End of training
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- README.md +19 -12
- config.json +18 -15
- logs/events.out.tfevents.1740157634.a2d653e866f9.226.3 +3 -0
- logs/events.out.tfevents.1740162891.0a0ba32201a8.2151.21 +3 -0
- logs/events.out.tfevents.1740163730.0a0ba32201a8.2151.22 +3 -0
- model.safetensors +2 -2
- model_stats.json +157 -238
- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
- trial_0/checkpoint-292/config.json +50 -0
- trial_0/checkpoint-292/model.safetensors +3 -0
- trial_0/checkpoint-292/optimizer.pt +3 -0
- trial_0/checkpoint-292/rng_state.pth +3 -0
- trial_0/checkpoint-292/scheduler.pt +3 -0
- trial_0/checkpoint-292/special_tokens_map.json +37 -0
- trial_0/checkpoint-292/tokenizer.json +0 -0
- trial_0/checkpoint-292/tokenizer_config.json +58 -0
- trial_0/checkpoint-292/trainer_state.json +314 -0
- trial_0/checkpoint-292/training_args.bin +3 -0
- trial_0/checkpoint-292/vocab.txt +0 -0
- trial_0/checkpoint-584/config.json +50 -0
- trial_0/checkpoint-584/model.safetensors +3 -0
- trial_0/checkpoint-584/optimizer.pt +3 -0
- trial_0/checkpoint-584/rng_state.pth +3 -0
- trial_0/checkpoint-584/scheduler.pt +3 -0
- trial_0/checkpoint-584/special_tokens_map.json +37 -0
- trial_0/checkpoint-584/tokenizer.json +0 -0
- trial_0/checkpoint-584/tokenizer_config.json +58 -0
- trial_0/checkpoint-584/trainer_state.json +595 -0
- trial_0/checkpoint-584/training_args.bin +3 -0
- trial_0/checkpoint-584/vocab.txt +0 -0
- trial_0/checkpoint-876/config.json +50 -0
- trial_0/checkpoint-876/model.safetensors +3 -0
- trial_0/checkpoint-876/optimizer.pt +3 -0
- trial_0/checkpoint-876/rng_state.pth +3 -0
- trial_0/checkpoint-876/scheduler.pt +3 -0
- trial_0/checkpoint-876/special_tokens_map.json +37 -0
- trial_0/checkpoint-876/tokenizer.json +0 -0
- trial_0/checkpoint-876/tokenizer_config.json +58 -0
- trial_0/checkpoint-876/trainer_state.json +876 -0
- trial_0/checkpoint-876/training_args.bin +3 -0
- trial_0/checkpoint-876/vocab.txt +0 -0
- trial_0/logs/events.out.tfevents.1740158198.a2d653e866f9.226.4 +3 -0
- trial_0/logs/events.out.tfevents.1740161296.0a0ba32201a8.2151.0 +3 -0
- trial_0/logs/events.out.tfevents.1740161531.0a0ba32201a8.2151.1 +3 -0
- trial_0/logs/events.out.tfevents.1740161645.0a0ba32201a8.2151.2 +3 -0
- trial_1/checkpoint-146/config.json +50 -0
- trial_1/checkpoint-146/model.safetensors +3 -0
- trial_1/checkpoint-146/optimizer.pt +3 -0
README.md
CHANGED
@@ -1,8 +1,10 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
-
base_model: dccuchile/
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
|
|
6 |
model-index:
|
7 |
- name: bluesky-spanish-classifier
|
8 |
results: []
|
@@ -13,10 +15,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# bluesky-spanish-classifier
|
15 |
|
16 |
-
This model is a fine-tuned version of [dccuchile/
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 2.
|
19 |
-
- Classification Report: {'ar': {'precision': 0.
|
|
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -35,20 +38,24 @@ More information needed
|
|
35 |
### Training hyperparameters
|
36 |
|
37 |
The following hyperparameters were used during training:
|
38 |
-
- learning_rate:
|
39 |
-
- train_batch_size:
|
40 |
-
- eval_batch_size:
|
41 |
- seed: 42
|
42 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
43 |
- lr_scheduler_type: linear
|
44 |
-
-
|
45 |
-
-
|
46 |
|
47 |
### Training results
|
48 |
|
49 |
-
| Training Loss | Epoch
|
50 |
-
|
51 |
-
|
|
|
|
|
|
|
|
|
|
52 |
|
53 |
|
54 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
+
base_model: dccuchile/bert-base-spanish-wwm-uncased
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
+
metrics:
|
7 |
+
- f1
|
8 |
model-index:
|
9 |
- name: bluesky-spanish-classifier
|
10 |
results: []
|
|
|
15 |
|
16 |
# bluesky-spanish-classifier
|
17 |
|
18 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 2.3731
|
21 |
+
- Classification Report: {'ar': {'precision': 0.4898785425101215, 'recall': 0.32180851063829785, 'f1-score': 0.3884430176565008, 'support': 376.0}, 'cl': {'precision': 0.3626666666666667, 'recall': 0.4722222222222222, 'f1-score': 0.41025641025641024, 'support': 576.0}, 'co': {'precision': 0.34656084656084657, 'recall': 0.3808139534883721, 'f1-score': 0.3628808864265928, 'support': 344.0}, 'es': {'precision': 0.4630738522954092, 'recall': 0.427255985267035, 'f1-score': 0.4444444444444444, 'support': 543.0}, 'mx': {'precision': 0.43380855397148677, 'recall': 0.43917525773195876, 'f1-score': 0.4364754098360656, 'support': 485.0}, 'pe': {'precision': 0.3769968051118211, 'recall': 0.3390804597701149, 'f1-score': 0.35703479576399394, 'support': 348.0}, 'pr': {'precision': 0.5736434108527132, 'recall': 0.7326732673267327, 'f1-score': 0.6434782608695652, 'support': 101.0}, 'uy': {'precision': 0.35096153846153844, 'recall': 0.3201754385964912, 'f1-score': 0.3348623853211009, 'support': 228.0}, 've': {'precision': 0.16666666666666666, 'recall': 0.045454545454545456, 'f1-score': 0.07142857142857142, 'support': 22.0}, 'accuracy': 0.4085345683096262, 'macro avg': {'precision': 0.39602854256636333, 'recall': 0.38651773783286336, 'f1-score': 0.3832560202225828, 'support': 3023.0}, 'weighted avg': {'precision': 0.4124949665181113, 'recall': 0.4085345683096262, 'f1-score': 0.40601279016852304, 'support': 3023.0}}
|
22 |
+
- F1: 0.3833
|
23 |
|
24 |
## Model description
|
25 |
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2.8600231011639855e-05
|
42 |
+
- train_batch_size: 8
|
43 |
+
- eval_batch_size: 8
|
44 |
- seed: 42
|
45 |
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_ratio: 0.11531859504380029
|
48 |
+
- num_epochs: 5
|
49 |
|
50 |
### Training results
|
51 |
|
52 |
+
| Training Loss | Epoch | Step | Validation Loss | Classification Report | F1 |
|
53 |
+
|:-------------:|:-----:|:----:|:---------------:|:--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:------:|
|
54 |
+
| 1.7603 | 1.0 | 882 | 1.7406 | {'ar': {'precision': 0.35516372795969775, 'recall': 0.375, 'f1-score': 0.3648124191461837, 'support': 376.0}, 'cl': {'precision': 0.3016759776536313, 'recall': 0.28125, 'f1-score': 0.29110512129380056, 'support': 576.0}, 'co': {'precision': 0.3670886075949367, 'recall': 0.25290697674418605, 'f1-score': 0.29948364888123924, 'support': 344.0}, 'es': {'precision': 0.3584905660377358, 'recall': 0.4548802946593002, 'f1-score': 0.400974025974026, 'support': 543.0}, 'mx': {'precision': 0.32465753424657534, 'recall': 0.488659793814433, 'f1-score': 0.39012345679012345, 'support': 485.0}, 'pe': {'precision': 0.3958333333333333, 'recall': 0.27298850574712646, 'f1-score': 0.3231292517006803, 'support': 348.0}, 'pr': {'precision': 0.5631067961165048, 'recall': 0.5742574257425742, 'f1-score': 0.5686274509803921, 'support': 101.0}, 'uy': {'precision': 0.4666666666666667, 'recall': 0.18421052631578946, 'f1-score': 0.2641509433962264, 'support': 228.0}, 've': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 22.0}, 'accuracy': 0.3536222295732716, 'macro avg': {'precision': 0.34807591217878686, 'recall': 0.3204615025581566, 'f1-score': 0.32248959090696355, 'support': 3023.0}, 'weighted avg': {'precision': 0.35948675942105285, 'recall': 0.3536222295732716, 'f1-score': 0.3456546260541325, 'support': 3023.0}} | 0.3225 |
|
55 |
+
| 1.4223 | 2.0 | 1764 | 1.6758 | {'ar': {'precision': 0.4349315068493151, 'recall': 0.3377659574468085, 'f1-score': 0.38023952095808383, 'support': 376.0}, 'cl': {'precision': 0.336996336996337, 'recall': 0.3194444444444444, 'f1-score': 0.32798573975044565, 'support': 576.0}, 'co': {'precision': 0.36333333333333334, 'recall': 0.3168604651162791, 'f1-score': 0.3385093167701863, 'support': 344.0}, 'es': {'precision': 0.38980716253443526, 'recall': 0.5211786372007366, 'f1-score': 0.44602048857368004, 'support': 543.0}, 'mx': {'precision': 0.35246995994659547, 'recall': 0.5443298969072164, 'f1-score': 0.42787682333873583, 'support': 485.0}, 'pe': {'precision': 0.44308943089430897, 'recall': 0.3132183908045977, 'f1-score': 0.367003367003367, 'support': 348.0}, 'pr': {'precision': 0.759493670886076, 'recall': 0.594059405940594, 'f1-score': 0.6666666666666666, 'support': 101.0}, 'uy': {'precision': 0.5542168674698795, 'recall': 0.20175438596491227, 'f1-score': 0.2958199356913183, 'support': 228.0}, 've': {'precision': 1.0, 'recall': 0.09090909090909091, 'f1-score': 0.16666666666666666, 'support': 22.0}, 'accuracy': 0.3916639100231558, 'macro avg': {'precision': 0.5149264743233645, 'recall': 0.35994674163718665, 'f1-score': 0.3796431694910167, 'support': 3023.0}, 'weighted avg': {'precision': 0.4116802685001794, 'recall': 0.3916639100231558, 'f1-score': 0.3851176158170783, 'support': 3023.0}} | 0.3796 |
|
56 |
+
| 0.9068 | 3.0 | 2646 | 1.9523 | {'ar': {'precision': 0.39574468085106385, 'recall': 0.4946808510638298, 'f1-score': 0.4397163120567376, 'support': 376.0}, 'cl': {'precision': 0.35144927536231885, 'recall': 0.3368055555555556, 'f1-score': 0.34397163120567376, 'support': 576.0}, 'co': {'precision': 0.31555555555555553, 'recall': 0.4127906976744186, 'f1-score': 0.35768261964735515, 'support': 344.0}, 'es': {'precision': 0.47113163972286376, 'recall': 0.3756906077348066, 'f1-score': 0.4180327868852459, 'support': 543.0}, 'mx': {'precision': 0.43680709534368073, 'recall': 0.4061855670103093, 'f1-score': 0.42094017094017094, 'support': 485.0}, 'pe': {'precision': 0.38661710037174724, 'recall': 0.2988505747126437, 'f1-score': 0.3371150729335494, 'support': 348.0}, 'pr': {'precision': 0.64, 'recall': 0.6336633663366337, 'f1-score': 0.6368159203980099, 'support': 101.0}, 'uy': {'precision': 0.30662020905923343, 'recall': 0.38596491228070173, 'f1-score': 0.341747572815534, 'support': 228.0}, 've': {'precision': 0.18181818181818182, 'recall': 0.09090909090909091, 'f1-score': 0.12121212121212122, 'support': 22.0}, 'accuracy': 0.3906715183592458, 'macro avg': {'precision': 0.3873048597871828, 'recall': 0.3817268025864433, 'f1-score': 0.37969268978826637, 'support': 3023.0}, 'weighted avg': {'precision': 0.3971399185993649, 'recall': 0.3906715183592458, 'f1-score': 0.3902981034934984, 'support': 3023.0}} | 0.3797 |
|
57 |
+
