Upload folder using huggingface_hub
Browse files- config.json +39 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +97 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"id2label": {
|
12 |
+
"0": "miscellaneous",
|
13 |
+
"1": "taxation",
|
14 |
+
"2": "insurance",
|
15 |
+
"3": "stocks",
|
16 |
+
"4": "mutualFunds"
|
17 |
+
},
|
18 |
+
"initializer_range": 0.02,
|
19 |
+
"label2id": {
|
20 |
+
"insurance": 2,
|
21 |
+
"miscellaneous": 0,
|
22 |
+
"mutualFunds": 4,
|
23 |
+
"stocks": 3,
|
24 |
+
"taxation": 1
|
25 |
+
},
|
26 |
+
"max_position_embeddings": 512,
|
27 |
+
"model_type": "distilbert",
|
28 |
+
"n_heads": 12,
|
29 |
+
"n_layers": 6,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"problem_type": "single_label_classification",
|
32 |
+
"qa_dropout": 0.1,
|
33 |
+
"seq_classif_dropout": 0.2,
|
34 |
+
"sinusoidal_pos_embds": false,
|
35 |
+
"tie_weights_": true,
|
36 |
+
"torch_dtype": "float32",
|
37 |
+
"transformers_version": "4.41.2",
|
38 |
+
"vocab_size": 30522
|
39 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd69d626c9ec6f972671d0c2312f7041a3aed4bef74b5bde2b7e8605e417c35e
|
3 |
+
size 267841796
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afdc8f0e1808173b785d01bcc201118b982e41827b326764d16035713e36781f
|
3 |
+
size 535745722
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37c568a1e3a7f6e1788db2f0b5223a34b157bbeb26cfb0ccfb4bece1499d51d7
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b182744ab1bcfd025dce5a9a0e89277828dccb29e9e707310ea52f02f708968d
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.13778184354305267,
|
3 |
+
"best_model_checkpoint": "bert-intent-classifier/checkpoint-1071",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 2142,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.9990662931839402,
|
13 |
+
"grad_norm": 5.298245906829834,
|
14 |
+
"learning_rate": 1.600747663551402e-05,
|
15 |
+
"loss": 0.3131,
|
16 |
+
"step": 535
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.9990662931839402,
|
20 |
+
"eval_accuracy": 0.9557281024383599,
|
21 |
+
"eval_loss": 0.16336975991725922,
|
22 |
+
"eval_runtime": 25.6475,
|
23 |
+
"eval_samples_per_second": 286.227,
|
24 |
+
"eval_steps_per_second": 17.897,
|
25 |
+
"step": 535
|
26 |
+
},
|
27 |
+
{
|
28 |
+
"epoch": 2.0,
|
29 |
+
"grad_norm": 5.548210620880127,
|
30 |
+
"learning_rate": 1.2e-05,
|
31 |
+
"loss": 0.1143,
|
32 |
+
"step": 1071
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 2.0,
|
36 |
+
"eval_accuracy": 0.9619942787086228,
|
37 |
+
"eval_loss": 0.13778184354305267,
|
38 |
+
"eval_runtime": 25.2843,
|
39 |
+
"eval_samples_per_second": 290.339,
|
40 |
+
"eval_steps_per_second": 18.154,
|
41 |
+
"step": 1071
|
42 |
+
},
|
43 |
+
{
|
44 |
+
"epoch": 2.9990662931839402,
|
45 |
+
"grad_norm": 3.810972213745117,
|
46 |
+
"learning_rate": 8.000000000000001e-06,
|
47 |
+
"loss": 0.0754,
|
48 |
+
"step": 1606
|
49 |
+
},
|
50 |
+
{
|
51 |
+
"epoch": 2.9990662931839402,
|
52 |
+
"eval_accuracy": 0.9653998092902875,
|
53 |
+
"eval_loss": 0.13948151469230652,
|
54 |
+
"eval_runtime": 25.178,
|
55 |
+
"eval_samples_per_second": 291.564,
|
56 |
+
"eval_steps_per_second": 18.23,
|
57 |
+
"step": 1606
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.0,
|
61 |
+
"grad_norm": 0.10682384669780731,
|
62 |
+
"learning_rate": 3.992523364485982e-06,
|
63 |
+
"loss": 0.0571,
|
64 |
+
"step": 2142
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 4.0,
|
68 |
+
"eval_accuracy": 0.9644462607274213,
|
69 |
+
"eval_loss": 0.13912545144557953,
|
70 |
+
"eval_runtime": 25.6125,
|
71 |
+
"eval_samples_per_second": 286.618,
|
72 |
+
"eval_steps_per_second": 17.921,
|
73 |
+
"step": 2142
|
74 |
+
}
|
75 |
+
],
|
76 |
+
"logging_steps": 500,
|
77 |
+
"max_steps": 2675,
|
78 |
+
"num_input_tokens_seen": 0,
|
79 |
+
"num_train_epochs": 5,
|
80 |
+
"save_steps": 500,
|
81 |
+
"stateful_callbacks": {
|
82 |
+
"TrainerControl": {
|
83 |
+
"args": {
|
84 |
+
"should_epoch_stop": false,
|
85 |
+
"should_evaluate": false,
|
86 |
+
"should_log": false,
|
87 |
+
"should_save": true,
|
88 |
+
"should_training_stop": false
|
89 |
+
},
|
90 |
+
"attributes": {}
|
91 |
+
}
|
92 |
+
},
|
93 |
+
"total_flos": 9072755267279040.0,
|
94 |
+
"train_batch_size": 16,
|
95 |
+
"trial_name": null,
|
96 |
+
"trial_params": null
|
97 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:70c8edfbdca06cfdf3f99677f66b086a4373547e38961782d5a9931c1a141fc1
|
3 |
+
size 5112
|