Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- checkpoint-115/config.json +39 -0
- checkpoint-115/model.safetensors +3 -0
- checkpoint-115/optimizer.pt +3 -0
- checkpoint-115/rng_state.pth +3 -0
- checkpoint-115/scheduler.pt +3 -0
- checkpoint-115/special_tokens_map.json +51 -0
- checkpoint-115/tokenizer.json +0 -0
- checkpoint-115/tokenizer_config.json +61 -0
- checkpoint-115/trainer_state.json +148 -0
- checkpoint-115/training_args.bin +3 -0
- checkpoint-138/config.json +39 -0
- checkpoint-138/model.safetensors +3 -0
- checkpoint-138/optimizer.pt +3 -0
- checkpoint-138/rng_state.pth +3 -0
- checkpoint-138/scheduler.pt +3 -0
- checkpoint-138/special_tokens_map.json +51 -0
- checkpoint-138/tokenizer.json +0 -0
- checkpoint-138/tokenizer_config.json +61 -0
- checkpoint-138/trainer_state.json +172 -0
- checkpoint-138/training_args.bin +3 -0
- checkpoint-23/config.json +39 -0
- checkpoint-23/model.safetensors +3 -0
- checkpoint-23/optimizer.pt +3 -0
- checkpoint-23/rng_state.pth +3 -0
- checkpoint-23/scheduler.pt +3 -0
- checkpoint-23/special_tokens_map.json +51 -0
- checkpoint-23/tokenizer.json +0 -0
- checkpoint-23/tokenizer_config.json +61 -0
- checkpoint-23/trainer_state.json +45 -0
- checkpoint-23/training_args.bin +3 -0
- checkpoint-46/config.json +39 -0
- checkpoint-46/model.safetensors +3 -0
- checkpoint-46/optimizer.pt +3 -0
- checkpoint-46/rng_state.pth +3 -0
- checkpoint-46/scheduler.pt +3 -0
- checkpoint-46/special_tokens_map.json +51 -0
- checkpoint-46/tokenizer.json +0 -0
- checkpoint-46/tokenizer_config.json +61 -0
- checkpoint-46/trainer_state.json +69 -0
- checkpoint-46/training_args.bin +3 -0
- checkpoint-69/config.json +39 -0
- checkpoint-69/model.safetensors +3 -0
- checkpoint-69/optimizer.pt +3 -0
- checkpoint-69/rng_state.pth +3 -0
- checkpoint-69/scheduler.pt +3 -0
- checkpoint-69/special_tokens_map.json +51 -0
- checkpoint-69/tokenizer.json +0 -0
- checkpoint-69/tokenizer_config.json +61 -0
- checkpoint-69/trainer_state.json +93 -0
- checkpoint-69/training_args.bin +3 -0
checkpoint-115/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pysentimiento/robertuito-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "negativo",
|
| 16 |
+
"1": "neutro",
|
| 17 |
+
"2": "positivo"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negativo": 0,
|
| 23 |
+
"neutro": 1,
|
| 24 |
+
"positivo": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 130,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.40.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30000
|
| 39 |
+
}
|
checkpoint-115/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec395f7c1fca82fb468ac147982d245d365a047251f70c2af5aa99669f550980
|
| 3 |
+
size 435182156
|
checkpoint-115/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e78fb9fec1edd539e07ccebc0fcbee1f86c89bf4a6c8e1c2ce166c8d2bcc1e0c
|
| 3 |
+
size 870478987
|
checkpoint-115/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33f4bbc62477e25154824a380cf85066ce49eed96ddf9e0c5e705b2aca7a8276
|
| 3 |
+
size 14455
|
checkpoint-115/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26385997b9ecefddd34ac85cc05a24d425a9bcdc0eb0ac1a2cda77240d74c887
|
| 3 |
+
size 1465
|
checkpoint-115/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-115/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-115/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 128,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
checkpoint-115/trainer_state.json
ADDED
|
@@ -0,0 +1,148 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9329080276448697,
|
| 3 |
+
"best_model_checkpoint": "./priority_model\\checkpoint-92",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 115,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.43478260869565216,
|
| 13 |
+
"grad_norm": 5.8311944007873535,