| 0.4818 | 4.0 | 3528 | 2.3731 | {'ar': {'precision': 0.4898785425101215, 'recall': 0.32180851063829785, 'f1-score': 0.3884430176565008, 'support': 376.0}, 'cl': {'precision': 0.3626666666666667, 'recall': 0.4722222222222222, 'f1-score': 0.41025641025641024, 'support': 576.0}, 'co': {'precision': 0.34656084656084657, 'recall': 0.3808139534883721, 'f1-score': 0.3628808864265928, 'support': 344.0}, 'es': {'precision': 0.4630738522954092, 'recall': 0.427255985267035, 'f1-score': 0.4444444444444444, 'support': 543.0}, 'mx': {'precision': 0.43380855397148677, 'recall': 0.43917525773195876, 'f1-score': 0.4364754098360656, 'support': 485.0}, 'pe': {'precision': 0.3769968051118211, 'recall': 0.3390804597701149, 'f1-score': 0.35703479576399394, 'support': 348.0}, 'pr': {'precision': 0.5736434108527132, 'recall': 0.7326732673267327, 'f1-score': 0.6434782608695652, 'support': 101.0}, 'uy': {'precision': 0.35096153846153844, 'recall': 0.3201754385964912, 'f1-score': 0.3348623853211009, 'support': 228.0}, 've': {'precision': 0.16666666666666666, 'recall': 0.045454545454545456, 'f1-score': 0.07142857142857142, 'support': 22.0}, 'accuracy': 0.4085345683096262, 'macro avg': {'precision': 0.39602854256636333, 'recall': 0.38651773783286336, 'f1-score': 0.3832560202225828, 'support': 3023.0}, 'weighted avg': {'precision': 0.4124949665181113, 'recall': 0.4085345683096262, 'f1-score': 0.40601279016852304, 'support': 3023.0}} | 0.3833 |
|
58 |
+
| 0.2357 | 5.0 | 4410 | 2.7721 | {'ar': {'precision': 0.42168674698795183, 'recall': 0.3723404255319149, 'f1-score': 0.3954802259887006, 'support': 376.0}, 'cl': {'precision': 0.38753799392097266, 'recall': 0.4427083333333333, 'f1-score': 0.413290113452188, 'support': 576.0}, 'co': {'precision': 0.35051546391752575, 'recall': 0.3953488372093023, 'f1-score': 0.37158469945355194, 'support': 344.0}, 'es': {'precision': 0.4642857142857143, 'recall': 0.40699815837937386, 'f1-score': 0.4337585868498528, 'support': 543.0}, 'mx': {'precision': 0.43089430894308944, 'recall': 0.43711340206185567, 'f1-score': 0.43398157625383826, 'support': 485.0}, 'pe': {'precision': 0.3407960199004975, 'recall': 0.3936781609195402, 'f1-score': 0.36533333333333334, 'support': 348.0}, 'pr': {'precision': 0.6601941747572816, 'recall': 0.6732673267326733, 'f1-score': 0.6666666666666666, 'support': 101.0}, 'uy': {'precision': 0.40853658536585363, 'recall': 0.29385964912280704, 'f1-score': 0.34183673469387754, 'support': 228.0}, 've': {'precision': 0.0, 'recall': 0.0, 'f1-score': 0.0, 'support': 22.0}, 'accuracy': 0.40886536553092956, 'macro avg': {'precision': 0.3849385564532096, 'recall': 0.3794793659212001, 'f1-score': 0.38021465963244544, 'support': 3023.0}, 'weighted avg': {'precision': 0.41080624270175103, 'recall': 0.40886536553092956, 'f1-score': 0.4078732692419294, 'support': 3023.0}} | 0.3802 |
|
59 |
|
60 |
|
61 |
### Framework versions
|
config.json
CHANGED
@@ -1,13 +1,14 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "dccuchile/
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "ar",
|
13 |
"1": "cl",
|
@@ -20,6 +21,7 @@
|
|
20 |
"8": "ve"
|
21 |
},
|
22 |
"initializer_range": 0.02,
|
|
|
23 |
"label2id": {
|
24 |
"ar": 0,
|
25 |
"cl": 1,
|
@@ -31,17 +33,18 @@
|
|
31 |
"uy": 7,
|
32 |
"ve": 8
|
33 |
},
|
|
|
34 |
"max_position_embeddings": 512,
|
35 |
-
"model_type": "
|
36 |
-
"
|
37 |
-
"
|
38 |
-
"
|
|
|
|
|
39 |
"problem_type": "single_label_classification",
|
40 |
-
"qa_dropout": 0.1,
|
41 |
-
"seq_classif_dropout": 0.2,
|
42 |
-
"sinusoidal_pos_embds": true,
|
43 |
-
"tie_weights_": true,
|
44 |
"torch_dtype": "float32",
|
45 |
"transformers_version": "4.48.3",
|
|
|
|
|
46 |
"vocab_size": 31002
|
47 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
|
|
3 |
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "ar",
|
14 |
"1": "cl",
|
|
|
21 |
"8": "ve"
|
22 |
},
|
23 |
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
"label2id": {
|
26 |
"ar": 0,
|
27 |
"cl": 1,
|
|
|
33 |
"uy": 7,
|
34 |
"ve": 8
|
35 |
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
45 |
"torch_dtype": "float32",
|
46 |
"transformers_version": "4.48.3",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
"vocab_size": 31002
|
50 |
}
|
logs/events.out.tfevents.1740157634.a2d653e866f9.226.3
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:646126b025c968bf4bd3116e12b41d96bfb11ffd3e476cc70526ebb920ce8b86
|
3 |
+
size 354
|
logs/events.out.tfevents.1740162891.0a0ba32201a8.2151.21
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ab77507abc6135face2f24050935579841c0edd04ed429b2b14a790d9de3346
|
3 |
+
size 100428
|
logs/events.out.tfevents.1740163730.0a0ba32201a8.2151.22
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c9e1f0c540ff78c3cd5ed026bc180b0a9e5b858cf3411c46ddbc70bd2f355ef
|
3 |
+
size 405
|
model.safetensors
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 sha256:9640bf7ca7b6a541089109fcdb8dd4b103d14e514f0b0b70e6032897467855b5
|
3 |
+
size 439454740
|
model_stats.json
CHANGED
@@ -1,177 +1,96 @@
|
|
1 |
{
|
2 |
"dataset": {
|
3 |
-
"
|
|
|
|
|
4 |
"train": {
|
5 |
-
"
|
6 |
-
|
7 |
-
"
|
8 |
-
|
9 |
-
|
10 |
-
"
|
11 |
-
"
|
12 |
-
|
13 |
-
|
14 |
-
"
|
15 |
-
"
|
16 |
-
|
17 |
-
|
18 |
-
"
|
19 |
-
"
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
"author": "apalet.bsky.social",
|
25 |
-
"country": "cl",
|
26 |
-
"post_text": "Me lloran los ojos sin pedir permiso ni razón.",
|
27 |
-
"created_at": "2024-12-31T01:15:04.751Z",
|
28 |
-
"likes": 8,
|
29 |
-
"quotes": 0,
|
30 |
-
"replies": 1,
|
31 |
-
"reposts": 0,
|
32 |
-
"post_id": "at://did:plc:y4bvfcu7wrx7jlyjg6qglqzl/app.bsky.feed.post/3lekuofg3xk2v",
|
33 |
-
"lang": "es",
|
34 |
-
"tags": "",
|
35 |
-
"image_links": "",
|
36 |
-
"profile_info": {
|
37 |
-
"description": "Leo y olvido \nwww.laurel.cl\nhttps://revistadossier.udp.cl",
|
38 |
-
"display_name": "Andrea Palet",
|
39 |
-
"feed_uri": null,
|
40 |
-
"followers_count": 1355,
|
41 |
-
"follows_count": 304,
|
42 |
-
"indexed_at": "2024-11-30T20:22:38.048Z",
|
43 |
-
"posts_count": 515
|
44 |
-
},
|
45 |
-
"processed_text": "lloran ojos pedir permiso razón",
|
46 |
-
"__index_level_0__": 4653
|
47 |
},
|
48 |
-
"
|
49 |
-
"
|
50 |
-
|
51 |
-
|
52 |
-
|
53 |
-
"
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
"
|
58 |
-
|
59 |
-
|
60 |
-
|
61 |
-
"
|
62 |
-
|
63 |
-
"percentage": 21.784407542921475
|
64 |
-
},
|
65 |
-
"mx": {
|
66 |
-
"count": 473,
|
67 |
-
"percentage": 13.312693498452013
|
68 |
-
},
|
69 |
-
"pe": {
|
70 |
-
"count": 376,
|
71 |
-
"percentage": 10.582606248240923
|
72 |
-
},
|
73 |
-
"pr": {
|
74 |
-
"count": 117,
|
75 |
-
"percentage": 3.2929918378834784
|
76 |
-
},
|
77 |
-
"uy": {
|
78 |
-
"count": 267,
|
79 |
-
"percentage": 7.5147762454264
|
80 |
-
},
|
81 |
-
"ve": {
|
82 |
-
"count": 50,
|
83 |
-
"percentage": 1.407261469180974
|
84 |
-
}
|
85 |
}
|
86 |
},
|
87 |
"test": {
|
88 |
-
"
|
89 |
-
|
90 |
-
"
|
91 |
-
"country",
|
92 |
-
"post_text",
|
93 |
-
"created_at",
|
94 |
-
"likes",
|
95 |
-
"quotes",
|
96 |
-
"replies",
|
97 |
-
"reposts",
|
98 |
-
"post_id",
|
99 |
-
"lang",
|
100 |
-
"tags",
|
101 |
-
"image_links",
|
102 |
-
"profile_info",
|
103 |
-
"processed_text",
|
104 |
-
"__index_level_0__"
|
105 |
-
],
|
106 |
-
"first_example": {
|
107 |
-
"author": "rpalomino.bsky.social",
|
108 |
-
"country": "pe",
|
109 |
-
"post_text": "Dos libros que he estado esperando leer hace mucho.",
|
110 |
-
"created_at": "2024-12-25T16:32:48.934Z",
|
111 |
-
"likes": 2,
|
112 |
-
"quotes": 0,
|
113 |
-
"replies": 1,
|
114 |
-
"reposts": 0,
|
115 |
-
"post_id": "at://did:plc:65xzu4se42blbypbgmki3xxv/app.bsky.feed.post/3le5f5vxtmc2h",
|
116 |
-
"lang": "es",
|
117 |
-
"tags": "",
|
118 |
-
"image_links": "",
|
119 |
-
"profile_info": {
|
120 |
-
"description": "Literatura y sociedad.",
|
121 |
-
"display_name": "Roy Palomino",
|
122 |
-
"feed_uri": null,
|
123 |
-
"followers_count": 174,
|
124 |
-
"follows_count": 283,
|
125 |
-
"indexed_at": "2024-11-25T05:12:19.445Z",
|
126 |
-
"posts_count": 90
|
127 |
-
},
|
128 |
-
"processed_text": "libros esperando leer",
|
129 |
-
"__index_level_0__": 3477
|
130 |
},
|
131 |
-
"
|
132 |
-
"
|
133 |
-
|
134 |
-
|
135 |
-
|
136 |
-
"
|
137 |
-
|
138 |
-
|
139 |
-
|
140 |
-
"
|
141 |
-
|
142 |
-
|
143 |
-
|
144 |
-
"
|
145 |
-
|
146 |
-
|
147 |
-
|
148 |
-
"
|
149 |
-
|
150 |
-
|
151 |
-
|
152 |
-
"
|
153 |
-
|
154 |
-
|
155 |
-
|
156 |
-
"
|
157 |
-
|
158 |
-
|
159 |
-
|
160 |
-
"
|
161 |
-
|
162 |
-
"percentage": 7.545931758530183
|
163 |
-
},
|
164 |
-
"ve": {
|
165 |
-
"count": 22,
|
166 |
-
"percentage": 1.4435695538057742
|
167 |
-
}
|
168 |
}
|
169 |
}
|
170 |
},
|
171 |
-
"
|
172 |
-
"
|
173 |
-
"
|
174 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
175 |
},
|
176 |
"model": {
|
177 |
"name": "dccuchile/distilbert-base-spanish-uncased",
|
@@ -185,152 +104,152 @@
|
|
185 |
"hub_url": "https://huggingface.co/None/bluesky-spanish-classifier"
|
186 |
},
|
187 |
"training": {
|
188 |
-
"runtime_seconds":
|
189 |
-
"loss": 2.
|
190 |
-
"steps_per_second": 0.
|
191 |
},
|
192 |
"evaluation": {
|
193 |
"ar": {
|
194 |
-
"precision": 0.
|
195 |
-
"recall": 0.
|
196 |
-
"f1-score": 0.
|
197 |
"support": 207.0
|
198 |
},
|
199 |
"cl": {
|
200 |
-
"precision": 0.
|
201 |
-
"recall": 0.
|
202 |
-
"f1-score": 0.
|
203 |
"support": 263.0
|
204 |
},
|
205 |
"co": {
|
206 |
-
"precision": 0.
|
207 |
-
"recall": 0.
|
208 |
-
"f1-score": 0.
|
209 |
"support": 171.0
|
210 |
},
|
211 |
"es": {
|
212 |
-
"precision": 0.
|
213 |
-
"recall": 0.
|
214 |
-
"f1-score": 0.
|
215 |
"support": 332.0
|
216 |
},
|
217 |
"mx": {
|
218 |
-
"precision": 0.
|
219 |
-
"recall": 0.
|
220 |
-
"f1-score": 0.
|
221 |
"support": 203.0
|
222 |
},
|
223 |
"pe": {
|
224 |
-
"precision": 0.
|
225 |
-
"recall": 0.
|
226 |
-
"f1-score": 0.
|
227 |
"support": 161.0
|
228 |
},
|
229 |
"pr": {
|
230 |
-
"precision": 0.
|
231 |
-
"recall": 0.
|
232 |
-
"f1-score": 0.
|
233 |
"support": 50.0
|
234 |
},
|
235 |
"uy": {
|
236 |
-
"precision": 0.
|
237 |
-
"recall": 0.
|
238 |
-
"f1-score": 0.
|
239 |
"support": 115.0
|
240 |
},
|
241 |
"ve": {
|
242 |
-
"precision": 0.
|
243 |
-
"recall": 0.
|
244 |
-
"f1-score": 0.
|
245 |
"support": 22.0
|
246 |
},
|
247 |
-
"accuracy": 0.
|
248 |
"macro avg": {
|
249 |
-
"precision": 0.
|
250 |
-
"recall": 0.
|
251 |
-
"f1-score": 0.
|
252 |
"support": 1524.0
|
253 |
},
|
254 |
"weighted avg": {
|
255 |
-
"precision": 0.
|
256 |
-
"recall": 0.
|
257 |
-
"f1-score": 0.
|
258 |
"support": 1524.0
|
259 |
},
|
260 |
"final": {
|
261 |
-
"eval_loss": 2.
|
262 |
"eval_classification_report": {
|
263 |
"ar": {
|
264 |
-
"precision": 0.
|
265 |
-
"recall": 0.
|
266 |
-
"f1-score": 0.
|
267 |
"support": 207.0
|
268 |
},
|
269 |
"cl": {
|
270 |
-
"precision": 0.
|
271 |
-
"recall": 0.
|
272 |
-
"f1-score": 0.
|
273 |
"support": 263.0
|
274 |
},
|
275 |
"co": {
|
276 |
-
"precision": 0.
|
277 |
-
"recall": 0.
|
278 |
-
"f1-score": 0.
|
279 |
"support": 171.0
|
280 |
},
|
281 |
"es": {
|
282 |
-
"precision": 0.
|
283 |
-
"recall": 0.
|
284 |
-
"f1-score": 0.
|
285 |
"support": 332.0
|
286 |
},
|
287 |
"mx": {
|
288 |
-
"precision": 0.
|
289 |
-
"recall": 0.
|
290 |
-
"f1-score": 0.
|
291 |
"support": 203.0
|
292 |
},
|
293 |
"pe": {
|
294 |
-
"precision": 0.
|
295 |
-
"recall": 0.
|
296 |
-
"f1-score": 0.
|
297 |
"support": 161.0
|
298 |
},
|
299 |
"pr": {
|
300 |
-
"precision": 0.
|
301 |
-
"recall": 0.
|
302 |
-
"f1-score": 0.
