cnn_dm_no_bert
Browse files- config.json +75 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +15 -0
- tokenizer_config.json +15 -0
- trainer_state.json +386 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 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": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1",
|
| 33 |
+
"2": "LABEL_2"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"LABEL_0": 0,
|
| 39 |
+
"LABEL_1": 1,
|
| 40 |
+
"LABEL_2": 2
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"scale_embedding": false,
|
| 51 |
+
"task_specific_params": {
|
| 52 |
+
"summarization": {
|
| 53 |
+
"length_penalty": 1.0,
|
| 54 |
+
"max_length": 128,
|
| 55 |
+
"min_length": 12,
|
| 56 |
+
"num_beams": 4
|
| 57 |
+
},
|
| 58 |
+
"summarization_cnn": {
|
| 59 |
+
"length_penalty": 2.0,
|
| 60 |
+
"max_length": 142,
|
| 61 |
+
"min_length": 56,
|
| 62 |
+
"num_beams": 4
|
| 63 |
+
},
|
| 64 |
+
"summarization_xsum": {
|
| 65 |
+
"length_penalty": 1.0,
|
| 66 |
+
"max_length": 62,
|
| 67 |
+
"min_length": 11,
|
| 68 |
+
"num_beams": 6
|
| 69 |
+
}
|
| 70 |
+
},
|
| 71 |
+
"torch_dtype": "float32",
|
| 72 |
+
"transformers_version": "4.30.2",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 0,
|
| 3 |
+
"decoder_start_token_id": 2,
|
| 4 |
+
"early_stopping": true,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_bos_token_id": 0,
|
| 7 |
+
"forced_eos_token_id": 2,
|
| 8 |
+
"no_repeat_ngram_size": 3,
|
| 9 |
+
"num_beams": 4,
|
| 10 |
+
"pad_token_id": 1,
|
| 11 |
+
"transformers_version": "4.30.2"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c71e7b3aba77dfceb4cd6b91f30597a809391c95c0b708d15381eabf970cdce
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d71eb6e059c29bd924de0b9b519ff7644305a63a8aa073593371f7afccbc7091
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"clean_up_tokenization_spaces": true,
|
| 5 |
+
"cls_token": "<s>",
|
| 6 |
+
"eos_token": "</s>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"mask_token": "<mask>",
|
| 9 |
+
"model_max_length": 1024,
|
| 10 |
+
"pad_token": "<pad>",
|
| 11 |
+
"sep_token": "</s>",
|
| 12 |
+
"tokenizer_class": "BartTokenizer",
|
| 13 |
+
"trim_offsets": true,
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,386 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5572582892170521,
|
| 5 |
+
"global_step": 20000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 2.9880000000000002e-05,
|
| 13 |
+
"loss": 3.9111,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 2.92364e-05,
|
| 19 |
+
"loss": 3.4153,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.04,
|
| 24 |
+
"learning_rate": 2.8471266666666666e-05,
|
| 25 |
+
"loss": 3.3455,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 2.77046e-05,
|
| 31 |
+
"loss": 3.2935,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.06,
|
| 36 |
+
"eval_gen_len": 19.9971,
|
| 37 |
+
"eval_loss": 3.037526845932007,
|
| 38 |
+
"eval_rouge1": 0.2976,
|
| 39 |
+
"eval_rouge2": 0.1725,
|
| 40 |
+
"eval_rougeL": 0.2506,
|
| 41 |
+
"eval_rougeLsum": 0.2826,
|
| 42 |
+
"eval_runtime": 932.4818,
|
| 43 |
+
"eval_samples_per_second": 14.336,
|
| 44 |
+
"eval_steps_per_second": 1.792,
|
| 45 |
+
"step": 2000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.07,
|
| 49 |
+
"learning_rate": 2.6937933333333335e-05,
|
| 50 |
+
"loss": 3.2757,