|
| 14 |
+
"learning_rate": 1.8550724637681162e-05,
|
| 15 |
+
"loss": 1.0181,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8695652173913043,
|
| 20 |
+
"grad_norm": 7.023670196533203,
|
| 21 |
+
"learning_rate": 1.710144927536232e-05,
|
| 22 |
+
"loss": 0.8761,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.8888888888888888,
|
| 28 |
+
"eval_f1": 0.8887926887926887,
|
| 29 |
+
"eval_loss": 0.6216873526573181,
|
| 30 |
+
"eval_runtime": 1.0711,
|
| 31 |
+
"eval_samples_per_second": 42.014,
|
| 32 |
+
"eval_steps_per_second": 5.602,
|
| 33 |
+
"step": 23
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.3043478260869565,
|
| 37 |
+
"grad_norm": 5.623006820678711,
|
| 38 |
+
"learning_rate": 1.565217391304348e-05,
|
| 39 |
+
"loss": 0.7532,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.7391304347826086,
|
| 44 |
+
"grad_norm": 9.884881973266602,
|
| 45 |
+
"learning_rate": 1.420289855072464e-05,
|
| 46 |
+
"loss": 0.5316,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_accuracy": 0.9111111111111111,
|
| 52 |
+
"eval_f1": 0.9095029239766083,
|
| 53 |
+
"eval_loss": 0.3368909955024719,
|
| 54 |
+
"eval_runtime": 1.0808,
|
| 55 |
+
"eval_samples_per_second": 41.635,
|
| 56 |
+
"eval_steps_per_second": 5.551,
|
| 57 |
+
"step": 46
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.1739130434782608,
|
| 61 |
+
"grad_norm": 4.106278896331787,
|
| 62 |
+
"learning_rate": 1.2753623188405797e-05,
|
| 63 |
+
"loss": 0.3776,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.608695652173913,
|
| 68 |
+
"grad_norm": 3.0185980796813965,
|
| 69 |
+
"learning_rate": 1.1304347826086957e-05,
|
| 70 |
+
"loss": 0.2772,
|
| 71 |
+
"step": 60
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"eval_accuracy": 0.9333333333333333,
|
| 76 |
+
"eval_f1": 0.9318062180540958,
|
| 77 |
+
"eval_loss": 0.22048650681972504,
|
| 78 |
+
"eval_runtime": 1.0754,
|
| 79 |
+
"eval_samples_per_second": 41.846,
|
| 80 |
+
"eval_steps_per_second": 5.579,
|
| 81 |
+
"step": 69
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.0434782608695654,
|
| 85 |
+
"grad_norm": 5.088245391845703,
|
| 86 |
+
"learning_rate": 9.855072463768118e-06,
|
| 87 |
+
"loss": 0.2582,
|
| 88 |
+
"step": 70
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.4782608695652173,
|
| 92 |
+
"grad_norm": 7.887622356414795,
|
| 93 |
+
"learning_rate": 8.405797101449275e-06,
|
| 94 |
+
"loss": 0.1718,
|
| 95 |
+
"step": 80
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.9130434782608696,
|
| 99 |
+
"grad_norm": 2.031566619873047,
|
| 100 |
+
"learning_rate": 6.956521739130435e-06,
|
| 101 |
+
"loss": 0.1757,
|
| 102 |
+
"step": 90
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.0,
|
| 106 |
+
"eval_accuracy": 0.9333333333333333,
|
| 107 |
+
"eval_f1": 0.9329080276448697,
|
| 108 |
+
"eval_loss": 0.17431004345417023,
|
| 109 |
+
"eval_runtime": 1.0809,
|
| 110 |
+
"eval_samples_per_second": 41.631,
|
| 111 |
+
"eval_steps_per_second": 5.551,
|
| 112 |
+
"step": 92
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.3478260869565215,
|
| 116 |
+
"grad_norm": 1.8258976936340332,
|
| 117 |
+
"learning_rate": 5.507246376811595e-06,
|
| 118 |
+
"loss": 0.1246,
|
| 119 |
+
"step": 100
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.782608695652174,
|
| 123 |
+
"grad_norm": 1.9977986812591553,
|
| 124 |
+
"learning_rate": 4.057971014492754e-06,
|
| 125 |
+
"loss": 0.0982,
|
| 126 |
+
"step": 110
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.0,
|
| 130 |
+
"eval_accuracy": 0.9333333333333333,
|
| 131 |
+
"eval_f1": 0.9329080276448697,
|
| 132 |
+
"eval_loss": 0.16062292456626892,
|
| 133 |
+
"eval_runtime": 1.0756,
|
| 134 |
+
"eval_samples_per_second": 41.837,
|
| 135 |
+
"eval_steps_per_second": 5.578,
|
| 136 |
+
