intial commit
Browse files- all_results.json +23 -0
- config.json +36 -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 +1045 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.86706672091131,
|
| 4 |
+
"eval_loss": 0.5289081931114197,
|
| 5 |
+
"eval_mem_cpu_alloc_delta": 5726208,
|
| 6 |
+
"eval_mem_cpu_peaked_delta": 159744,
|
| 7 |
+
"eval_mem_gpu_alloc_delta": 0,
|
| 8 |
+
"eval_mem_gpu_peaked_delta": 738891264,
|
| 9 |
+
"eval_runtime": 34.059,
|
| 10 |
+
"eval_samples": 9832,
|
| 11 |
+
"eval_samples_per_second": 288.675,
|
| 12 |
+
"init_mem_cpu_alloc_delta": 2168487936,
|
| 13 |
+
"init_mem_cpu_peaked_delta": 124821504,
|
| 14 |
+
"init_mem_gpu_alloc_delta": 1341395456,
|
| 15 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 16 |
+
"train_mem_cpu_alloc_delta": 346263552,
|
| 17 |
+
"train_mem_cpu_peaked_delta": 14974976,
|
| 18 |
+
"train_mem_gpu_alloc_delta": 4024268288,
|
| 19 |
+
"train_mem_gpu_peaked_delta": 8017385472,
|
| 20 |
+
"train_runtime": 14794.1737,
|
| 21 |
+
"train_samples": 392702,
|
| 22 |
+
"train_samples_per_second": 2.489
|
| 23 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bert-large-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"finetuning_task": "mnli",
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"id2label": {
|
| 13 |
+
"0": "LABEL_0",
|
| 14 |
+
"1": "LABEL_1",
|
| 15 |
+
"2": "LABEL_2"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"LABEL_0": 0,
|
| 21 |
+
"LABEL_1": 1,
|
| 22 |
+
"LABEL_2": 2
|
| 23 |
+
},
|
| 24 |
+
"layer_norm_eps": 1e-12,
|
| 25 |
+
"max_position_embeddings": 512,
|
| 26 |
+
"model_type": "bert",
|
| 27 |
+
"num_attention_heads": 16,
|
| 28 |
+
"num_hidden_layers": 24,
|
| 29 |
+
"pad_token_id": 0,
|
| 30 |
+
"position_embedding_type": "absolute",
|
| 31 |
+
"problem_type": "single_label_classification",
|
| 32 |
+
"transformers_version": "4.6.1",
|
| 33 |
+
"type_vocab_size": 2,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30522
|
| 36 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_accuracy": 0.86706672091131,
|
| 4 |
+
"eval_loss": 0.5289081931114197,
|
| 5 |
+
"eval_mem_cpu_alloc_delta": 5726208,
|
| 6 |
+
"eval_mem_cpu_peaked_delta": 159744,
|
| 7 |
+
"eval_mem_gpu_alloc_delta": 0,
|
| 8 |
+
"eval_mem_gpu_peaked_delta": 738891264,
|
| 9 |
+
"eval_runtime": 34.059,
|
| 10 |
+
"eval_samples": 9832,
|
| 11 |
+
"eval_samples_per_second": 288.675
|
| 12 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af0a7d997fbd268720c286ac54df43296fdc3829221b1de61828721e04502756
|
| 3 |
+
size 1340746969
|
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-large-uncased"}
|
train_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"init_mem_cpu_alloc_delta": 2168487936,
|
| 4 |
+
"init_mem_cpu_peaked_delta": 124821504,
|
| 5 |
+
"init_mem_gpu_alloc_delta": 1341395456,
|
| 6 |
+
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 346263552,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 14974976,
|
| 9 |
+
"train_mem_gpu_alloc_delta": 4024268288,
|
| 10 |
+
"train_mem_gpu_peaked_delta": 8017385472,
|
| 11 |
+
"train_runtime": 14794.1737,
|
| 12 |
+
"train_samples": 392702,
|
| 13 |
+
"train_samples_per_second": 2.489
|
| 14 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1045 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 36816,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.9930309764864052e-05,
|
| 13 |
+
"loss": 0.9224,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"eval_accuracy": 0.7422312786551197,
|
| 19 |
+
"eval_loss": 0.6256920099258423,
|
| 20 |
+
"eval_runtime": 34.0513,
|
| 21 |
+
"eval_samples_per_second": 288.242,
|
| 22 |
+
"step": 500
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.08,
|
| 26 |
+
"learning_rate": 1.965648750240075e-05,
|
| 27 |
+
"loss": 0.6107,
|
| 28 |
+
"step": 1000
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.08,
|
| 32 |
+
"eval_accuracy": 0.7959246051961284,
|
| 33 |
+
"eval_loss": 0.5218016505241394,
|
| 34 |
+
"eval_runtime": 34.3716,
|
| 35 |
+
"eval_samples_per_second": 285.555,
|
| 36 |
+
"step": 1000
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"epoch": 0.12,
|
| 40 |
+
"learning_rate": 1.93821164979285e-05,
|
| 41 |
+
"loss": 0.5464,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.12,
|
| 46 |
+
"eval_accuracy": 0.8036678553234845,
|
| 47 |
+
"eval_loss": 0.4963739216327667,
|
| 48 |
