uvegesistvan
commited on
Upload folder using huggingface_hub
Browse files- checkpoint-7764/config.json +51 -0
- checkpoint-7764/model.safetensors +3 -0
- checkpoint-7764/optimizer.pt +3 -0
- checkpoint-7764/rng_state.pth +3 -0
- checkpoint-7764/scheduler.pt +3 -0
- checkpoint-7764/trainer_state.json +80 -0
- checkpoint-7764/training_args.bin +3 -0
- config.json +51 -0
- events.out.tfevents.1734268801.5dc78d0c0094.597.10 +3 -0
- events.out.tfevents.1734292683.26dae68edbc1.519.0 +3 -0
- events.out.tfevents.1734293482.15565a6fdb0d.517.0 +3 -0
- events.out.tfevents.1734299316.15565a6fdb0d.14799.0 +3 -0
- events.out.tfevents.1734305996.15565a6fdb0d.14799.1 +3 -0
- events.out.tfevents.1736275701.ccf8e4cfc100.602.0 +3 -0
- events.out.tfevents.1736278450.ccf8e4cfc100.602.1 +3 -0
- events.out.tfevents.1736347759.affcea672b22.1013.0 +3 -0
- events.out.tfevents.1736347909.a7ec1308ad87.517.0 +3 -0
- events.out.tfevents.1736348086.a7ec1308ad87.1015.0 +3 -0
- events.out.tfevents.1736348328.892f0a65915d.511.0 +3 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
checkpoint-7764/config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4,
|
32 |
+
"LABEL_5": 5,
|
33 |
+
"LABEL_6": 6,
|
34 |
+
"LABEL_7": 7,
|
35 |
+
"LABEL_8": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "xlm-roberta",
|
40 |
+
"num_attention_heads": 16,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"output_past": true,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"position_embedding_type": "absolute",
|
45 |
+
"problem_type": "single_label_classification",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.47.1",
|
48 |
+
"type_vocab_size": 1,
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 250002
|
51 |
+
}
|
checkpoint-7764/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a7b8ef1b3e96e2516c9d2d4e5a9f9787e9ce4cfe580b70da9afd20e15ae2b0f
|
3 |
+
size 2239647372
|
checkpoint-7764/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ed83a1e327ef74f7fede4df05060fb573cdb63d34244eace40355cd7f3f4961
|
3 |
+
size 4479530129
|
checkpoint-7764/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0067ad005cb20daf27fe0f370a747c0a6b9354342a060c948e27ecbb1e0c2069
|
3 |
+
size 14244
|
checkpoint-7764/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8516ed6c50391464633a188b964551a58e7799eecbb585a06b076190247f74b3
|
3 |
+
size 1064
|
checkpoint-7764/trainer_state.json
ADDED
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.812045693397522,
|
3 |
+
"best_model_checkpoint": "model/checkpoint-7764",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 7764,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 1.0,
|
13 |
+
"grad_norm": 0.674655020236969,
|
14 |
+
"learning_rate": 8.333333333333334e-06,
|
15 |
+
"loss": 0.9449,
|
16 |
+
"step": 3882
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 1.0,
|
20 |
+
"eval_accuracy": 0.7022153529108707,
|
21 |
+
"eval_f1": 0.7081847210276373,
|
22 |
+
"eval_loss": 0.822690486907959,
|
23 |
+
"eval_precision": 0.7291759000665414,
|
24 |
+
"eval_recall": 0.7022153529108707,
|
25 |
+
"eval_runtime": 81.8846,
|
26 |
+
"eval_samples_per_second": 94.816,
|
27 |
+
"eval_steps_per_second": 5.935,
|
28 |
+
"step": 3882
|
29 |
+
},
|
30 |
+
{
|
31 |
+
"epoch": 2.0,
|
32 |
+
"grad_norm": 42.98274612426758,
|
33 |
+
"learning_rate": 6.666666666666667e-06,
|
34 |
+
"loss": 0.7484,
|
35 |
+
"step": 7764
|
36 |
+
},
|
37 |
+
{
|
38 |
+
"epoch": 2.0,
|
39 |
+
"eval_accuracy": 0.7163833075734157,
|
40 |
+
"eval_f1": 0.7173737978381436,
|
41 |
+
"eval_loss": 0.812045693397522,
|
42 |
+
"eval_precision": 0.719085449369722,
|
43 |
+
"eval_recall": 0.7163833075734157,
|
44 |
+
"eval_runtime": 81.913,
|
45 |
+
"eval_samples_per_second": 94.783,
|
46 |
+
"eval_steps_per_second": 5.933,
|
47 |
+
"step": 7764
|
48 |
+
}
|
49 |
+
],
|
50 |
+
"logging_steps": 100,
|
51 |
+
"max_steps": 23292,
|
52 |
+
"num_input_tokens_seen": 0,
|
53 |
+
"num_train_epochs": 6,
|
54 |
+
"save_steps": 100,
|
55 |
+
"stateful_callbacks": {
|
56 |
+
"EarlyStoppingCallback": {
|
57 |
+
"args": {
|
58 |
+
"early_stopping_patience": 2,
|
59 |
+
"early_stopping_threshold": 0.0
|
60 |
+
},
|
61 |
+
"attributes": {
|
62 |
+
"early_stopping_patience_counter": 0