"step": 115
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"logging_steps": 10,
|
| 140 |
+
"max_steps": 138,
|
| 141 |
+
"num_input_tokens_seen": 0,
|
| 142 |
+
"num_train_epochs": 6,
|
| 143 |
+
"save_steps": 500,
|
| 144 |
+
"total_flos": 40931608832100.0,
|
| 145 |
+
"train_batch_size": 8,
|
| 146 |
+
"trial_name": null,
|
| 147 |
+
"trial_params": null
|
| 148 |
+
}
|
checkpoint-115/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c13074aab0b71652da1adedf2d491b62943baf1565114518d1b0e2608cf96b4
|
| 3 |
+
size 5329
|
checkpoint-138/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pysentimiento/robertuito-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "negativo",
|
| 16 |
+
"1": "neutro",
|
| 17 |
+
"2": "positivo"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negativo": 0,
|
| 23 |
+
"neutro": 1,
|
| 24 |
+
"positivo": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 130,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.40.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30000
|
| 39 |
+
}
|
checkpoint-138/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:691ca7a9c662a8ff2254887f7a78a0e91f6da2ec17bfc6eff700bc2b68422eaa
|
| 3 |
+
size 435182156
|
checkpoint-138/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6eeb907d36b46fdafd9a284ab0633e28e54399759c0ff52a05b2a47902a1aba8
|
| 3 |
+
size 870478987
|
checkpoint-138/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8532300d96c4c446b5b8b726b81c7f18e0c306a1503b8139437ea3fd9e4d1bd3
|
| 3 |
+
size 14455
|
checkpoint-138/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1943a8475477ba59cc3b3fb041295953872c48e7f00df2ba11e3870f016f75e7
|
| 3 |
+
size 1465
|
checkpoint-138/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-138/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-138/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 128,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
checkpoint-138/trainer_state.json
ADDED
|
@@ -0,0 +1,172 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9329080276448697,
|
| 3 |
+
"best_model_checkpoint": "./priority_model\\checkpoint-92",
|
| 4 |
+
"epoch": 6.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 138,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.43478260869565216,
|
| 13 |
+
"grad_norm": 5.8311944007873535,
|
| 14 |
+
"learning_rate": 1.8550724637681162e-05,
|
| 15 |
+
"loss": 1.0181,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8695652173913043,
|
| 20 |
+
"grad_norm": 7.023670196533203,
|
| 21 |
+
"learning_rate": 1.710144927536232e-05,
|
| 22 |
+
"loss": 0.8761,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.8888888888888888,
|
| 28 |
+
"eval_f1": 0.8887926887926887,
|
| 29 |
+
"eval_loss": 0.6216873526573181,
|
| 30 |
+
"eval_runtime": 1.0711,
|
| 31 |
+
"eval_samples_per_second": 42.014,
|
| 32 |
+
"eval_steps_per_second": 5.602,
|
| 33 |
+
"step": 23
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.3043478260869565,
|
| 37 |
+
"grad_norm": 5.623006820678711,
|
| 38 |
+
"learning_rate": 1.565217391304348e-05,
|
| 39 |
+
"loss": 0.7532,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.7391304347826086,
|
| 44 |
+
"grad_norm": 9.884881973266602,
|
| 45 |
+
"learning_rate": 1.420289855072464e-05,
|
| 46 |
+
"loss": 0.5316,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_accuracy": 0.9111111111111111,
|
| 52 |
+
"eval_f1": 0.9095029239766083,
|
| 53 |
+
"eval_loss": 0.3368909955024719,
|
| 54 |
+
"eval_runtime": 1.0808,
|
| 55 |
+
"eval_samples_per_second": 41.635,
|
| 56 |
+
"eval_steps_per_second": 5.551,
|
| 57 |
+
"step": 46
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.1739130434782608,
|
| 61 |
+
"grad_norm": 4.106278896331787,
|
| 62 |
+
"learning_rate": 1.2753623188405797e-05,
|
| 63 |
+
