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 +567 -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": 2530299,
|
| 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": 18524938,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 158585376,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1692413440,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 10976766464,
|
| 11 |
+
"train_runtime": 81966.5582,
|
| 12 |
+
"train_samples": 2039878,
|
| 13 |
+
"train_samples_per_second": 0.486
|
| 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:ea53bcee568c3824685208d1531a0b60c92b162f80828761d9598ae07e9db8c6
|
| 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": 2530299,
|
| 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": 18524938,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 158585376,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1692413440,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 10976766464,
|
| 11 |
+
"train_runtime": 81966.5582,
|
| 12 |
+
"train_samples": 2039878,
|
| 13 |
+
"train_samples_per_second": 0.486
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,567 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.999937252933425,
|
| 5 |
+
"global_step": 39840,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.13,
|
| 12 |
+
"learning_rate": 2.9636044176706825e-06,
|
| 13 |
+
"loss": 2.8976,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.25,
|
| 18 |
+
"learning_rate": 2.927208835341366e-06,
|
| 19 |
+
"loss": 2.6491,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.38,
|
| 24 |
+
"learning_rate": 2.8908132530120482e-06,
|
| 25 |
+
"loss": 2.5824,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.5,
|
| 30 |
+
"learning_rate": 2.854417670682731e-06,
|
| 31 |
+
"loss": 2.5408,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.63,
|
| 36 |
+
"learning_rate": 2.8180220883534135e-06,
|
| 37 |
+
"loss": 2.5086,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.75,
|
| 42 |
+
"learning_rate": 2.7816265060240964e-06,
|
| 43 |
+
"loss": 2.4829,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.88,
|
| 48 |
+
"learning_rate": 2.7452309236947792e-06,
|
| 49 |
+
"loss": 2.4628,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 1.0,
|
| 54 |
+
"eval_loss": 2.4354708194732666,
|
| 55 |
+
"eval_runtime": 73.1046,
|
| 56 |
+
"eval_samples_per_second": 281.843,
|
| 57 |
+
"step": 3984
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.0,
|
| 61 |
+
"learning_rate": 2.7088353413654617e-06,
|
| 62 |
+
"loss": 2.4451,
|
| 63 |
+
"step": 4000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.13,
|
| 67 |
+
"learning_rate": 2.672439759036145e-06,
|
| 68 |
+
"loss": 2.4269,
|
| 69 |
+
"step": 4500
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.26,
|
| 73 |
+
"learning_rate": 2.6360441767068274e-06,
|
| 74 |
+
"loss": 2.4118,
|
| 75 |
+
"step": 5000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.38,
|
| 79 |
+
"learning_rate": 2.5996485943775102e-06,
|
| 80 |
+
"loss": 2.3986,
|
| 81 |
+
"step": 5500
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.51,
|
| 85 |
+
"learning_rate": 2.5632530120481927e-06,
|
| 86 |
+
"loss": 2.387,
|
| 87 |
+
"step": 6000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.63,
|
| 91 |
+
"learning_rate": 2.5268574297188755e-06,
|
| 92 |
+
"loss": 2.376,
|
| 93 |
+
"step": 6500
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.76,
|
| 97 |
+
"learning_rate": 2.4904618473895584e-06,
|
| 98 |
+
"loss": 2.366,
|
| 99 |
+
"step": 7000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 1.88,
|
| 103 |
+
"learning_rate": 2.454066265060241e-06,
|
| 104 |
+
"loss": 2.3572,
|
| 105 |
+
"step": 7500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.0,
|
| 109 |
+
"eval_loss": 2.3434979915618896,
|
| 110 |
+
"eval_runtime": 73.6648,
|
| 111 |
+
"eval_samples_per_second": 279.699,
|
| 112 |
+
"step": 7968
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.01,
|
| 116 |
+
"learning_rate": 2.4176706827309237e-06,
|
| 117 |
+
"loss": 2.3493,
|
| 118 |
+
"step": 8000
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 2.13,
|
| 122 |
+
"learning_rate": 2.3812751004016065e-06,
|
| 123 |
+
"loss": 2.3394,