|
303 |
"support": 50.0
|
304 |
},
|
305 |
"uy": {
|
306 |
-
"precision": 0.
|
307 |
-
"recall": 0.
|
308 |
-
"f1-score": 0.
|
309 |
"support": 115.0
|
310 |
},
|
311 |
"ve": {
|
312 |
-
"precision": 0.
|
313 |
-
"recall": 0.
|
314 |
-
"f1-score": 0.
|
315 |
"support": 22.0
|
316 |
},
|
317 |
-
"accuracy": 0.
|
318 |
"macro avg": {
|
319 |
-
"precision": 0.
|
320 |
-
"recall": 0.
|
321 |
-
"f1-score": 0.
|
322 |
"support": 1524.0
|
323 |
},
|
324 |
"weighted avg": {
|
325 |
-
"precision": 0.
|
326 |
-
"recall": 0.
|
327 |
-
"f1-score": 0.
|
328 |
"support": 1524.0
|
329 |
}
|
330 |
},
|
331 |
-
"eval_runtime":
|
332 |
-
"eval_samples_per_second": 15.
|
333 |
-
"eval_steps_per_second": 3.
|
334 |
"epoch": 0.0022497187851518562
|
335 |
}
|
336 |
}
|
|
|
1 |
{
|
2 |
"dataset": {
|
3 |
+
"train_size": 3553,
|
4 |
+
"test_size": 1524,
|
5 |
+
"country_distribution": {
|
6 |
"train": {
|
7 |
+
"ar": {
|
8 |
+
"count": 483,
|
9 |
+
"percentage": 13.594145792288206
|
10 |
+
},
|
11 |
+
"cl": {
|
12 |
+
"count": 614,
|
13 |
+
"percentage": 17.28117084154236
|
14 |
+
},
|
15 |
+
"co": {
|
16 |
+
"count": 399,
|
17 |
+
"percentage": 11.229946524064172
|
18 |
+
},
|
19 |
+
"es": {
|
20 |
+
"count": 774,
|
21 |
+
"percentage": 21.784407542921475
|
22 |
+
},
|
23 |
+
"mx": {
|
24 |
+
"count": 473,
|
25 |
+
"percentage": 13.312693498452013
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
},
|
27 |
+
"pe": {
|
28 |
+
"count": 376,
|
29 |
+
"percentage": 10.582606248240923
|
30 |
+
},
|
31 |
+
"pr": {
|
32 |
+
"count": 117,
|
33 |
+
"percentage": 3.2929918378834784
|
34 |
+
},
|
35 |
+
"uy": {
|
36 |
+
"count": 267,
|
37 |
+
"percentage": 7.5147762454264
|
38 |
+
},
|
39 |
+
"ve": {
|
40 |
+
"count": 50,
|
41 |
+
"percentage": 1.407261469180974
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
42 |
}
|
43 |
},
|
44 |
"test": {
|
45 |
+
"ar": {
|
46 |
+
"count": 207,
|
47 |
+
"percentage": 13.582677165354331
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
},
|
49 |
+
"cl": {
|
50 |
+
"count": 263,
|
51 |
+
"percentage": 17.25721784776903
|
52 |
+
},
|
53 |
+
"co": {
|
54 |
+
"count": 171,
|
55 |
+
"percentage": 11.220472440944881
|
56 |
+
},
|
57 |
+
"es": {
|
58 |
+
"count": 332,
|
59 |
+
"percentage": 21.784776902887142
|
60 |
+
},
|
61 |
+
"mx": {
|
62 |
+
"count": 203,
|
63 |
+
"percentage": 13.32020997375328
|
64 |
+
},
|
65 |
+
"pe": {
|
66 |
+
"count": 161,
|
67 |
+
"percentage": 10.564304461942257
|
68 |
+
},
|
69 |
+
"pr": {
|
70 |
+
"count": 50,
|
71 |
+
"percentage": 3.2808398950131235
|
72 |
+
},
|
73 |
+
"uy": {
|
74 |
+
"count": 115,
|
75 |
+
"percentage": 7.545931758530183
|
76 |
+
},
|
77 |
+
"ve": {
|
78 |
+
"count": 22,
|
79 |
+
"percentage": 1.4435695538057742
|
|
|
|
|
|
|
|
|
|
|
|
|
80 |
}
|
81 |
}
|
82 |
},
|
83 |
+
"unique_countries": [
|
84 |
+
"ar",
|
85 |
+
"cl",
|
86 |
+
"co",
|
87 |
+
"es",
|
88 |
+
"mx",
|
89 |
+
"pe",
|
90 |
+
"pr",
|
91 |
+
"uy",
|
92 |
+
"ve"
|
93 |
+
]
|
94 |
},
|
95 |
"model": {
|
96 |
"name": "dccuchile/distilbert-base-spanish-uncased",
|
|
|
104 |
"hub_url": "https://huggingface.co/None/bluesky-spanish-classifier"
|
105 |
},
|
106 |
"training": {
|
107 |
+
"runtime_seconds": 105.9611,
|
108 |
+
"loss": 2.257941484451294,
|
109 |
+
"steps_per_second": 0.019
|
110 |
},
|
111 |
"evaluation": {
|
112 |
"ar": {
|
113 |
+
"precision": 0.125,
|
114 |
+
"recall": 0.014492753623188406,
|
115 |
+
"f1-score": 0.025974025974025976,
|
116 |
"support": 207.0
|
117 |
},
|
118 |
"cl": {
|
119 |
+
"precision": 0.0,
|
120 |
+
"recall": 0.0,
|
121 |
+
"f1-score": 0.0,
|
122 |
"support": 263.0
|
123 |
},
|
124 |
"co": {
|
125 |
+
"precision": 0.0,
|
126 |
+
"recall": 0.0,
|
127 |
+
"f1-score": 0.0,
|
128 |
"support": 171.0
|
129 |
},
|
130 |
"es": {
|
131 |
+
"precision": 0.6666666666666666,
|
132 |
+
"recall": 0.006024096385542169,
|
133 |
+
"f1-score": 0.011940298507462687,
|
134 |
"support": 332.0
|
135 |
},
|
136 |
"mx": {
|
137 |
+
"precision": 0.0,
|
138 |
+
"recall": 0.0,
|
139 |
+
"f1-score": 0.0,
|
140 |
"support": 203.0
|
141 |
},
|
142 |
"pe": {
|
143 |
+
"precision": 0.03333333333333333,
|
144 |
+
"recall": 0.006211180124223602,
|
145 |
+
"f1-score": 0.010471204188481676,
|
146 |
"support": 161.0
|
147 |
},
|
148 |
"pr": {
|
149 |
+
"precision": 0.09401709401709402,
|
150 |
+
"recall": 0.22,
|
151 |
+
"f1-score": 0.1317365269461078,
|
152 |
"support": 50.0
|
153 |
},
|
154 |
"uy": {
|
155 |
+
"precision": 0.07073715562174236,
|
156 |
+
"recall": 0.8260869565217391,
|
157 |
+
"f1-score": 0.13031550068587106,
|
158 |
"support": 115.0
|
159 |
},
|
160 |
"ve": {
|
161 |
+
"precision": 0.0,
|
162 |
+
"recall": 0.0,
|
163 |
+
"f1-score": 0.0,
|
164 |
"support": 22.0
|
165 |
},
|
166 |
+
"accuracy": 0.07349081364829396,
|
167 |
"macro avg": {
|
168 |
+
"precision": 0.10997269440431515,
|
169 |
+
"recall": 0.1192016651838548,
|
170 |
+
"f1-score": 0.03449306181132769,
|
171 |
"support": 1524.0
|
172 |
},
|
173 |
"weighted avg": {
|
174 |
+
"precision": 0.17415395511637471,
|
175 |
+
"recall": 0.07349081364829396,
|
176 |
+
"f1-score": 0.021390928662484977,
|
177 |
"support": 1524.0
|
178 |
},
|
179 |
"final": {
|
180 |
+
"eval_loss": 2.2149105072021484,
|
181 |
"eval_classification_report": {
|
182 |
"ar": {
|
183 |
+
"precision": 0.125,
|
184 |
+
"recall": 0.014492753623188406,
|
185 |
+
"f1-score": 0.025974025974025976,
|
186 |
"support": 207.0
|
187 |
},
|
188 |
"cl": {
|
189 |
+
"precision": 0.0,
|
190 |
+
"recall": 0.0,
|
191 |
+
"f1-score": 0.0,
|
192 |
"support": 263.0
|
193 |
},
|
194 |
"co": {
|
195 |
+
"precision": 0.0,
|
196 |
+
"recall": 0.0,
|
197 |
+
"f1-score": 0.0,
|
198 |
"support": 171.0
|
199 |
},
|
200 |
"es": {
|
201 |
+
"precision": 0.6666666666666666,
|
202 |
+
"recall": 0.006024096385542169,
|
203 |
+
"f1-score": 0.011940298507462687,
|
204 |
"support": 332.0
|
205 |
},
|
206 |
"mx": {
|
207 |
+
"precision": 0.0,
|
208 |
+
"recall": 0.0,
|
209 |
+
"f1-score": 0.0,
|
210 |
"support": 203.0
|
211 |
},
|
212 |
"pe": {
|
213 |
+
"precision": 0.03333333333333333,
|
214 |
+
"recall": 0.006211180124223602,
|
215 |
+
"f1-score": 0.010471204188481676,
|
216 |
"support": 161.0
|
217 |
},
|
218 |
"pr": {
|
219 |
+
"precision": 0.09401709401709402,
|
220 |
+
"recall": 0.22,
|
221 |
+
"f1-score": 0.1317365269461078,
|
222 |
"support": 50.0
|
223 |
},
|
224 |
"uy": {
|
225 |
+
"precision": 0.07073715562174236,
|
226 |
+
"recall": 0.8260869565217391,
|
227 |
+
"f1-score": 0.13031550068587106,
|
228 |
"support": 115.0
|
229 |
},
|
230 |
"ve": {
|
231 |
+
"precision": 0.0,
|
232 |
+
"recall": 0.0,
|
233 |
+
"f1-score": 0.0,
|
234 |
"support": 22.0
|
235 |
},
|
236 |
+
"accuracy": 0.07349081364829396,
|
237 |
"macro avg": {
|
238 |
+
"precision": 0.10997269440431515,
|
239 |
+
"recall": 0.1192016651838548,
|
240 |
+
"f1-score": 0.03449306181132769,
|
241 |
"support": 1524.0
|
242 |
},
|
243 |
"weighted avg": {
|
244 |
+
"precision": 0.17415395511637471,
|
245 |
+
"recall": 0.07349081364829396,
|
246 |
+
"f1-score": 0.021390928662484977,
|
247 |
"support": 1524.0
|
248 |
}
|
249 |
},
|
250 |
+
"eval_runtime": 98.563,
|
251 |
+
"eval_samples_per_second": 15.462,
|
252 |
+
"eval_steps_per_second": 3.866,
|
253 |
"epoch": 0.0022497187851518562
|
254 |
}
|
255 |
}
|
tokenizer.json
CHANGED
@@ -2,13 +2,13 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
-
"Fixed":
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 64,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
"padding": {
|
10 |
"strategy": {
|
11 |
+
"Fixed": 64
|
12 |
},
|
13 |
"direction": "Right",
|
14 |
"pad_to_multiple_of": null,
|
tokenizer_config.json
CHANGED
@@ -53,6 +53,6 @@
|
|
53 |
"sep_token": "[SEP]",
|
54 |
"strip_accents": false,
|
55 |
"tokenize_chinese_chars": true,
|
56 |
-
"tokenizer_class": "
|
57 |
"unk_token": "[UNK]"
|
58 |
}
|
|
|
53 |
"sep_token": "[SEP]",
|
54 |
"strip_accents": false,
|
55 |
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
"unk_token": "[UNK]"
|
58 |
}
|
training_args.bin
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:a2de174b6ea17c52db95df91a80925879ae293fdc8fa93e84445ba29d1a5e95b
|
3 |
+
size 5432
|
trial_0/checkpoint-292/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ar",
|
14 |
+
"1": "cl",
|
15 |
+
"2": "co",
|
16 |
+
"3": "es",
|
17 |
+
"4": "mx",
|
18 |
+
"5": "pe",
|
19 |
+
"6": "pr",
|
20 |
+
"7": "uy",
|
21 |
+
"8": "ve"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"ar": 0,
|
27 |
+
"cl": 1,
|
28 |
+
"co": 2,
|
29 |
+
"es": 3,
|
30 |
+
"mx": 4,
|
31 |
+
"pe": 5,
|
32 |
+
"pr": 6,
|
33 |
+
"uy": 7,
|
34 |
+
"ve": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.48.3",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 31002
|
50 |
+
}
|
trial_0/checkpoint-292/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76e0b013258938faa56136402a7e40a933eef90038e3f931c5780cf4f69b10bd
|
3 |
+
size 439454740
|
trial_0/checkpoint-292/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:751bd43e029cbd1d226e60e6a4fd7af47fee03b3990b3f6a8ecbc3ec83eeba06
|
3 |
+
size 879030522
|
trial_0/checkpoint-292/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0df68380976b6dbabd78e6cbea5eb7a814681ecd61ae85ed04b274788a2e922
|
3 |
+
size 14244
|
trial_0/checkpoint-292/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1778d089cccff46f89357266568881d0aa63539ed46bc3a93cfb7fba7fc007c3
|
3 |
+
size 1064
|
trial_0/checkpoint-292/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
trial_0/checkpoint-292/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trial_0/checkpoint-292/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
trial_0/checkpoint-292/trainer_state.json
ADDED
@@ -0,0 +1,314 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.2140692864641761,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_0/checkpoint-292",
|
4 |
+
"epoch": 1.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 292,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03424657534246575,
|
13 |
+
"grad_norm": 8.432939529418945,
|
14 |
+
"learning_rate": 8.18270817933484e-07,
|
15 |
+
"loss": 2.2234,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0684931506849315,
|
20 |
+
"grad_norm": 8.3140230178833,
|
21 |
+
"learning_rate": 1.636541635866968e-06,
|
22 |
+
"loss": 2.2403,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10273972602739725,
|
27 |
+
"grad_norm": 7.506945610046387,
|
28 |
+
"learning_rate": 2.454812453800452e-06,
|
29 |
+
"loss": 2.2297,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.136986301369863,
|
34 |
+
"grad_norm": 8.531285285949707,
|
35 |
+
"learning_rate": 3.273083271733936e-06,
|
36 |
+
"loss": 2.1823,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17123287671232876,
|
41 |
+
"grad_norm": 7.951968669891357,
|
42 |
+
"learning_rate": 4.091354089667421e-06,
|
43 |
+
"loss": 2.1696,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2054794520547945,
|
48 |
+
"grad_norm": 8.328391075134277,
|
49 |
+
"learning_rate": 4.909624907600904e-06,
|
50 |
+
"loss": 2.1415,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.23972602739726026,
|
55 |
+
"grad_norm": 7.337668418884277,
|
56 |
+
"learning_rate": 5.727895725534388e-06,
|
57 |
+
"loss": 2.1206,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.273972602739726,
|
62 |
+
"grad_norm": 7.09800386428833,
|
63 |
+
"learning_rate": 6.546166543467872e-06,
|
64 |
+
"loss": 2.0949,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3082191780821918,
|
69 |
+
"grad_norm": 6.549777507781982,