"loss": 0.3776,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.608695652173913,
|
| 68 |
+
"grad_norm": 3.0185980796813965,
|
| 69 |
+
"learning_rate": 1.1304347826086957e-05,
|
| 70 |
+
"loss": 0.2772,
|
| 71 |
+
"step": 60
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"eval_accuracy": 0.9333333333333333,
|
| 76 |
+
"eval_f1": 0.9318062180540958,
|
| 77 |
+
"eval_loss": 0.22048650681972504,
|
| 78 |
+
"eval_runtime": 1.0754,
|
| 79 |
+
"eval_samples_per_second": 41.846,
|
| 80 |
+
"eval_steps_per_second": 5.579,
|
| 81 |
+
"step": 69
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 3.0434782608695654,
|
| 85 |
+
"grad_norm": 5.088245391845703,
|
| 86 |
+
"learning_rate": 9.855072463768118e-06,
|
| 87 |
+
"loss": 0.2582,
|
| 88 |
+
"step": 70
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 3.4782608695652173,
|
| 92 |
+
"grad_norm": 7.887622356414795,
|
| 93 |
+
"learning_rate": 8.405797101449275e-06,
|
| 94 |
+
"loss": 0.1718,
|
| 95 |
+
"step": 80
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 3.9130434782608696,
|
| 99 |
+
"grad_norm": 2.031566619873047,
|
| 100 |
+
"learning_rate": 6.956521739130435e-06,
|
| 101 |
+
"loss": 0.1757,
|
| 102 |
+
"step": 90
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 4.0,
|
| 106 |
+
"eval_accuracy": 0.9333333333333333,
|
| 107 |
+
"eval_f1": 0.9329080276448697,
|
| 108 |
+
"eval_loss": 0.17431004345417023,
|
| 109 |
+
"eval_runtime": 1.0809,
|
| 110 |
+
"eval_samples_per_second": 41.631,
|
| 111 |
+
"eval_steps_per_second": 5.551,
|
| 112 |
+
"step": 92
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 4.3478260869565215,
|
| 116 |
+
"grad_norm": 1.8258976936340332,
|
| 117 |
+
"learning_rate": 5.507246376811595e-06,
|
| 118 |
+
"loss": 0.1246,
|
| 119 |
+
"step": 100
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 4.782608695652174,
|
| 123 |
+
"grad_norm": 1.9977986812591553,
|
| 124 |
+
"learning_rate": 4.057971014492754e-06,
|
| 125 |
+
"loss": 0.0982,
|
| 126 |
+
"step": 110
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 5.0,
|
| 130 |
+
"eval_accuracy": 0.9333333333333333,
|
| 131 |
+
"eval_f1": 0.9329080276448697,
|
| 132 |
+
"eval_loss": 0.16062292456626892,
|
| 133 |
+
"eval_runtime": 1.0756,
|
| 134 |
+
"eval_samples_per_second": 41.837,
|
| 135 |
+
"eval_steps_per_second": 5.578,
|
| 136 |
+
"step": 115
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 5.217391304347826,
|
| 140 |
+
"grad_norm": 1.5564908981323242,
|
| 141 |
+
"learning_rate": 2.6086956521739132e-06,
|
| 142 |
+
"loss": 0.096,
|
| 143 |
+
"step": 120
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 5.6521739130434785,
|
| 147 |
+
"grad_norm": 0.8947910070419312,
|
| 148 |
+
"learning_rate": 1.1594202898550726e-06,
|
| 149 |
+
"loss": 0.1061,
|
| 150 |
+
"step": 130
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 6.0,
|
| 154 |
+
"eval_accuracy": 0.9333333333333333,
|
| 155 |
+
"eval_f1": 0.9329080276448697,
|
| 156 |
+
"eval_loss": 0.1549370437860489,
|
| 157 |
+
"eval_runtime": 1.0706,
|
| 158 |
+
"eval_samples_per_second": 42.031,
|
| 159 |
+
"eval_steps_per_second": 5.604,
|
| 160 |
+
"step": 138
|
| 161 |
+
}
|
| 162 |
+
],
|
| 163 |
+
"logging_steps": 10,
|
| 164 |
+
"max_steps": 138,
|
| 165 |
+
"num_input_tokens_seen": 0,
|
| 166 |
+
"num_train_epochs": 6,
|
| 167 |
+
"save_steps": 500,
|
| 168 |
+
"total_flos": 49117930598520.0,
|
| 169 |
+
"train_batch_size": 8,
|
| 170 |
+
"trial_name": null,
|
| 171 |
+
"trial_params": null
|
| 172 |
+
}
|
checkpoint-138/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c13074aab0b71652da1adedf2d491b62943baf1565114518d1b0e2608cf96b4
|
| 3 |
+
size 5329
|
checkpoint-23/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pysentimiento/robertuito-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "negativo",
