initial commit
Browse files- all_results.json +23 -0
- config.json +35 -0
- eval_results.json +12 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- train_results.json +14 -0
- trainer_state.json +533 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.8954,
|
| 4 |
+
"eval_loss": 0.39298728108406067,
|
| 5 |
+
"eval_mem_cpu_alloc_delta": 8691712,
|
| 6 |
+
"eval_mem_cpu_peaked_delta": 69632,
|
| 7 |
+
"eval_mem_gpu_alloc_delta": 0,
|
| 8 |
+
"eval_mem_gpu_peaked_delta": 94720512,
|
| 9 |
+
"eval_runtime": 79.8082,
|
| 10 |
+
"eval_samples": 10000,
|
| 11 |
+
"eval_samples_per_second": 125.3,
|
| 12 |
+
"init_mem_cpu_alloc_delta": 1917988864,
|
| 13 |
+
"init_mem_cpu_peaked_delta": 469221376,
|
| 14 |
+
"init_mem_gpu_alloc_delta": 439075328,
|
| 15 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 16 |
+
"train_mem_cpu_alloc_delta": 702259200,
|
| 17 |
+
"train_mem_cpu_peaked_delta": 539131904,
|
| 18 |
+
"train_mem_gpu_alloc_delta": 1315466240,
|
| 19 |
+
"train_mem_gpu_peaked_delta": 9074219520,
|
| 20 |
+
"train_runtime": 34216.2349,
|
| 21 |
+
"train_samples": 550152,
|
| 22 |
+
"train_samples_per_second": 1.256
|
| 23 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"finetuning_task": "snli",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "entailment",
|
| 14 |
+
"1": "neutral",
|
| 15 |
+
"2": "contradiction"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 3072,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"contradiction": 2,
|
| 21 |
+
"entailment": 0,
|
| 22 |
+
"neutral": 1
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 12,
|
| 28 |
+
"num_hidden_layers": 12,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"transformers_version": "4.6.0.dev0",
|
| 32 |
+
"type_vocab_size": 2,
|
| 33 |
+
"use_cache": true,
|
| 34 |
+
"vocab_size": 30522
|
| 35 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.8954,
|
| 4 |
+
"eval_loss": 0.39298728108406067,
|
| 5 |
+
"eval_mem_cpu_alloc_delta": 8691712,
|
| 6 |
+
"eval_mem_cpu_peaked_delta": 69632,
|
| 7 |
+
"eval_mem_gpu_alloc_delta": 0,
|
| 8 |
+
"eval_mem_gpu_peaked_delta": 94720512,
|
| 9 |
+
"eval_runtime": 79.8082,
|
| 10 |
+
"eval_samples": 10000,
|
| 11 |
+
"eval_samples_per_second": 125.3
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0748deda3ebf8d1407e89fc984c788b36d0a2a7c61ce568cd37001ce3d2085ec
|
| 3 |
+
size 438027529
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased"}
|
train_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 1917988864,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 469221376,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 439075328,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 702259200,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 539131904,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 1315466240,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 9074219520,
|
| 11 |
+
"train_runtime": 34216.2349,
|
| 12 |
+
"train_samples": 550152,
|
| 13 |
+
"train_samples_per_second": 1.256
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,533 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 42985,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1.976736070722345e-05,
|
| 13 |
+
"loss": 0.6539,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 1.95347214144469e-05,
|
| 19 |
+
"loss": 0.503,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.17,
|
| 24 |
+
"learning_rate": 1.930208212167035e-05,
|
| 25 |
+
"loss": 0.4624,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.23,
|
| 30 |
+
"learning_rate": 1.9069442828893803e-05,
|
| 31 |
+
"loss": 0.4344,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.29,
|
| 36 |
+
"learning_rate": 1.8836803536117253e-05,
|
| 37 |
+
"loss": 0.4245,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.35,
|
| 42 |
+
"learning_rate": 1.8604164243340703e-05,
|
| 43 |
+