|
| 51 |
+
"step": 2500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.08,
|
| 55 |
+
"learning_rate": 2.6171266666666668e-05,
|
| 56 |
+
"loss": 3.2389,
|
| 57 |
+
"step": 3000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.1,
|
| 61 |
+
"learning_rate": 2.54046e-05,
|
| 62 |
+
"loss": 3.2265,
|
| 63 |
+
"step": 3500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.11,
|
| 67 |
+
"learning_rate": 2.4637933333333333e-05,
|
| 68 |
+
"loss": 3.199,
|
| 69 |
+
"step": 4000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.11,
|
| 73 |
+
"eval_gen_len": 19.9952,
|
| 74 |
+
"eval_loss": 2.974107265472412,
|
| 75 |
+
"eval_rouge1": 0.2964,
|
| 76 |
+
"eval_rouge2": 0.1713,
|
| 77 |
+
"eval_rougeL": 0.2495,
|
| 78 |
+
"eval_rougeLsum": 0.2811,
|
| 79 |
+
"eval_runtime": 954.7338,
|
| 80 |
+
"eval_samples_per_second": 14.002,
|
| 81 |
+
"eval_steps_per_second": 1.75,
|
| 82 |
+
"step": 4000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.13,
|
| 86 |
+
"learning_rate": 2.3871266666666666e-05,
|
| 87 |
+
"loss": 3.2012,
|
| 88 |
+
"step": 4500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.14,
|
| 92 |
+
"learning_rate": 2.31046e-05,
|
| 93 |
+
"loss": 3.1897,
|
| 94 |
+
"step": 5000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.15,
|
| 98 |
+
"learning_rate": 2.2337933333333335e-05,
|
| 99 |
+
"loss": 3.1739,
|
| 100 |
+
"step": 5500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.17,
|
| 104 |
+
"learning_rate": 2.1571266666666668e-05,
|
| 105 |
+
"loss": 3.1519,
|
| 106 |
+
"step": 6000
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.17,
|
| 110 |
+
"eval_gen_len": 19.9981,
|
| 111 |
+
"eval_loss": 2.9583373069763184,
|
| 112 |
+
"eval_rouge1": 0.2952,
|
| 113 |
+
"eval_rouge2": 0.1704,
|
| 114 |
+
"eval_rougeL": 0.2484,
|
| 115 |
+
"eval_rougeLsum": 0.2803,
|
| 116 |
+
"eval_runtime": 950.337,
|
| 117 |
+
"eval_samples_per_second": 14.067,
|
| 118 |
+
"eval_steps_per_second": 1.758,
|
| 119 |
+
"step": 6000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.18,
|
| 123 |
+
"learning_rate": 2.08046e-05,
|
| 124 |
+
"loss": 3.13,
|
| 125 |
+
"step": 6500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.2,
|
| 129 |
+
"learning_rate": 2.0037933333333333e-05,
|
| 130 |
+
"loss": 3.139,
|
| 131 |
+
"step": 7000
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.21,
|
| 135 |
+
"learning_rate": 1.9271266666666666e-05,
|
| 136 |
+
"loss": 3.133,
|
| 137 |
+
"step": 7500
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.22,
|
| 141 |
+
"learning_rate": 1.8506133333333336e-05,
|
| 142 |
+
"loss": 3.1212,
|
| 143 |
+
"step": 8000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.22,
|
| 147 |
+
"eval_gen_len": 19.9968,
|
| 148 |
+
"eval_loss": 2.9247806072235107,
|
| 149 |
+
"eval_rouge1": 0.2968,
|
| 150 |
+
"eval_rouge2": 0.1723,
|
| 151 |
+
"eval_rougeL": 0.2499,
|
| 152 |
+
"eval_rougeLsum": 0.2817,
|
| 153 |
+
"eval_runtime": 945.3475,
|
| 154 |
+
"eval_samples_per_second": 14.141,
|
| 155 |
+
"eval_steps_per_second": 1.768,
|
| 156 |
+
"step": 8000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.24,
|
| 160 |
+
"learning_rate": 1.7739466666666665e-05,
|
| 161 |
+
"loss": 3.1198,
|
| 162 |
+
"step": 8500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.25,
|
| 166 |
+
"learning_rate": 1.6972799999999998e-05,
