"learning_rate": 2.1428571428571428e-05,
|
29 |
+
"loss": 1.1727,
|
30 |
+
"step": 9
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.17647058823529413,
|
34 |
+
"grad_norm": 7.644276142120361,
|
35 |
+
"learning_rate": 2.857142857142857e-05,
|
36 |
+
"loss": 1.1962,
|
37 |
+
"step": 12
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.22058823529411764,
|
41 |
+
"grad_norm": 6.449653625488281,
|
42 |
+
"learning_rate": 3.571428571428572e-05,
|
43 |
+
"loss": 1.1334,
|
44 |
+
"step": 15
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2647058823529412,
|
48 |
+
"grad_norm": 3.3152713775634766,
|
49 |
+
"learning_rate": 4.2857142857142856e-05,
|
50 |
+
"loss": 1.0897,
|
51 |
+
"step": 18
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.3088235294117647,
|
55 |
+
"grad_norm": 6.6442036628723145,
|
56 |
+
"learning_rate": 5e-05,
|
57 |
+
"loss": 1.1438,
|
58 |
+
"step": 21
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.35294117647058826,
|
62 |
+
"grad_norm": 3.3698086738586426,
|
63 |
+
"learning_rate": 4.918032786885246e-05,
|
64 |
+
"loss": 1.2006,
|
65 |
+
"step": 24
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.39705882352941174,
|
69 |
+
"grad_norm": 7.311341762542725,
|
70 |
+
"learning_rate": 4.836065573770492e-05,
|
71 |
+
"loss": 1.0572,
|
72 |
+
"step": 27
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.4411764705882353,
|
76 |
+
"grad_norm": 8.757562637329102,
|
77 |
+
"learning_rate": 4.754098360655738e-05,
|
78 |
+
"loss": 1.0659,
|
79 |
+
"step": 30
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.4852941176470588,
|
83 |
+
"grad_norm": 7.169471263885498,
|
84 |
+
"learning_rate": 4.672131147540984e-05,
|
85 |
+
"loss": 1.1263,
|
86 |
+
"step": 33
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.5294117647058824,
|
90 |
+
"grad_norm": 6.60593843460083,
|
91 |
+
"learning_rate": 4.59016393442623e-05,
|
92 |
+
"loss": 1.0724,
|
93 |
+
"step": 36
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.5735294117647058,
|
97 |
+
"grad_norm": 5.335102558135986,
|
98 |
+
"learning_rate": 4.508196721311476e-05,
|
99 |
+
"loss": 1.0535,
|
100 |
+
"step": 39
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.6176470588235294,
|
104 |
+
"grad_norm": 5.638067245483398,
|
105 |
+
"learning_rate": 4.426229508196721e-05,
|
106 |
+
"loss": 1.0671,
|
107 |
+
"step": 42
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.6617647058823529,
|
111 |
+
"grad_norm": 3.3761277198791504,
|
112 |
+
"learning_rate": 4.3442622950819674e-05,
|
113 |
+
"loss": 1.0608,
|
114 |
+
"step": 45
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.7058823529411765,
|
118 |
+
"grad_norm": 3.7545318603515625,
|
119 |
+
"learning_rate": 4.262295081967213e-05,
|
120 |
+
"loss": 1.036,
|
121 |
+
"step": 48
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.75,
|
125 |
+
"grad_norm": 3.6131749153137207,
|
126 |
+
"learning_rate": 4.1803278688524595e-05,
|
127 |
+
"loss": 1.0085,
|
128 |
+
"step": 51
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.7941176470588235,
|
132 |
+
"grad_norm": 10.428824424743652,
|
133 |
+
"learning_rate": 4.098360655737705e-05,
|
134 |
+
"loss": 0.9663,
|
135 |
+
"step": 54
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.8382352941176471,
|
139 |
+
"grad_norm": 9.748165130615234,
|
140 |
+
"learning_rate": 4.016393442622951e-05,
|
141 |
+
"loss": 0.9838,
|
142 |
+
