Upload folder using huggingface_hub
Browse files- config.json +28 -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 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "distilroberta-base",
|
3 |
+
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 514,
|
17 |
+
"model_type": "roberta",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 6,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"position_embedding_type": "absolute",
|
22 |
+
"problem_type": "single_label_classification",
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.35.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1d79d65ef56faee6fa8a95b647a736c59665dc2f0554df0e4dfd5a446a636f65
|
3 |
+
size 328492280
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4d98adaabe124d75394fe6cf7f0f2dec15aaf7658bf540d8323950cb9538f8d0
|
3 |
+
size 657047610
|
rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:808274c57b05c7ec524c446b1d005db2cf8594d25b358cea975cd19338c6b371
|
3 |
+
size 14244
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:38aa736e4a62cc825312a3c2c50e2f35a526d6bd6ef7085fc22426848d5ceba9
|
3 |
+
size 1064
|
trainer_state.json
ADDED
@@ -0,0 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.998118178396688,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 6640,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.38,
|
13 |
+
"learning_rate": 4.9800000000000004e-05,
|
14 |
+
"loss": 0.0423,
|
15 |
+
"step": 500
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.75,
|
19 |
+
"learning_rate": 4.919280091260669e-05,
|
20 |
+
"loss": 0.0599,
|
21 |
+
"step": 1000
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 1.13,
|
25 |
+
"learning_rate": 4.681083744859544e-05,
|
26 |
+
"loss": 0.0611,
|
27 |
+
"step": 1500
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.51,
|
31 |
+
"learning_rate": 4.30091452205688e-05,
|
32 |
+
"loss": 0.0538,
|
33 |
+
"step": 2000
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.88,
|
37 |
+
"learning_rate": 3.803518706991396e-05,
|
38 |
+
"loss": 0.0524,
|
39 |
+
"step": 2500
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 2.26,
|
43 |
+
"learning_rate": 3.221273192453827e-05,
|
44 |
+
"loss": 0.0414,
|
45 |
+
"step": 3000
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 2.63,
|
49 |
+
"learning_rate": 2.5920779768580868e-05,
|
50 |
+
"loss": 0.0344,
|
51 |
+
"step": 3500
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 3.01,
|
55 |
+
"learning_rate": 1.9568891467307694e-05,
|
56 |
+
"loss": 0.03,
|
57 |
+
"step": 4000
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 3.39,
|
61 |
+
"learning_rate": 1.3593288155812168e-05,
|
62 |
+
"loss": 0.0209,
|
63 |
+
"step": 4500
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 3.76,
|
67 |
+
"learning_rate": 8.335204956563933e-06,
|
68 |
+
"loss": 0.0182,
|
69 |
+
"step": 5000
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 4.14,
|
73 |
+
"learning_rate": 4.161880145220276e-06,
|
74 |
+
"loss": 0.0133,
|
75 |
+
"step": 5500
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 4.52,
|
79 |
+
"learning_rate": 1.344967173429157e-06,
|
80 |
+
"loss": 0.0113,
|
81 |
+
"step": 6000
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 4.89,
|
85 |
+
"learning_rate": 6.877170722064397e-08,
|
86 |
+
"loss": 0.0086,
|
87 |
+
"step": 6500
|
88 |
+
}
|
89 |
+
],
|
90 |
+
"logging_steps": 500,
|
91 |
+
"max_steps": 6640,
|
92 |
+
"num_train_epochs": 5,
|
93 |
+
"save_steps": 500,
|
94 |
+
"total_flos": 5.628910677609677e+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 sha256:90e21d9531ad6a4b44e6b0111c9d1db5f6781f649344867b47bffb15d66c727b
|
3 |
+
size 4664
|