Upload 9 files
Browse files- all_results.json +14 -0
- config.json +75 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +351 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 2530385,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 19115,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 560977408,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 10661100,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 158574198,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1692417536,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 10976762368,
|
| 11 |
+
"train_runtime": 43960.8836,
|
| 12 |
+
"train_samples": 1104153,
|
| 13 |
+
"train_samples_per_second": 0.49
|
| 14 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "./exps/bart-base-chinese",
|
| 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": 101,
|
| 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": 102,
|
| 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": 102,
|
| 27 |
+
"forced_eos_token_id": 102,
|
| 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_length": 100,
|
| 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": 0,
|
| 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 |
+
"tokenizer_class": "BertTokenizer",
|
| 72 |
+
"transformers_version": "4.4.1",
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 51271
|
| 75 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7495d58964300f0aaea06081d8a5480a948d4b10b5c341d09259b5971667056c
|
| 3 |
+
size 561073657
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./exps/bart-base-chinese"}
|
train_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 2530385,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 19115,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 560977408,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 10661100,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 158574198,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1692417536,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 10976762368,
|
| 11 |
+
"train_runtime": 43960.8836,
|
| 12 |
+
"train_samples": 1104153,
|
| 13 |
+
"train_samples_per_second": 0.49
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,351 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.99965225454967,
|
| 5 |
+
"global_step": 21560,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.23,
|
| 12 |
+
"learning_rate": 2.9327458256029684e-06,
|
| 13 |
+
"loss": 2.8974,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.46,
|
| 18 |
+
"learning_rate": 2.865491651205937e-06,
|
| 19 |
+
"loss": 2.6495,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.7,
|
| 24 |
+
"learning_rate": 2.798237476808905e-06,
|
| 25 |
+
"loss": 2.5817,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.93,
|
| 30 |
+
"learning_rate": 2.730983302411874e-06,
|
| 31 |
+
"loss": 2.5431,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 1.0,
|
| 36 |
+
"eval_loss": 2.508946657180786,
|
| 37 |
+
"eval_runtime": 7.4005,
|
| 38 |
+
"eval_samples_per_second": 274.846,
|
| 39 |
+
"step": 2156
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.16,
|
| 43 |
+
"learning_rate": 2.6637291280148424e-06,
|
| 44 |
+
"loss": 2.5157,
|
| 45 |
+
"step": 2500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.39,
|
| 49 |
+
"learning_rate": 2.5964749536178107e-06,
|
| 50 |
+
"loss": 2.487,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.62,
|
| 55 |
+
"learning_rate": 2.529220779220779e-06,
|
| 56 |
+
"loss": 2.4657,
|
| 57 |
+
"step": 3500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.85,
|
| 61 |
+
"learning_rate": 2.461966604823748e-06,
|
| 62 |
+
"loss": 2.4489,
|
| 63 |
+
"step": 4000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.0,
|
| 67 |
+
"eval_loss": 2.421372413635254,
|
| 68 |
+
"eval_runtime": 7.4016,
|
| 69 |
+
"eval_samples_per_second": 274.805,
|
| 70 |
+
"step": 4312
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 2.09,
|
| 74 |
+
"learning_rate": 2.3947124304267163e-06,
|