+
"eval_runtime": 34.3352,
|
| 49 |
+
"eval_samples_per_second": 285.858,
|
| 50 |
+
"step": 1500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.16,
|
| 54 |
+
"learning_rate": 1.9107745493456255e-05,
|
| 55 |
+
"loss": 0.5153,
|
| 56 |
+
"step": 2000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.16,
|
| 60 |
+
"eval_accuracy": 0.8173204279164544,
|
| 61 |
+
"eval_loss": 0.4657774269580841,
|
| 62 |
+
"eval_runtime": 34.4768,
|
| 63 |
+
"eval_samples_per_second": 284.684,
|
| 64 |
+
"step": 2000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.2,
|
| 68 |
+
"learning_rate": 1.8833374488984006e-05,
|
| 69 |
+
"loss": 0.4934,
|
| 70 |
+
"step": 2500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.2,
|
| 74 |
+
"eval_accuracy": 0.8264900662251655,
|
| 75 |
+
"eval_loss": 0.4544191062450409,
|
| 76 |
+
"eval_runtime": 34.2913,
|
| 77 |
+
"eval_samples_per_second": 286.224,
|
| 78 |
+
"step": 2500
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.24,
|
| 82 |
+
"learning_rate": 1.8559003484511758e-05,
|
| 83 |
+
"loss": 0.4863,
|
| 84 |
+
"step": 3000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.24,
|
| 88 |
+
"eval_accuracy": 0.817014773306164,
|
| 89 |
+
"eval_loss": 0.469377726316452,
|
| 90 |
+
"eval_runtime": 34.3798,
|
| 91 |
+
"eval_samples_per_second": 285.488,
|
| 92 |
+
"step": 3000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.29,
|
| 96 |
+
"learning_rate": 1.828463248003951e-05,
|
| 97 |
+
"loss": 0.4639,
|
| 98 |
+
"step": 3500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.29,
|
| 102 |
+
"eval_accuracy": 0.8337238920020377,
|
| 103 |
+
"eval_loss": 0.44527676701545715,
|
| 104 |
+
"eval_runtime": 34.3542,
|
| 105 |
+
"eval_samples_per_second": 285.7,
|
| 106 |
+
"step": 3500
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.33,
|
| 110 |
+
"learning_rate": 1.8010261475567264e-05,
|
| 111 |
+
"loss": 0.477,
|
| 112 |
+
"step": 4000
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.33,
|
| 116 |
+
"eval_accuracy": 0.83841059602649,
|
| 117 |
+
"eval_loss": 0.4258698523044586,
|
| 118 |
+
"eval_runtime": 34.3114,
|
| 119 |
+
"eval_samples_per_second": 286.056,
|
| 120 |
+
"step": 4000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.37,
|
| 124 |
+
"learning_rate": 1.7735890471095016e-05,
|
| 125 |
+
"loss": 0.4592,
|
| 126 |
+
"step": 4500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.37,
|
| 130 |
+
"eval_accuracy": 0.8421803362200713,
|
| 131 |
+
"eval_loss": 0.4147617518901825,
|
| 132 |
+
"eval_runtime": 34.3201,
|
| 133 |
+
"eval_samples_per_second": 285.984,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.41,
|
| 138 |
+
"learning_rate": 1.746151946662277e-05,
|
| 139 |
+
"loss": 0.4449,
|
| 140 |
+
"step": 5000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.41,
|
| 144 |
+
"eval_accuracy": 0.8431991849210392,
|
| 145 |
+
"eval_loss": 0.42169830203056335,
|
| 146 |
+
"eval_runtime": 34.3613,
|
| 147 |
+
"eval_samples_per_second": 285.641,
|
| 148 |
+
"step": 5000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.45,
|
| 152 |
+
"learning_rate": 1.718714846215052e-05,
|
| 153 |
+
"loss": 0.4448,
|
| 154 |
+
"step": 5500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.45,
|
| 158 |
+
"eval_accuracy": 0.844319918492104,
|
| 159 |
+
"eval_loss": 0.4075462818145752,
|
| 160 |
+
"eval_runtime": 34.3101,
|
| 161 |
+
"eval_samples_per_second": 286.067,
|
| 162 |
+
"step": 5500
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.49,
|
| 166 |
+
"learning_rate": 1.6912777457678273e-05,
|
| 167 |
+
"loss": 0.4416,
|
| 168 |
+
"step": 6000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.49,
|
| 172 |
+
"eval_accuracy": 0.8473764645950076,
|
| 173 |
+
"eval_loss": 0.40427786111831665,
|
| 174 |
+
"eval_runtime": 34.3011,
|
| 175 |
+
"eval_samples_per_second": 286.142,
|
| 176 |
+
"step": 6000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.53,
|
| 180 |
+
"learning_rate": 1.6638406453206025e-05,
|
| 181 |
+
"loss": 0.4396,
|
| 182 |
+
"step": 6500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.53,
|
| 186 |
+
"eval_accuracy": 0.845746306673459,
|
| 187 |
+
"eval_loss": 0.40583938360214233,
|
| 188 |
+
"eval_runtime": 34.3317,
|
| 189 |
+
"eval_samples_per_second": 285.887,
|
| 190 |
+
"step": 6500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.57,
|
| 194 |
+
"learning_rate": 1.636403544873378e-05,
