Commit
•
bc68836
1
Parent(s):
8f4f18f
commit files to HF hub
Browse files- .ipynb_checkpoints/README-checkpoint.md +30 -0
- README.md +30 -0
- config.json +145 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- scheduler.pt +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +489 -0
- training_args.bin +3 -0
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
tags:
|
| 4 |
+
- text-generation
|
| 5 |
+
- spanish
|
| 6 |
+
- encoder-decoder
|
| 7 |
+
- beto
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
datasets:
|
| 10 |
+
- cc-news-es
|
| 11 |
+
model-index:
|
| 12 |
+
- name: beto2beto
|
| 13 |
+
results:
|
| 14 |
+
widget:
|
| 15 |
+
- text: |
|
| 16 |
+
La chocotorta, el tradicional y práctico antojo dulce de los argentinos, fue elegida como el mejor postre del mundo por críticos de restaurants internacionales, a casi 40 años de su creación.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
## beto2beto
|
| 20 |
+
Add description.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
Entrenado por 3 epochs sobre CC-NEWS-ES (2019), aproximadamente 68.000 steps. Encoder max length: 40•Decoder max length: 128
|
| 24 |
+
|
| 25 |
+
## Hyperparameters
|
| 26 |
+
## Usage
|
| 27 |
+
## Results
|
| 28 |
+
| key | value |
|
| 29 |
+
| --- | ----- |
|
| 30 |
+
| test_loss | 2.65148806571960452 |
|
README.md
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: es
|
| 3 |
+
tags:
|
| 4 |
+
- text-generation
|
| 5 |
+
- spanish
|
| 6 |
+
- encoder-decoder
|
| 7 |
+
- beto
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
datasets:
|
| 10 |
+
- cc-news-es
|
| 11 |
+
model-index:
|
| 12 |
+
- name: beto2beto
|
| 13 |
+
results:
|
| 14 |
+
widget:
|
| 15 |
+
- text: |
|
| 16 |
+
La chocotorta, el tradicional y práctico antojo dulce de los argentinos, fue elegida como el mejor postre del mundo por críticos de restaurants internacionales, a casi 40 años de su creación.
|
| 17 |
+
|
| 18 |
+
---
|
| 19 |
+
## beto2beto
|
| 20 |
+
Add description.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
Entrenado por 3 epochs sobre CC-NEWS-ES (2019), aproximadamente 68.000 steps. Encoder max length: 40•Decoder max length: 128
|
| 24 |
+
|
| 25 |
+
## Hyperparameters
|
| 26 |
+
## Usage
|
| 27 |
+
## Results
|
| 28 |
+
| key | value |
|
| 29 |
+
| --- | ----- |
|
| 30 |
+
| test_loss | 2.65148806571960452 |
|
config.json
ADDED
|
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"EncoderDecoderModel"
|
| 4 |
+
],
|
| 5 |
+
"decoder": {
|
| 6 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
| 7 |
+
"add_cross_attention": true,
|
| 8 |
+
"architectures": [
|
| 9 |
+
"BertForMaskedLM"
|
| 10 |
+
],
|
| 11 |
+
"attention_probs_dropout_prob": 0.1,
|
| 12 |
+
"bad_words_ids": null,
|
| 13 |
+
"bos_token_id": null,
|
| 14 |
+
"chunk_size_feed_forward": 0,
|
| 15 |
+
"decoder_start_token_id": null,
|
| 16 |
+
"diversity_penalty": 0.0,
|
| 17 |
+
"do_sample": false,
|
| 18 |
+
"early_stopping": false,
|
| 19 |
+
"eos_token_id": null,
|
| 20 |
+
"finetuning_task": null,
|
| 21 |
+
"gradient_checkpointing": false,
|
| 22 |
+
"hidden_act": "gelu",
|
| 23 |
+
"hidden_dropout_prob": 0.1,
|
| 24 |
+
"hidden_size": 768,
|
| 25 |
+
"id2label": {
|
| 26 |
+
"0": "LABEL_0",
|
| 27 |
+
"1": "LABEL_1"
|
| 28 |
+
},
|
| 29 |
+
"initializer_range": 0.02,
|
| 30 |
+
"intermediate_size": 3072,
|
| 31 |
+
"is_decoder": true,
|
| 32 |
+
"is_encoder_decoder": false,
|
| 33 |
+
"label2id": {
|
| 34 |
+
"LABEL_0": 0,
|
| 35 |
+
"LABEL_1": 1
|
| 36 |
+
},
|
| 37 |
+
"layer_norm_eps": 1e-12,
|
| 38 |
+
"length_penalty": 1.0,
|
| 39 |
+
"max_length": 20,
|
| 40 |
+
"max_position_embeddings": 512,
|
| 41 |
+
"min_length": 0,
|
| 42 |
+
"model_type": "bert",
|
| 43 |
+
"no_repeat_ngram_size": 0,
|
| 44 |
+
"num_attention_heads": 12,
|
| 45 |
+
"num_beam_groups": 1,