"step": 57
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8823529411764706,
|
146 |
+
"grad_norm": 7.34658145904541,
|
147 |
+
"learning_rate": 3.934426229508197e-05,
|
148 |
+
"loss": 0.914,
|
149 |
+
"step": 60
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.9264705882352942,
|
153 |
+
"grad_norm": 9.839737892150879,
|
154 |
+
"learning_rate": 3.8524590163934424e-05,
|
155 |
+
"loss": 1.0774,
|
156 |
+
"step": 63
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.9705882352941176,
|
160 |
+
"grad_norm": 6.513272762298584,
|
161 |
+
"learning_rate": 3.7704918032786885e-05,
|
162 |
+
"loss": 0.9173,
|
163 |
+
"step": 66
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 1.0,
|
167 |
+
"eval_accuracy": 0.6074074074074074,
|
168 |
+
"eval_f1_macro": 0.5499705029992206,
|
169 |
+
"eval_f1_micro": 0.6074074074074074,
|
170 |
+
"eval_f1_weighted": 0.5499705029992207,
|
171 |
+
"eval_loss": 0.9292003512382507,
|
172 |
+
"eval_precision_macro": 0.6655672369958084,
|
173 |
+
"eval_precision_micro": 0.6074074074074074,
|
174 |
+
"eval_precision_weighted": 0.6655672369958084,
|
175 |
+
"eval_recall_macro": 0.6074074074074074,
|
176 |
+
"eval_recall_micro": 0.6074074074074074,
|
177 |
+
"eval_recall_weighted": 0.6074074074074074,
|
178 |
+
"eval_runtime": 134.9252,
|
179 |
+
"eval_samples_per_second": 1.001,
|
180 |
+
"eval_steps_per_second": 0.067,
|
181 |
+
"step": 68
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 1.0147058823529411,
|
185 |
+
"grad_norm": 6.397573947906494,
|
186 |
+
"learning_rate": 3.6885245901639346e-05,
|
187 |
+
"loss": 1.1385,
|
188 |
+
"step": 69
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 1.0588235294117647,
|
192 |
+
"grad_norm": 8.004409790039062,
|
193 |
+
"learning_rate": 3.6065573770491806e-05,
|
194 |
+
"loss": 0.8346,
|
195 |
+
"step": 72
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 1.1029411764705883,
|
199 |
+
"grad_norm": 9.197546005249023,
|
200 |
+
"learning_rate": 3.524590163934427e-05,
|
201 |
+
"loss": 0.7762,
|
202 |
+
"step": 75
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 1.1470588235294117,
|
206 |
+
"grad_norm": 15.531254768371582,
|
207 |
+
"learning_rate": 3.442622950819672e-05,
|
208 |
+
"loss": 1.0938,
|
209 |
+
"step": 78
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 1.1911764705882353,
|
213 |
+
"grad_norm": 9.45050048828125,
|
214 |
+
"learning_rate": 3.360655737704918e-05,
|
215 |
+
"loss": 0.7187,
|
216 |
+
"step": 81
|
217 |
+
},
|
218 |
+
{
|
219 |
+
"epoch": 1.2352941176470589,
|
220 |
+
"grad_norm": 7.438510417938232,
|
221 |
+
"learning_rate": 3.2786885245901635e-05,
|
222 |
+
"loss": 0.6956,
|
223 |
+
"step": 84
|
224 |
+
},
|
225 |
+
{
|
226 |
+
"epoch": 1.2794117647058822,
|
227 |
+
"grad_norm": 7.671905994415283,
|
228 |
+
"learning_rate": 3.19672131147541e-05,
|
229 |
+
"loss": 0.8591,
|
230 |
+
"step": 87
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 1.3235294117647058,
|
234 |
+
"grad_norm": 5.862545013427734,
|
235 |
+
"learning_rate": 3.114754098360656e-05,
|
236 |
+
"loss": 0.7878,
|
237 |
+
"step": 90
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 1.3676470588235294,
|
241 |
+
"grad_norm": 12.08448314666748,
|
242 |
+
"learning_rate": 3.0327868852459017e-05,
|
243 |
+
"loss": 0.922,
|
244 |
+
"step": 93
|
245 |
+
},
|
246 |
+
{
|
247 |
+
"epoch": 1.4117647058823528,
|
248 |
+
"grad_norm": 25.875642776489258,