|
| 195 |
+
"loss": 0.4262,
|
| 196 |
+
"step": 7000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.57,
|
| 200 |
+
"eval_accuracy": 0.8414671421293938,
|
| 201 |
+
"eval_loss": 0.4056021273136139,
|
| 202 |
+
"eval_runtime": 34.3275,
|
| 203 |
+
"eval_samples_per_second": 285.923,
|
| 204 |
+
"step": 7000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.61,
|
| 208 |
+
"learning_rate": 1.609076192827942e-05,
|
| 209 |
+
"loss": 0.4181,
|
| 210 |
+
"step": 7500
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.61,
|
| 214 |
+
"eval_accuracy": 0.8471726948548141,
|
| 215 |
+
"eval_loss": 0.4094808101654053,
|
| 216 |
+
"eval_runtime": 34.3454,
|
| 217 |
+
"eval_samples_per_second": 285.773,
|
| 218 |
+
"step": 7500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.65,
|
| 222 |
+
"learning_rate": 1.5816390923807176e-05,
|
| 223 |
+
"loss": 0.4277,
|
| 224 |
+
"step": 8000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.65,
|
| 228 |
+
"eval_accuracy": 0.8513499745287825,
|
| 229 |
+
"eval_loss": 0.3897625207901001,
|
| 230 |
+
"eval_runtime": 34.3305,
|
| 231 |
+
"eval_samples_per_second": 285.898,
|
| 232 |
+
"step": 8000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.69,
|
| 236 |
+
"learning_rate": 1.5542019919334924e-05,
|
| 237 |
+
"loss": 0.4204,
|
| 238 |
+
"step": 8500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.69,
|
| 242 |
+
"eval_accuracy": 0.8414671421293938,
|
| 243 |
+
"eval_loss": 0.40381574630737305,
|
| 244 |
+
"eval_runtime": 34.3185,
|
| 245 |
+
"eval_samples_per_second": 285.997,
|
| 246 |
+
"step": 8500
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.73,
|
| 250 |
+
"learning_rate": 1.526764891486268e-05,
|
| 251 |
+
"loss": 0.408,
|
| 252 |
+
"step": 9000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.73,
|
| 256 |
+
"eval_accuracy": 0.8490066225165563,
|
| 257 |
+
"eval_loss": 0.39596864581108093,
|
| 258 |
+
"eval_runtime": 34.3274,
|
| 259 |
+
"eval_samples_per_second": 285.923,
|
| 260 |
+
"step": 9000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.77,
|
| 264 |
+
"learning_rate": 1.4993277910390432e-05,
|
| 265 |
+
"loss": 0.4147,
|
| 266 |
+
"step": 9500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.77,
|
| 270 |
+
"eval_accuracy": 0.8508405501782985,
|
| 271 |
+
"eval_loss": 0.39388328790664673,
|
| 272 |
+
"eval_runtime": 34.3118,
|
| 273 |
+
"eval_samples_per_second": 286.053,
|
| 274 |
+
"step": 9500
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.81,
|
| 278 |
+
"learning_rate": 1.4718906905918185e-05,
|
| 279 |
+
"loss": 0.4087,
|
| 280 |
+
"step": 10000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.81,
|
| 284 |
+
"eval_accuracy": 0.8454406520631687,
|
| 285 |
+
"eval_loss": 0.3990323841571808,
|
| 286 |
+
"eval_runtime": 34.3039,
|
| 287 |
+
"eval_samples_per_second": 286.119,
|
| 288 |
+
"step": 10000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.86,
|
| 292 |
+
"learning_rate": 1.4444535901445937e-05,
|
| 293 |
+
"loss": 0.4182,
|
| 294 |
+
"step": 10500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.86,
|
| 298 |
+
"eval_accuracy": 0.8559347936831381,
|
| 299 |
+
"eval_loss": 0.37663206458091736,
|
| 300 |
+
"eval_runtime": 34.3301,
|
| 301 |
+
"eval_samples_per_second": 285.901,
|
| 302 |
+
"step": 10500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.9,
|
| 306 |
+
"learning_rate": 1.4170164896973688e-05,
|
| 307 |
+
"loss": 0.3974,
|
| 308 |
+
"step": 11000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.9,
|
| 312 |
+
"eval_accuracy": 0.8542027508914927,
|
| 313 |
+
"eval_loss": 0.38825666904449463,
|
| 314 |
+
"eval_runtime": 34.3094,
|
| 315 |
+
"eval_samples_per_second": 286.073,
|
| 316 |
+
"step": 11000
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.94,
|
| 320 |
+
"learning_rate": 1.3895793892501441e-05,
|
| 321 |
+
"loss": 0.4031,
|
| 322 |
+
"step": 11500
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.94,
|
| 326 |
+
"eval_accuracy": 0.8604177279673968,
|
| 327 |
+
"eval_loss": 0.372531533241272,
|
| 328 |
+
"eval_runtime": 34.3046,
|
| 329 |
+
"eval_samples_per_second": 286.113,
|
| 330 |
+
"step": 11500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.98,
|
| 334 |
+
"learning_rate": 1.3621422888029194e-05,
|
| 335 |
+
"loss": 0.4012,
|
| 336 |
+
"step": 12000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.98,