|
| 46 |
+
"num_beams": 1,
|
| 47 |
+
"num_hidden_layers": 12,
|
| 48 |
+
"num_return_sequences": 1,
|
| 49 |
+
"output_attentions": false,
|
| 50 |
+
"output_hidden_states": false,
|
| 51 |
+
"output_past": true,
|
| 52 |
+
"pad_token_id": 1,
|
| 53 |
+
"position_embedding_type": "absolute",
|
| 54 |
+
"prefix": null,
|
| 55 |
+
"pruned_heads": {},
|
| 56 |
+
"repetition_penalty": 1.0,
|
| 57 |
+
"return_dict": true,
|
| 58 |
+
"sep_token_id": null,
|
| 59 |
+
"task_specific_params": null,
|
| 60 |
+
"temperature": 1.0,
|
| 61 |
+
"tie_encoder_decoder": false,
|
| 62 |
+
"tie_word_embeddings": true,
|
| 63 |
+
"tokenizer_class": null,
|
| 64 |
+
"top_k": 50,
|
| 65 |
+
"top_p": 1.0,
|
| 66 |
+
"torchscript": false,
|
| 67 |
+
"type_vocab_size": 2,
|
| 68 |
+
"use_bfloat16": false,
|
| 69 |
+
"vocab_size": 31002,
|
| 70 |
+
"xla_device": null
|
| 71 |
+
},
|
| 72 |
+
"decoder_start_token_id": 4,
|
| 73 |
+
"encoder": {
|
| 74 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
| 75 |
+
"add_cross_attention": false,
|
| 76 |
+
"architectures": [
|
| 77 |
+
"BertForMaskedLM"
|
| 78 |
+
],
|
| 79 |
+
"attention_probs_dropout_prob": 0.1,
|
| 80 |
+
"bad_words_ids": null,
|
| 81 |
+
"bos_token_id": null,
|
| 82 |
+
"chunk_size_feed_forward": 0,
|
| 83 |
+
"decoder_start_token_id": null,
|
| 84 |
+
"diversity_penalty": 0.0,
|
| 85 |
+
"do_sample": false,
|
| 86 |
+
"early_stopping": false,
|
| 87 |
+
"eos_token_id": null,
|
| 88 |
+
"finetuning_task": null,
|
| 89 |
+
"gradient_checkpointing": false,
|
| 90 |
+
"hidden_act": "gelu",
|
| 91 |
+
"hidden_dropout_prob": 0.1,
|
| 92 |
+
"hidden_size": 768,
|
| 93 |
+
"id2label": {
|
| 94 |
+
"0": "LABEL_0",
|
| 95 |
+
"1": "LABEL_1"
|
| 96 |
+
},
|
| 97 |
+
"initializer_range": 0.02,
|
| 98 |
+
"intermediate_size": 3072,
|
| 99 |
+
"is_decoder": false,
|
| 100 |
+
"is_encoder_decoder": false,
|
| 101 |
+
"label2id": {
|
| 102 |
+
"LABEL_0": 0,
|
| 103 |
+
"LABEL_1": 1
|
| 104 |
+
},
|
| 105 |
+
"layer_norm_eps": 1e-12,
|
| 106 |
+
"length_penalty": 1.0,
|
| 107 |
+
"max_length": 20,
|
| 108 |
+
"max_position_embeddings": 512,
|
| 109 |
+
"min_length": 0,
|
| 110 |
+
"model_type": "bert",
|
| 111 |
+
"no_repeat_ngram_size": 0,
|
| 112 |
+
"num_attention_heads": 12,
|
| 113 |
+
"num_beam_groups": 1,
|
| 114 |
+
"num_beams": 1,
|
| 115 |
+
"num_hidden_layers": 12,
|
| 116 |
+
"num_return_sequences": 1,
|
| 117 |
+
"output_attentions": false,
|
| 118 |
+
"output_hidden_states": false,
|
| 119 |
+
"output_past": true,
|
| 120 |
+
"pad_token_id": 1,
|
| 121 |
+
"position_embedding_type": "absolute",
|
| 122 |
+
"prefix": null,
|
| 123 |
+
"pruned_heads": {},
|
| 124 |
+
"repetition_penalty": 1.0,
|
| 125 |
+
"return_dict": true,
|
| 126 |
+
"sep_token_id": null,
|
| 127 |
+
"task_specific_params": null,
|
| 128 |
+
"temperature": 1.0,
|
| 129 |
+
"tie_encoder_decoder": false,
|
| 130 |
+
"tie_word_embeddings": true,
|
| 131 |
+
"tokenizer_class": null,
|
| 132 |
+
"top_k": 50,
|
| 133 |
+
"top_p": 1.0,
|
| 134 |
+
"torchscript": false,
|
| 135 |
+
"type_vocab_size": 2,
|
| 136 |
+
"use_bfloat16": false,
|
| 137 |
+
"vocab_size": 31002,
|
| 138 |
+
"xla_device": null
|
| 139 |
+
},
|
| 140 |
+
"eos_token_id": 5,
|
| 141 |
+
"is_encoder_decoder": true,
|
| 142 |
+
"model_type": "encoder-decoder",
|
| 143 |
+
"pad_token_id": 1,
|
| 144 |
+
"vocab_size": 31002
|
| 145 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:443eed5e3293a26ca7209b632fbfcda08ec59217aca14fc5b20097b99342256b
|
| 3 |
+
size 1984967250
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7463bcd122acb915ce42ba133800aa35741aa7a6a5da38d6d4e68f8c9f351479
|
| 3 |
+
size 992553531
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e9530584dadfb58ac64717884699380bbb65c47a6e68b39740f72277bac4a76
|
| 3 |
+
size 330