"loss": 0.4102,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.41,
|
| 48 |
+
"learning_rate": 1.8371524950564152e-05,
|
| 49 |
+
"loss": 0.4059,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.47,
|
| 54 |
+
"learning_rate": 1.8138885657787602e-05,
|
| 55 |
+
"loss": 0.3898,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.52,
|
| 60 |
+
"learning_rate": 1.790624636501105e-05,
|
| 61 |
+
"loss": 0.3791,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.58,
|
| 66 |
+
"learning_rate": 1.76736070722345e-05,
|
| 67 |
+
"loss": 0.3763,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.64,
|
| 72 |
+
"learning_rate": 1.744096777945795e-05,
|
| 73 |
+
"loss": 0.3773,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.7,
|
| 78 |
+
"learning_rate": 1.7208328486681404e-05,
|
| 79 |
+
"loss": 0.3731,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.76,
|
| 84 |
+
"learning_rate": 1.6975689193904853e-05,
|
| 85 |
+
"loss": 0.36,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.81,
|
| 90 |
+
"learning_rate": 1.67430499011283e-05,
|
| 91 |
+
"loss": 0.358,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.87,
|
| 96 |
+
"learning_rate": 1.6510410608351752e-05,
|
| 97 |
+
"loss": 0.356,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.93,
|
| 102 |
+
"learning_rate": 1.6277771315575202e-05,
|
| 103 |
+
"loss": 0.3576,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.99,
|
| 108 |
+
"learning_rate": 1.604513202279865e-05,
|
| 109 |
+
"loss": 0.3501,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.05,
|
| 114 |
+
"learning_rate": 1.58124927300221e-05,
|
| 115 |
+
"loss": 0.3034,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.11,
|
| 120 |
+
"learning_rate": 1.557985343724555e-05,
|
| 121 |
+
"loss": 0.2965,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.16,
|
| 126 |
+
"learning_rate": 1.5347214144469004e-05,
|
| 127 |
+
"loss": 0.2923,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.22,
|
| 132 |
+
"learning_rate": 1.5114574851692452e-05,
|
| 133 |
+
"loss": 0.3006,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.28,
|
| 138 |
+
"learning_rate": 1.4881935558915903e-05,
|
| 139 |
+
"loss": 0.2882,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.34,
|
| 144 |
+
"learning_rate": 1.4649296266139352e-05,
|
| 145 |
+
"loss": 0.2911,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.4,
|
| 150 |
+
"learning_rate": 1.4416656973362802e-05,
|
| 151 |
+
"loss": 0.2882,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.45,
|
| 156 |
+
"learning_rate": 1.4184017680586253e-05,
|
| 157 |
+
"loss": 0.2886,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.51,
|
| 162 |
+
"learning_rate": 1.3951378387809701e-05,
|
| 163 |
+
"loss": 0.2867,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.57,
|
| 168 |
+
"learning_rate": 1.371873909503315e-05,
|
| 169 |
+
"loss": 0.2905,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.63,
|
| 174 |
+
"learning_rate": 1.3486099802256602e-05,
|
| 175 |
+
"loss": 0.2897,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.69,
|
| 180 |
+
"learning_rate": 1.3253460509480052e-05,
|
| 181 |
+
"loss": 0.2852,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.74,
|
| 186 |
+
"learning_rate": 1.3020821216703503e-05,
|
| 187 |
+
"loss": 0.2893,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.8,
|
| 192 |
+
"learning_rate": 1.2788181923926953e-05,
|
| 193 |
+
"loss": 0.2905,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.86,
|
| 198 |
+
"learning_rate": 1.2555542631150402e-05,
|
| 199 |
+
"loss": 0.288,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.92,
|
| 204 |
+
"learning_rate": 1.2322903338373853e-05,
|
| 205 |
+
"loss": 0.287,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.98,
|
| 210 |
+
"learning_rate": 1.2090264045597301e-05,
|
| 211 |
+
"loss": 0.285,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.04,
