jfernandez
commited on
Commit
•
85bf5fd
1
Parent(s):
5839feb
Upload 12 files
Browse files- checkpoint-10000/config.json +26 -0
- checkpoint-10000/optimizer.pt +3 -0
- checkpoint-10000/pytorch_model.bin +3 -0
- checkpoint-10000/rng_state.pth +3 -0
- checkpoint-10000/scheduler.pt +3 -0
- checkpoint-10000/trainer_state.json +136 -0
- checkpoint-10000/training_args.bin +3 -0
- config.json +26 -0
- pytorch_model.bin +3 -0
- runs/Jan07_03-24-07_fec26fa8b457/1673061866.9062183/events.out.tfevents.1673061866.fec26fa8b457.1308.1 +3 -0
- runs/Jan07_03-24-07_fec26fa8b457/events.out.tfevents.1673061866.fec26fa8b457.1308.0 +3 -0
- training_args.bin +3 -0
checkpoint-10000/config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RobertaForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "roberta",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.25.1",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 52000
|
26 |
+
}
|
checkpoint-10000/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d528b6983aea75e56ee61b1ab94fb125f4dadd9f8c62fb5ff8d68baf5d47b212
|
3 |
+
size 668097477
|
checkpoint-10000/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fece542e3e1d5eee328cf5ab03fe4f57aaba90eeccf613b89be0ad0dcb792ef3
|
3 |
+
size 334058169
|
checkpoint-10000/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f1f964d633a8d747a79e604915cf6a0e0040c812fc0ddf5a173fbcd5b4e9beb
|
3 |
+
size 14575
|
checkpoint-10000/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f3b81df0eebc3ff73583701a929ff0c4e18f1a9be3237af6d1f9dad4091c54b
|
3 |
+
size 627
|
checkpoint-10000/trainer_state.json
ADDED
@@ -0,0 +1,136 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7599361653621096,
|
5 |
+
"global_step": 10000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.04,
|
12 |
+
"learning_rate": 4.810015958659473e-05,
|
13 |
+
"loss": 7.3864,
|
14 |
+
"step": 500
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.08,
|
18 |
+
"learning_rate": 4.6200319173189456e-05,
|
19 |
+
"loss": 6.8171,
|
20 |
+
"step": 1000
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.11,
|
24 |
+
"learning_rate": 4.430047875978418e-05,
|
25 |
+
"loss": 6.6465,
|
26 |
+
"step": 1500
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.15,
|
30 |
+
"learning_rate": 4.240063834637891e-05,
|
31 |
+
"loss": 6.5187,
|
32 |
+
"step": 2000
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.19,
|
36 |
+
"learning_rate": 4.050079793297363e-05,
|
37 |
+
"loss": 6.4542,
|
38 |
+
"step": 2500
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.23,
|
42 |
+
"learning_rate": 3.860095751956836e-05,
|
43 |
+
"loss": 6.392,
|
44 |
+
"step": 3000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.27,
|
48 |
+
"learning_rate": 3.6701117106163084e-05,
|
49 |
+
"loss": 6.2944,
|
50 |
+
"step": 3500
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.3,
|
54 |
+
"learning_rate": 3.480127669275781e-05,
|
55 |
+
"loss": 6.1424,
|
56 |
+
"step": 4000
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.34,
|
60 |
+
"learning_rate": 3.290143627935254e-05,
|
61 |
+
"loss": 6.1603,
|
62 |
+
"step": 4500
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.38,
|
66 |
+
"learning_rate": 3.1001595865947265e-05,
|
67 |
+
"loss": 6.0149,
|
68 |
+
"step": 5000
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.42,
|
72 |
+
"learning_rate": 2.910175545254199e-05,
|
73 |
+
"loss": 5.9559,
|
74 |
+
"step": 5500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.46,
|
78 |
+
"learning_rate": 2.7201915039136716e-05,
|
79 |
+
"loss": 5.8511,
|
80 |
+
"step": 6000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.49,
|
84 |
+
"learning_rate": 2.5302074625731443e-05,
|
85 |
+
"loss": 5.8782,
|
86 |
+
"step": 6500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.53,
|
90 |
+
"learning_rate": 2.3402234212326166e-05,
|
91 |
+
"loss": 5.8042,
|
92 |
+
"step": 7000
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.57,
|
96 |
+
"learning_rate": 2.1502393798920893e-05,
|
97 |
+
"loss": 5.7415,
|
98 |
+
"step": 7500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.61,
|
102 |
+
"learning_rate": 1.9602553385515617e-05,
|
103 |
+
"loss": 5.6506,
|
104 |
+
"step": 8000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.65,
|
108 |
+
"learning_rate": 1.7702712972110344e-05,
|
109 |
+
"loss": 5.699,
|
110 |
+
"step": 8500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.68,
|
114 |
+
"learning_rate": 1.580287255870507e-05,
|
115 |
+
"loss": 5.627,
|
116 |
+
"step": 9000
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.72,
|
120 |
+
"learning_rate": 1.3903032145299796e-05,
|
121 |
+
"loss": 5.615,
|
122 |
+
"step": 9500
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.76,
|
126 |
+
"learning_rate": 1.2003191731894521e-05,
|
127 |
+
"loss": 5.4553,
|
128 |
+
"step": 10000
|
129 |
+
}
|
130 |
+
],
|
131 |
+
"max_steps": 13159,
|
132 |
+
"num_train_epochs": 1,
|
133 |
+
"total_flos": 1084338745132032.0,
|
134 |
+
"trial_name": null,
|
135 |
+
"trial_params": null
|
136 |
+
}
|
checkpoint-10000/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a9da38f20ddf6ab9aae7fb8129a73b1be6438ba4499e818f468e12abf4faafd
|
3 |
+
size 3387
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"RobertaForMaskedLM"
|
4 |
+
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"bos_token_id": 0,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"layer_norm_eps": 1e-12,
|
15 |
+
"max_position_embeddings": 514,
|
16 |
+
"model_type": "roberta",
|
17 |
+
"num_attention_heads": 12,
|
18 |
+
"num_hidden_layers": 6,
|
19 |
+
"pad_token_id": 1,
|
20 |
+
"position_embedding_type": "absolute",
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.25.1",
|
23 |
+
"type_vocab_size": 1,
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 52000
|
26 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df804d392ccd2da7c023807b67106053ac068f20b5b58af56beda8dc3469a2a7
|
3 |
+
size 334058169
|
runs/Jan07_03-24-07_fec26fa8b457/1673061866.9062183/events.out.tfevents.1673061866.fec26fa8b457.1308.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f00f5ce096cb7a52daf273f093cd6c86bc29442ac21078574aa1a288d5a205b4
|
3 |
+
size 5518
|
runs/Jan07_03-24-07_fec26fa8b457/events.out.tfevents.1673061866.fec26fa8b457.1308.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d6dbbca552448001d8c831c3e6de067cb11ca134d4abd62506af7ebb59c34a1
|
3 |
+
size 8082
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2a9da38f20ddf6ab9aae7fb8129a73b1be6438ba4499e818f468e12abf4faafd
|
3 |
+
size 3387
|