|
249 |
+
"learning_rate": 2.9508196721311478e-05,
|
250 |
+
"loss": 0.806,
|
251 |
+
"step": 96
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.4558823529411764,
|
255 |
+
"grad_norm": 7.914124488830566,
|
256 |
+
"learning_rate": 2.8688524590163935e-05,
|
257 |
+
"loss": 0.7999,
|
258 |
+
"step": 99
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 1.5,
|
262 |
+
"grad_norm": 7.366003513336182,
|
263 |
+
"learning_rate": 2.7868852459016392e-05,
|
264 |
+
"loss": 0.8753,
|
265 |
+
"step": 102
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 1.5441176470588234,
|
269 |
+
"grad_norm": 7.287258625030518,
|
270 |
+
"learning_rate": 2.7049180327868856e-05,
|
271 |
+
"loss": 0.75,
|
272 |
+
"step": 105
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.5882352941176472,
|
276 |
+
"grad_norm": 6.466761112213135,
|
277 |
+
"learning_rate": 2.6229508196721314e-05,
|
278 |
+
"loss": 0.7331,
|
279 |
+
"step": 108
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.6323529411764706,
|
283 |
+
"grad_norm": 11.213692665100098,
|
284 |
+
"learning_rate": 2.540983606557377e-05,
|
285 |
+
"loss": 0.9052,
|
286 |
+
"step": 111
|
287 |
+
},
|
288 |
+
{
|
289 |
+
"epoch": 1.6764705882352942,
|
290 |
+
"grad_norm": 10.924762725830078,
|
291 |
+
"learning_rate": 2.459016393442623e-05,
|
292 |
+
"loss": 1.0455,
|
293 |
+
"step": 114
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.7205882352941178,
|
297 |
+
"grad_norm": 8.067938804626465,
|
298 |
+
"learning_rate": 2.377049180327869e-05,
|
299 |
+
"loss": 0.8233,
|
300 |
+
"step": 117
|
301 |
+
},
|
302 |
+
{
|
303 |
+
"epoch": 1.7647058823529411,
|
304 |
+
"grad_norm": 6.702548027038574,
|
305 |
+
"learning_rate": 2.295081967213115e-05,
|
306 |
+
"loss": 1.0777,
|
307 |
+
"step": 120
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 1.8088235294117647,
|
311 |
+
"grad_norm": 5.71842098236084,
|
312 |
+
"learning_rate": 2.2131147540983607e-05,
|
313 |
+
"loss": 0.6789,
|
314 |
+
"step": 123
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.8529411764705883,
|
318 |
+
"grad_norm": 8.926857948303223,
|
319 |
+
"learning_rate": 2.1311475409836064e-05,
|
320 |
+
"loss": 0.6347,
|
321 |
+
"step": 126
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.8970588235294117,
|
325 |
+
"grad_norm": 21.031246185302734,
|
326 |
+
"learning_rate": 2.0491803278688525e-05,
|
327 |
+
"loss": 0.7921,
|
328 |
+
"step": 129
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 1.9411764705882353,
|
332 |
+
"grad_norm": 12.221565246582031,
|
333 |
+
"learning_rate": 1.9672131147540985e-05,
|
334 |
+
"loss": 0.8242,
|
335 |
+
"step": 132
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.9852941176470589,
|
339 |
+
"grad_norm": 4.548130035400391,
|
340 |
+
"learning_rate": 1.8852459016393442e-05,
|
341 |
+
"loss": 0.5987,
|
342 |
+
"step": 135
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 2.0,
|
346 |
+
"eval_accuracy": 0.6888888888888889,
|
347 |
+
"eval_f1_macro": 0.6845081103855066,
|
348 |
+
"eval_f1_micro": 0.6888888888888889,
|
349 |
+
"eval_f1_weighted": 0.6845081103855067,
|
350 |
+
"eval_loss": 0.811522901058197,
|
351 |
+
"eval_precision_macro": 0.7045918367346938,
|
352 |
+
"eval_precision_micro": 0.6888888888888889,
|
353 |
+
"eval_precision_weighted": 0.7045918367346938,
|
354 |
+
"eval_recall_macro": 0.6888888888888888,
|
355 |
+
"eval_recall_micro": 0.6888888888888889,