|
| 216 |
+
"learning_rate": 1.1857624752820753e-05,
|
| 217 |
+
"loss": 0.2427,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.09,
|
| 222 |
+
"learning_rate": 1.1624985460044202e-05,
|
| 223 |
+
"loss": 0.2328,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 2.15,
|
| 228 |
+
"learning_rate": 1.1392346167267652e-05,
|
| 229 |
+
"loss": 0.2206,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 2.21,
|
| 234 |
+
"learning_rate": 1.1159706874491103e-05,
|
| 235 |
+
"loss": 0.2262,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.27,
|
| 240 |
+
"learning_rate": 1.0927067581714553e-05,
|
| 241 |
+
"loss": 0.2358,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.33,
|
| 246 |
+
"learning_rate": 1.0694428288938004e-05,
|
| 247 |
+
"loss": 0.2221,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.38,
|
| 252 |
+
"learning_rate": 1.0461788996161452e-05,
|
| 253 |
+
"loss": 0.2233,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.44,
|
| 258 |
+
"learning_rate": 1.0229149703384902e-05,
|
| 259 |
+
"loss": 0.2266,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.5,
|
| 264 |
+
"learning_rate": 9.996510410608353e-06,
|
| 265 |
+
"loss": 0.2241,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.56,
|
| 270 |
+
"learning_rate": 9.763871117831802e-06,
|
| 271 |
+
"loss": 0.2305,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.62,
|
| 276 |
+
"learning_rate": 9.531231825055252e-06,
|
| 277 |
+
"loss": 0.2242,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.68,
|
| 282 |
+
"learning_rate": 9.298592532278703e-06,
|
| 283 |
+
"loss": 0.2323,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.73,
|
| 288 |
+
"learning_rate": 9.065953239502153e-06,
|
| 289 |
+
"loss": 0.227,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.79,
|
| 294 |
+
"learning_rate": 8.833313946725602e-06,
|
| 295 |
+
"loss": 0.2313,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.85,
|
| 300 |
+
"learning_rate": 8.600674653949052e-06,
|
| 301 |
+
"loss": 0.2318,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.91,
|
| 306 |
+
"learning_rate": 8.368035361172503e-06,
|
| 307 |
+
"loss": 0.2313,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.97,
|
| 312 |
+
"learning_rate": 8.135396068395953e-06,
|
| 313 |
+
"loss": 0.2292,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.02,
|
| 318 |
+
"learning_rate": 7.902756775619403e-06,
|
| 319 |
+
"loss": 0.2063,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 3.08,
|
| 324 |
+
"learning_rate": 7.670117482842852e-06,
|
| 325 |
+
"loss": 0.1837,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 3.14,
|
| 330 |
+
"learning_rate": 7.437478190066303e-06,
|
| 331 |
+
"loss": 0.1811,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 3.2,
|
| 336 |
+
"learning_rate": 7.204838897289753e-06,
|
| 337 |
+
"loss": 0.1777,
|
| 338 |
+
"step": 27500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 3.26,
|
| 342 |
+
"learning_rate": 6.972199604513203e-06,
|
| 343 |
+
"loss": 0.1847,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.32,
|
| 348 |
+
"learning_rate": 6.739560311736652e-06,
|
| 349 |
+
"loss": 0.1849,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.37,
|
| 354 |
+
"learning_rate": 6.506921018960103e-06,
|
| 355 |
+
"loss": 0.1811,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.43,
|
| 360 |
+
"learning_rate": 6.274281726183553e-06,
|
| 361 |
+
"loss": 0.1833,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 3.49,
|
| 366 |
+
"learning_rate": 6.0416424334070035e-06,
|
| 367 |
+
"loss": 0.1816,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.55,
|
| 372 |
+
"learning_rate": 5.809003140630452e-06,
|
| 373 |
+
"loss": 0.1754,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.61,
|
| 378 |
+
"learning_rate": 5.576363847853903e-06,
|
| 379 |
+