| 75 |
+
"loss": 2.4348,
|
| 76 |
+
"step": 4500
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 2.32,
|
| 80 |
+
"learning_rate": 2.3274582560296846e-06,
|
| 81 |
+
"loss": 2.4173,
|
| 82 |
+
"step": 5000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 2.55,
|
| 86 |
+
"learning_rate": 2.2602040816326534e-06,
|
| 87 |
+
"loss": 2.4072,
|
| 88 |
+
"step": 5500
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 2.78,
|
| 92 |
+
"learning_rate": 2.192949907235622e-06,
|
| 93 |
+
"loss": 2.3947,
|
| 94 |
+
"step": 6000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 3.0,
|
| 98 |
+
"eval_loss": 2.36946177482605,
|
| 99 |
+
"eval_runtime": 7.3581,
|
| 100 |
+
"eval_samples_per_second": 276.432,
|
| 101 |
+
"step": 6468
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.01,
|
| 105 |
+
"learning_rate": 2.12569573283859e-06,
|
| 106 |
+
"loss": 2.3883,
|
| 107 |
+
"step": 6500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 3.25,
|
| 111 |
+
"learning_rate": 2.0584415584415585e-06,
|
| 112 |
+
"loss": 2.3753,
|
| 113 |
+
"step": 7000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 3.48,
|
| 117 |
+
"learning_rate": 1.991187384044527e-06,
|
| 118 |
+
"loss": 2.3672,
|
| 119 |
+
"step": 7500
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 3.71,
|
| 123 |
+
"learning_rate": 1.9239332096474953e-06,
|
| 124 |
+
"loss": 2.3598,
|
| 125 |
+
"step": 8000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 3.94,
|
| 129 |
+
"learning_rate": 1.8566790352504636e-06,
|
| 130 |
+
"loss": 2.3535,
|
| 131 |
+
"step": 8500
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 4.0,
|
| 135 |
+
"eval_loss": 2.3385844230651855,
|
| 136 |
+
"eval_runtime": 7.2305,
|
| 137 |
+
"eval_samples_per_second": 281.308,
|
| 138 |
+
"step": 8624
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 4.17,
|
| 142 |
+
"learning_rate": 1.789424860853432e-06,
|
| 143 |
+
"loss": 2.3509,
|
| 144 |
+
"step": 9000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 4.41,
|
| 148 |
+
"learning_rate": 1.7221706864564008e-06,
|
| 149 |
+
"loss": 2.3405,
|
| 150 |
+
"step": 9500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 4.64,
|
| 154 |
+
"learning_rate": 1.6549165120593692e-06,
|
| 155 |
+
"loss": 2.3338,
|
| 156 |
+
"step": 10000
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 4.87,
|
| 160 |
+
"learning_rate": 1.5876623376623378e-06,
|
| 161 |
+
"loss": 2.3324,
|
| 162 |
+
"step": 10500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 5.0,
|
| 166 |
+
"eval_loss": 2.3173904418945312,
|
| 167 |
+
"eval_runtime": 7.3244,
|
| 168 |
+
"eval_samples_per_second": 277.701,
|
| 169 |
+
"step": 10780
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 5.1,
|
| 173 |
+
"learning_rate": 1.5204081632653061e-06,
|
| 174 |
+
"loss": 2.3301,
|
| 175 |
+
"step": 11000
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.33,
|
| 179 |
+
"learning_rate": 1.4531539888682747e-06,
|
| 180 |
+
"loss": 2.3218,
|
| 181 |
+
"step": 11500
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.57,
|
| 185 |
+
"learning_rate": 1.385899814471243e-06,
|
| 186 |
+
"loss": 2.319,
|
| 187 |
+
"step": 12000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 5.8,
|
| 191 |
+
"learning_rate": 1.3186456400742119e-06,
|
| 192 |
+
"loss": 2.3136,
|
| 193 |
+
"step": 12500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 6.0,
|
| 197 |
+
"eval_loss": 2.3008077144622803,
|
| 198 |
+
"eval_runtime": 7.2793,
|
| 199 |
+
"eval_samples_per_second": 279.423,
|
| 200 |
+
"step": 12936
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 6.03,
|
| 204 |
+
"learning_rate": 1.2513914656771802e-06,
|
| 205 |
+
"loss": 2.3135,
|
| 206 |
+
"step": 13000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 6.26,
|
| 210 |
+
"learning_rate": 1.1841372912801486e-06,
|
| 211 |
+
"loss": 2.3073,
|
| 212 |
+
"step": 13500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 6.49,
|
| 216 |
+
"learning_rate": 1.116883116883117e-06,
|
| 217 |
+
"loss": 2.3051,