|
| 124 |
+
"step": 8500
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 2.26,
|
| 128 |
+
"learning_rate": 2.344879518072289e-06,
|
| 129 |
+
"loss": 2.3331,
|
| 130 |
+
"step": 9000
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.38,
|
| 134 |
+
"learning_rate": 2.308483935742972e-06,
|
| 135 |
+
"loss": 2.3268,
|
| 136 |
+
"step": 9500
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.51,
|
| 140 |
+
"learning_rate": 2.2720883534136547e-06,
|
| 141 |
+
"loss": 2.3215,
|
| 142 |
+
"step": 10000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.64,
|
| 146 |
+
"learning_rate": 2.2356927710843376e-06,
|
| 147 |
+
"loss": 2.3149,
|
| 148 |
+
"step": 10500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.76,
|
| 152 |
+
"learning_rate": 2.19929718875502e-06,
|
| 153 |
+
"loss": 2.3102,
|
| 154 |
+
"step": 11000
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.89,
|
| 158 |
+
"learning_rate": 2.162901606425703e-06,
|
| 159 |
+
"loss": 2.3042,
|
| 160 |
+
"step": 11500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 3.0,
|
| 164 |
+
"eval_loss": 2.2957260608673096,
|
| 165 |
+
"eval_runtime": 73.5103,
|
| 166 |
+
"eval_samples_per_second": 280.287,
|
| 167 |
+
"step": 11952
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 3.01,
|
| 171 |
+
"learning_rate": 2.1265060240963857e-06,
|
| 172 |
+
"loss": 2.3003,
|
| 173 |
+
"step": 12000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.14,
|
| 177 |
+
"learning_rate": 2.090110441767068e-06,
|
| 178 |
+
"loss": 2.2937,
|
| 179 |
+
"step": 12500
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 3.26,
|
| 183 |
+
"learning_rate": 2.053714859437751e-06,
|
| 184 |
+
"loss": 2.2903,
|
| 185 |
+
"step": 13000
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 3.39,
|
| 189 |
+
"learning_rate": 2.017319277108434e-06,
|
| 190 |
+
"loss": 2.2849,
|
| 191 |
+
"step": 13500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 3.51,
|
| 195 |
+
"learning_rate": 1.9809236947791167e-06,
|
| 196 |
+
"loss": 2.2819,
|
| 197 |
+
"step": 14000
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 3.64,
|
| 201 |
+
"learning_rate": 1.9445281124497996e-06,
|
| 202 |
+
"loss": 2.2775,
|
| 203 |
+
"step": 14500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 3.77,
|
| 207 |
+
"learning_rate": 1.908132530120482e-06,
|
| 208 |
+
"loss": 2.2734,
|
| 209 |
+
"step": 15000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 3.89,
|
| 213 |
+
"learning_rate": 1.871736947791165e-06,
|
| 214 |
+
"loss": 2.2714,
|
| 215 |
+
"step": 15500
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 4.0,
|
| 219 |
+
"eval_loss": 2.2644200325012207,
|
| 220 |
+
"eval_runtime": 73.6047,
|
| 221 |
+
"eval_samples_per_second": 279.928,
|
| 222 |
+
"step": 15936
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 4.02,
|
| 226 |
+
"learning_rate": 1.8353413654618473e-06,
|
| 227 |
+
"loss": 2.2707,
|
| 228 |
+
"step": 16000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 4.14,
|
| 232 |
+
"learning_rate": 1.7989457831325302e-06,
|
| 233 |
+
"loss": 2.265,
|
| 234 |
+
"step": 16500
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.27,
|
| 238 |
+
"learning_rate": 1.7625502008032132e-06,
|
| 239 |
+
"loss": 2.2617,
|
| 240 |
+
"step": 17000
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 4.39,
|
| 244 |
+
"learning_rate": 1.7261546184738955e-06,
|
| 245 |
+
"loss": 2.2593,
|
| 246 |
+
"step": 17500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 4.52,
|
| 250 |
+
"learning_rate": 1.6897590361445783e-06,
|
| 251 |
+
"loss": 2.256,
|
| 252 |
+
"step": 18000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 4.64,
|
| 256 |
+
"learning_rate": 1.6533634538152614e-06,
|
| 257 |
+
"loss": 2.2539,
|
| 258 |
+
"step": 18500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 4.77,
|
| 262 |
+
"learning_rate": 1.616967871485944e-06,
|
| 263 |
+
"loss": 2.2507,
|
| 264 |
+
"step": 19000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 4.89,
|
| 268 |
+
"learning_rate": 1.5805722891566265e-06,
|
| 269 |
+
"loss": 2.2492,
|
| 270 |
+
"step": 19500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 5.0,
|
| 274 |
+
"eval_loss": 2.2463769912719727,
|
| 275 |
+