|
| 340 |
+
"eval_accuracy": 0.8586856851757514,
|
| 341 |
+
"eval_loss": 0.3715327978134155,
|
| 342 |
+
"eval_runtime": 34.3023,
|
| 343 |
+
"eval_samples_per_second": 286.133,
|
| 344 |
+
"step": 12000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.02,
|
| 348 |
+
"learning_rate": 1.334760062556589e-05,
|
| 349 |
+
"loss": 0.3364,
|
| 350 |
+
"step": 12500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.02,
|
| 354 |
+
"eval_accuracy": 0.8536933265410087,
|
| 355 |
+
"eval_loss": 0.4157598912715912,
|
| 356 |
+
"eval_runtime": 34.3192,
|
| 357 |
+
"eval_samples_per_second": 285.992,
|
| 358 |
+
"step": 12500
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 1.06,
|
| 362 |
+
"learning_rate": 1.3073229621093644e-05,
|
| 363 |
+
"loss": 0.256,
|
| 364 |
+
"step": 13000
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 1.06,
|
| 368 |
+
"eval_accuracy": 0.8565461029037188,
|
| 369 |
+
"eval_loss": 0.4385443329811096,
|
| 370 |
+
"eval_runtime": 34.3274,
|
| 371 |
+
"eval_samples_per_second": 285.923,
|
| 372 |
+
"step": 13000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.1,
|
| 376 |
+
"learning_rate": 1.2798858616621397e-05,
|
| 377 |
+
"loss": 0.2682,
|
| 378 |
+
"step": 13500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.1,
|
| 382 |
+
"eval_accuracy": 0.8606214977075904,
|
| 383 |
+
"eval_loss": 0.40176108479499817,
|
| 384 |
+
"eval_runtime": 34.3252,
|
| 385 |
+
"eval_samples_per_second": 285.941,
|
| 386 |
+
"step": 13500
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 1.14,
|
| 390 |
+
"learning_rate": 1.252448761214915e-05,
|
| 391 |
+
"loss": 0.2566,
|
| 392 |
+
"step": 14000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.14,
|
| 396 |
+
"eval_accuracy": 0.8628629648497198,
|
| 397 |
+
"eval_loss": 0.40525978803634644,
|
| 398 |
+
"eval_runtime": 34.3427,
|
| 399 |
+
"eval_samples_per_second": 285.796,
|
| 400 |
+
"step": 14000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 1.18,
|
| 404 |
+
"learning_rate": 1.22501166076769e-05,
|
| 405 |
+
"loss": 0.2672,
|
| 406 |
+
"step": 14500
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 1.18,
|
| 410 |
+
"eval_accuracy": 0.8600101884870097,
|
| 411 |
+
"eval_loss": 0.41904282569885254,
|
| 412 |
+
"eval_runtime": 34.3153,
|
| 413 |
+
"eval_samples_per_second": 286.024,
|
| 414 |
+
"step": 14500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.22,
|
| 418 |
+
"learning_rate": 1.1975745603204653e-05,
|
| 419 |
+
"loss": 0.2614,
|
| 420 |
+
"step": 15000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.22,
|
| 424 |
+
"eval_accuracy": 0.8596026490066225,
|
| 425 |
+
"eval_loss": 0.4234951138496399,
|
| 426 |
+
"eval_runtime": 34.3391,
|
| 427 |
+
"eval_samples_per_second": 285.825,
|
| 428 |
+
"step": 15000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.26,
|
| 432 |
+
"learning_rate": 1.1701374598732406e-05,
|
| 433 |
+
"loss": 0.2581,
|
| 434 |
+
"step": 15500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.26,
|
| 438 |
+
"eval_accuracy": 0.8562404482934284,
|
| 439 |
+
"eval_loss": 0.4271596670150757,
|
| 440 |
+
"eval_runtime": 34.3468,
|
| 441 |
+
"eval_samples_per_second": 285.762,
|
| 442 |
+
"step": 15500
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 1.3,
|
| 446 |
+
"learning_rate": 1.142700359426016e-05,
|
| 447 |
+
"loss": 0.2623,
|
| 448 |
+
"step": 16000
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 1.3,
|
| 452 |
+
"eval_accuracy": 0.8616403464085584,
|
| 453 |
+
"eval_loss": 0.42012786865234375,
|
| 454 |
+
"eval_runtime": 34.342,
|
| 455 |
+
"eval_samples_per_second": 285.802,
|
| 456 |
+
"step": 16000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 1.34,
|
| 460 |
+
"learning_rate": 1.1153181331796856e-05,
|
| 461 |
+
"loss": 0.2536,
|
| 462 |
+
"step": 16500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 1.34,
|
| 466 |
+
"eval_accuracy": 0.8611309220580744,
|
| 467 |
+
"eval_loss": 0.42309054732322693,
|
| 468 |
+
"eval_runtime": 34.3494,
|
| 469 |
+
"eval_samples_per_second": 285.74,
|
| 470 |
+
"step": 16500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.39,
|
| 474 |
+
"learning_rate": 1.0878810327324609e-05,
|
| 475 |
+
"loss": 0.2595,
|
| 476 |
+
"step": 17000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.39,
|
| 480 |
+
"eval_accuracy": 0.863779928680591,
|
| 481 |
+
"eval_loss": 0.408088356256485,