|
63 |
+
}
|
64 |
+
},
|
65 |
+
"TrainerControl": {
|
66 |
+
"args": {
|
67 |
+
"should_epoch_stop": false,
|
68 |
+
"should_evaluate": false,
|
69 |
+
"should_log": false,
|
70 |
+
"should_save": true,
|
71 |
+
"should_training_stop": false
|
72 |
+
},
|
73 |
+
"attributes": {}
|
74 |
+
}
|
75 |
+
},
|
76 |
+
"total_flos": 5.787710230624358e+16,
|
77 |
+
"train_batch_size": 16,
|
78 |
+
"trial_name": null,
|
79 |
+
"trial_params": null
|
80 |
+
}
|
checkpoint-7764/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
|
3 |
+
size 5240
|
config.json
ADDED
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "xlm-roberta-large",
|
3 |
+
"architectures": [
|
4 |
+
"XLMRobertaForSequenceClassification"
|
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": 1024,
|
13 |
+
"id2label": {
|
14 |
+
"0": "LABEL_0",
|
15 |
+
"1": "LABEL_1",
|
16 |
+
"2": "LABEL_2",
|
17 |
+
"3": "LABEL_3",
|
18 |
+
"4": "LABEL_4",
|
19 |
+
"5": "LABEL_5",
|
20 |
+
"6": "LABEL_6",
|
21 |
+
"7": "LABEL_7",
|
22 |
+
"8": "LABEL_8"
|
23 |
+
},
|
24 |
+
"initializer_range": 0.02,
|
25 |
+
"intermediate_size": 4096,
|
26 |
+
"label2id": {
|
27 |
+
"LABEL_0": 0,
|
28 |
+
"LABEL_1": 1,
|
29 |
+
"LABEL_2": 2,
|
30 |
+
"LABEL_3": 3,
|
31 |
+
"LABEL_4": 4,
|
32 |
+
"LABEL_5": 5,
|
33 |
+
"LABEL_6": 6,
|
34 |
+
"LABEL_7": 7,
|
35 |
+
"LABEL_8": 8
|
36 |
+
},
|
37 |
+
"layer_norm_eps": 1e-05,
|
38 |
+
"max_position_embeddings": 514,
|
39 |
+
"model_type": "xlm-roberta",
|
40 |
+
"num_attention_heads": 16,
|
41 |
+
"num_hidden_layers": 24,
|
42 |
+
"output_past": true,
|
43 |
+
"pad_token_id": 1,
|
44 |
+
"position_embedding_type": "absolute",
|
45 |
+
"problem_type": "single_label_classification",
|
46 |
+
"torch_dtype": "float32",
|
47 |
+
"transformers_version": "4.47.1",
|
48 |
+
"type_vocab_size": 1,
|
49 |
+
"use_cache": true,
|
50 |
+
"vocab_size": 250002
|
51 |
+
}
|
events.out.tfevents.1734268801.5dc78d0c0094.597.10
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cc1315c7e1f2183cb5b32925df2e7b72f36542226b646d07a45f3c2ae0533f0
|
3 |
+
size 8513
|
events.out.tfevents.1734292683.26dae68edbc1.519.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:153851a01c1db2c0602694cc5524d930f1f95c7a7c3a8cd4d23bbb7b09b9dc0a
|
3 |
+
size 5395
|
events.out.tfevents.1734293482.15565a6fdb0d.517.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5315719c053e1861da202c80e15d78116f848d40ccf4a2f40dcb34688c8375dc
|
3 |
+
size 7444
|
events.out.tfevents.1734299316.15565a6fdb0d.14799.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b30436099c0ccf2daef57aa51b47cca5db54f956c27940eddb55b1a3664918dc
|
3 |
+
size 8481
|
events.out.tfevents.1734305996.15565a6fdb0d.14799.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60026a51a67f1cd87355d4a35d74e7f092d77e110549e5808328478f692f45f4
|
3 |
+
size 9164
|
events.out.tfevents.1736275701.ccf8e4cfc100.602.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e6f36308fbef6bcf0fd81c4e7d64d450c8eaf5800a624df96fa1aa07a6895801
|
3 |
+
size 5395
|
events.out.tfevents.1736278450.ccf8e4cfc100.602.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f65837e8097fba7e1c62f4323abc004c45d8d76c915594caedfac13d1992850
|
3 |
+
size 9183
|
events.out.tfevents.1736347759.affcea672b22.1013.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eddd5f5bb8672975a8cd0b0171c1ba334ad85b542ee025aa522b9df4570fa05
|
3 |
+
size 5395
|
events.out.tfevents.1736347909.a7ec1308ad87.517.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49bcc672afaf6045e973673ac75f3625ea2ad3cacf8d098f50e4385bad595f79
|
3 |
+
size 5395
|
events.out.tfevents.1736348086.a7ec1308ad87.1015.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bf5216291240dba6beaa7e66bdb7888f5b358c46ed8ddd08f935a4e380772ec
|
3 |
+
size 5395
|
events.out.tfevents.1736348328.892f0a65915d.511.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:222f7266238deb428ba3800c68968ba8f80f58aa05b3318929ffb0a9a7e5b1e9
|
3 |
+
size 8481
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a7b8ef1b3e96e2516c9d2d4e5a9f9787e9ce4cfe580b70da9afd20e15ae2b0f
|
3 |
+
size 2239647372
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8de273838f57747afd3006ebd4c66d232f4334f36315cdb16f0ef458d93b5f23
|
3 |
+
size 5240
|