"loss": 0.1808,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.66,
|
| 384 |
+
"learning_rate": 5.343724555077353e-06,
|
| 385 |
+
"loss": 0.184,
|
| 386 |
+
"step": 31500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.72,
|
| 390 |
+
"learning_rate": 5.111085262300804e-06,
|
| 391 |
+
"loss": 0.1812,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.78,
|
| 396 |
+
"learning_rate": 4.878445969524253e-06,
|
| 397 |
+
"loss": 0.1835,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.84,
|
| 402 |
+
"learning_rate": 4.645806676747703e-06,
|
| 403 |
+
"loss": 0.1797,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.9,
|
| 408 |
+
"learning_rate": 4.413167383971153e-06,
|
| 409 |
+
"loss": 0.1816,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.95,
|
| 414 |
+
"learning_rate": 4.180528091194604e-06,
|
| 415 |
+
"loss": 0.1766,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 4.01,
|
| 420 |
+
"learning_rate": 3.947888798418053e-06,
|
| 421 |
+
"loss": 0.1744,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 4.07,
|
| 426 |
+
"learning_rate": 3.7152495056415033e-06,
|
| 427 |
+
"loss": 0.1536,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 4.13,
|
| 432 |
+
"learning_rate": 3.482610212864953e-06,
|
| 433 |
+
"loss": 0.1549,
|
| 434 |
+
"step": 35500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.19,
|
| 438 |
+
"learning_rate": 3.2499709200884033e-06,
|
| 439 |
+
"loss": 0.1483,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.25,
|
| 444 |
+
"learning_rate": 3.017331627311853e-06,
|
| 445 |
+
"loss": 0.1529,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.3,
|
| 450 |
+
"learning_rate": 2.7846923345353034e-06,
|
| 451 |
+
"loss": 0.1519,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.36,
|
| 456 |
+
"learning_rate": 2.552053041758753e-06,
|
| 457 |
+
"loss": 0.1518,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 4.42,
|
| 462 |
+
"learning_rate": 2.3194137489822034e-06,
|
| 463 |
+
"loss": 0.1474,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 4.48,
|
| 468 |
+
"learning_rate": 2.0867744562056534e-06,
|
| 469 |
+
"loss": 0.1523,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 4.54,
|
| 474 |
+
"learning_rate": 1.8541351634291032e-06,
|
| 475 |
+
"loss": 0.1491,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.59,
|
| 480 |
+
"learning_rate": 1.6214958706525532e-06,
|
| 481 |
+
"loss": 0.1474,
|
| 482 |
+
"step": 39500
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 4.65,
|
| 486 |
+
"learning_rate": 1.3888565778760033e-06,
|
| 487 |
+
"loss": 0.1469,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.71,
|
| 492 |
+
"learning_rate": 1.1562172850994535e-06,
|
| 493 |
+
"loss": 0.1447,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.77,
|
| 498 |
+
"learning_rate": 9.235779923229034e-07,
|
| 499 |
+
"loss": 0.1515,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.83,
|
| 504 |
+
"learning_rate": 6.909386995463534e-07,
|
| 505 |
+
"loss": 0.1473,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 4.89,
|
| 510 |
+
"learning_rate": 4.5829940676980343e-07,
|
| 511 |
+
"loss": 0.151,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.94,
|
| 516 |
+
"learning_rate": 2.256601139932535e-07,
|
| 517 |
+
"loss": 0.15,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 5.0,
|
| 522 |
+
"step": 42985,
|
| 523 |
+
"total_flos": 4.625905344087859e+17,
|
| 524 |
+
"train_runtime": 34216.2349,
|
| 525 |
+
"train_samples_per_second": 1.256
|
| 526 |
+
}
|
| 527 |
+
],
|
| 528 |
+
"max_steps": 42985,
|
| 529 |
+
"num_train_epochs": 5,
|
| 530 |
+
"total_flos": 4.625905344087859e+17,
|
| 531 |
+
"trial_name": null,
|
| 532 |
+
"trial_params": null
|
| 533 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:92156cdd92d0bb57a09266d6412e6cee3856335a41bb32f0319046c2fc35e8f9
|
| 3 |
+
size 2415
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|