|
| 167 |
+
"loss": 3.1188,
|
| 168 |
+
"step": 9000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.26,
|
| 172 |
+
"learning_rate": 1.620613333333333e-05,
|
| 173 |
+
"loss": 3.0867,
|
| 174 |
+
"step": 9500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.28,
|
| 178 |
+
"learning_rate": 1.5439466666666667e-05,
|
| 179 |
+
"loss": 3.0878,
|
| 180 |
+
"step": 10000
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.28,
|
| 184 |
+
"eval_gen_len": 19.993,
|
| 185 |
+
"eval_loss": 2.902503252029419,
|
| 186 |
+
"eval_rouge1": 0.2979,
|
| 187 |
+
"eval_rouge2": 0.1741,
|
| 188 |
+
"eval_rougeL": 0.2513,
|
| 189 |
+
"eval_rougeLsum": 0.2833,
|
| 190 |
+
"eval_runtime": 940.9908,
|
| 191 |
+
"eval_samples_per_second": 14.206,
|
| 192 |
+
"eval_steps_per_second": 1.776,
|
| 193 |
+
"step": 10000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 0.29,
|
| 197 |
+
"learning_rate": 1.4674333333333335e-05,
|
| 198 |
+
"loss": 3.0868,
|
| 199 |
+
"step": 10500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.31,
|
| 203 |
+
"learning_rate": 1.3907666666666667e-05,
|
| 204 |
+
"loss": 3.0931,
|
| 205 |
+
"step": 11000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.32,
|
| 209 |
+
"learning_rate": 1.3141e-05,
|
| 210 |
+
"loss": 3.0737,
|
| 211 |
+
"step": 11500
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 0.33,
|
| 215 |
+
"learning_rate": 1.2374333333333336e-05,
|
| 216 |
+
"loss": 3.0811,
|
| 217 |
+
"step": 12000
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.33,
|
| 221 |
+
"eval_gen_len": 19.9961,
|
| 222 |
+
"eval_loss": 2.905233144760132,
|
| 223 |
+
"eval_rouge1": 0.2937,
|
| 224 |
+
"eval_rouge2": 0.1708,
|
| 225 |
+
"eval_rougeL": 0.2481,
|
| 226 |
+
"eval_rougeLsum": 0.279,
|
| 227 |
+
"eval_runtime": 940.0256,
|
| 228 |
+
"eval_samples_per_second": 14.221,
|
| 229 |
+
"eval_steps_per_second": 1.778,
|
| 230 |
+
"step": 12000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.35,
|
| 234 |
+
"learning_rate": 1.16092e-05,
|
| 235 |
+
"loss": 3.0607,
|
| 236 |
+
"step": 12500
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.36,
|
| 240 |
+
"learning_rate": 1.0842533333333333e-05,
|
| 241 |
+
"loss": 3.0761,
|
| 242 |
+
"step": 13000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.38,
|
| 246 |
+
"learning_rate": 1.0075866666666666e-05,
|
| 247 |
+
"loss": 3.0731,
|
| 248 |
+
"step": 13500
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.39,
|
| 252 |
+
"learning_rate": 9.309200000000002e-06,
|
| 253 |
+
"loss": 3.0606,
|
| 254 |
+
"step": 14000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.39,
|
| 258 |
+
"eval_gen_len": 19.996,
|
| 259 |
+
"eval_loss": 2.873690366744995,
|
| 260 |
+
"eval_rouge1": 0.2977,
|
| 261 |
+
"eval_rouge2": 0.1743,
|
| 262 |
+
"eval_rougeL": 0.2516,
|
| 263 |
+
"eval_rougeLsum": 0.2832,
|
| 264 |
+
"eval_runtime": 943.8325,
|
| 265 |
+
"eval_samples_per_second": 14.164,
|
| 266 |
+
"eval_steps_per_second": 1.77,
|
| 267 |
+
"step": 14000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.4,
|
| 271 |
+
"learning_rate": 8.544066666666668e-06,
|
| 272 |
+
"loss": 3.0655,
|
| 273 |
+
"step": 14500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.42,
|
| 277 |
+
"learning_rate": 7.777400000000001e-06,
|
| 278 |
+
"loss": 3.0538,
|
| 279 |
+
"step": 15000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.43,