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
| 1 |
+
{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/root/.cache/huggingface/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "LeoCordoba/mt5-small-mlsum"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,489 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9539427243405263,
|
| 5 |
+
"global_step": 68000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.043440014769605025,
|
| 12 |
+
"learning_rate": 4.9275991891109183e-05,
|
| 13 |
+
"loss": 3.7321220703125,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08688002953921005,
|
| 18 |
+
"learning_rate": 4.8551983782218364e-05,
|
| 19 |
+
"loss": 3.381878173828125,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.13032004430881505,
|
| 24 |
+
"learning_rate": 4.782797567332754e-05,
|
| 25 |
+
"loss": 3.26605712890625,
|
| 26 |
+
"step": 3000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.1737600590784201,
|
| 30 |
+
"learning_rate": 4.7103967564436726e-05,
|
| 31 |
+
"loss": 3.197267333984375,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.21720007384802512,
|
| 36 |
+
"learning_rate": 4.63799594555459e-05,
|
| 37 |
+
"loss": 3.14855224609375,
|
| 38 |
+
"step": 5000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.21720007384802512,
|
| 42 |
+
"eval_loss": 3.0360004901885986,
|
| 43 |
+
"step": 5000
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.2606400886176301,
|
| 47 |
+
"learning_rate": 4.565595134665508e-05,
|
| 48 |
+
"loss": 3.114377685546875,
|
| 49 |
+
"step": 6000
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.3040801033872352,
|
| 53 |
+
"learning_rate": 4.493194323776426e-05,
|
| 54 |
+
"loss": 3.08016552734375,
|
| 55 |
+
"step": 7000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.3475201181568402,
|
| 59 |
+
"learning_rate": 4.4207935128873444e-05,
|
| 60 |
+
"loss": 3.05526904296875,
|
| 61 |
+
"step": 8000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.3909601329264452,
|
| 65 |
+
"learning_rate": 4.3483927019982625e-05,
|
| 66 |
+
"loss": 3.033037353515625,
|
| 67 |
+
"step": 9000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.43440014769605023,
|
| 71 |
+
"learning_rate": 4.2759918911091806e-05,
|
| 72 |
+
"loss": 3.012407958984375,
|
| 73 |
+
"step": 10000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.43440014769605023,
|
| 77 |
+
"eval_loss": 2.9199917316436768,
|
| 78 |
+
"step": 10000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.47784016246565525,
|
| 82 |
+
"learning_rate": 4.203591080220099e-05,
|
| 83 |
+
"loss": 2.992706298828125,
|
| 84 |
+
"step": 11000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.5212801772352602,
|
| 88 |
+
"learning_rate": 4.131190269331017e-05,
|
| 89 |
+
"loss": 2.975831298828125,
|
| 90 |
+
"step": 12000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.5647201920048652,
|
| 94 |
+
"learning_rate": 4.058789458441934e-05,
|
| 95 |
+
"loss": 2.96051806640625,
|
| 96 |
+
"step": 13000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.6081602067744704,
|
| 100 |
+
"learning_rate": 3.986388647552853e-05,
|
| 101 |
+
"loss": 2.9437431640625,
|
| 102 |
+
"step": 14000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.6516002215440754,
|
| 106 |
+
"learning_rate": 3.9139878366637704e-05,
|
| 107 |
+
"loss": 2.9307431640625,
|
| 108 |
+
"step": 15000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6516002215440754,
|
| 112 |
+
"eval_loss": 2.8523595333099365,
|
| 113 |
+
"step": 15000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.6950402363136804,
|
| 117 |
+
"learning_rate": 3.841587025774689e-05,
|
| 118 |
+
"loss": 2.916943359375,
|
| 119 |
+
"step": 16000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.7384802510832854,
|
| 123 |
+
"learning_rate": 3.7691862148856066e-05,
