Gaetano-Rossiello
commited on
Commit
•
791cd25
1
Parent(s):
680ec5d
GenRL SimpleQuestions model upload
Browse files- all_results.json +15 -0
- config.json +72 -0
- eval_results.json +12 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +6 -0
- trainer_state.json +599 -0
- training_args.bin +3 -0
- vocab.json +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gen_len": 14.568,
|
| 4 |
+
"eval_loss": 0.3667319715023041,
|
| 5 |
+
"eval_rouge1": 99.1838,
|
| 6 |
+
"eval_rouge2": 98.7426,
|
| 7 |
+
"eval_rougeL": 99.1798,
|
| 8 |
+
"eval_rougeLsum": 99.1824,
|
| 9 |
+
"eval_runtime": 460.8704,
|
| 10 |
+
"eval_samples": 5606,
|
| 11 |
+
"eval_samples_per_second": 12.164,
|
| 12 |
+
"train_runtime": 28299.6455,
|
| 13 |
+
"train_samples": 19235,
|
| 14 |
+
"train_samples_per_second": 1.699
|
| 15 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-large",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 1024,
|
| 15 |
+
"decoder_attention_heads": 16,
|
| 16 |
+
"decoder_ffn_dim": 4096,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 12,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 16,
|
| 23 |
+
"encoder_ffn_dim": 4096,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 12,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": 3,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"num_beams": 4,
|
| 46 |
+
"num_hidden_layers": 12,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"scale_embedding": false,
|
| 49 |
+
"task_specific_params": {
|
| 50 |
+
"summarization": {
|
| 51 |
+
"length_penalty": 1.0,
|
| 52 |
+
"max_length": 128,
|
| 53 |
+
"min_length": 12,
|
| 54 |
+
"num_beams": 4
|
| 55 |
+
},
|
| 56 |
+
"summarization_cnn": {
|
| 57 |
+
"length_penalty": 2.0,
|
| 58 |
+
"max_length": 142,
|
| 59 |
+
"min_length": 56,
|
| 60 |
+
"num_beams": 4
|
| 61 |
+
},
|
| 62 |
+
"summarization_xsum": {
|
| 63 |
+
"length_penalty": 1.0,
|
| 64 |
+
"max_length": 62,
|
| 65 |
+
"min_length": 11,
|
| 66 |
+
"num_beams": 6
|
| 67 |
+
}
|
| 68 |
+
},
|
| 69 |
+
"transformers_version": "4.5.0.dev0",
|
| 70 |
+
"use_cache": true,
|
| 71 |
+
"vocab_size": 50265
|
| 72 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_gen_len": 14.568,
|
| 4 |
+
"eval_loss": 0.3667319715023041,
|
| 5 |
+
"eval_rouge1": 99.1838,
|
| 6 |
+
"eval_rouge2": 98.7426,
|
| 7 |
+
"eval_rougeL": 99.1798,
|
| 8 |
+
"eval_rougeLsum": 99.1824,
|
| 9 |
+
"eval_runtime": 460.8704,
|
| 10 |
+
"eval_samples": 5606,
|
| 11 |
+
"eval_samples_per_second": 12.164
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04b2e25d9d97cada0fcc61af9397e8fb7dc2eb7cc50982ed08a6d12578988dce
|
| 3 |
+
size 1625569391
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large"}
|
train_results.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"train_runtime": 28299.6455,
|
| 4 |
+
"train_samples": 19235,
|
| 5 |
+
"train_samples_per_second": 1.699
|
| 6 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,599 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"global_step": 48090,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 4.948014140153878e-05,
|
| 13 |
+
"loss": 0.7397,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 4.8960282803077565e-05,
|
| 19 |
+
"loss": 0.2767,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.31,
|
| 24 |
+
"learning_rate": 4.844042420461635e-05,
|
| 25 |
+
"loss": 0.4767,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.42,
|
| 30 |
+
"learning_rate": 4.792056560615513e-05,
|
| 31 |
+
"loss": 0.4352,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.52,
|
| 36 |
+
"learning_rate": 4.740070700769391e-05,
|
| 37 |
+
"loss": 0.6092,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.62,
|
| 42 |
+
"learning_rate": 4.688084840923269e-05,
|
| 43 |
+
"loss": 0.1961,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.73,
|
| 48 |
+
"learning_rate": 4.636098981077147e-05,
|
| 49 |
+
"loss": 0.2384,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.83,
|
| 54 |
+
"learning_rate": 4.5841131212310254e-05,
|
| 55 |
+
"loss": 0.2925,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.94,
|
| 60 |
+
"learning_rate": 4.532127261384904e-05,
|
| 61 |
+
"loss": 0.1461,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.04,
|
| 66 |