|
356 |
+
"eval_recall_weighted": 0.6888888888888889,
|
357 |
+
"eval_runtime": 131.5615,
|
358 |
+
"eval_samples_per_second": 1.026,
|
359 |
+
"eval_steps_per_second": 0.068,
|
360 |
+
"step": 136
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 2.0294117647058822,
|
364 |
+
"grad_norm": 7.7553510665893555,
|
365 |
+
"learning_rate": 1.8032786885245903e-05,
|
366 |
+
"loss": 0.6751,
|
367 |
+
"step": 138
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 2.073529411764706,
|
371 |
+
"grad_norm": 3.660639762878418,
|
372 |
+
"learning_rate": 1.721311475409836e-05,
|
373 |
+
"loss": 0.637,
|
374 |
+
"step": 141
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 2.1176470588235294,
|
378 |
+
"grad_norm": 7.876177787780762,
|
379 |
+
"learning_rate": 1.6393442622950818e-05,
|
380 |
+
"loss": 0.6454,
|
381 |
+
"step": 144
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 2.161764705882353,
|
385 |
+
"grad_norm": 8.173316955566406,
|
386 |
+
"learning_rate": 1.557377049180328e-05,
|
387 |
+
"loss": 0.5053,
|
388 |
+
"step": 147
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 2.2058823529411766,
|
392 |
+
"grad_norm": 7.380105018615723,
|
393 |
+
"learning_rate": 1.4754098360655739e-05,
|
394 |
+
"loss": 0.64,
|
395 |
+
"step": 150
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 2.25,
|
399 |
+
"grad_norm": 13.381223678588867,
|
400 |
+
"learning_rate": 1.3934426229508196e-05,
|
401 |
+
"loss": 0.7163,
|
402 |
+
"step": 153
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 2.2941176470588234,
|
406 |
+
"grad_norm": 21.8228759765625,
|
407 |
+
"learning_rate": 1.3114754098360657e-05,
|
408 |
+
"loss": 0.8269,
|
409 |
+
"step": 156
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 2.338235294117647,
|
413 |
+
"grad_norm": 6.742076396942139,
|
414 |
+
"learning_rate": 1.2295081967213116e-05,
|
415 |
+
"loss": 0.5206,
|
416 |
+
"step": 159
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 2.3823529411764706,
|
420 |
+
"grad_norm": 8.277242660522461,
|
421 |
+
"learning_rate": 1.1475409836065575e-05,
|
422 |
+
"loss": 0.5042,
|
423 |
+
"step": 162
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 2.426470588235294,
|
427 |
+
"grad_norm": 9.727288246154785,
|
428 |
+
"learning_rate": 1.0655737704918032e-05,
|
429 |
+
"loss": 0.6658,
|
430 |
+
"step": 165
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 2.4705882352941178,
|
434 |
+
"grad_norm": 18.33995819091797,
|
435 |
+
"learning_rate": 9.836065573770493e-06,
|
436 |
+
"loss": 0.6377,
|
437 |
+
"step": 168
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 2.514705882352941,
|
441 |
+
"grad_norm": 8.533559799194336,
|
442 |
+
"learning_rate": 9.016393442622952e-06,
|
443 |
+
"loss": 0.8016,
|
444 |
+
"step": 171
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 2.5588235294117645,
|
448 |
+
"grad_norm": 22.230371475219727,
|
449 |
+
"learning_rate": 8.196721311475409e-06,
|
450 |
+
"loss": 0.6268,
|
451 |
+
"step": 174
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.6029411764705883,
|
455 |
+
"grad_norm": 7.892202854156494,
|
456 |
+
"learning_rate": 7.3770491803278695e-06,
|
457 |
+
"loss": 0.732,
|
458 |
+
"step": 177
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 2.6470588235294117,
|
462 |
+
"grad_norm": 6.714171886444092,
|
463 |
+
"learning_rate": 6.557377049180328e-06,
|
464 |
+
"loss": 0.6977,
|
465 |
+