|
| 482 |
+
"eval_runtime": 34.2723,
|
| 483 |
+
"eval_samples_per_second": 286.383,
|
| 484 |
+
"step": 17000
|
| 485 |
+
},
|
| 486 |
+
{
|
| 487 |
+
"epoch": 1.43,
|
| 488 |
+
"learning_rate": 1.0604439322852362e-05,
|
| 489 |
+
"loss": 0.2626,
|
| 490 |
+
"step": 17500
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.43,
|
| 494 |
+
"eval_accuracy": 0.8558329088130413,
|
| 495 |
+
"eval_loss": 0.4161333441734314,
|
| 496 |
+
"eval_runtime": 34.2334,
|
| 497 |
+
"eval_samples_per_second": 286.708,
|
| 498 |
+
"step": 17500
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 1.47,
|
| 502 |
+
"learning_rate": 1.0330068318380115e-05,
|
| 503 |
+
"loss": 0.2607,
|
| 504 |
+
"step": 18000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.47,
|
| 508 |
+
"eval_accuracy": 0.8580743759551707,
|
| 509 |
+
"eval_loss": 0.42380374670028687,
|
| 510 |
+
"eval_runtime": 34.2608,
|
| 511 |
+
"eval_samples_per_second": 286.479,
|
| 512 |
+
"step": 18000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.51,
|
| 516 |
+
"learning_rate": 1.0055697313907867e-05,
|
| 517 |
+
"loss": 0.268,
|
| 518 |
+
"step": 18500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.51,
|
| 522 |
+
"eval_accuracy": 0.8599083036169128,
|
| 523 |
+
"eval_loss": 0.43461742997169495,
|
| 524 |
+
"eval_runtime": 34.234,
|
| 525 |
+
"eval_samples_per_second": 286.703,
|
| 526 |
+
"step": 18500
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.55,
|
| 530 |
+
"learning_rate": 9.78132630943562e-06,
|
| 531 |
+
"loss": 0.2702,
|
| 532 |
+
"step": 19000
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.55,
|
| 536 |
+
"eval_accuracy": 0.8628629648497198,
|
| 537 |
+
"eval_loss": 0.4047214388847351,
|
| 538 |
+
"eval_runtime": 34.2365,
|
| 539 |
+
"eval_samples_per_second": 286.682,
|
| 540 |
+
"step": 19000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.59,
|
| 544 |
+
"learning_rate": 9.506955304963372e-06,
|
| 545 |
+
"loss": 0.2496,
|
| 546 |
+
"step": 19500
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 1.59,
|
| 550 |
+
"eval_accuracy": 0.8595007641365258,
|
| 551 |
+
"eval_loss": 0.4368164539337158,
|
| 552 |
+
"eval_runtime": 34.2332,
|
| 553 |
+
"eval_samples_per_second": 286.71,
|
| 554 |
+
"step": 19500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.63,
|
| 558 |
+
"learning_rate": 9.232584300491125e-06,
|
| 559 |
+
"loss": 0.2681,
|
| 560 |
+
"step": 20000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.63,
|
| 564 |
+
"eval_accuracy": 0.867142129393785,
|
| 565 |
+
"eval_loss": 0.400213360786438,
|
| 566 |
+
"eval_runtime": 34.2373,
|
| 567 |
+
"eval_samples_per_second": 286.675,
|
| 568 |
+
"step": 20000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 1.67,
|
| 572 |
+
"learning_rate": 8.958762038027821e-06,
|
| 573 |
+
"loss": 0.2608,
|
| 574 |
+
"step": 20500
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 1.67,
|
| 578 |
+
"eval_accuracy": 0.863779928680591,
|
| 579 |
+
"eval_loss": 0.40518832206726074,
|
| 580 |
+
"eval_runtime": 34.2681,
|
| 581 |
+
"eval_samples_per_second": 286.418,
|
| 582 |
+
"step": 20500
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 1.71,
|
| 586 |
+
"learning_rate": 8.684939775564519e-06,
|
| 587 |
+
"loss": 0.261,
|
| 588 |
+
"step": 21000
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 1.71,
|
| 592 |
+
"eval_accuracy": 0.8655119714722364,
|
| 593 |
+
"eval_loss": 0.3955936133861542,
|
| 594 |
+
"eval_runtime": 34.2769,
|
| 595 |
+
"eval_samples_per_second": 286.344,
|
| 596 |
+
"step": 21000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 1.75,
|
| 600 |
+
"learning_rate": 8.41056877109227e-06,
|
| 601 |
+
"loss": 0.267,
|
| 602 |
+
"step": 21500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 1.75,
|
| 606 |
+
"eval_accuracy": 0.8610290371879776,
|
| 607 |
+
"eval_loss": 0.40947309136390686,
|
| 608 |
+
"eval_runtime": 34.2634,
|
| 609 |
+
"eval_samples_per_second": 286.457,
|
| 610 |
+
"step": 21500
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 1.79,
|
| 614 |
+
"learning_rate": 8.136197766620024e-06,
|
| 615 |
+
"loss": 0.2598,
|
| 616 |
+
"step": 22000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 1.79,
|
| 620 |
+
"eval_accuracy": 0.8642893530310749,
|
| 621 |
+
"eval_loss": 0.38150227069854736,
|
| 622 |
+
"eval_runtime": 34.2625,
|
| 623 |
+
"eval_samples_per_second": 286.465,