+
"learning_rate": 4.4801414015387816e-05,
|
| 67 |
+
"loss": 0.1366,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.14,
|
| 72 |
+
"learning_rate": 4.4281555416926594e-05,
|
| 73 |
+
"loss": 0.0943,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.25,
|
| 78 |
+
"learning_rate": 4.376169681846538e-05,
|
| 79 |
+
"loss": 0.098,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.35,
|
| 84 |
+
"learning_rate": 4.324183822000416e-05,
|
| 85 |
+
"loss": 0.2768,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.46,
|
| 90 |
+
"learning_rate": 4.272197962154294e-05,
|
| 91 |
+
"loss": 0.1589,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.56,
|
| 96 |
+
"learning_rate": 4.220212102308173e-05,
|
| 97 |
+
"loss": 0.2075,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.66,
|
| 102 |
+
"learning_rate": 4.1682262424620505e-05,
|
| 103 |
+
"loss": 0.1032,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.77,
|
| 108 |
+
"learning_rate": 4.116240382615928e-05,
|
| 109 |
+
"loss": 0.092,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.87,
|
| 114 |
+
"learning_rate": 4.064254522769807e-05,
|
| 115 |
+
"loss": 0.0877,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.98,
|
| 120 |
+
"learning_rate": 4.012268662923685e-05,
|
| 121 |
+
"loss": 0.1081,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.08,
|
| 126 |
+
"learning_rate": 3.960282803077563e-05,
|
| 127 |
+
"loss": 0.0561,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.18,
|
| 132 |
+
"learning_rate": 3.9082969432314415e-05,
|
| 133 |
+
"loss": 0.0463,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 2.29,
|
| 138 |
+
"learning_rate": 3.856311083385319e-05,
|
| 139 |
+
"loss": 0.0453,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.39,
|
| 144 |
+
"learning_rate": 3.804325223539197e-05,
|
| 145 |
+
"loss": 0.0466,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.5,
|
| 150 |
+
"learning_rate": 3.7523393636930756e-05,
|
| 151 |
+
"loss": 0.0484,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.6,
|
| 156 |
+
"learning_rate": 3.700353503846954e-05,
|
| 157 |
+
"loss": 0.0442,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.7,
|
| 162 |
+
"learning_rate": 3.648367644000832e-05,
|
| 163 |
+
"loss": 0.1853,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.81,
|
| 168 |
+
"learning_rate": 3.59638178415471e-05,
|
| 169 |
+
"loss": 0.0908,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.91,
|
| 174 |
+
"learning_rate": 3.544395924308588e-05,
|
| 175 |
+
"loss": 0.0353,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 3.02,
|
| 180 |
+
"learning_rate": 3.4924100644624667e-05,
|
| 181 |
+
"loss": 0.0333,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 3.12,
|
| 186 |
+
"learning_rate": 3.4404242046163445e-05,
|
| 187 |
+
"loss": 0.0379,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 3.22,
|
| 192 |
+
"learning_rate": 3.388438344770223e-05,
|
| 193 |
+
"loss": 0.0439,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 3.33,
|
| 198 |
+
"learning_rate": 3.336452484924101e-05,
|
| 199 |
+
"loss": 0.0419,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 3.43,
|
| 204 |
+
"learning_rate": 3.2844666250779785e-05,
|
| 205 |
+
"loss": 0.0355,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.54,
|
| 210 |
+
"learning_rate": 3.232480765231857e-05,
|
| 211 |
+
"loss": 0.0368,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 3.64,
|
| 216 |
+
"learning_rate": 3.1804949053857355e-05,
|
| 217 |
+
"loss": 0.0336,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 3.74,
|
| 222 |
+
"learning_rate": 3.128509045539613e-05,
|
| 223 |
+
"loss": 0.176,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 3.85,
|
| 228 |
+
"learning_rate": 3.076523185693492e-05,
|
| 229 |
+
"loss": 0.2009,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 3.95,
|
| 234 |
+
"learning_rate": 3.0245373258473696e-05,
|
| 235 |
+
"loss": 0.1369,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 4.05,
|
| 240 |
+
"learning_rate": 2.9725514660012477e-05,
|
| 241 |
+
"loss": 0.1509,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 4.16,
|
| 246 |
+
"learning_rate": 2.9205656061551262e-05,
|
| 247 |
+