|
70 |
+
"learning_rate": 7.364437361401356e-06,
|
71 |
+
"loss": 2.076,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.3424657534246575,
|
76 |
+
"grad_norm": 7.464539051055908,
|
77 |
+
"learning_rate": 8.182708179334841e-06,
|
78 |
+
"loss": 2.096,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3767123287671233,
|
83 |
+
"grad_norm": 6.982883930206299,
|
84 |
+
"learning_rate": 9.000978997268324e-06,
|
85 |
+
"loss": 2.0615,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.410958904109589,
|
90 |
+
"grad_norm": 7.149113655090332,
|
91 |
+
"learning_rate": 9.819249815201808e-06,
|
92 |
+
"loss": 2.0785,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4452054794520548,
|
97 |
+
"grad_norm": 6.507534503936768,
|
98 |
+
"learning_rate": 1.0637520633135292e-05,
|
99 |
+
"loss": 2.0865,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4794520547945205,
|
104 |
+
"grad_norm": 6.1932196617126465,
|
105 |
+
"learning_rate": 1.1455791451068777e-05,
|
106 |
+
"loss": 2.0533,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5136986301369864,
|
111 |
+
"grad_norm": 7.072916507720947,
|
112 |
+
"learning_rate": 1.1783771409556479e-05,
|
113 |
+
"loss": 2.0613,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.547945205479452,
|
118 |
+
"grad_norm": 8.155049324035645,
|
119 |
+
"learning_rate": 1.1621460508598402e-05,
|
120 |
+
"loss": 2.0284,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5821917808219178,
|
125 |
+
"grad_norm": 9.3668851852417,
|
126 |
+
"learning_rate": 1.1459149607640322e-05,
|
127 |
+
"loss": 2.0137,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6164383561643836,
|
132 |
+
"grad_norm": 8.165146827697754,
|
133 |
+
"learning_rate": 1.1296838706682245e-05,
|
134 |
+
"loss": 1.9835,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6506849315068494,
|
139 |
+
"grad_norm": 9.0431547164917,
|
140 |
+
"learning_rate": 1.1134527805724166e-05,
|
141 |
+
"loss": 1.9934,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.684931506849315,
|
146 |
+
"grad_norm": 8.92784309387207,
|
147 |
+
"learning_rate": 1.0972216904766088e-05,
|
148 |
+
"loss": 2.0081,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7191780821917808,
|
153 |
+
"grad_norm": 9.184441566467285,
|
154 |
+
"learning_rate": 1.0809906003808009e-05,
|
155 |
+
"loss": 1.9567,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7534246575342466,
|
160 |
+
"grad_norm": 10.262762069702148,
|
161 |
+
"learning_rate": 1.0647595102849931e-05,
|
162 |
+
"loss": 1.966,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7876712328767124,
|
167 |
+
"grad_norm": 7.367489337921143,
|
168 |
+
"learning_rate": 1.0485284201891854e-05,
|
169 |
+
"loss": 2.051,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.821917808219178,
|
174 |
+
"grad_norm": 8.76405143737793,
|
175 |
+
"learning_rate": 1.0322973300933776e-05,
|
176 |
+
"loss": 2.0785,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8561643835616438,
|
181 |
+
"grad_norm": 7.100874900817871,
|
182 |
+
"learning_rate": 1.0160662399975697e-05,
|
183 |
+
"loss": 1.9977,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8904109589041096,
|
188 |
+
"grad_norm": 8.239387512207031,
|
189 |
+
"learning_rate": 9.998351499017618e-06,
|
190 |
+
"loss": 2.0099,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9246575342465754,
|
195 |
+
"grad_norm": 7.704412460327148,
|
196 |
+
"learning_rate": 9.83604059805954e-06,
|
197 |
+
"loss": 1.9851,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.958904109589041,
|
202 |
+
"grad_norm": 7.8163652420043945,
|
203 |
+
"learning_rate": 9.673729697101463e-06,
|
204 |
+
"loss": 2.0085,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9931506849315068,
|
209 |
+
"grad_norm": 8.153071403503418,
|
210 |
+
"learning_rate": 9.511418796143383e-06,
|
211 |
+
"loss": 1.9962,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.0,
|
216 |
+
"eval_classification_report": {
|
217 |
+
"accuracy": 0.2375,
|
218 |
+
"ar": {
|
219 |
+
"f1-score": 0.0622568093385214,
|
220 |
+
"precision": 0.1568627450980392,
|
221 |
+
"recall": 0.038834951456310676,
|
222 |
+
"support": 206.0
|
223 |
+
},
|
224 |
+
"cl": {
|
225 |
+
"f1-score": 0.2011173184357542,
|
226 |
+
"precision": 0.16901408450704225,
|
227 |
+
"recall": 0.2482758620689655,
|
228 |
+
"support": 290.0
|
229 |
+
},
|
230 |
+
"co": {
|
231 |
+
"f1-score": 0.31543624161073824,
|
232 |
+
"precision": 0.23383084577114427,
|
233 |
+
"recall": 0.4845360824742268,
|
234 |
+
"support": 291.0
|
235 |
+
},
|
236 |
+
"es": {
|
237 |
+
"f1-score": 0.27364185110663986,
|
238 |
+
"precision": 0.3119266055045872,
|
239 |
+
"recall": 0.24372759856630824,
|
240 |
+
"support": 279.0
|
241 |
+
},
|
242 |
+
"macro avg": {
|
243 |
+
"f1-score": 0.2140692864641761,
|
244 |
+
"precision": 0.24922489036795273,
|
245 |
+
"recall": 0.22042150190811827,
|
246 |
+
"support": 2000.0
|
247 |
+
},
|
248 |
+
"mx": {
|
249 |
+
"f1-score": 0.22950819672131148,
|
250 |
+
"precision": 0.28426395939086296,
|
251 |
+
"recall": 0.19243986254295534,
|
252 |
+
"support": 291.0
|
253 |
+
},
|
254 |
+
"pe": {
|
255 |
+
"f1-score": 0.10610079575596817,
|
256 |
+
"precision": 0.23255813953488372,
|
257 |
+
"recall": 0.06872852233676977,
|
258 |
+
"support": 291.0
|
259 |
+
},
|
260 |
+
"pr": {
|
261 |
+
"f1-score": 0.5030674846625767,
|
262 |
+
"precision": 0.6612903225806451,
|
263 |
+
"recall": 0.40594059405940597,
|
264 |
+
"support": 101.0
|
265 |
+
},
|
266 |
+
"uy": {
|
267 |
+
"f1-score": 0.2354948805460751,
|
268 |
+
"precision": 0.19327731092436976,
|
269 |
+
"recall": 0.30131004366812225,
|
270 |
+
"support": 229.0
|
271 |
+
},
|
272 |
+
"ve": {
|
273 |
+
"f1-score": 0.0,
|
274 |
+
"precision": 0.0,
|
275 |
+
"recall": 0.0,
|
276 |
+
"support": 22.0
|
277 |
+
},
|
278 |
+
"weighted avg": {
|
279 |
+
"f1-score": 0.22084365412222065,
|
280 |
+
"precision": 0.24892308331106963,
|
281 |
+
"recall": 0.2375,
|
282 |
+
"support": 2000.0
|
283 |
+
}
|
284 |
+
},
|
285 |
+
"eval_f1": 0.2140692864641761,
|
286 |
+
"eval_loss": 1.964627742767334,
|
287 |
+
"eval_runtime": 3.948,
|
288 |
+
"eval_samples_per_second": 506.591,
|
289 |
+
"eval_steps_per_second": 31.662,
|
290 |
+
"step": 292
|
291 |
+
}
|
292 |
+
],
|
293 |
+
"logging_steps": 10,
|
294 |
+
"max_steps": 876,
|
295 |
+
"num_input_tokens_seen": 0,
|
296 |
+
"num_train_epochs": 3,
|
297 |
+
"save_steps": 500,
|
298 |
+
"stateful_callbacks": {
|
299 |
+
"TrainerControl": {
|
300 |
+
"args": {
|
301 |
+
"should_epoch_stop": false,
|
302 |
+
"should_evaluate": false,
|
303 |
+
"should_log": false,
|
304 |
+
"should_save": true,
|
305 |
+
"should_training_stop": false
|
306 |
+
},
|
307 |
+
"attributes": {}
|
308 |
+
}
|
309 |
+
},
|
310 |
+
"total_flos": 306938335993344.0,
|
311 |
+
"train_batch_size": 16,
|
312 |
+
"trial_name": null,
|
313 |
+
"trial_params": null
|
314 |
+
}
|
trial_0/checkpoint-292/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf983bab71d39717083fd85c30b7e0fd950e8d457e647f61a7ff596cb390b138
|
3 |
+
size 5368
|
trial_0/checkpoint-292/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trial_0/checkpoint-584/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ar",
|
14 |
+
"1": "cl",
|
15 |
+
"2": "co",
|
16 |
+
"3": "es",
|
17 |
+
"4": "mx",
|
18 |
+
"5": "pe",
|
19 |
+
"6": "pr",
|
20 |
+
"7": "uy",
|
21 |
+
"8": "ve"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"ar": 0,
|
27 |
+
"cl": 1,
|
28 |
+
"co": 2,
|
29 |
+
"es": 3,
|
30 |
+
"mx": 4,
|
31 |
+
"pe": 5,
|
32 |
+
"pr": 6,
|
33 |
+
"uy": 7,
|
34 |
+
"ve": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.48.3",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 31002
|
50 |
+
}
|
trial_0/checkpoint-584/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c4bd824eba668c9f99dbdde707cc6253632a9e5404c4c7bef800e5dba0b97408
|
3 |
+
size 439454740
|
trial_0/checkpoint-584/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9e5a12946127f3bcd02446e83b50c11c5b9bd0d42c2769ab3843e2416a6ea45
|
3 |
+
size 879030522
|
trial_0/checkpoint-584/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:29298f33af39c877ad364d333a5cea911258abeb5e708833407727da7ed21d36
|
3 |
+
size 14244
|
trial_0/checkpoint-584/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3ae5ac764505bf16f8c0111375ef98ea91c30113225dcd6204117dc37e31e3b
|
3 |
+
size 1064
|
trial_0/checkpoint-584/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
trial_0/checkpoint-584/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trial_0/checkpoint-584/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
trial_0/checkpoint-584/trainer_state.json
ADDED
@@ -0,0 +1,595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.28404923689784706,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_0/checkpoint-584",
|
4 |
+
"epoch": 2.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 584,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03424657534246575,
|
13 |
+
"grad_norm": 8.432939529418945,
|
14 |
+
"learning_rate": 8.18270817933484e-07,
|
15 |
+
"loss": 2.2234,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0684931506849315,
|
20 |
+
"grad_norm": 8.3140230178833,
|
21 |
+
"learning_rate": 1.636541635866968e-06,
|
22 |
+
"loss": 2.2403,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10273972602739725,
|
27 |
+
"grad_norm": 7.506945610046387,
|
28 |
+
"learning_rate": 2.454812453800452e-06,
|
29 |
+
"loss": 2.2297,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.136986301369863,
|
34 |
+
"grad_norm": 8.531285285949707,
|
35 |
+
"learning_rate": 3.273083271733936e-06,
|
36 |
+
"loss": 2.1823,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17123287671232876,
|
41 |
+
"grad_norm": 7.951968669891357,
|
42 |
+
"learning_rate": 4.091354089667421e-06,
|
43 |
+
"loss": 2.1696,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2054794520547945,
|
48 |
+
"grad_norm": 8.328391075134277,
|
49 |
+
"learning_rate": 4.909624907600904e-06,
|
50 |
+
"loss": 2.1415,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.23972602739726026,
|
55 |
+
"grad_norm": 7.337668418884277,
|
56 |
+
"learning_rate": 5.727895725534388e-06,
|
57 |
+
"loss": 2.1206,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.273972602739726,
|
62 |
+
"grad_norm": 7.09800386428833,
|
63 |
+
"learning_rate": 6.546166543467872e-06,
|
64 |
+
"loss": 2.0949,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3082191780821918,
|
69 |
+
"grad_norm": 6.549777507781982,
|
70 |
+
"learning_rate": 7.364437361401356e-06,
|
71 |
+
"loss": 2.076,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.3424657534246575,
|
76 |
+
"grad_norm": 7.464539051055908,
|
77 |
+
"learning_rate": 8.182708179334841e-06,
|
78 |
+
"loss": 2.096,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3767123287671233,
|
83 |
+
"grad_norm": 6.982883930206299,
|
84 |
+
"learning_rate": 9.000978997268324e-06,
|
85 |
+
"loss": 2.0615,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.410958904109589,
|
90 |
+
"grad_norm": 7.149113655090332,
|
91 |
+
"learning_rate": 9.819249815201808e-06,
|
92 |
+
"loss": 2.0785,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4452054794520548,
|
97 |
+
"grad_norm": 6.507534503936768,
|
98 |
+
"learning_rate": 1.0637520633135292e-05,
|
99 |
+
"loss": 2.0865,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4794520547945205,
|
104 |
+
"grad_norm": 6.1932196617126465,
|
105 |
+
"learning_rate": 1.1455791451068777e-05,
|
106 |
+