|
| 124 |
+
"loss": 2.905533447265625,
|
| 125 |
+
"step": 17000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.7819202658528904,
|
| 129 |
+
"learning_rate": 3.696785403996525e-05,
|
| 130 |
+
"loss": 2.892618896484375,
|
| 131 |
+
"step": 18000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.8253602806224954,
|
| 135 |
+
"learning_rate": 3.624384593107443e-05,
|
| 136 |
+
"loss": 2.885263671875,
|
| 137 |
+
"step": 19000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.8688002953921005,
|
| 141 |
+
"learning_rate": 3.551983782218361e-05,
|
| 142 |
+
"loss": 2.873368896484375,
|
| 143 |
+
"step": 20000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.8688002953921005,
|
| 147 |
+
"eval_loss": 2.808135986328125,
|
| 148 |
+
"step": 20000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.9122403101617055,
|
| 152 |
+
"learning_rate": 3.479582971329279e-05,
|
| 153 |
+
"loss": 2.860178955078125,
|
| 154 |
+
"step": 21000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.9556803249313105,
|
| 158 |
+
"learning_rate": 3.407182160440197e-05,
|
| 159 |
+
"loss": 2.853407958984375,
|
| 160 |
+
"step": 22000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.9991203397009155,
|
| 164 |
+
"learning_rate": 3.334781349551115e-05,
|
| 165 |
+
"loss": 2.846532470703125,
|
| 166 |
+
"step": 23000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.042571214474213,
|
| 170 |
+
"learning_rate": 3.262380538662033e-05,
|
| 171 |
+
"loss": 2.816125244140625,
|
| 172 |
+
"step": 24000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.086011229243818,
|
| 176 |
+
"learning_rate": 3.189979727772951e-05,
|
| 177 |
+
"loss": 2.8096533203125,
|
| 178 |
+
"step": 25000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.086011229243818,
|
| 182 |
+
"eval_loss": 2.7750799655914307,
|
| 183 |
+
"step": 25000
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.129451244013423,
|
| 187 |
+
"learning_rate": 3.1175789168838695e-05,
|
| 188 |
+
"loss": 2.803942626953125,
|
| 189 |
+
"step": 26000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 1.172891258783028,
|
| 193 |
+
"learning_rate": 3.045178105994787e-05,
|
| 194 |
+
"loss": 2.798123046875,
|
| 195 |
+
"step": 27000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 1.216331273552633,
|
| 199 |
+
"learning_rate": 2.9727772951057054e-05,
|
| 200 |
+
"loss": 2.79141748046875,
|
| 201 |
+
"step": 28000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.259771288322238,
|
| 205 |
+
"learning_rate": 2.900376484216623e-05,
|
| 206 |
+
"loss": 2.784273193359375,
|
| 207 |
+
"step": 29000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.303211303091843,
|
| 211 |
+
"learning_rate": 2.8279756733275416e-05,
|
| 212 |
+
"loss": 2.777781494140625,
|
| 213 |
+
"step": 30000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.303211303091843,
|
| 217 |
+
"eval_loss": 2.746640205383301,
|
| 218 |
+
"step": 30000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.346651317861448,
|
| 222 |
+
"learning_rate": 2.7555748624384593e-05,
|
| 223 |
+
"loss": 2.774093994140625,
|
| 224 |
+
"step": 31000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.3900913326310531,
|
| 228 |
+
"learning_rate": 2.6831740515493774e-05,
|
| 229 |
+
"loss": 2.765812744140625,
|
| 230 |
+
"step": 32000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.4335313474006581,
|
| 234 |
+
"learning_rate": 2.6107732406602952e-05,
|
| 235 |
+
"loss": 2.763001708984375,
|
| 236 |
+
"step": 33000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.4769713621702631,
|
| 240 |
+
"learning_rate": 2.5383724297712136e-05,
|
| 241 |
+
"loss": 2.756827880859375,
|
| 242 |
+
"step": 34000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.5204113769398682,
|
| 246 |
+
"learning_rate": 2.4659716188821317e-05,