|
| 624 |
+
"step": 22000
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 1.83,
|
| 628 |
+
"learning_rate": 7.861826762147777e-06,
|
| 629 |
+
"loss": 0.2577,
|
| 630 |
+
"step": 22500
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 1.83,
|
| 634 |
+
"eval_accuracy": 0.8641874681609781,
|
| 635 |
+
"eval_loss": 0.401090145111084,
|
| 636 |
+
"eval_runtime": 34.2614,
|
| 637 |
+
"eval_samples_per_second": 286.474,
|
| 638 |
+
"step": 22500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.87,
|
| 642 |
+
"learning_rate": 7.587455757675529e-06,
|
| 643 |
+
"loss": 0.2583,
|
| 644 |
+
"step": 23000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.87,
|
| 648 |
+
"eval_accuracy": 0.8678553234844626,
|
| 649 |
+
"eval_loss": 0.39116695523262024,
|
| 650 |
+
"eval_runtime": 34.2797,
|
| 651 |
+
"eval_samples_per_second": 286.321,
|
| 652 |
+
"step": 23000
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 1.91,
|
| 656 |
+
"learning_rate": 7.313084753203282e-06,
|
| 657 |
+
"loss": 0.2623,
|
| 658 |
+
"step": 23500
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 1.91,
|
| 662 |
+
"eval_accuracy": 0.8622516556291391,
|
| 663 |
+
"eval_loss": 0.3969860076904297,
|
| 664 |
+
"eval_runtime": 34.2798,
|
| 665 |
+
"eval_samples_per_second": 286.32,
|
| 666 |
+
"step": 23500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 1.96,
|
| 670 |
+
"learning_rate": 7.038713748731034e-06,
|
| 671 |
+
"loss": 0.2475,
|
| 672 |
+
"step": 24000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 1.96,
|
| 676 |
+
"eval_accuracy": 0.862761079979623,
|
| 677 |
+
"eval_loss": 0.4156796634197235,
|
| 678 |
+
"eval_runtime": 34.2085,
|
| 679 |
+
"eval_samples_per_second": 286.917,
|
| 680 |
+
"step": 24000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.0,
|
| 684 |
+
"learning_rate": 6.764342744258787e-06,
|
| 685 |
+
"loss": 0.2576,
|
| 686 |
+
"step": 24500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.0,
|
| 690 |
+
"eval_accuracy": 0.8691798267957208,
|
| 691 |
+
"eval_loss": 0.38194480538368225,
|
| 692 |
+
"eval_runtime": 34.1983,
|
| 693 |
+
"eval_samples_per_second": 287.003,
|
| 694 |
+
"step": 24500
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 2.04,
|
| 698 |
+
"learning_rate": 6.490520481795485e-06,
|
| 699 |
+
"loss": 0.1544,
|
| 700 |
+
"step": 25000
|
| 701 |
+
},
|
| 702 |
+
{
|
| 703 |
+
"epoch": 2.04,
|
| 704 |
+
"eval_accuracy": 0.8614365766683647,
|
| 705 |
+
"eval_loss": 0.5428063273429871,
|
| 706 |
+
"eval_runtime": 34.103,
|
| 707 |
+
"eval_samples_per_second": 287.804,
|
| 708 |
+
"step": 25000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 2.08,
|
| 712 |
+
"learning_rate": 6.2161494773232365e-06,
|
| 713 |
+
"loss": 0.1431,
|
| 714 |
+
"step": 25500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 2.08,
|
| 718 |
+
"eval_accuracy": 0.8678553234844626,
|
| 719 |
+
"eval_loss": 0.509951114654541,
|
| 720 |
+
"eval_runtime": 34.213,
|
| 721 |
+
"eval_samples_per_second": 286.879,
|
| 722 |
+
"step": 25500
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 2.12,
|
| 726 |
+
"learning_rate": 5.94177847285099e-06,
|
| 727 |
+
"loss": 0.1481,
|
| 728 |
+
"step": 26000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.12,
|
| 732 |
+
"eval_accuracy": 0.8615384615384616,
|
| 733 |
+
"eval_loss": 0.523091733455658,
|
| 734 |
+
"eval_runtime": 34.1262,
|
| 735 |
+
"eval_samples_per_second": 287.609,
|
| 736 |
+
"step": 26000
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 2.16,
|
| 740 |
+
"learning_rate": 5.667407468378742e-06,
|
| 741 |
+
"loss": 0.1367,
|
| 742 |
+
"step": 26500
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 2.16,
|
| 746 |
+
"eval_accuracy": 0.8649006622516556,
|
| 747 |
+
"eval_loss": 0.5161163806915283,
|
| 748 |
+
"eval_runtime": 34.1588,
|
| 749 |
+
"eval_samples_per_second": 287.335,
|
| 750 |
+
"step": 26500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 2.2,
|
| 754 |
+
"learning_rate": 5.393036463906494e-06,
|
| 755 |
+
"loss": 0.1452,
|
| 756 |
+
"step": 27000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 2.2,
|
| 760 |
+
"eval_accuracy": 0.8658176260825268,
|
| 761 |
+
"eval_loss": 0.505763053894043,
|
| 762 |
+
"eval_runtime": 34.1846,
|
| 763 |
+
"eval_samples_per_second": 287.118,
|
| 764 |
+
"step": 27000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.24,
|
| 768 |
+