|
| 16 |
+
"1": "neutro",
|
| 17 |
+
"2": "positivo"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negativo": 0,
|
| 23 |
+
"neutro": 1,
|
| 24 |
+
"positivo": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 130,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.40.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30000
|
| 39 |
+
}
|
checkpoint-23/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:109a07a0e511e90594e0c79921d77ea098ee1408bd1745582cb30851508d395f
|
| 3 |
+
size 435182156
|
checkpoint-23/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0fb27cc4b69fd1b6a3877489ef8f7203570dd6c9fdddbdb5a25152168de989f
|
| 3 |
+
size 870478987
|
checkpoint-23/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:738e4f60d0354e8074f393490de3d4642e7dc2e104190b4d3fbfef991f854517
|
| 3 |
+
size 14455
|
checkpoint-23/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86c5ad062279d9c0f004bc5e16caf24225395946239bc0f028b87e75a717946f
|
| 3 |
+
size 1465
|
checkpoint-23/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-23/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-23/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 128,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
checkpoint-23/trainer_state.json
ADDED
|
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8887926887926887,
|
| 3 |
+
"best_model_checkpoint": "./priority_model\\checkpoint-23",
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 23,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.43478260869565216,
|
| 13 |
+
"grad_norm": 5.8311944007873535,
|
| 14 |
+
"learning_rate": 1.8550724637681162e-05,
|
| 15 |
+
"loss": 1.0181,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8695652173913043,
|
| 20 |
+
"grad_norm": 7.023670196533203,
|
| 21 |
+
"learning_rate": 1.710144927536232e-05,
|
| 22 |
+
"loss": 0.8761,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.8888888888888888,
|
| 28 |
+
"eval_f1": 0.8887926887926887,
|
| 29 |
+
"eval_loss": 0.6216873526573181,
|
| 30 |
+
"eval_runtime": 1.0711,
|
| 31 |
+
"eval_samples_per_second": 42.014,
|
| 32 |
+
"eval_steps_per_second": 5.602,
|
| 33 |
+
"step": 23
|
| 34 |
+
}
|
| 35 |
+
],
|
| 36 |
+
"logging_steps": 10,
|
| 37 |
+
"max_steps": 138,
|
| 38 |
+
"num_input_tokens_seen": 0,
|
| 39 |
+
"num_train_epochs": 6,
|
| 40 |
+
"save_steps": 500,
|
| 41 |
+
"total_flos": 8186321766420.0,
|
| 42 |
+
"train_batch_size": 8,
|
| 43 |
+
"trial_name": null,
|
| 44 |
+
"trial_params": null
|
| 45 |
+
}
|
checkpoint-23/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c13074aab0b71652da1adedf2d491b62943baf1565114518d1b0e2608cf96b4
|
| 3 |
+
size 5329
|
checkpoint-46/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pysentimiento/robertuito-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "negativo",
|
| 16 |
+
"1": "neutro",
|
| 17 |
+
"2": "positivo"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negativo": 0,
|
| 23 |
+
"neutro": 1,
|
| 24 |
+
"positivo": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 130,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.40.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30000
|
| 39 |
+
}
|
checkpoint-46/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d84a3e8ba5f45a227274c3ebfeb356db49d114f38c2a899add5b1c57f97b1a68
|
| 3 |
+
size 435182156
|
checkpoint-46/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ea7702c939385b3eda4383c33e48a6a49d2f58ab539fdece5ba79a01e5676ef
|
| 3 |
+
size 870478987
|
checkpoint-46/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:829cdd8c49d7b06793c6f3365022e861503cfd21045f274def7ea63e2ab4fb1a
|
| 3 |
+
size 14455
|
checkpoint-46/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8591433f5c1a9738d85c23e189458fc4e8f9e23a3b2aa3bc106e8b1c174d87a
|
| 3 |
+