|
| 247 |
+
"loss": 2.753128173828125,
|
| 248 |
+
"step": 35000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.5204113769398682,
|
| 252 |
+
"eval_loss": 2.725342035293579,
|
| 253 |
+
"step": 35000
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 1.5638513917094732,
|
| 257 |
+
"learning_rate": 2.3935708079930498e-05,
|
| 258 |
+
"loss": 2.7459052734375,
|
| 259 |
+
"step": 36000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.6072914064790782,
|
| 263 |
+
"learning_rate": 2.3211699971039676e-05,
|
| 264 |
+
"loss": 2.738887451171875,
|
| 265 |
+
"step": 37000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 1.6507314212486832,
|
| 269 |
+
"learning_rate": 2.2487691862148857e-05,
|
| 270 |
+
"loss": 2.738287109375,
|
| 271 |
+
"step": 38000
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.6941714360182882,
|
| 275 |
+
"learning_rate": 2.1763683753258038e-05,
|
| 276 |
+
"loss": 2.731450439453125,
|
| 277 |
+
"step": 39000
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.7376114507878933,
|
| 281 |
+
"learning_rate": 2.103967564436722e-05,
|
| 282 |
+
"loss": 2.726150390625,
|
| 283 |
+
"step": 40000
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.7376114507878933,
|
| 287 |
+
"eval_loss": 2.706486225128174,
|
| 288 |
+
"step": 40000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.7810514655574983,
|
| 292 |
+
"learning_rate": 2.03156675354764e-05,
|
| 293 |
+
"loss": 2.72658447265625,
|
| 294 |
+
"step": 41000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.8244914803271033,
|
| 298 |
+
"learning_rate": 1.9591659426585578e-05,
|
| 299 |
+
"loss": 2.723203125,
|
| 300 |
+
"step": 42000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.8679314950967083,
|
| 304 |
+
"learning_rate": 1.886765131769476e-05,
|
| 305 |
+
"loss": 2.715607177734375,
|
| 306 |
+
"step": 43000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.9113715098663133,
|
| 310 |
+
"learning_rate": 1.814364320880394e-05,
|
| 311 |
+
"loss": 2.7112373046875,
|
| 312 |
+
"step": 44000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.9548115246359183,
|
| 316 |
+
"learning_rate": 1.741963509991312e-05,
|
| 317 |
+
"loss": 2.7094580078125,
|
| 318 |
+
"step": 45000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.9548115246359183,
|
| 322 |
+
"eval_loss": 2.690136432647705,
|
| 323 |
+
"step": 45000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.9982515394055234,
|
| 327 |
+
"learning_rate": 1.66956269910223e-05,
|
| 328 |
+
"loss": 2.70530859375,
|
| 329 |
+
"step": 46000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.041702414178821,
|
| 333 |
+
"learning_rate": 1.5971618882131483e-05,
|
| 334 |
+
"loss": 2.68336376953125,
|
| 335 |
+
"step": 47000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.085142428948426,
|
| 339 |
+
"learning_rate": 1.5247610773240662e-05,
|
| 340 |
+
"loss": 2.68182470703125,
|
| 341 |
+
"step": 48000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.128582443718031,
|
| 345 |
+
"learning_rate": 1.4523602664349841e-05,
|
| 346 |
+
"loss": 2.67953466796875,
|
| 347 |
+
"step": 49000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 2.172022458487636,
|
| 351 |
+
"learning_rate": 1.3799594555459022e-05,
|
| 352 |
+
"loss": 2.67869482421875,
|
| 353 |
+
"step": 50000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 2.172022458487636,
|
| 357 |
+
"eval_loss": 2.679882287979126,
|
| 358 |
+
"step": 50000
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 2.215462473257241,
|
| 362 |
+
"learning_rate": 1.3075586446568203e-05,
|
| 363 |
+
"loss": 2.67307861328125,
|
| 364 |
+
"step": 51000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 2.258902488026846,
|
| 368 |
+
"learning_rate": 1.2351578337677383e-05,
|
| 369 |
+
"loss": 2.6713193359375,
|