"learning_rate": 5.119214201443192e-06,
|
| 769 |
+
"loss": 0.1401,
|
| 770 |
+
"step": 27500
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 2.24,
|
| 774 |
+
"eval_accuracy": 0.8645950076413652,
|
| 775 |
+
"eval_loss": 0.5186136960983276,
|
| 776 |
+
"eval_runtime": 34.2274,
|
| 777 |
+
"eval_samples_per_second": 286.758,
|
| 778 |
+
"step": 27500
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 2.28,
|
| 782 |
+
"learning_rate": 4.844843196970945e-06,
|
| 783 |
+
"loss": 0.1418,
|
| 784 |
+
"step": 28000
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.28,
|
| 788 |
+
"eval_accuracy": 0.8596026490066225,
|
| 789 |
+
"eval_loss": 0.5330820083618164,
|
| 790 |
+
"eval_runtime": 34.2035,
|
| 791 |
+
"eval_samples_per_second": 286.959,
|
| 792 |
+
"step": 28000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 2.32,
|
| 796 |
+
"learning_rate": 4.570472192498697e-06,
|
| 797 |
+
"loss": 0.1381,
|
| 798 |
+
"step": 28500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.32,
|
| 802 |
+
"eval_accuracy": 0.8654100866021396,
|
| 803 |
+
"eval_loss": 0.5446536540985107,
|
| 804 |
+
"eval_runtime": 34.125,
|
| 805 |
+
"eval_samples_per_second": 287.619,
|
| 806 |
+
"step": 28500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.36,
|
| 810 |
+
"learning_rate": 4.296101188026449e-06,
|
| 811 |
+
"loss": 0.1416,
|
| 812 |
+
"step": 29000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.36,
|
| 816 |
+
"eval_accuracy": 0.8622516556291391,
|
| 817 |
+
"eval_loss": 0.540454626083374,
|
| 818 |
+
"eval_runtime": 34.1047,
|
| 819 |
+
"eval_samples_per_second": 287.79,
|
| 820 |
+
"step": 29000
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 2.4,
|
| 824 |
+
"learning_rate": 4.0217301835542025e-06,
|
| 825 |
+
"loss": 0.1444,
|
| 826 |
+
"step": 29500
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 2.4,
|
| 830 |
+
"eval_accuracy": 0.8650025471217524,
|
| 831 |
+
"eval_loss": 0.5085907578468323,
|
| 832 |
+
"eval_runtime": 34.0859,
|
| 833 |
+
"eval_samples_per_second": 287.949,
|
| 834 |
+
"step": 29500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.44,
|
| 838 |
+
"learning_rate": 3.747359179081955e-06,
|
| 839 |
+
"loss": 0.1409,
|
| 840 |
+
"step": 30000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 2.44,
|
| 844 |
+
"eval_accuracy": 0.8621497707590423,
|
| 845 |
+
"eval_loss": 0.5341202616691589,
|
| 846 |
+
"eval_runtime": 34.1606,
|
| 847 |
+
"eval_samples_per_second": 287.319,
|
| 848 |
+
"step": 30000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.49,
|
| 852 |
+
"learning_rate": 3.473536916618652e-06,
|
| 853 |
+
"loss": 0.1348,
|
| 854 |
+
"step": 30500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.49,
|
| 858 |
+
"eval_accuracy": 0.8643912379011717,
|
| 859 |
+
"eval_loss": 0.5396838784217834,
|
| 860 |
+
"eval_runtime": 34.1392,
|
| 861 |
+
"eval_samples_per_second": 287.499,
|
| 862 |
+
"step": 30500
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.53,
|
| 866 |
+
"learning_rate": 3.199165912146405e-06,
|
| 867 |
+
"loss": 0.1389,
|
| 868 |
+
"step": 31000
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 2.53,
|
| 872 |
+
"eval_accuracy": 0.8635761589403973,
|
| 873 |
+
"eval_loss": 0.548418402671814,
|
| 874 |
+
"eval_runtime": 34.1565,
|
| 875 |
+
"eval_samples_per_second": 287.354,
|
| 876 |
+
"step": 31000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 2.57,
|
| 880 |
+
"learning_rate": 2.924794907674157e-06,
|
| 881 |
+
"loss": 0.1483,
|
| 882 |
+
"step": 31500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 2.57,
|
| 886 |
+
"eval_accuracy": 0.86571574121243,
|
| 887 |
+
"eval_loss": 0.5054455399513245,
|
| 888 |
+
"eval_runtime": 34.1767,
|
| 889 |
+
"eval_samples_per_second": 287.184,
|
| 890 |
+
"step": 31500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 2.61,
|
| 894 |
+
"learning_rate": 2.65042390320191e-06,
|
| 895 |
+
"loss": 0.1384,
|
| 896 |
+
"step": 32000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 2.61,
|
| 900 |
+
"eval_accuracy": 0.8688741721854305,
|
| 901 |
+
"eval_loss": 0.5029205083847046,
|
| 902 |
+
"eval_runtime": 34.1709,
|
| 903 |
+
"eval_samples_per_second": 287.233,
|
| 904 |
+
"step": 32000
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 2.65,
|
| 908 |
+
"learning_rate": 2.3760528987296626e-06,
|
| 909 |
+
"loss": 0.1374,
|
| 910 |
+
"step": 32500