"eval_runtime": 73.2603,
|
| 276 |
+
"eval_samples_per_second": 281.244,
|
| 277 |
+
"step": 19920
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 5.02,
|
| 281 |
+
"learning_rate": 1.5441767068273091e-06,
|
| 282 |
+
"loss": 2.2493,
|
| 283 |
+
"step": 20000
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 5.15,
|
| 287 |
+
"learning_rate": 1.5077811244979922e-06,
|
| 288 |
+
"loss": 2.2447,
|
| 289 |
+
"step": 20500
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 5.27,
|
| 293 |
+
"learning_rate": 1.4713855421686746e-06,
|
| 294 |
+
"loss": 2.2426,
|
| 295 |
+
"step": 21000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.4,
|
| 299 |
+
"learning_rate": 1.4349899598393575e-06,
|
| 300 |
+
"loss": 2.2412,
|
| 301 |
+
"step": 21500
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.52,
|
| 305 |
+
"learning_rate": 1.3985943775100403e-06,
|
| 306 |
+
"loss": 2.2393,
|
| 307 |
+
"step": 22000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.65,
|
| 311 |
+
"learning_rate": 1.3621987951807228e-06,
|
| 312 |
+
"loss": 2.2375,
|
| 313 |
+
"step": 22500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 5.77,
|
| 317 |
+
"learning_rate": 1.3258032128514056e-06,
|
| 318 |
+
"loss": 2.236,
|
| 319 |
+
"step": 23000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 5.9,
|
| 323 |
+
"learning_rate": 1.2894076305220885e-06,
|
| 324 |
+
"loss": 2.2342,
|
| 325 |
+
"step": 23500
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 6.0,
|
| 329 |
+
"eval_loss": 2.2327213287353516,
|
| 330 |
+
"eval_runtime": 73.1203,
|
| 331 |
+
"eval_samples_per_second": 281.782,
|
| 332 |
+
"step": 23904
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 6.02,
|
| 336 |
+
"learning_rate": 1.253012048192771e-06,
|
| 337 |
+
"loss": 2.2346,
|
| 338 |
+
"step": 24000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 6.15,
|
| 342 |
+
"learning_rate": 1.2166164658634538e-06,
|
| 343 |
+
"loss": 2.2312,
|
| 344 |
+
"step": 24500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 6.28,
|
| 348 |
+
"learning_rate": 1.1802208835341366e-06,
|
| 349 |
+
"loss": 2.2291,
|
| 350 |
+
"step": 25000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 6.4,
|
| 354 |
+
"learning_rate": 1.1438253012048195e-06,
|
| 355 |
+
"loss": 2.2283,
|
| 356 |
+
"step": 25500
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.53,
|
| 360 |
+
"learning_rate": 1.107429718875502e-06,
|
| 361 |
+
"loss": 2.2279,
|
| 362 |
+
"step": 26000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 6.65,
|
| 366 |
+
"learning_rate": 1.0710341365461848e-06,
|
| 367 |
+
"loss": 2.2269,
|
| 368 |
+
"step": 26500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 6.78,
|
| 372 |
+
"learning_rate": 1.0346385542168676e-06,
|
| 373 |
+
"loss": 2.2251,
|
| 374 |
+
"step": 27000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 6.9,
|
| 378 |
+
"learning_rate": 9.9824297188755e-07,
|
| 379 |
+
"loss": 2.2245,
|
| 380 |
+
"step": 27500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 7.0,
|
| 384 |
+
"eval_loss": 2.223916530609131,
|
| 385 |
+
"eval_runtime": 72.7667,
|
| 386 |
+
"eval_samples_per_second": 283.152,
|
| 387 |
+
"step": 27888
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.03,
|
| 391 |
+
"learning_rate": 9.61847389558233e-07,
|
| 392 |
+
"loss": 2.2247,
|
| 393 |
+
"step": 28000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 7.15,
|
| 397 |
+
"learning_rate": 9.254518072289157e-07,
|
| 398 |
+
"loss": 2.221,
|
| 399 |
+
"step": 28500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 7.28,
|
| 403 |
+
"learning_rate": 8.890562248995984e-07,
|
| 404 |
+
"loss": 2.2214,
|
| 405 |
+
"step": 29000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 7.4,
|
| 409 |
+
"learning_rate": 8.526606425702813e-07,
|
| 410 |
+
"loss": 2.2206,
|
| 411 |
+
"step": 29500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 7.53,
|
| 415 |
+
"learning_rate": 8.162650602409637e-07,
|
| 416 |
+
"loss": 2.2187,
|
| 417 |
+
"step": 30000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 7.66,
|
| 421 |
+
"learning_rate": 7.798694779116466e-07,
|
| 422 |
+
"loss": 2.2178,
|
| 423 |
+
"step": 30500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 7.78,