"loss": 2.0533,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5136986301369864,
|
111 |
+
"grad_norm": 7.072916507720947,
|
112 |
+
"learning_rate": 1.1783771409556479e-05,
|
113 |
+
"loss": 2.0613,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.547945205479452,
|
118 |
+
"grad_norm": 8.155049324035645,
|
119 |
+
"learning_rate": 1.1621460508598402e-05,
|
120 |
+
"loss": 2.0284,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5821917808219178,
|
125 |
+
"grad_norm": 9.3668851852417,
|
126 |
+
"learning_rate": 1.1459149607640322e-05,
|
127 |
+
"loss": 2.0137,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6164383561643836,
|
132 |
+
"grad_norm": 8.165146827697754,
|
133 |
+
"learning_rate": 1.1296838706682245e-05,
|
134 |
+
"loss": 1.9835,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6506849315068494,
|
139 |
+
"grad_norm": 9.0431547164917,
|
140 |
+
"learning_rate": 1.1134527805724166e-05,
|
141 |
+
"loss": 1.9934,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.684931506849315,
|
146 |
+
"grad_norm": 8.92784309387207,
|
147 |
+
"learning_rate": 1.0972216904766088e-05,
|
148 |
+
"loss": 2.0081,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7191780821917808,
|
153 |
+
"grad_norm": 9.184441566467285,
|
154 |
+
"learning_rate": 1.0809906003808009e-05,
|
155 |
+
"loss": 1.9567,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7534246575342466,
|
160 |
+
"grad_norm": 10.262762069702148,
|
161 |
+
"learning_rate": 1.0647595102849931e-05,
|
162 |
+
"loss": 1.966,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7876712328767124,
|
167 |
+
"grad_norm": 7.367489337921143,
|
168 |
+
"learning_rate": 1.0485284201891854e-05,
|
169 |
+
"loss": 2.051,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.821917808219178,
|
174 |
+
"grad_norm": 8.76405143737793,
|
175 |
+
"learning_rate": 1.0322973300933776e-05,
|
176 |
+
"loss": 2.0785,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8561643835616438,
|
181 |
+
"grad_norm": 7.100874900817871,
|
182 |
+
"learning_rate": 1.0160662399975697e-05,
|
183 |
+
"loss": 1.9977,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8904109589041096,
|
188 |
+
"grad_norm": 8.239387512207031,
|
189 |
+
"learning_rate": 9.998351499017618e-06,
|
190 |
+
"loss": 2.0099,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9246575342465754,
|
195 |
+
"grad_norm": 7.704412460327148,
|
196 |
+
"learning_rate": 9.83604059805954e-06,
|
197 |
+
"loss": 1.9851,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.958904109589041,
|
202 |
+
"grad_norm": 7.8163652420043945,
|
203 |
+
"learning_rate": 9.673729697101463e-06,
|
204 |
+
"loss": 2.0085,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9931506849315068,
|
209 |
+
"grad_norm": 8.153071403503418,
|
210 |
+
"learning_rate": 9.511418796143383e-06,
|
211 |
+
"loss": 1.9962,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.0,
|
216 |
+
"eval_classification_report": {
|
217 |
+
"accuracy": 0.2375,
|
218 |
+
"ar": {
|
219 |
+
"f1-score": 0.0622568093385214,
|
220 |
+
"precision": 0.1568627450980392,
|
221 |
+
"recall": 0.038834951456310676,
|
222 |
+
"support": 206.0
|
223 |
+
},
|
224 |
+
"cl": {
|
225 |
+
"f1-score": 0.2011173184357542,
|
226 |
+
"precision": 0.16901408450704225,
|
227 |
+
"recall": 0.2482758620689655,
|
228 |
+
"support": 290.0
|
229 |
+
},
|
230 |
+
"co": {
|
231 |
+
"f1-score": 0.31543624161073824,
|
232 |
+
"precision": 0.23383084577114427,
|
233 |
+
"recall": 0.4845360824742268,
|
234 |
+
"support": 291.0
|
235 |
+
},
|
236 |
+
"es": {
|
237 |
+
"f1-score": 0.27364185110663986,
|
238 |
+
"precision": 0.3119266055045872,
|
239 |
+
"recall": 0.24372759856630824,
|
240 |
+
"support": 279.0
|
241 |
+
},
|
242 |
+
"macro avg": {
|
243 |
+
"f1-score": 0.2140692864641761,
|
244 |
+
"precision": 0.24922489036795273,
|
245 |
+
"recall": 0.22042150190811827,
|
246 |
+
"support": 2000.0
|
247 |
+
},
|
248 |
+
"mx": {
|
249 |
+
"f1-score": 0.22950819672131148,
|
250 |
+
"precision": 0.28426395939086296,
|
251 |
+
"recall": 0.19243986254295534,
|
252 |
+
"support": 291.0
|
253 |
+
},
|
254 |
+
"pe": {
|
255 |
+
"f1-score": 0.10610079575596817,
|
256 |
+
"precision": 0.23255813953488372,
|
257 |
+
"recall": 0.06872852233676977,
|
258 |
+
"support": 291.0
|
259 |
+
},
|
260 |
+
"pr": {
|
261 |
+
"f1-score": 0.5030674846625767,
|
262 |
+
"precision": 0.6612903225806451,
|
263 |
+
"recall": 0.40594059405940597,
|
264 |
+
"support": 101.0
|
265 |
+
},
|
266 |
+
"uy": {
|
267 |
+
"f1-score": 0.2354948805460751,
|
268 |
+
"precision": 0.19327731092436976,
|
269 |
+
"recall": 0.30131004366812225,
|
270 |
+
"support": 229.0
|
271 |
+
},
|
272 |
+
"ve": {
|
273 |
+
"f1-score": 0.0,
|
274 |
+
"precision": 0.0,
|
275 |
+
"recall": 0.0,
|
276 |
+
"support": 22.0
|
277 |
+
},
|
278 |
+
"weighted avg": {
|
279 |
+
"f1-score": 0.22084365412222065,
|
280 |
+
"precision": 0.24892308331106963,
|
281 |
+
"recall": 0.2375,
|
282 |
+
"support": 2000.0
|
283 |
+
}
|
284 |
+
},
|
285 |
+
"eval_f1": 0.2140692864641761,
|
286 |
+
"eval_loss": 1.964627742767334,
|
287 |
+
"eval_runtime": 3.948,
|
288 |
+
"eval_samples_per_second": 506.591,
|
289 |
+
"eval_steps_per_second": 31.662,
|
290 |
+
"step": 292
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.0273972602739727,
|
294 |
+
"grad_norm": 7.403143882751465,
|
295 |
+
"learning_rate": 9.349107895185306e-06,
|
296 |
+
"loss": 1.9144,
|
297 |
+
"step": 300
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.0616438356164384,
|
301 |
+
"grad_norm": 7.673084735870361,
|
302 |
+
"learning_rate": 9.186796994227228e-06,
|
303 |
+
"loss": 1.8783,
|
304 |
+
"step": 310
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.095890410958904,
|
308 |
+
"grad_norm": 7.875649452209473,
|
309 |
+
"learning_rate": 9.024486093269149e-06,
|
310 |
+
"loss": 1.9275,
|
311 |
+
"step": 320
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.13013698630137,
|
315 |
+
"grad_norm": 8.519344329833984,
|
316 |
+
"learning_rate": 8.86217519231107e-06,
|
317 |
+
"loss": 1.9603,
|
318 |
+
"step": 330
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.1643835616438356,
|
322 |
+
"grad_norm": 11.323283195495605,
|
323 |
+
"learning_rate": 8.699864291352992e-06,
|
324 |
+
"loss": 1.923,
|
325 |
+
"step": 340
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.1986301369863013,
|
329 |
+
"grad_norm": 8.269103050231934,
|
330 |
+
"learning_rate": 8.537553390394915e-06,
|
331 |
+
"loss": 1.9427,
|
332 |
+
"step": 350
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.2328767123287672,
|
336 |
+
"grad_norm": 9.630481719970703,
|
337 |
+
"learning_rate": 8.375242489436837e-06,
|
338 |
+
"loss": 1.8944,
|
339 |
+
"step": 360
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.2671232876712328,
|
343 |
+
"grad_norm": 10.00069808959961,
|
344 |
+
"learning_rate": 8.212931588478758e-06,
|
345 |
+
"loss": 1.8854,
|
346 |
+
"step": 370
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.3013698630136985,
|
350 |
+
"grad_norm": 10.448683738708496,
|
351 |
+
"learning_rate": 8.05062068752068e-06,
|
352 |
+
"loss": 1.9484,
|
353 |
+
"step": 380
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.3356164383561644,
|
357 |
+
"grad_norm": 9.772107124328613,
|
358 |
+
"learning_rate": 7.888309786562601e-06,
|
359 |
+
"loss": 1.8663,
|
360 |
+
"step": 390
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.36986301369863,
|
364 |
+
"grad_norm": 10.358853340148926,
|
365 |
+
"learning_rate": 7.725998885604523e-06,
|
366 |
+
"loss": 1.9082,
|
367 |
+
"step": 400
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.404109589041096,
|
371 |
+
"grad_norm": 11.836031913757324,
|
372 |
+
"learning_rate": 7.563687984646444e-06,
|
373 |
+
"loss": 1.881,
|
374 |
+
"step": 410
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.4383561643835616,
|
378 |
+
"grad_norm": 11.461163520812988,
|
379 |
+
"learning_rate": 7.401377083688367e-06,
|
380 |
+
"loss": 1.964,
|
381 |
+
"step": 420
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.4726027397260273,
|
385 |
+
"grad_norm": 9.836813926696777,
|
386 |
+
"learning_rate": 7.239066182730289e-06,
|
387 |
+
"loss": 1.8552,
|
388 |
+
"step": 430
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.5068493150684932,
|
392 |
+
"grad_norm": 12.651612281799316,
|
393 |
+
"learning_rate": 7.076755281772211e-06,
|
394 |
+
"loss": 1.8211,
|
395 |
+
"step": 440
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.541095890410959,
|
399 |
+
"grad_norm": 10.353775024414062,
|
400 |
+
"learning_rate": 6.9144443808141315e-06,
|
401 |
+
"loss": 1.905,
|
402 |
+
"step": 450
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.5753424657534247,
|
406 |
+
"grad_norm": 9.688141822814941,
|
407 |
+
"learning_rate": 6.752133479856054e-06,
|
408 |
+
"loss": 1.8525,
|
409 |
+
"step": 460
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.6095890410958904,
|
413 |
+
"grad_norm": 10.979829788208008,
|
414 |
+
"learning_rate": 6.5898225788979756e-06,
|
415 |
+
"loss": 1.8468,
|
416 |
+
"step": 470
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.643835616438356,
|
420 |
+
"grad_norm": 11.913898468017578,
|
421 |
+
"learning_rate": 6.427511677939898e-06,
|
422 |
+
"loss": 1.8301,
|
423 |
+
"step": 480
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.678082191780822,
|
427 |
+
"grad_norm": 9.506439208984375,
|
428 |
+
"learning_rate": 6.265200776981819e-06,
|
429 |
+
"loss": 1.9175,
|
430 |
+
"step": 490
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.7123287671232876,
|
434 |
+
"grad_norm": 11.259939193725586,
|
435 |
+
"learning_rate": 6.102889876023741e-06,
|
436 |
+
"loss": 1.8674,
|
437 |
+
"step": 500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.7465753424657535,
|
441 |
+
"grad_norm": 10.506684303283691,
|
442 |
+
"learning_rate": 5.940578975065663e-06,
|
443 |
+
"loss": 1.8201,
|
444 |
+
"step": 510
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.7808219178082192,
|
448 |
+
"grad_norm": 10.255843162536621,
|
449 |
+
"learning_rate": 5.7782680741075844e-06,
|
450 |
+
"loss": 1.83,
|
451 |
+
"step": 520
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.8150684931506849,
|
455 |
+
"grad_norm": 10.053559303283691,
|
456 |
+
"learning_rate": 5.615957173149507e-06,
|
457 |
+
"loss": 1.8929,
|
458 |
+
"step": 530
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.8493150684931505,
|
462 |
+
"grad_norm": 11.122831344604492,
|
463 |
+
"learning_rate": 5.4536462721914285e-06,
|
464 |
+
"loss": 1.8836,
|
465 |
+
"step": 540
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.8835616438356164,
|
469 |
+
"grad_norm": 10.520340919494629,
|
470 |
+
"learning_rate": 5.29133537123335e-06,
|
471 |
+
"loss": 1.8587,
|
472 |
+
"step": 550
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.9178082191780823,
|
476 |
+
"grad_norm": 10.444989204406738,
|
477 |
+
"learning_rate": 5.129024470275272e-06,
|
478 |
+
"loss": 1.9133,
|
479 |
+
"step": 560
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.952054794520548,
|
483 |
+
"grad_norm": 9.19580078125,
|
484 |
+
"learning_rate": 4.966713569317194e-06,
|
485 |
+
"loss": 1.7403,
|
486 |
+
"step": 570
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.9863013698630136,
|
490 |
+
"grad_norm": 9.467530250549316,
|
491 |
+
"learning_rate": 4.804402668359115e-06,
|
492 |
+
"loss": 1.854,
|
493 |
+
"step": 580
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.0,
|
497 |
+
"eval_classification_report": {
|
498 |
+
"accuracy": 0.3015,
|
499 |
+
"ar": {
|