|
| 283 |
+
"learning_rate": 7.010733333333332e-06,
|
| 284 |
+
"loss": 3.0404,
|
| 285 |
+
"step": 15500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.45,
|
| 289 |
+
"learning_rate": 6.244066666666668e-06,
|
| 290 |
+
"loss": 3.0549,
|
| 291 |
+
"step": 16000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.45,
|
| 295 |
+
"eval_gen_len": 19.9976,
|
| 296 |
+
"eval_loss": 2.8780670166015625,
|
| 297 |
+
"eval_rouge1": 0.2962,
|
| 298 |
+
"eval_rouge2": 0.1732,
|
| 299 |
+
"eval_rougeL": 0.2502,
|
| 300 |
+
"eval_rougeLsum": 0.2815,
|
| 301 |
+
"eval_runtime": 950.3131,
|
| 302 |
+
"eval_samples_per_second": 14.067,
|
| 303 |
+
"eval_steps_per_second": 1.758,
|
| 304 |
+
"step": 16000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.46,
|
| 308 |
+
"learning_rate": 5.477400000000001e-06,
|
| 309 |
+
"loss": 3.0445,
|
| 310 |
+
"step": 16500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.47,
|
| 314 |
+
"learning_rate": 4.710733333333334e-06,
|
| 315 |
+
"loss": 3.0493,
|
| 316 |
+
"step": 17000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.49,
|
| 320 |
+
"learning_rate": 3.944066666666667e-06,
|
| 321 |
+
"loss": 3.0537,
|
| 322 |
+
"step": 17500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.5,
|
| 326 |
+
"learning_rate": 3.1773999999999994e-06,
|
| 327 |
+
"loss": 3.0334,
|
| 328 |
+
"step": 18000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.5,
|
| 332 |
+
"eval_gen_len": 19.9954,
|
| 333 |
+
"eval_loss": 2.859384298324585,
|
| 334 |
+
"eval_rouge1": 0.2991,
|
| 335 |
+
"eval_rouge2": 0.1752,
|
| 336 |
+
"eval_rougeL": 0.2523,
|
| 337 |
+
"eval_rougeLsum": 0.2842,
|
| 338 |
+
"eval_runtime": 939.8429,
|
| 339 |
+
"eval_samples_per_second": 14.224,
|
| 340 |
+
"eval_steps_per_second": 1.778,
|
| 341 |
+
"step": 18000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 0.52,
|
| 345 |
+
"learning_rate": 2.4107333333333318e-06,
|
| 346 |
+
"loss": 3.0302,
|
| 347 |
+
"step": 18500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 0.53,
|
| 351 |
+
"learning_rate": 1.644066666666668e-06,
|
| 352 |
+
"loss": 3.0466,
|
| 353 |
+
"step": 19000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.54,
|
| 357 |
+
"learning_rate": 8.774000000000007e-07,
|
| 358 |
+
"loss": 3.023,
|
| 359 |
+
"step": 19500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.56,
|
| 363 |
+
"learning_rate": 1.1226666666666582e-07,
|
| 364 |
+
"loss": 3.0427,
|
| 365 |
+
"step": 20000
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 0.56,
|
| 369 |
+
"eval_gen_len": 19.9973,
|
| 370 |
+
"eval_loss": 2.85703706741333,
|
| 371 |
+
"eval_rouge1": 0.2988,
|
| 372 |
+
"eval_rouge2": 0.1757,
|
| 373 |
+
"eval_rougeL": 0.2526,
|
| 374 |
+
"eval_rougeLsum": 0.2841,
|
| 375 |
+
"eval_runtime": 945.8157,
|
| 376 |
+
"eval_samples_per_second": 14.134,
|
| 377 |
+
"eval_steps_per_second": 1.767,
|
| 378 |
+
"step": 20000
|
| 379 |
+
}
|
| 380 |
+
],
|
| 381 |
+
"max_steps": 20000,
|
| 382 |
+
"num_train_epochs": 1,
|
| 383 |
+
"total_flos": 9.711081075032064e+16,
|
| 384 |
+
"trial_name": null,
|
| 385 |
+
"trial_params": null
|
| 386 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a403513fec848e823f9b53422418d60238d5a9005f4215232c6717edc9e70b12
|
| 3 |
+
size 4027
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|