size 1465
|
checkpoint-46/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-46/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-46/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 128,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
checkpoint-46/trainer_state.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9095029239766083,
|
| 3 |
+
"best_model_checkpoint": "./priority_model\\checkpoint-46",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 46,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.43478260869565216,
|
| 13 |
+
"grad_norm": 5.8311944007873535,
|
| 14 |
+
"learning_rate": 1.8550724637681162e-05,
|
| 15 |
+
"loss": 1.0181,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8695652173913043,
|
| 20 |
+
"grad_norm": 7.023670196533203,
|
| 21 |
+
"learning_rate": 1.710144927536232e-05,
|
| 22 |
+
"loss": 0.8761,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.8888888888888888,
|
| 28 |
+
"eval_f1": 0.8887926887926887,
|
| 29 |
+
"eval_loss": 0.6216873526573181,
|
| 30 |
+
"eval_runtime": 1.0711,
|
| 31 |
+
"eval_samples_per_second": 42.014,
|
| 32 |
+
"eval_steps_per_second": 5.602,
|
| 33 |
+
"step": 23
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.3043478260869565,
|
| 37 |
+
"grad_norm": 5.623006820678711,
|
| 38 |
+
"learning_rate": 1.565217391304348e-05,
|
| 39 |
+
"loss": 0.7532,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.7391304347826086,
|
| 44 |
+
"grad_norm": 9.884881973266602,
|
| 45 |
+
"learning_rate": 1.420289855072464e-05,
|
| 46 |
+
"loss": 0.5316,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_accuracy": 0.9111111111111111,
|
| 52 |
+
"eval_f1": 0.9095029239766083,
|
| 53 |
+
"eval_loss": 0.3368909955024719,
|
| 54 |
+
"eval_runtime": 1.0808,
|
| 55 |
+
"eval_samples_per_second": 41.635,
|
| 56 |
+
"eval_steps_per_second": 5.551,
|
| 57 |
+
"step": 46
|
| 58 |
+
}
|
| 59 |
+
],
|
| 60 |
+
"logging_steps": 10,
|
| 61 |
+
"max_steps": 138,
|
| 62 |
+
"num_input_tokens_seen": 0,
|
| 63 |
+
"num_train_epochs": 6,
|
| 64 |
+
"save_steps": 500,
|
| 65 |
+
"total_flos": 16372643532840.0,
|
| 66 |
+
"train_batch_size": 8,
|
| 67 |
+
"trial_name": null,
|
| 68 |
+
"trial_params": null
|
| 69 |
+
}
|
checkpoint-46/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c13074aab0b71652da1adedf2d491b62943baf1565114518d1b0e2608cf96b4
|
| 3 |
+
size 5329
|
checkpoint-69/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "pysentimiento/robertuito-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "negativo",
|
| 16 |
+
"1": "neutro",
|
| 17 |
+
"2": "positivo"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"negativo": 0,
|
| 23 |
+
"neutro": 1,
|
| 24 |
+
"positivo": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-12,
|
| 27 |
+
"max_position_embeddings": 130,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.40.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 30000
|
| 39 |
+
}
|
checkpoint-69/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19161b7681bf5c57f7a556561380a4b05c63a061006504654ba72c40ba550f5f
|
| 3 |
+
size 435182156
|
checkpoint-69/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06f114739b9aac3dad7c92c8b257a49f956d35669f8dfa37f49042887c8b32d8
|
| 3 |
+
size 870478987
|
checkpoint-69/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fce0263451ccb1ed284530141dfe957abcec56b9453a069d502c706cff1bf73
|
| 3 |
+
size 14455
|
checkpoint-69/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b15c5f54b832af3c87fcebb2f90da02d60dda83bd05ed7d248bdb8767d048958
|
| 3 |
+
size 1465
|
checkpoint-69/special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
checkpoint-69/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-69/tokenizer_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<s>",
|