"loss": 0.1126,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 4.26,
|
| 252 |
+
"learning_rate": 2.868579746309004e-05,
|
| 253 |
+
"loss": 0.0878,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 4.37,
|
| 258 |
+
"learning_rate": 2.816593886462882e-05,
|
| 259 |
+
"loss": 0.0961,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.47,
|
| 264 |
+
"learning_rate": 2.76460802661676e-05,
|
| 265 |
+
"loss": 0.1387,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 4.57,
|
| 270 |
+
"learning_rate": 2.7126221667706388e-05,
|
| 271 |
+
"loss": 0.0979,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 4.68,
|
| 276 |
+
"learning_rate": 2.6606363069245166e-05,
|
| 277 |
+
"loss": 0.0647,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.78,
|
| 282 |
+
"learning_rate": 2.6086504470783947e-05,
|
| 283 |
+
"loss": 0.05,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 4.89,
|
| 288 |
+
"learning_rate": 2.5566645872322732e-05,
|
| 289 |
+
"loss": 0.0221,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 4.99,
|
| 294 |
+
"learning_rate": 2.504678727386151e-05,
|
| 295 |
+
"loss": 0.0252,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 5.09,
|
| 300 |
+
"learning_rate": 2.452692867540029e-05,
|
| 301 |
+
"loss": 0.0245,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 5.2,
|
| 306 |
+
"learning_rate": 2.4007070076939073e-05,
|
| 307 |
+
"loss": 0.0195,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 5.3,
|
| 312 |
+
"learning_rate": 2.3487211478477854e-05,
|
| 313 |
+
"loss": 0.023,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.41,
|
| 318 |
+
"learning_rate": 2.296735288001664e-05,
|
| 319 |
+
"loss": 0.0204,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 5.51,
|
| 324 |
+
"learning_rate": 2.2447494281555417e-05,
|
| 325 |
+
"loss": 0.0789,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 5.61,
|
| 330 |
+
"learning_rate": 2.19276356830942e-05,
|
| 331 |
+
"loss": 0.056,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 5.72,
|
| 336 |
+
"learning_rate": 2.140777708463298e-05,
|
| 337 |
+
"loss": 0.0301,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 5.82,
|
| 342 |
+
"learning_rate": 2.088791848617176e-05,
|
| 343 |
+
"loss": 0.0439,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 5.93,
|
| 348 |
+
"learning_rate": 2.0368059887710546e-05,
|
| 349 |
+
"loss": 0.0254,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.03,
|
| 354 |
+
"learning_rate": 1.9848201289249324e-05,
|
| 355 |
+
"loss": 0.0132,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.13,
|
| 360 |
+
"learning_rate": 1.9328342690788105e-05,
|
| 361 |
+
"loss": 0.019,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.24,
|
| 366 |
+
"learning_rate": 1.880848409232689e-05,
|
| 367 |
+
"loss": 0.0187,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.34,
|
| 372 |
+
"learning_rate": 1.8288625493865668e-05,
|
| 373 |
+
"loss": 0.0196,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.45,
|
| 378 |
+
"learning_rate": 1.776876689540445e-05,
|
| 379 |
+
"loss": 0.062,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 6.55,
|
| 384 |
+
"learning_rate": 1.7248908296943234e-05,
|
| 385 |
+
"loss": 0.0454,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 6.65,
|
| 390 |
+
"learning_rate": 1.6729049698482012e-05,
|
| 391 |
+
"loss": 0.0153,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 6.76,
|
| 396 |
+
"learning_rate": 1.6209191100020797e-05,
|
| 397 |
+
"loss": 0.0133,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 6.86,
|
| 402 |
+
"learning_rate": 1.5689332501559575e-05,
|
| 403 |
+
"loss": 0.0158,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 6.97,
|
| 408 |
+
"learning_rate": 1.5169473903098358e-05,
|
| 409 |
+
"loss": 0.0143,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 7.07,
|
| 414 |
+
"learning_rate": 1.464961530463714e-05,
|
| 415 |
+
"loss": 0.0196,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 7.17,
|
| 420 |
+
"learning_rate": 1.412975670617592e-05,
|
| 421 |
+
"loss": 0.01,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 7.28,
|
| 426 |
+
"learning_rate": 1.3609898107714703e-05,
|
| 427 |
+
"loss": 0.0089,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 7.38,
|
| 432 |
+