|
| 427 |
+
"learning_rate": 7.434738955823293e-07,
|
| 428 |
+
"loss": 2.2178,
|
| 429 |
+
"step": 31000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 7.91,
|
| 433 |
+
"learning_rate": 7.070783132530122e-07,
|
| 434 |
+
"loss": 2.2178,
|
| 435 |
+
"step": 31500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 8.0,
|
| 439 |
+
"eval_loss": 2.2174229621887207,
|
| 440 |
+
"eval_runtime": 72.9337,
|
| 441 |
+
"eval_samples_per_second": 282.503,
|
| 442 |
+
"step": 31872
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 8.03,
|
| 446 |
+
"learning_rate": 6.706827309236949e-07,
|
| 447 |
+
"loss": 2.2183,
|
| 448 |
+
"step": 32000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 8.16,
|
| 452 |
+
"learning_rate": 6.342871485943774e-07,
|
| 453 |
+
"loss": 2.2157,
|
| 454 |
+
"step": 32500
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 8.28,
|
| 458 |
+
"learning_rate": 5.978915662650604e-07,
|
| 459 |
+
"loss": 2.2157,
|
| 460 |
+
"step": 33000
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 8.41,
|
| 464 |
+
"learning_rate": 5.614959839357429e-07,
|
| 465 |
+
"loss": 2.2133,
|
| 466 |
+
"step": 33500
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 8.53,
|
| 470 |
+
"learning_rate": 5.251004016064259e-07,
|
| 471 |
+
"loss": 2.2145,
|
| 472 |
+
"step": 34000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 8.66,
|
| 476 |
+
"learning_rate": 4.887048192771084e-07,
|
| 477 |
+
"loss": 2.2136,
|
| 478 |
+
"step": 34500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 8.79,
|
| 482 |
+
"learning_rate": 4.5230923694779105e-07,
|
| 483 |
+
"loss": 2.214,
|
| 484 |
+
"step": 35000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 8.91,
|
| 488 |
+
"learning_rate": 4.15913654618474e-07,
|
| 489 |
+
"loss": 2.2134,
|
| 490 |
+
"step": 35500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 9.0,
|
| 494 |
+
"eval_loss": 2.213841676712036,
|
| 495 |
+
"eval_runtime": 72.9648,
|
| 496 |
+
"eval_samples_per_second": 282.383,
|
| 497 |
+
"step": 35856
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 9.04,
|
| 501 |
+
"learning_rate": 3.795180722891565e-07,
|
| 502 |
+
"loss": 2.2125,
|
| 503 |
+
"step": 36000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 9.16,
|
| 507 |
+
"learning_rate": 3.431224899598395e-07,
|
| 508 |
+
"loss": 2.2122,
|
| 509 |
+
"step": 36500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 9.29,
|
| 513 |
+
"learning_rate": 3.0672690763052206e-07,
|
| 514 |
+
"loss": 2.2127,
|
| 515 |
+
"step": 37000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.41,
|
| 519 |
+
"learning_rate": 2.703313253012047e-07,
|
| 520 |
+
"loss": 2.2116,
|
| 521 |
+
"step": 37500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 9.54,
|
| 525 |
+
"learning_rate": 2.3393574297188764e-07,
|
| 526 |
+
"loss": 2.2102,
|
| 527 |
+
"step": 38000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 9.66,
|
| 531 |
+
"learning_rate": 1.975401606425702e-07,
|
| 532 |
+
"loss": 2.2104,
|
| 533 |
+
"step": 38500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 9.79,
|
| 537 |
+
"learning_rate": 1.6114457831325312e-07,
|
| 538 |
+
"loss": 2.2104,
|
| 539 |
+
"step": 39000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.91,
|
| 543 |
+
"learning_rate": 1.2474899598393572e-07,
|
| 544 |
+
"loss": 2.2113,
|
| 545 |
+
"step": 39500
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 10.0,
|
| 549 |
+
"eval_loss": 2.212301254272461,
|
| 550 |
+
"eval_runtime": 77.5042,
|
| 551 |
+
"eval_samples_per_second": 265.844,
|
| 552 |
+
"step": 39840
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 10.0,
|
| 556 |
+
"step": 39840,
|
| 557 |
+
"total_flos": 1.5755091071960033e+18,
|
| 558 |
+
"train_runtime": 81966.5582,
|
| 559 |
+
"train_samples_per_second": 0.486
|
| 560 |
+
}
|
| 561 |
+
],
|
| 562 |
+
"max_steps": 39840,
|
| 563 |
+
"num_train_epochs": 10,
|
| 564 |
+
"total_flos": 1.5755091071960033e+18,
|
| 565 |
+
"trial_name": null,
|
| 566 |
+
"trial_params": null
|
| 567 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:651fdb408f64c77e296af06e77c855fdd81fc3fb4ad48b701668de9f5632f042
|
| 3 |
+
size 2415
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|