| 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 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "<mask>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"bos_token": "<s>",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
+
"cls_token": "<s>",
|
| 47 |
+
"eos_token": "</s>",
|
| 48 |
+
"mask_token": "<mask>",
|
| 49 |
+
"max_length": 128,
|
| 50 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 51 |
+
"pad_to_multiple_of": null,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"pad_token_type_id": 0,
|
| 54 |
+
"padding_side": "right",
|
| 55 |
+
"sep_token": "</s>",
|
| 56 |
+
"stride": 0,
|
| 57 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 58 |
+
"truncation_side": "right",
|
| 59 |
+
"truncation_strategy": "longest_first",
|
| 60 |
+
"unk_token": "<unk>"
|
| 61 |
+
}
|
checkpoint-69/trainer_state.json
ADDED
|
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.9318062180540958,
|
| 3 |
+
"best_model_checkpoint": "./priority_model\\checkpoint-69",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 69,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.43478260869565216,
|
| 13 |
+
"grad_norm": 5.8311944007873535,
|
| 14 |
+
"learning_rate": 1.8550724637681162e-05,
|
| 15 |
+
"loss": 1.0181,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.8695652173913043,
|
| 20 |
+
"grad_norm": 7.023670196533203,
|
| 21 |
+
"learning_rate": 1.710144927536232e-05,
|
| 22 |
+
"loss": 0.8761,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 1.0,
|
| 27 |
+
"eval_accuracy": 0.8888888888888888,
|
| 28 |
+
"eval_f1": 0.8887926887926887,
|
| 29 |
+
"eval_loss": 0.6216873526573181,
|
| 30 |
+
"eval_runtime": 1.0711,
|
| 31 |
+
"eval_samples_per_second": 42.014,
|
| 32 |
+
"eval_steps_per_second": 5.602,
|
| 33 |
+
"step": 23
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.3043478260869565,
|
| 37 |
+
"grad_norm": 5.623006820678711,
|
| 38 |
+
"learning_rate": 1.565217391304348e-05,
|
| 39 |
+
"loss": 0.7532,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.7391304347826086,
|
| 44 |
+
"grad_norm": 9.884881973266602,
|
| 45 |
+
"learning_rate": 1.420289855072464e-05,
|
| 46 |
+
"loss": 0.5316,
|
| 47 |
+
"step": 40
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 2.0,
|
| 51 |
+
"eval_accuracy": 0.9111111111111111,
|
| 52 |
+
"eval_f1": 0.9095029239766083,
|
| 53 |
+
"eval_loss": 0.3368909955024719,
|
| 54 |
+
"eval_runtime": 1.0808,
|
| 55 |
+
"eval_samples_per_second": 41.635,
|
| 56 |
+
"eval_steps_per_second": 5.551,
|
| 57 |
+
"step": 46
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 2.1739130434782608,
|
| 61 |
+
"grad_norm": 4.106278896331787,
|
| 62 |
+
"learning_rate": 1.2753623188405797e-05,
|
| 63 |
+
"loss": 0.3776,
|
| 64 |
+
"step": 50
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.608695652173913,
|
| 68 |
+
"grad_norm": 3.0185980796813965,
|
| 69 |
+
"learning_rate": 1.1304347826086957e-05,
|
| 70 |
+
"loss": 0.2772,
|
| 71 |
+
"step": 60
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 3.0,
|
| 75 |
+
"eval_accuracy": 0.9333333333333333,
|
| 76 |
+
"eval_f1": 0.9318062180540958,
|
| 77 |
+
"eval_loss": 0.22048650681972504,
|
| 78 |
+
"eval_runtime": 1.0754,
|
| 79 |
+
"eval_samples_per_second": 41.846,
|
| 80 |
+
"eval_steps_per_second": 5.579,
|
| 81 |
+
"step": 69
|
| 82 |
+
}
|
| 83 |
+
],
|
| 84 |
+
"logging_steps": 10,
|
| 85 |
+
"max_steps": 138,
|
| 86 |
+
"num_input_tokens_seen": 0,
|
| 87 |
+
"num_train_epochs": 6,
|
| 88 |
+
"save_steps": 500,
|
| 89 |
+
"total_flos": 24558965299260.0,
|
| 90 |
+
"train_batch_size": 8,
|
| 91 |
+
"trial_name": null,
|
| 92 |
+
"trial_params": null
|
| 93 |
+
}
|
checkpoint-69/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c13074aab0b71652da1adedf2d491b62943baf1565114518d1b0e2608cf96b4
|
| 3 |
+
size 5329
|