|
| 218 |
+
"step": 14000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 6.73,
|
| 222 |
+
"learning_rate": 1.0496289424860854e-06,
|
| 223 |
+
"loss": 2.3025,
|
| 224 |
+
"step": 14500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 6.96,
|
| 228 |
+
"learning_rate": 9.823747680890537e-07,
|
| 229 |
+
"loss": 2.2988,
|
| 230 |
+
"step": 15000
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 7.0,
|
| 234 |
+
"eval_loss": 2.290546178817749,
|
| 235 |
+
"eval_runtime": 7.6918,
|
| 236 |
+
"eval_samples_per_second": 264.438,
|
| 237 |
+
"step": 15092
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 7.19,
|
| 241 |
+
"learning_rate": 9.151205936920222e-07,
|
| 242 |
+
"loss": 2.3011,
|
| 243 |
+
"step": 15500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 7.42,
|
| 247 |
+
"learning_rate": 8.478664192949909e-07,
|
| 248 |
+
"loss": 2.2951,
|
| 249 |
+
"step": 16000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 7.65,
|
| 253 |
+
"learning_rate": 7.806122448979594e-07,
|
| 254 |
+
"loss": 2.2928,
|
| 255 |
+
"step": 16500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 7.88,
|
| 259 |
+
"learning_rate": 7.133580705009277e-07,
|
| 260 |
+
"loss": 2.292,
|
| 261 |
+
"step": 17000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.0,
|
| 265 |
+
"eval_loss": 2.2825968265533447,
|
| 266 |
+
"eval_runtime": 7.4803,
|
| 267 |
+
"eval_samples_per_second": 271.914,
|
| 268 |
+
"step": 17248
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 8.12,
|
| 272 |
+
"learning_rate": 6.461038961038962e-07,
|
| 273 |
+
"loss": 2.295,
|
| 274 |
+
"step": 17500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 8.35,
|
| 278 |
+
"learning_rate": 5.788497217068646e-07,
|
| 279 |
+
"loss": 2.2893,
|
| 280 |
+
"step": 18000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 8.58,
|
| 284 |
+
"learning_rate": 5.11595547309833e-07,
|
| 285 |
+
"loss": 2.2864,
|
| 286 |
+
"step": 18500
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 8.81,
|
| 290 |
+
"learning_rate": 4.443413729128013e-07,
|
| 291 |
+
"loss": 2.2859,
|
| 292 |
+
"step": 19000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 9.0,
|
| 296 |
+
"eval_loss": 2.277188539505005,
|
| 297 |
+
"eval_runtime": 7.6113,
|
| 298 |
+
"eval_samples_per_second": 267.234,
|
| 299 |
+
"step": 19404
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 9.04,
|
| 303 |
+
"learning_rate": 3.770871985157698e-07,
|
| 304 |
+
"loss": 2.2881,
|
| 305 |
+
"step": 19500
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 9.28,
|
| 309 |
+
"learning_rate": 3.0983302411873853e-07,
|
| 310 |
+
"loss": 2.2851,
|
| 311 |
+
"step": 20000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 9.51,
|
| 315 |
+
"learning_rate": 2.4257884972170696e-07,
|
| 316 |
+
"loss": 2.2844,
|
| 317 |
+
"step": 20500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 9.74,
|
| 321 |
+
"learning_rate": 1.7532467532467535e-07,
|
| 322 |
+
"loss": 2.2839,
|
| 323 |
+
"step": 21000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 9.97,
|
| 327 |
+
"learning_rate": 1.0807050092764375e-07,
|
| 328 |
+
"loss": 2.2814,
|
| 329 |
+
"step": 21500
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 10.0,
|
| 333 |
+
"eval_loss": 2.2749264240264893,
|
| 334 |
+
"eval_runtime": 7.3513,
|
| 335 |
+
"eval_samples_per_second": 276.685,
|
| 336 |
+
"step": 21560
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 10.0,
|
| 340 |
+
"step": 21560,
|
| 341 |
+
"total_flos": 8.526747522191754e+17,
|
| 342 |
+
"train_runtime": 43960.8836,
|
| 343 |
+
"train_samples_per_second": 0.49
|
| 344 |
+
}
|
| 345 |
+
],
|
| 346 |
+
"max_steps": 21560,
|
| 347 |
+
"num_train_epochs": 10,
|
| 348 |
+
"total_flos": 8.526747522191754e+17,
|
| 349 |
+
"trial_name": null,
|
| 350 |
+
"trial_params": null
|
| 351 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1577728559dd352480ec92efb7766e8ed15068659ac2f8b704452bdabbbcd73
|
| 3 |
+
size 2415
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|