| 370 |
+
"step": 52000
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.302342502796451,
|
| 374 |
+
"learning_rate": 1.1627570228786564e-05,
|
| 375 |
+
"loss": 2.666735107421875,
|
| 376 |
+
"step": 53000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.345782517566056,
|
| 380 |
+
"learning_rate": 1.0903562119895745e-05,
|
| 381 |
+
"loss": 2.665475341796875,
|
| 382 |
+
"step": 54000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.389222532335661,
|
| 386 |
+
"learning_rate": 1.0179554011004924e-05,
|
| 387 |
+
"loss": 2.665841796875,
|
| 388 |
+
"step": 55000
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.389222532335661,
|
| 392 |
+
"eval_loss": 2.66998553276062,
|
| 393 |
+
"step": 55000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.432662547105266,
|
| 397 |
+
"learning_rate": 9.455545902114105e-06,
|
| 398 |
+
"loss": 2.66330908203125,
|
| 399 |
+
"step": 56000
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.476102561874871,
|
| 403 |
+
"learning_rate": 8.731537793223284e-06,
|
| 404 |
+
"loss": 2.66229638671875,
|
| 405 |
+
"step": 57000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.519542576644476,
|
| 409 |
+
"learning_rate": 8.007529684332465e-06,
|
| 410 |
+
"loss": 2.65796484375,
|
| 411 |
+
"step": 58000
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.562982591414081,
|
| 415 |
+
"learning_rate": 7.283521575441646e-06,
|
| 416 |
+
"loss": 2.657759033203125,
|
| 417 |
+
"step": 59000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.606422606183686,
|
| 421 |
+
"learning_rate": 6.559513466550826e-06,
|
| 422 |
+
"loss": 2.65596875,
|
| 423 |
+
"step": 60000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.606422606183686,
|
| 427 |
+
"eval_loss": 2.6612513065338135,
|
| 428 |
+
"step": 60000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.649862620953291,
|
| 432 |
+
"learning_rate": 5.835505357660006e-06,
|
| 433 |
+
"loss": 2.656216064453125,
|
| 434 |
+
"step": 61000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.693302635722896,
|
| 438 |
+
"learning_rate": 5.111497248769187e-06,
|
| 439 |
+
"loss": 2.654870361328125,
|
| 440 |
+
"step": 62000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 2.736742650492501,
|
| 444 |
+
"learning_rate": 4.387489139878367e-06,
|
| 445 |
+
"loss": 2.653074951171875,
|
| 446 |
+
"step": 63000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 2.7801826652621062,
|
| 450 |
+
"learning_rate": 3.663481030987547e-06,
|
| 451 |
+
"loss": 2.64907958984375,
|
| 452 |
+
"step": 64000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.8236226800317112,
|
| 456 |
+
"learning_rate": 2.9394729220967276e-06,
|
| 457 |
+
"loss": 2.650592529296875,
|
| 458 |
+
"step": 65000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.8236226800317112,
|
| 462 |
+
"eval_loss": 2.655712127685547,
|
| 463 |
+
"step": 65000
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 2.8670626948013163,
|
| 467 |
+
"learning_rate": 2.2154648132059077e-06,
|
| 468 |
+
"loss": 2.651447998046875,
|
| 469 |
+
"step": 66000
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 2.9105027095709213,
|
| 473 |
+
"learning_rate": 1.4914567043150885e-06,
|
| 474 |
+
"loss": 2.647968994140625,
|
| 475 |
+
"step": 67000
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 2.9539427243405263,
|
| 479 |
+
"learning_rate": 7.674485954242688e-07,
|
| 480 |
+
"loss": 2.647386962890625,
|
| 481 |
+
"step": 68000
|
| 482 |
+
}
|
| 483 |
+
],
|
| 484 |
+
"max_steps": 69060,
|
| 485 |
+
"num_train_epochs": 3,
|
| 486 |
+
"total_flos": 4353523817019612480,
|
| 487 |
+
"trial_name": null,
|
| 488 |
+
"trial_params": null
|
| 489 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfd7b0f18e3fd3ba9df5e591c4a83b55f49e1eb8675880dcc38ad465bf0647a5
|
| 3 |
+
size 1816
|