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 2.65,
|
| 914 |
+
"eval_accuracy": 0.8649006622516556,
|
| 915 |
+
"eval_loss": 0.5312877893447876,
|
| 916 |
+
"eval_runtime": 34.1909,
|
| 917 |
+
"eval_samples_per_second": 287.065,
|
| 918 |
+
"step": 32500
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 2.69,
|
| 922 |
+
"learning_rate": 2.101681894257415e-06,
|
| 923 |
+
"loss": 0.135,
|
| 924 |
+
"step": 33000
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 2.69,
|
| 928 |
+
"eval_accuracy": 0.86571574121243,
|
| 929 |
+
"eval_loss": 0.5231665372848511,
|
| 930 |
+
"eval_runtime": 34.184,
|
| 931 |
+
"eval_samples_per_second": 287.123,
|
| 932 |
+
"step": 33000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 2.73,
|
| 936 |
+
"learning_rate": 1.8273108897851676e-06,
|
| 937 |
+
"loss": 0.1331,
|
| 938 |
+
"step": 33500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 2.73,
|
| 942 |
+
"eval_accuracy": 0.8667345899133979,
|
| 943 |
+
"eval_loss": 0.5193073749542236,
|
| 944 |
+
"eval_runtime": 34.2139,
|
| 945 |
+
"eval_samples_per_second": 286.872,
|
| 946 |
+
"step": 33500
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 2.77,
|
| 950 |
+
"learning_rate": 1.5529398853129202e-06,
|
| 951 |
+
"loss": 0.1287,
|
| 952 |
+
"step": 34000
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 2.77,
|
| 956 |
+
"eval_accuracy": 0.8639836984207845,
|
| 957 |
+
"eval_loss": 0.5389389395713806,
|
| 958 |
+
"eval_runtime": 34.2048,
|
| 959 |
+
"eval_samples_per_second": 286.948,
|
| 960 |
+
"step": 34000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 2.81,
|
| 964 |
+
"learning_rate": 1.278568880840673e-06,
|
| 965 |
+
"loss": 0.1399,
|
| 966 |
+
"step": 34500
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 2.81,
|
| 970 |
+
"eval_accuracy": 0.8647987773815589,
|
| 971 |
+
"eval_loss": 0.5319520235061646,
|
| 972 |
+
"eval_runtime": 34.136,
|
| 973 |
+
"eval_samples_per_second": 287.527,
|
| 974 |
+
"step": 34500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 2.85,
|
| 978 |
+
"learning_rate": 1.0041978763684254e-06,
|
| 979 |
+
"loss": 0.1371,
|
| 980 |
+
"step": 35000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 2.85,
|
| 984 |
+
"eval_accuracy": 0.867142129393785,
|
| 985 |
+
"eval_loss": 0.5155227184295654,
|
| 986 |
+
"eval_runtime": 34.0818,
|
| 987 |
+
"eval_samples_per_second": 287.984,
|
| 988 |
+
"step": 35000
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"epoch": 2.89,
|
| 992 |
+
"learning_rate": 7.298268718961781e-07,
|
| 993 |
+
"loss": 0.1403,
|
| 994 |
+
"step": 35500
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 2.89,
|
| 998 |
+
"eval_accuracy": 0.8650025471217524,
|
| 999 |
+
"eval_loss": 0.5259838104248047,
|
| 1000 |
+
"eval_runtime": 34.0228,
|
| 1001 |
+
"eval_samples_per_second": 288.483,
|
| 1002 |
+
"step": 35500
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 2.93,
|
| 1006 |
+
"learning_rate": 4.5655335144181967e-07,
|
| 1007 |
+
"loss": 0.1402,
|
| 1008 |
+
"step": 36000
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 2.93,
|
| 1012 |
+
"eval_accuracy": 0.8661232806928171,
|
| 1013 |
+
"eval_loss": 0.5214368104934692,
|
| 1014 |
+
"eval_runtime": 34.0674,
|
| 1015 |
+
"eval_samples_per_second": 288.105,
|
| 1016 |
+
"step": 36000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 2.97,
|
| 1020 |
+
"learning_rate": 1.8218234696957227e-07,
|
| 1021 |
+
"loss": 0.1343,
|
| 1022 |
+
"step": 36500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 2.97,
|
| 1026 |
+
"eval_accuracy": 0.8656138563423331,
|
| 1027 |
+
"eval_loss": 0.522437572479248,
|
| 1028 |
+
"eval_runtime": 34.0148,
|
| 1029 |
+
"eval_samples_per_second": 288.551,
|
| 1030 |
+
"step": 36500
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 3.0,
|
| 1034 |
+
"step": 36816,
|
| 1035 |
+
"total_flos": 3.032342720870999e+17,
|
| 1036 |
+
"train_runtime": 14794.1737,
|
| 1037 |
+
"train_samples_per_second": 2.489
|
| 1038 |
+
}
|
| 1039 |
+
],
|
| 1040 |
+
"max_steps": 36816,
|
| 1041 |
+
"num_train_epochs": 3,
|
| 1042 |
+
"total_flos": 3.032342720870999e+17,
|
| 1043 |
+
"trial_name": null,
|
| 1044 |
+
"trial_params": null
|
| 1045 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e50cad69ce0c20b4364c6f732e16e528648aabdd86497866f31223f5720ec3a9
|
| 3 |
+
size 2543
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|