"step": 180
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 2.6911764705882355,
|
469 |
+
"grad_norm": 5.960449695587158,
|
470 |
+
"learning_rate": 5.737704918032787e-06,
|
471 |
+
"loss": 0.3479,
|
472 |
+
"step": 183
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 2.735294117647059,
|
476 |
+
"grad_norm": 5.625789165496826,
|
477 |
+
"learning_rate": 4.918032786885246e-06,
|
478 |
+
"loss": 0.5536,
|
479 |
+
"step": 186
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 2.7794117647058822,
|
483 |
+
"grad_norm": 3.9824419021606445,
|
484 |
+
"learning_rate": 4.098360655737704e-06,
|
485 |
+
"loss": 0.6288,
|
486 |
+
"step": 189
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 2.8235294117647056,
|
490 |
+
"grad_norm": 4.617522716522217,
|
491 |
+
"learning_rate": 3.278688524590164e-06,
|
492 |
+
"loss": 0.4954,
|
493 |
+
"step": 192
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.8676470588235294,
|
497 |
+
"grad_norm": 5.714521408081055,
|
498 |
+
"learning_rate": 2.459016393442623e-06,
|
499 |
+
"loss": 0.4388,
|
500 |
+
"step": 195
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 2.911764705882353,
|
504 |
+
"grad_norm": 11.925094604492188,
|
505 |
+
"learning_rate": 1.639344262295082e-06,
|
506 |
+
"loss": 0.871,
|
507 |
+
"step": 198
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 2.9558823529411766,
|
511 |
+
"grad_norm": 9.523457527160645,
|
512 |
+
"learning_rate": 8.19672131147541e-07,
|
513 |
+
"loss": 0.5172,
|
514 |
+
"step": 201
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 3.0,
|
518 |
+
"grad_norm": 19.425655364990234,
|
519 |
+
"learning_rate": 0.0,
|
520 |
+
"loss": 0.4496,
|
521 |
+
"step": 204
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 3.0,
|
525 |
+
"eval_accuracy": 0.674074074074074,
|
526 |
+
"eval_f1_macro": 0.6722359201219389,
|
527 |
+
"eval_f1_micro": 0.674074074074074,
|
528 |
+
"eval_f1_weighted": 0.6722359201219389,
|
529 |
+
"eval_loss": 0.7707859873771667,
|
530 |
+
"eval_precision_macro": 0.6750194250194249,
|
531 |
+
"eval_precision_micro": 0.674074074074074,
|
532 |
+
"eval_precision_weighted": 0.675019425019425,
|
533 |
+
"eval_recall_macro": 0.674074074074074,
|
534 |
+
"eval_recall_micro": 0.674074074074074,
|
535 |
+
"eval_recall_weighted": 0.674074074074074,
|
536 |
+
"eval_runtime": 139.3011,
|
537 |
+
"eval_samples_per_second": 0.969,
|
538 |
+
"eval_steps_per_second": 0.065,
|
539 |
+
"step": 204
|
540 |
+
}
|
541 |
+
],
|
542 |
+
"logging_steps": 3,
|
543 |
+
"max_steps": 204,
|
544 |
+
"num_input_tokens_seen": 0,
|
545 |
+
"num_train_epochs": 3,
|
546 |
+
"save_steps": 500,
|
547 |
+
"stateful_callbacks": {
|
548 |
+
"EarlyStoppingCallback": {
|
549 |
+
"args": {
|
550 |
+
"early_stopping_patience": 5,
|
551 |
+
"early_stopping_threshold": 0.01
|
552 |
+
},
|
553 |
+
"attributes": {
|
554 |
+
"early_stopping_patience_counter": 0
|
555 |
+
}
|
556 |
+
},
|
557 |
+
"TrainerControl": {
|
558 |
+
"args": {
|
559 |
+
"should_epoch_stop": false,
|
560 |
+
"should_evaluate": false,
|
561 |
+
"should_log": false,
|
562 |
+
"should_save": true,
|
563 |
+
"should_training_stop": true
|
564 |
+
},
|
565 |
+
"attributes": {}
|
566 |
+
}
|
567 |
+
},
|
568 |
+
"total_flos": 423875715959808.0,
|
569 |
+
"train_batch_size": 8,
|
570 |
+
"trial_name": null,
|
571 |
+
"trial_params": null
|
572 |
+
}
|