500 |
+
"f1-score": 0.20817843866171004,
|
501 |
+
"precision": 0.4444444444444444,
|
502 |
+
"recall": 0.13592233009708737,
|
503 |
+
"support": 206.0
|
504 |
+
},
|
505 |
+
"cl": {
|
506 |
+
"f1-score": 0.24404761904761904,
|
507 |
+
"precision": 0.21465968586387435,
|
508 |
+
"recall": 0.2827586206896552,
|
509 |
+
"support": 290.0
|
510 |
+
},
|
511 |
+
"co": {
|
512 |
+
"f1-score": 0.3091190108191654,
|
513 |
+
"precision": 0.2808988764044944,
|
514 |
+
"recall": 0.3436426116838488,
|
515 |
+
"support": 291.0
|
516 |
+
},
|
517 |
+
"es": {
|
518 |
+
"f1-score": 0.36363636363636365,
|
519 |
+
"precision": 0.31891891891891894,
|
520 |
+
"recall": 0.4229390681003584,
|
521 |
+
"support": 279.0
|
522 |
+
},
|
523 |
+
"macro avg": {
|
524 |
+
"f1-score": 0.28404923689784706,
|
525 |
+
"precision": 0.313232548351025,
|
526 |
+
"recall": 0.28845705885930073,
|
527 |
+
"support": 2000.0
|
528 |
+
},
|
529 |
+
"mx": {
|
530 |
+
"f1-score": 0.3058350100603622,
|
531 |
+
"precision": 0.36893203883495146,
|
532 |
+
"recall": 0.2611683848797251,
|
533 |
+
"support": 291.0
|
534 |
+
},
|
535 |
+
"pe": {
|
536 |
+
"f1-score": 0.23582089552238805,
|
537 |
+
"precision": 0.20844327176781002,
|
538 |
+
"recall": 0.27147766323024053,
|
539 |
+
"support": 291.0
|
540 |
+
},
|
541 |
+
"pr": {
|
542 |
+
"f1-score": 0.5688888888888889,
|
543 |
+
"precision": 0.5161290322580645,
|
544 |
+
"recall": 0.6336633663366337,
|
545 |
+
"support": 101.0
|
546 |
+
},
|
547 |
+
"uy": {
|
548 |
+
"f1-score": 0.3209169054441261,
|
549 |
+
"precision": 0.4666666666666667,
|
550 |
+
"recall": 0.2445414847161572,
|
551 |
+
"support": 229.0
|
552 |
+
},
|
553 |
+
"ve": {
|
554 |
+
"f1-score": 0.0,
|
555 |
+
"precision": 0.0,
|
556 |
+
"recall": 0.0,
|
557 |
+
"support": 22.0
|
558 |
+
},
|
559 |
+
"weighted avg": {
|
560 |
+
"f1-score": 0.29681818157005363,
|
561 |
+
"precision": 0.3257693650891501,
|
562 |
+
"recall": 0.3015,
|
563 |
+
"support": 2000.0
|
564 |
+
}
|
565 |
+
},
|
566 |
+
"eval_f1": 0.28404923689784706,
|
567 |
+
"eval_loss": 1.8588982820510864,
|
568 |
+
"eval_runtime": 3.9624,
|
569 |
+
"eval_samples_per_second": 504.741,
|
570 |
+
"eval_steps_per_second": 31.546,
|
571 |
+
"step": 584
|
572 |
+
}
|
573 |
+
],
|
574 |
+
"logging_steps": 10,
|
575 |
+
"max_steps": 876,
|
576 |
+
"num_input_tokens_seen": 0,
|
577 |
+
"num_train_epochs": 3,
|
578 |
+
"save_steps": 500,
|
579 |
+
"stateful_callbacks": {
|
580 |
+
"TrainerControl": {
|
581 |
+
"args": {
|
582 |
+
"should_epoch_stop": false,
|
583 |
+
"should_evaluate": false,
|
584 |
+
"should_log": false,
|
585 |
+
"should_save": true,
|
586 |
+
"should_training_stop": false
|
587 |
+
},
|
588 |
+
"attributes": {}
|
589 |
+
}
|
590 |
+
},
|
591 |
+
"total_flos": 613876671986688.0,
|
592 |
+
"train_batch_size": 16,
|
593 |
+
"trial_name": null,
|
594 |
+
"trial_params": null
|
595 |
+
}
|
trial_0/checkpoint-584/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf983bab71d39717083fd85c30b7e0fd950e8d457e647f61a7ff596cb390b138
|
3 |
+
size 5368
|
trial_0/checkpoint-584/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trial_0/checkpoint-876/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ar",
|
14 |
+
"1": "cl",
|
15 |
+
"2": "co",
|
16 |
+
"3": "es",
|
17 |
+
"4": "mx",
|
18 |
+
"5": "pe",
|
19 |
+
"6": "pr",
|
20 |
+
"7": "uy",
|
21 |
+
"8": "ve"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"ar": 0,
|
27 |
+
"cl": 1,
|
28 |
+
"co": 2,
|
29 |
+
"es": 3,
|
30 |
+
"mx": 4,
|
31 |
+
"pe": 5,
|
32 |
+
"pr": 6,
|
33 |
+
"uy": 7,
|
34 |
+
"ve": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.48.3",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 31002
|
50 |
+
}
|
trial_0/checkpoint-876/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf854bf20a145ed4aea50832d905cbc3b7c185076aa225249307cba72e17e404
|
3 |
+
size 439454740
|
trial_0/checkpoint-876/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a57e2c02488f59dc935a6f5d7b68b0210f98125fd0c15d37ff039eb0f9a9cb9e
|
3 |
+
size 879030522
|
trial_0/checkpoint-876/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5ec19cccb67f774cb5d9d70fcb09d0964e6b44cd2249c3f0f947bc6c27a2d1c
|
3 |
+
size 14244
|
trial_0/checkpoint-876/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5f3e075f9e406a57a0eebb4f878639933cb4c2996bf03eaa3ac48b55e42597a6
|
3 |
+
size 1064
|
trial_0/checkpoint-876/special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
trial_0/checkpoint-876/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trial_0/checkpoint-876/tokenizer_config.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[MASK]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "[PAD]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"3": {
|
20 |
+
"content": "[UNK]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"4": {
|
28 |
+
"content": "[CLS]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"5": {
|
36 |
+
"content": "[SEP]",
|
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_basic_tokenize": true,
|
47 |
+
"do_lower_case": true,
|
48 |
+
"extra_special_tokens": {},
|
49 |
+
"mask_token": "[MASK]",
|
50 |
+
"model_max_length": 512,
|
51 |
+
"never_split": null,
|
52 |
+
"pad_token": "[PAD]",
|
53 |
+
"sep_token": "[SEP]",
|
54 |
+
"strip_accents": false,
|
55 |
+
"tokenize_chinese_chars": true,
|
56 |
+
"tokenizer_class": "BertTokenizer",
|
57 |
+
"unk_token": "[UNK]"
|
58 |
+
}
|
trial_0/checkpoint-876/trainer_state.json
ADDED
@@ -0,0 +1,876 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.30473656895821705,
|
3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/model_outputs/trial_0/checkpoint-876",
|
4 |
+
"epoch": 3.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 876,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03424657534246575,
|
13 |
+
"grad_norm": 8.432939529418945,
|
14 |
+
"learning_rate": 8.18270817933484e-07,
|
15 |
+
"loss": 2.2234,
|
16 |
+
"step": 10
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.0684931506849315,
|
20 |
+
"grad_norm": 8.3140230178833,
|
21 |
+
"learning_rate": 1.636541635866968e-06,
|
22 |
+
"loss": 2.2403,
|
23 |
+
"step": 20
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.10273972602739725,
|
27 |
+
"grad_norm": 7.506945610046387,
|
28 |
+
"learning_rate": 2.454812453800452e-06,
|
29 |
+
"loss": 2.2297,
|
30 |
+
"step": 30
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.136986301369863,
|
34 |
+
"grad_norm": 8.531285285949707,
|
35 |
+
"learning_rate": 3.273083271733936e-06,
|
36 |
+
"loss": 2.1823,
|
37 |
+
"step": 40
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.17123287671232876,
|
41 |
+
"grad_norm": 7.951968669891357,
|
42 |
+
"learning_rate": 4.091354089667421e-06,
|
43 |
+
"loss": 2.1696,
|
44 |
+
"step": 50
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.2054794520547945,
|
48 |
+
"grad_norm": 8.328391075134277,
|
49 |
+
"learning_rate": 4.909624907600904e-06,
|
50 |
+
"loss": 2.1415,
|
51 |
+
"step": 60
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.23972602739726026,
|
55 |
+
"grad_norm": 7.337668418884277,
|
56 |
+
"learning_rate": 5.727895725534388e-06,
|
57 |
+
"loss": 2.1206,
|
58 |
+
"step": 70
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.273972602739726,
|
62 |
+
"grad_norm": 7.09800386428833,
|
63 |
+
"learning_rate": 6.546166543467872e-06,
|
64 |
+
"loss": 2.0949,
|
65 |
+
"step": 80
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.3082191780821918,
|
69 |
+
"grad_norm": 6.549777507781982,
|
70 |
+
"learning_rate": 7.364437361401356e-06,
|
71 |
+
"loss": 2.076,
|
72 |
+
"step": 90
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.3424657534246575,
|
76 |
+
"grad_norm": 7.464539051055908,
|
77 |
+
"learning_rate": 8.182708179334841e-06,
|
78 |
+
"loss": 2.096,
|
79 |
+
"step": 100
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.3767123287671233,
|
83 |
+
"grad_norm": 6.982883930206299,
|
84 |
+
"learning_rate": 9.000978997268324e-06,
|
85 |
+
"loss": 2.0615,
|
86 |
+
"step": 110
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.410958904109589,
|
90 |
+
"grad_norm": 7.149113655090332,
|
91 |
+
"learning_rate": 9.819249815201808e-06,
|
92 |
+
"loss": 2.0785,
|
93 |
+
"step": 120
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.4452054794520548,
|
97 |
+
"grad_norm": 6.507534503936768,
|
98 |
+
"learning_rate": 1.0637520633135292e-05,
|
99 |
+
"loss": 2.0865,
|
100 |
+
"step": 130
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.4794520547945205,
|
104 |
+
"grad_norm": 6.1932196617126465,
|
105 |
+
"learning_rate": 1.1455791451068777e-05,
|
106 |
+
"loss": 2.0533,
|
107 |
+
"step": 140
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.5136986301369864,
|
111 |
+
"grad_norm": 7.072916507720947,
|
112 |
+
"learning_rate": 1.1783771409556479e-05,
|
113 |
+
"loss": 2.0613,
|
114 |
+
"step": 150
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.547945205479452,
|
118 |
+
"grad_norm": 8.155049324035645,
|
119 |
+
"learning_rate": 1.1621460508598402e-05,
|
120 |
+
"loss": 2.0284,
|
121 |
+
"step": 160
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.5821917808219178,
|
125 |
+
"grad_norm": 9.3668851852417,
|
126 |
+
"learning_rate": 1.1459149607640322e-05,
|
127 |
+
"loss": 2.0137,
|
128 |
+
"step": 170
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.6164383561643836,
|
132 |
+
"grad_norm": 8.165146827697754,
|
133 |
+
"learning_rate": 1.1296838706682245e-05,
|
134 |
+
"loss": 1.9835,
|
135 |
+
"step": 180
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.6506849315068494,
|
139 |
+
"grad_norm": 9.0431547164917,
|
140 |
+
"learning_rate": 1.1134527805724166e-05,
|
141 |
+
"loss": 1.9934,
|
142 |
+
"step": 190
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.684931506849315,
|
146 |
+
"grad_norm": 8.92784309387207,
|
147 |
+
"learning_rate": 1.0972216904766088e-05,
|
148 |
+
"loss": 2.0081,
|
149 |
+
"step": 200
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.7191780821917808,
|
153 |
+
"grad_norm": 9.184441566467285,
|
154 |
+
"learning_rate": 1.0809906003808009e-05,
|
155 |
+
"loss": 1.9567,
|
156 |
+
"step": 210
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.7534246575342466,
|
160 |
+
"grad_norm": 10.262762069702148,
|
161 |
+
"learning_rate": 1.0647595102849931e-05,
|
162 |
+
"loss": 1.966,
|
163 |
+
"step": 220
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 0.7876712328767124,
|
167 |
+
"grad_norm": 7.367489337921143,
|
168 |
+
"learning_rate": 1.0485284201891854e-05,
|
169 |
+
"loss": 2.051,
|
170 |
+
"step": 230
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.821917808219178,
|
174 |
+
"grad_norm": 8.76405143737793,
|
175 |
+
"learning_rate": 1.0322973300933776e-05,
|
176 |
+
"loss": 2.0785,
|
177 |
+
"step": 240
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.8561643835616438,
|
181 |
+
"grad_norm": 7.100874900817871,
|
182 |
+
"learning_rate": 1.0160662399975697e-05,
|
183 |
+
"loss": 1.9977,
|
184 |
+
"step": 250
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 0.8904109589041096,
|
188 |
+
"grad_norm": 8.239387512207031,
|
189 |
+
"learning_rate": 9.998351499017618e-06,
|
190 |
+
"loss": 2.0099,
|
191 |
+
"step": 260
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.9246575342465754,
|
195 |
+
"grad_norm": 7.704412460327148,
|
196 |
+
"learning_rate": 9.83604059805954e-06,
|
197 |
+
"loss": 1.9851,
|
198 |
+
"step": 270
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 0.958904109589041,
|
202 |
+