"learning_rate": 1.3090039509253486e-05,
|
| 433 |
+
"loss": 0.0106,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 7.49,
|
| 438 |
+
"learning_rate": 1.2570180910792265e-05,
|
| 439 |
+
"loss": 0.0093,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 7.59,
|
| 444 |
+
"learning_rate": 1.2050322312331047e-05,
|
| 445 |
+
"loss": 0.0082,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 7.69,
|
| 450 |
+
"learning_rate": 1.1530463713869828e-05,
|
| 451 |
+
"loss": 0.0112,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 7.8,
|
| 456 |
+
"learning_rate": 1.101060511540861e-05,
|
| 457 |
+
"loss": 0.0132,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 7.9,
|
| 462 |
+
"learning_rate": 1.0490746516947391e-05,
|
| 463 |
+
"loss": 0.0092,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 8.01,
|
| 468 |
+
"learning_rate": 9.970887918486172e-06,
|
| 469 |
+
"loss": 0.0109,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 8.11,
|
| 474 |
+
"learning_rate": 9.451029320024954e-06,
|
| 475 |
+
"loss": 0.0083,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 8.21,
|
| 480 |
+
"learning_rate": 8.931170721563735e-06,
|
| 481 |
+
"loss": 0.0049,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 8.32,
|
| 486 |
+
"learning_rate": 8.411312123102517e-06,
|
| 487 |
+
"loss": 0.0076,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 8.42,
|
| 492 |
+
"learning_rate": 7.891453524641298e-06,
|
| 493 |
+
"loss": 0.0054,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 8.53,
|
| 498 |
+
"learning_rate": 7.3715949261800795e-06,
|
| 499 |
+
"loss": 0.0033,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 8.63,
|
| 504 |
+
"learning_rate": 6.851736327718861e-06,
|
| 505 |
+
"loss": 0.0051,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 8.73,
|
| 510 |
+
"learning_rate": 6.3318777292576415e-06,
|
| 511 |
+
"loss": 0.0057,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 8.84,
|
| 516 |
+
"learning_rate": 5.812019130796424e-06,
|
| 517 |
+
"loss": 0.008,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.94,
|
| 522 |
+
"learning_rate": 5.292160532335205e-06,
|
| 523 |
+
"loss": 0.005,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 9.05,
|
| 528 |
+
"learning_rate": 4.7723019338739865e-06,
|
| 529 |
+
"loss": 0.0058,
|
| 530 |
+
"step": 43500
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 9.15,
|
| 534 |
+
"learning_rate": 4.252443335412768e-06,
|
| 535 |
+
"loss": 0.0042,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 9.25,
|
| 540 |
+
"learning_rate": 3.7325847369515494e-06,
|
| 541 |
+
"loss": 0.0034,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 9.36,
|
| 546 |
+
"learning_rate": 3.2127261384903308e-06,
|
| 547 |
+
"loss": 0.0029,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 9.46,
|
| 552 |
+
"learning_rate": 2.692867540029112e-06,
|
| 553 |
+
"loss": 0.0036,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 9.57,
|
| 558 |
+
"learning_rate": 2.1730089415678936e-06,
|
| 559 |
+
"loss": 0.0034,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 9.67,
|
| 564 |
+
"learning_rate": 1.6531503431066752e-06,
|
| 565 |
+
"loss": 0.0021,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 9.77,
|
| 570 |
+
"learning_rate": 1.1332917446454564e-06,
|
| 571 |
+
"loss": 0.0039,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 9.88,
|
| 576 |
+
"learning_rate": 6.134331461842379e-07,
|
| 577 |
+
"loss": 0.0033,
|
| 578 |
+
"step": 47500
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 9.98,
|
| 582 |
+
"learning_rate": 9.357454772301934e-08,
|
| 583 |
+
"loss": 0.0068,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 10.0,
|
| 588 |
+
"step": 48090,
|
| 589 |
+
"total_flos": 1.579934745091154e+17,
|
| 590 |
+
"train_runtime": 28299.6455,
|
| 591 |
+
"train_samples_per_second": 1.699
|
| 592 |
+
}
|
| 593 |
+
],
|
| 594 |
+
"max_steps": 48090,
|
| 595 |
+
"num_train_epochs": 10,
|
| 596 |
+
"total_flos": 1.579934745091154e+17,
|
| 597 |
+
"trial_name": null,
|
| 598 |
+
"trial_params": null
|
| 599 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4aa59bf7e322008b43f08ff148a2439c76c1d1183a7bc8cc92407fbf14246ed7
|
| 3 |
+
size 2415
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|