checkpoint-204/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1550e876129ae1704204c60fb45f33e85191bff8672387b6a59b66b9f95d1d3f
|
3 |
+
size 5304
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google-bert/bert-base-uncased",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"architectures": [
|
5 |
+
"BertForSequenceClassification"
|
6 |
+
],
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"gradient_checkpointing": false,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"id2label": {
|
14 |
+
"0": "negative",
|
15 |
+
"1": "neutral",
|
16 |
+
"2": "positive"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"intermediate_size": 3072,
|
20 |
+
"label2id": {
|
21 |
+
"negative": 0,
|
22 |
+
"neutral": 1,
|
23 |
+
"positive": 2
|
24 |
+
},
|
25 |
+
"layer_norm_eps": 1e-12,
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "bert",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"position_embedding_type": "absolute",
|
32 |
+
"problem_type": "single_label_classification",
|
33 |
+
"torch_dtype": "float32",
|
34 |
+
"transformers_version": "4.46.2",
|
35 |
+
"type_vocab_size": 2,
|
36 |
+
"use_cache": true,
|
37 |
+
"vocab_size": 30522
|
38 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4bbbe5875da93c0545e4b00e4c26a9ba77e95c072477d03317c7a23345145b3
|
3 |
+
size 437961724
|
runs/Nov21_14-36-08_r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d/events.out.tfevents.1732199772.r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d.440.0
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:e49b64a9aa05a3b54901fe88e5bcd73969728ee6d199912f15f6ad9ad32836f2
|
3 |
+
size 22278
|
runs/Nov21_14-36-08_r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d/events.out.tfevents.1732206073.r-kafikani-autotrain-advanced-2-c61oi8cw-8786c-qk50d.440.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a76eaaf1a8d5558a448c85cd4b79956f2606833e227397e4c3f6cea621f5a02
|
3 |
+
size 921
|
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 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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": false,
|
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": "BertTokenizer",
|
54 |
+
"unk_token": "[UNK]"
|
55 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1550e876129ae1704204c60fb45f33e85191bff8672387b6a59b66b9f95d1d3f
|
3 |
+
size 5304
|
training_params.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"data_path": "bert-balanced-v1/autotrain-data",
|
3 |
+
"model": "google-bert/bert-base-uncased",
|
4 |
+
"lr": 5e-05,
|
5 |
+
"epochs": 3,
|
6 |
+
"max_seq_length": 512,
|
7 |
+
"batch_size": 8,
|
8 |
+
"warmup_ratio": 0.1,
|
9 |
+
"gradient_accumulation": 1,
|
10 |
+
"optimizer": "adamw_torch",
|
11 |
+
"scheduler": "linear",
|
12 |
+
"weight_decay": 0.0,
|
13 |
+
"max_grad_norm": 1.0,
|
14 |
+
"seed": 42,
|
15 |
+
"train_split": "train",
|
16 |
+
"valid_split": "validation",
|
17 |
+
"text_column": "autotrain_text",
|
18 |
+
"target_column": "autotrain_label",
|
19 |
+
"logging_steps": -1,
|
20 |
+
"project_name": "bert-balanced-v1",
|
21 |
+
"auto_find_batch_size": false,
|
22 |
+
"mixed_precision": "fp16",
|
23 |
+
"save_total_limit": 1,
|
24 |
+
"push_to_hub": true,
|
25 |
+
"eval_strategy": "epoch",
|
26 |
+
"username": "kafikani",
|
27 |
+
"log": "tensorboard",
|
28 |
+
"early_stopping_patience": 5,
|
29 |
+
"early_stopping_threshold": 0.01
|
30 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|