"grad_norm": 7.8163652420043945,
|
203 |
+
"learning_rate": 9.673729697101463e-06,
|
204 |
+
"loss": 2.0085,
|
205 |
+
"step": 280
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 0.9931506849315068,
|
209 |
+
"grad_norm": 8.153071403503418,
|
210 |
+
"learning_rate": 9.511418796143383e-06,
|
211 |
+
"loss": 1.9962,
|
212 |
+
"step": 290
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 1.0,
|
216 |
+
"eval_classification_report": {
|
217 |
+
"accuracy": 0.2375,
|
218 |
+
"ar": {
|
219 |
+
"f1-score": 0.0622568093385214,
|
220 |
+
"precision": 0.1568627450980392,
|
221 |
+
"recall": 0.038834951456310676,
|
222 |
+
"support": 206.0
|
223 |
+
},
|
224 |
+
"cl": {
|
225 |
+
"f1-score": 0.2011173184357542,
|
226 |
+
"precision": 0.16901408450704225,
|
227 |
+
"recall": 0.2482758620689655,
|
228 |
+
"support": 290.0
|
229 |
+
},
|
230 |
+
"co": {
|
231 |
+
"f1-score": 0.31543624161073824,
|
232 |
+
"precision": 0.23383084577114427,
|
233 |
+
"recall": 0.4845360824742268,
|
234 |
+
"support": 291.0
|
235 |
+
},
|
236 |
+
"es": {
|
237 |
+
"f1-score": 0.27364185110663986,
|
238 |
+
"precision": 0.3119266055045872,
|
239 |
+
"recall": 0.24372759856630824,
|
240 |
+
"support": 279.0
|
241 |
+
},
|
242 |
+
"macro avg": {
|
243 |
+
"f1-score": 0.2140692864641761,
|
244 |
+
"precision": 0.24922489036795273,
|
245 |
+
"recall": 0.22042150190811827,
|
246 |
+
"support": 2000.0
|
247 |
+
},
|
248 |
+
"mx": {
|
249 |
+
"f1-score": 0.22950819672131148,
|
250 |
+
"precision": 0.28426395939086296,
|
251 |
+
"recall": 0.19243986254295534,
|
252 |
+
"support": 291.0
|
253 |
+
},
|
254 |
+
"pe": {
|
255 |
+
"f1-score": 0.10610079575596817,
|
256 |
+
"precision": 0.23255813953488372,
|
257 |
+
"recall": 0.06872852233676977,
|
258 |
+
"support": 291.0
|
259 |
+
},
|
260 |
+
"pr": {
|
261 |
+
"f1-score": 0.5030674846625767,
|
262 |
+
"precision": 0.6612903225806451,
|
263 |
+
"recall": 0.40594059405940597,
|
264 |
+
"support": 101.0
|
265 |
+
},
|
266 |
+
"uy": {
|
267 |
+
"f1-score": 0.2354948805460751,
|
268 |
+
"precision": 0.19327731092436976,
|
269 |
+
"recall": 0.30131004366812225,
|
270 |
+
"support": 229.0
|
271 |
+
},
|
272 |
+
"ve": {
|
273 |
+
"f1-score": 0.0,
|
274 |
+
"precision": 0.0,
|
275 |
+
"recall": 0.0,
|
276 |
+
"support": 22.0
|
277 |
+
},
|
278 |
+
"weighted avg": {
|
279 |
+
"f1-score": 0.22084365412222065,
|
280 |
+
"precision": 0.24892308331106963,
|
281 |
+
"recall": 0.2375,
|
282 |
+
"support": 2000.0
|
283 |
+
}
|
284 |
+
},
|
285 |
+
"eval_f1": 0.2140692864641761,
|
286 |
+
"eval_loss": 1.964627742767334,
|
287 |
+
"eval_runtime": 3.948,
|
288 |
+
"eval_samples_per_second": 506.591,
|
289 |
+
"eval_steps_per_second": 31.662,
|
290 |
+
"step": 292
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.0273972602739727,
|
294 |
+
"grad_norm": 7.403143882751465,
|
295 |
+
"learning_rate": 9.349107895185306e-06,
|
296 |
+
"loss": 1.9144,
|
297 |
+
"step": 300
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.0616438356164384,
|
301 |
+
"grad_norm": 7.673084735870361,
|
302 |
+
"learning_rate": 9.186796994227228e-06,
|
303 |
+
"loss": 1.8783,
|
304 |
+
"step": 310
|
305 |
+
},
|
306 |
+
{
|
307 |
+
"epoch": 1.095890410958904,
|
308 |
+
"grad_norm": 7.875649452209473,
|
309 |
+
"learning_rate": 9.024486093269149e-06,
|
310 |
+
"loss": 1.9275,
|
311 |
+
"step": 320
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.13013698630137,
|
315 |
+
"grad_norm": 8.519344329833984,
|
316 |
+
"learning_rate": 8.86217519231107e-06,
|
317 |
+
"loss": 1.9603,
|
318 |
+
"step": 330
|
319 |
+
},
|
320 |
+
{
|
321 |
+
"epoch": 1.1643835616438356,
|
322 |
+
"grad_norm": 11.323283195495605,
|
323 |
+
"learning_rate": 8.699864291352992e-06,
|
324 |
+
"loss": 1.923,
|
325 |
+
"step": 340
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 1.1986301369863013,
|
329 |
+
"grad_norm": 8.269103050231934,
|
330 |
+
"learning_rate": 8.537553390394915e-06,
|
331 |
+
"loss": 1.9427,
|
332 |
+
"step": 350
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.2328767123287672,
|
336 |
+
"grad_norm": 9.630481719970703,
|
337 |
+
"learning_rate": 8.375242489436837e-06,
|
338 |
+
"loss": 1.8944,
|
339 |
+
"step": 360
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.2671232876712328,
|
343 |
+
"grad_norm": 10.00069808959961,
|
344 |
+
"learning_rate": 8.212931588478758e-06,
|
345 |
+
"loss": 1.8854,
|
346 |
+
"step": 370
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 1.3013698630136985,
|
350 |
+
"grad_norm": 10.448683738708496,
|
351 |
+
"learning_rate": 8.05062068752068e-06,
|
352 |
+
"loss": 1.9484,
|
353 |
+
"step": 380
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.3356164383561644,
|
357 |
+
"grad_norm": 9.772107124328613,
|
358 |
+
"learning_rate": 7.888309786562601e-06,
|
359 |
+
"loss": 1.8663,
|
360 |
+
"step": 390
|
361 |
+
},
|
362 |
+
{
|
363 |
+
"epoch": 1.36986301369863,
|
364 |
+
"grad_norm": 10.358853340148926,
|
365 |
+
"learning_rate": 7.725998885604523e-06,
|
366 |
+
"loss": 1.9082,
|
367 |
+
"step": 400
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 1.404109589041096,
|
371 |
+
"grad_norm": 11.836031913757324,
|
372 |
+
"learning_rate": 7.563687984646444e-06,
|
373 |
+
"loss": 1.881,
|
374 |
+
"step": 410
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.4383561643835616,
|
378 |
+
"grad_norm": 11.461163520812988,
|
379 |
+
"learning_rate": 7.401377083688367e-06,
|
380 |
+
"loss": 1.964,
|
381 |
+
"step": 420
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.4726027397260273,
|
385 |
+
"grad_norm": 9.836813926696777,
|
386 |
+
"learning_rate": 7.239066182730289e-06,
|
387 |
+
"loss": 1.8552,
|
388 |
+
"step": 430
|
389 |
+
},
|
390 |
+
{
|
391 |
+
"epoch": 1.5068493150684932,
|
392 |
+
"grad_norm": 12.651612281799316,
|
393 |
+
"learning_rate": 7.076755281772211e-06,
|
394 |
+
"loss": 1.8211,
|
395 |
+
"step": 440
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.541095890410959,
|
399 |
+
"grad_norm": 10.353775024414062,
|
400 |
+
"learning_rate": 6.9144443808141315e-06,
|
401 |
+
"loss": 1.905,
|
402 |
+
"step": 450
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 1.5753424657534247,
|
406 |
+
"grad_norm": 9.688141822814941,
|
407 |
+
"learning_rate": 6.752133479856054e-06,
|
408 |
+
"loss": 1.8525,
|
409 |
+
"step": 460
|
410 |
+
},
|
411 |
+
{
|
412 |
+
"epoch": 1.6095890410958904,
|
413 |
+
"grad_norm": 10.979829788208008,
|
414 |
+
"learning_rate": 6.5898225788979756e-06,
|
415 |
+
"loss": 1.8468,
|
416 |
+
"step": 470
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.643835616438356,
|
420 |
+
"grad_norm": 11.913898468017578,
|
421 |
+
"learning_rate": 6.427511677939898e-06,
|
422 |
+
"loss": 1.8301,
|
423 |
+
"step": 480
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.678082191780822,
|
427 |
+
"grad_norm": 9.506439208984375,
|
428 |
+
"learning_rate": 6.265200776981819e-06,
|
429 |
+
"loss": 1.9175,
|
430 |
+
"step": 490
|
431 |
+
},
|
432 |
+
{
|
433 |
+
"epoch": 1.7123287671232876,
|
434 |
+
"grad_norm": 11.259939193725586,
|
435 |
+
"learning_rate": 6.102889876023741e-06,
|
436 |
+
"loss": 1.8674,
|
437 |
+
"step": 500
|
438 |
+
},
|
439 |
+
{
|
440 |
+
"epoch": 1.7465753424657535,
|
441 |
+
"grad_norm": 10.506684303283691,
|
442 |
+
"learning_rate": 5.940578975065663e-06,
|
443 |
+
"loss": 1.8201,
|
444 |
+
"step": 510
|
445 |
+
},
|
446 |
+
{
|
447 |
+
"epoch": 1.7808219178082192,
|
448 |
+
"grad_norm": 10.255843162536621,
|
449 |
+
"learning_rate": 5.7782680741075844e-06,
|
450 |
+
"loss": 1.83,
|
451 |
+
"step": 520
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 1.8150684931506849,
|
455 |
+
"grad_norm": 10.053559303283691,
|
456 |
+
"learning_rate": 5.615957173149507e-06,
|
457 |
+
"loss": 1.8929,
|
458 |
+
"step": 530
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.8493150684931505,
|
462 |
+
"grad_norm": 11.122831344604492,
|
463 |
+
"learning_rate": 5.4536462721914285e-06,
|
464 |
+
"loss": 1.8836,
|
465 |
+
"step": 540
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.8835616438356164,
|
469 |
+
"grad_norm": 10.520340919494629,
|
470 |
+
"learning_rate": 5.29133537123335e-06,
|
471 |
+
"loss": 1.8587,
|
472 |
+
"step": 550
|
473 |
+
},
|
474 |
+
{
|
475 |
+
"epoch": 1.9178082191780823,
|
476 |
+
"grad_norm": 10.444989204406738,
|
477 |
+
"learning_rate": 5.129024470275272e-06,
|
478 |
+
"loss": 1.9133,
|
479 |
+
"step": 560
|
480 |
+
},
|
481 |
+
{
|
482 |
+
"epoch": 1.952054794520548,
|
483 |
+
"grad_norm": 9.19580078125,
|
484 |
+
"learning_rate": 4.966713569317194e-06,
|
485 |
+
"loss": 1.7403,
|
486 |
+
"step": 570
|
487 |
+
},
|
488 |
+
{
|
489 |
+
"epoch": 1.9863013698630136,
|
490 |
+
"grad_norm": 9.467530250549316,
|
491 |
+
"learning_rate": 4.804402668359115e-06,
|
492 |
+
"loss": 1.854,
|
493 |
+
"step": 580
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.0,
|
497 |
+
"eval_classification_report": {
|
498 |
+
"accuracy": 0.3015,
|
499 |
+
"ar": {
|
500 |
+
"f1-score": 0.20817843866171004,
|
501 |
+
"precision": 0.4444444444444444,
|
502 |
+
"recall": 0.13592233009708737,
|
503 |
+
"support": 206.0
|
504 |
+
},
|
505 |
+
"cl": {
|
506 |
+
"f1-score": 0.24404761904761904,
|
507 |
+
"precision": 0.21465968586387435,
|
508 |
+
"recall": 0.2827586206896552,
|
509 |
+
"support": 290.0
|
510 |
+
},
|
511 |
+
"co": {
|
512 |
+
"f1-score": 0.3091190108191654,
|
513 |
+
"precision": 0.2808988764044944,
|
514 |
+
"recall": 0.3436426116838488,
|
515 |
+
"support": 291.0
|
516 |
+
},
|
517 |
+
"es": {
|
518 |
+
"f1-score": 0.36363636363636365,
|
519 |
+
"precision": 0.31891891891891894,
|
520 |
+
"recall": 0.4229390681003584,
|
521 |
+
"support": 279.0
|
522 |
+
},
|
523 |
+
"macro avg": {
|
524 |
+
"f1-score": 0.28404923689784706,
|
525 |
+
"precision": 0.313232548351025,
|
526 |
+
"recall": 0.28845705885930073,
|
527 |
+
"support": 2000.0
|
528 |
+
},
|
529 |
+
"mx": {
|
530 |
+
"f1-score": 0.3058350100603622,
|
531 |
+
"precision": 0.36893203883495146,
|
532 |
+
"recall": 0.2611683848797251,
|
533 |
+
"support": 291.0
|
534 |
+
},
|
535 |
+
"pe": {
|
536 |
+
"f1-score": 0.23582089552238805,
|
537 |
+
"precision": 0.20844327176781002,
|
538 |
+
"recall": 0.27147766323024053,
|
539 |
+
"support": 291.0
|
540 |
+
},
|
541 |
+
"pr": {
|
542 |
+
"f1-score": 0.5688888888888889,
|
543 |
+
"precision": 0.5161290322580645,
|
544 |
+
"recall": 0.6336633663366337,
|
545 |
+
"support": 101.0
|
546 |
+
},
|
547 |
+
"uy": {
|
548 |
+
"f1-score": 0.3209169054441261,
|
549 |
+
"precision": 0.4666666666666667,
|
550 |
+
"recall": 0.2445414847161572,
|
551 |
+
"support": 229.0
|
552 |
+
},
|
553 |
+
"ve": {
|
554 |
+
"f1-score": 0.0,
|
555 |
+
"precision": 0.0,
|
556 |
+
"recall": 0.0,
|
557 |
+
"support": 22.0
|
558 |
+
},
|
559 |
+
"weighted avg": {
|
560 |
+
"f1-score": 0.29681818157005363,
|
561 |
+
"precision": 0.3257693650891501,
|
562 |
+
"recall": 0.3015,
|
563 |
+
"support": 2000.0
|
564 |
+
}
|
565 |
+
},
|
566 |
+
"eval_f1": 0.28404923689784706,
|
567 |
+
"eval_loss": 1.8588982820510864,
|
568 |
+
"eval_runtime": 3.9624,
|
569 |
+
"eval_samples_per_second": 504.741,
|
570 |
+
"eval_steps_per_second": 31.546,
|
571 |
+
"step": 584
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.0205479452054793,
|
575 |
+
"grad_norm": 10.664342880249023,
|
576 |
+
"learning_rate": 4.642091767401037e-06,
|
577 |
+
"loss": 1.7675,
|
578 |
+
"step": 590
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 2.0547945205479454,
|
582 |
+
"grad_norm": 10.18624210357666,
|
583 |
+
"learning_rate": 4.479780866442959e-06,
|
584 |
+
"loss": 1.7303,
|
585 |
+
"step": 600
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 2.089041095890411,
|
589 |
+
"grad_norm": 9.922106742858887,
|
590 |
+
"learning_rate": 4.3174699654848806e-06,
|
591 |
+
"loss": 1.6809,
|
592 |
+
"step": 610
|
593 |
+
},
|
594 |
+
{
|
595 |
+
"epoch": 2.1232876712328768,
|
596 |
+
"grad_norm": 10.778169631958008,
|
597 |
+
"learning_rate": 4.155159064526802e-06,
|
598 |
+
"loss": 1.6858,
|
599 |
+
"step": 620
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 2.1575342465753424,
|
603 |
+
"grad_norm": 11.85101318359375,
|
604 |
+
"learning_rate": 3.992848163568725e-06,
|
605 |
+
"loss": 1.7164,
|
606 |
+
"step": 630
|
607 |
+
},
|
608 |
+
{
|
609 |
+
"epoch": 2.191780821917808,
|
610 |
+
"grad_norm": 10.55038833618164,
|
611 |
+
"learning_rate": 3.830537262610646e-06,
|
612 |
+
"loss": 1.7627,
|
613 |
+
"step": 640
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 2.2260273972602738,
|
617 |
+
"grad_norm": 12.37063217163086,
|
618 |
+
"learning_rate": 3.6682263616525683e-06,
|
619 |
+
"loss": 1.7254,
|
620 |
+
"step": 650
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 2.26027397260274,
|
624 |
+
"grad_norm": 12.823184967041016,
|
625 |
+
"learning_rate": 3.5059154606944894e-06,
|
626 |
+
"loss": 1.6745,
|
627 |
+
"step": 660
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 2.2945205479452055,
|
631 |
+
"grad_norm": 10.982261657714844,
|
632 |
+
"learning_rate": 3.3436045597364115e-06,
|
633 |
+
"loss": 1.6329,
|
634 |
+
"step": 670
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 2.328767123287671,
|
638 |
+
"grad_norm": 11.901023864746094,
|
639 |
+
"learning_rate": 3.181293658778333e-06,
|
640 |
+
"loss": 1.7054,
|
641 |
+
"step": 680
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 2.363013698630137,
|
645 |
+
"grad_norm": 12.643646240234375,
|
646 |
+
"learning_rate": 3.018982757820255e-06,
|
647 |
+
"loss": 1.6988,
|
648 |
+
"step": 690
|
649 |
+
},
|
650 |
+
{
|
651 |
+
"epoch": 2.3972602739726026,
|
652 |
+
"grad_norm": 11.213497161865234,
|
653 |
+
"learning_rate": 2.8566718568621767e-06,
|
654 |
+
"loss": 1.6856,
|
655 |
+
"step": 700
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 2.4315068493150687,
|
659 |
+
"grad_norm": 13.69401741027832,
|
660 |
+
"learning_rate": 2.6943609559040983e-06,
|
661 |
+
"loss": 1.7865,
|
662 |
+
"step": 710
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 2.4657534246575343,
|
666 |
+
"grad_norm": 11.204819679260254,
|
667 |
+
"learning_rate": 2.5320500549460203e-06,
|
668 |
+
"loss": 1.6012,
|
669 |
+
"step": 720
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 2.5,
|
673 |
+
"grad_norm": 11.135315895080566,
|
674 |
+
"learning_rate": 2.369739153987942e-06,
|
675 |
+
"loss": 1.7297,
|
676 |
+
"step": 730
|
677 |
+
},
|
678 |
+
{
|
679 |
+
"epoch": 2.5342465753424657,
|
680 |
+
"grad_norm": 11.281685829162598,
|
681 |
+
"learning_rate": 2.207428253029864e-06,
|
682 |
+
"loss": 1.7066,
|
683 |
+
"step": 740
|
684 |
+
},
|
685 |
+
{
|
686 |
+
"epoch": 2.5684931506849313,
|
687 |
+
"grad_norm": 12.174514770507812,
|
688 |
+
"learning_rate": 2.0451173520717856e-06,
|
689 |
+
"loss": 1.7291,
|
690 |
+
"step": 750
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 2.602739726027397,
|
694 |
+
"grad_norm": 11.84288501739502,
|
695 |
+
"learning_rate": 1.8828064511137074e-06,
|
696 |
+
"loss": 1.7143,
|
697 |
+
"step": 760
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 2.636986301369863,
|
701 |
+
"grad_norm": 13.132065773010254,
|
702 |
+
"learning_rate": 1.7204955501556292e-06,
|
703 |
+
"loss": 1.6739,
|
704 |
+
"step": 770
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 2.671232876712329,
|
708 |
+
"grad_norm": 10.684150695800781,
|
709 |
+
"learning_rate": 1.5581846491975508e-06,
|
710 |
+
"loss": 1.7677,
|
711 |
+
"step": 780
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 2.7054794520547945,
|
715 |
+
"grad_norm": 10.924251556396484,
|
716 |
+
"learning_rate": 1.3958737482394726e-06,
|
717 |
+
"loss": 1.7319,
|
718 |
+
"step": 790
|
719 |
+
},
|
720 |
+
{
|
721 |
+
"epoch": 2.73972602739726,
|
722 |
+
"grad_norm": 11.701458930969238,
|
723 |
+
"learning_rate": 1.2335628472813945e-06,
|
724 |
+
"loss": 1.633,
|
725 |
+
"step": 800
|
726 |
+
},
|
727 |
+
{
|
728 |
+
"epoch": 2.7739726027397262,
|
729 |
+
"grad_norm": 15.176057815551758,
|
730 |
+
"learning_rate": 1.0712519463233163e-06,
|
731 |
+
"loss": 1.7776,
|
732 |
+
"step": 810
|
733 |
+
},
|
734 |
+
{
|
735 |
+
"epoch": 2.808219178082192,
|
736 |
+
"grad_norm": 11.823851585388184,
|
737 |
+
"learning_rate": 9.08941045365238e-07,
|
738 |
+
"loss": 1.6718,
|
739 |
+
"step": 820
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 2.8424657534246576,
|
743 |
+
"grad_norm": 16.096837997436523,
|
744 |
+
"learning_rate": 7.466301444071598e-07,
|
745 |
+
"loss": 1.8125,
|
746 |
+
"step": 830
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 2.8767123287671232,
|
750 |
+
"grad_norm": 14.548500061035156,
|
751 |
+
"learning_rate": 5.843192434490816e-07,
|
752 |
+
"loss": 1.6709,
|
753 |
+
"step": 840
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 2.910958904109589,
|
757 |
+
"grad_norm": 14.510014533996582,
|
758 |
+
"learning_rate": 4.2200834249100337e-07,
|
759 |
+
"loss": 1.7332,
|
760 |
+
"step": 850
|
761 |
+
},
|
762 |
+
{
|
763 |
+
"epoch": 2.9452054794520546,
|
764 |
+
"grad_norm": 12.800880432128906,
|
765 |
+
"learning_rate": 2.5969744153292514e-07,
|
766 |
+
"loss": 1.656,
|
767 |
+
"step": 860
|
768 |
+
},
|
769 |
+
{
|
770 |
+
"epoch": 2.9794520547945207,
|
771 |
+
"grad_norm": 11.786734580993652,
|
772 |
+
"learning_rate": 9.738654057484693e-08,
|
773 |
+
"loss": 1.6054,
|
774 |
+
"step": 870
|
775 |
+
},
|
776 |
+
{
|
777 |
+
"epoch": 3.0,
|
778 |
+
"eval_classification_report": {
|
779 |
+
"accuracy": 0.321,
|
780 |
+
"ar": {
|
781 |
+
"f1-score": 0.24539877300613497,
|
782 |
+
"precision": 0.3333333333333333,
|
783 |
+
"recall": 0.1941747572815534,
|
784 |
+
"support": 206.0
|
785 |
+
},
|
786 |
+
"cl": {
|
787 |
+
"f1-score": 0.22151898734177214,
|
788 |
+
"precision": 0.2046783625730994,
|
789 |
+
"recall": 0.2413793103448276,
|
790 |
+
"support": 290.0
|
791 |
+
},
|
792 |
+
"co": {
|
793 |
+
"f1-score": 0.327212020033389,
|
794 |
+
"precision": 0.3181818181818182,
|
795 |
+
"recall": 0.33676975945017185,
|
796 |
+
"support": 291.0
|
797 |
+
},
|
798 |
+
"es": {
|
799 |
+
"f1-score": 0.39095315024232635,
|
800 |
+
"precision": 0.3558823529411765,
|
801 |
+
"recall": 0.4336917562724014,
|
802 |
+
"support": 279.0
|
803 |
+
},
|
804 |
+
"macro avg": {
|
805 |
+
"f1-score": 0.30473656895821705,
|
806 |
+
"precision": 0.31299377782399707,
|
807 |
+
"recall": 0.3074325006319518,
|
808 |
+
"support": 2000.0
|
809 |
+
},
|
810 |
+
"mx": {
|
811 |
+
"f1-score": 0.36075949367088606,
|
812 |
+
"precision": 0.3343108504398827,
|
813 |
+
"recall": 0.3917525773195876,
|
814 |
+
"support": 291.0
|
815 |
+
},
|
816 |
+
"pe": {
|
817 |
+
"f1-score": 0.23850085178875638,
|
818 |
+
"precision": 0.23648648648648649,
|
819 |
+
"recall": 0.24054982817869416,
|
820 |
+
"support": 291.0
|
821 |
+
},
|
822 |
+
"pr": {
|
823 |
+
"f1-score": 0.616822429906542,
|
824 |
+
"precision": 0.584070796460177,
|
825 |
+
"recall": 0.6534653465346535,
|
826 |
+
"support": 101.0
|
827 |
+
},
|
828 |
+
"uy": {
|
829 |
+
"f1-score": 0.34146341463414637,
|
830 |
+
"precision": 0.45,
|
831 |
+
"recall": 0.27510917030567683,
|
832 |
+
"support": 229.0
|
833 |
+
},
|
834 |
+
"ve": {
|
835 |
+
"f1-score": 0.0,
|
836 |
+
"precision": 0.0,
|
837 |
+
"recall": 0.0,
|
838 |
+
"support": 22.0
|
839 |
+
},
|
840 |
+
"weighted avg": {
|
841 |
+
"f1-score": 0.3169831141081196,
|
842 |
+
"precision": 0.3240243264312071,
|
843 |
+
"recall": 0.321,
|
844 |
+
"support": 2000.0
|
845 |
+
}
|
846 |
+
},
|
847 |
+
"eval_f1": 0.30473656895821705,
|
848 |
+
"eval_loss": 1.8237080574035645,
|
849 |
+
"eval_runtime": 3.9808,
|
850 |
+
"eval_samples_per_second": 502.417,
|
851 |
+
"eval_steps_per_second": 31.401,
|
852 |
+
"step": 876
|
853 |
+
}
|
854 |
+
],
|
855 |
+
"logging_steps": 10,
|
856 |
+
"max_steps": 876,
|
857 |
+
"num_input_tokens_seen": 0,
|
858 |
+
"num_train_epochs": 3,
|
859 |
+
"save_steps": 500,
|
860 |
+
"stateful_callbacks": {
|
861 |
+
"TrainerControl": {
|
862 |
+
"args": {
|
863 |
+
"should_epoch_stop": false,
|
864 |
+
"should_evaluate": false,
|
865 |
+
"should_log": false,
|
866 |
+
"should_save": true,
|
867 |
+
"should_training_stop": true
|
868 |
+
},
|
869 |
+
"attributes": {}
|
870 |
+
}
|
871 |
+
},
|
872 |
+
"total_flos": 920815007980032.0,
|
873 |
+
"train_batch_size": 16,
|
874 |
+
"trial_name": null,
|
875 |
+
"trial_params": null
|
876 |
+
}
|
trial_0/checkpoint-876/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf983bab71d39717083fd85c30b7e0fd950e8d457e647f61a7ff596cb390b138
|
3 |
+
size 5368
|
trial_0/checkpoint-876/vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
trial_0/logs/events.out.tfevents.1740158198.a2d653e866f9.226.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d93a76ea98cda8f1a1f299c4559552e6ff63b7201898fd12d91c00f7d63ab861
|
3 |
+
size 6723
|
trial_0/logs/events.out.tfevents.1740161296.0a0ba32201a8.2151.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e04278ab83601bb3ec7661f515626f6d5cc7e973b6bc6ef2761183a848daed5
|
3 |
+
size 30179
|
trial_0/logs/events.out.tfevents.1740161531.0a0ba32201a8.2151.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc6a4056a5185e518d4124b6179202d83d9aa7b9da6f6957c3776875c2345405
|
3 |
+
size 25089
|
trial_0/logs/events.out.tfevents.1740161645.0a0ba32201a8.2151.2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:76747c3b41f44365b9f8d4eabb3389f8487d7441a12322dc7488712efccf4d86
|
3 |
+
size 405
|
trial_1/checkpoint-146/config.json
ADDED
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
3 |
+
"architectures": [
|
4 |
+
"BertForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"gradient_checkpointing": false,
|
9 |
+
"hidden_act": "gelu",
|
10 |
+
"hidden_dropout_prob": 0.1,
|
11 |
+
"hidden_size": 768,
|
12 |
+
"id2label": {
|
13 |
+
"0": "ar",
|
14 |
+
"1": "cl",
|
15 |
+
"2": "co",
|
16 |
+
"3": "es",
|
17 |
+
"4": "mx",
|
18 |
+
"5": "pe",
|
19 |
+
"6": "pr",
|
20 |
+
"7": "uy",
|
21 |
+
"8": "ve"
|
22 |
+
},
|
23 |
+
"initializer_range": 0.02,
|
24 |
+
"intermediate_size": 3072,
|
25 |
+
"label2id": {
|
26 |
+
"ar": 0,
|
27 |
+
"cl": 1,
|
28 |
+
"co": 2,
|
29 |
+
"es": 3,
|
30 |
+
"mx": 4,
|
31 |
+
"pe": 5,
|
32 |
+
"pr": 6,
|
33 |
+
"uy": 7,
|
34 |
+
"ve": 8
|
35 |
+
},
|
36 |
+
"layer_norm_eps": 1e-12,
|
37 |
+
"max_position_embeddings": 512,
|
38 |
+
"model_type": "bert",
|
39 |
+
"num_attention_heads": 12,
|
40 |
+
"num_hidden_layers": 12,
|
41 |
+
"output_past": true,
|
42 |
+
"pad_token_id": 1,
|
43 |
+
"position_embedding_type": "absolute",
|
44 |
+
"problem_type": "single_label_classification",
|
45 |
+
"torch_dtype": "float32",
|
46 |
+
"transformers_version": "4.48.3",
|
47 |
+
"type_vocab_size": 2,
|
48 |
+
"use_cache": true,
|
49 |
+
"vocab_size": 31002
|
50 |
+
}
|
trial_1/checkpoint-146/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f148025042e8766377f58bd5b2cb8ab568f58cfee85f2f67d50d7b13949b896
|
3 |
+
size 439454740
|
trial_1/checkpoint-146/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5b16f9046371de70837c5fcfbbb97032ca47fd7b0f2f5f70b053c6733259e41
|
3 |
+
size 879030522
|