Upload 14 files
Browse files- config.json +44 -0
- generation_config.json +6 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.model +3 -0
- tokenizer_config.json +14 -0
- trainer_state.json +1216 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/datas/huggingface/chatglm2-6b",
|
3 |
+
"add_bias_linear": false,
|
4 |
+
"add_qkv_bias": true,
|
5 |
+
"apply_query_key_layer_scaling": true,
|
6 |
+
"apply_residual_connection_post_layernorm": false,
|
7 |
+
"architectures": [
|
8 |
+
"ChatGLMForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"attention_softmax_in_fp32": true,
|
12 |
+
"auto_map": {
|
13 |
+
"AutoConfig": "configuration_chatglm.ChatGLMConfig",
|
14 |
+
"AutoModel": "modeling_chatglm.ChatGLMForConditionalGeneration",
|
15 |
+
"AutoModelForSeq2SeqLM": "modeling_chatglm.ChatGLMForConditionalGeneration"
|
16 |
+
},
|
17 |
+
"bias_dropout_fusion": true,
|
18 |
+
"eos_token_id": 2,
|
19 |
+
"ffn_hidden_size": 13696,
|
20 |
+
"fp32_residual_connection": false,
|
21 |
+
"hidden_dropout": 0.0,
|
22 |
+
"hidden_size": 4096,
|
23 |
+
"kv_channels": 128,
|
24 |
+
"layernorm_epsilon": 1e-05,
|
25 |
+
"model_type": "chatglm",
|
26 |
+
"multi_query_attention": true,
|
27 |
+
"multi_query_group_num": 2,
|
28 |
+
"num_attention_heads": 32,
|
29 |
+
"num_layers": 28,
|
30 |
+
"original_rope": true,
|
31 |
+
"pad_token_id": 0,
|
32 |
+
"padded_vocab_size": 65024,
|
33 |
+
"post_layer_norm": true,
|
34 |
+
"pre_seq_len": 128,
|
35 |
+
"prefix_projection": false,
|
36 |
+
"quantization_bit": 0,
|
37 |
+
"rmsnorm": true,
|
38 |
+
"seq_length": 32768,
|
39 |
+
"tie_word_embeddings": false,
|
40 |
+
"torch_dtype": "float16",
|
41 |
+
"transformers_version": "4.30.2",
|
42 |
+
"use_cache": true,
|
43 |
+
"vocab_size": 65024
|
44 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"eos_token_id": 2,
|
4 |
+
"pad_token_id": 0,
|
5 |
+
"transformers_version": "4.30.2"
|
6 |
+
}
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce80793e503b4053fd56073024ca52246728c3b8ab67eb6a21efd93bcffd1ecd
|
3 |
+
size 14681455
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:883877edeb97f8a5de4485f41f765a05f9e836fce1c0b61f0039dc5d2dea9c77
|
3 |
+
size 7340861
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56d7bc51109ee416eeea130a408434a92cf71b44cfc2bc4442cf49c3e73e5e84
|
3 |
+
size 17655
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4a9142d19a888fa3c2928d7e1a55ddabe57796d1d2f03e32857acee73d237f2d
|
3 |
+
size 17655
|
rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b67abfc4add67328fa42ddcc43c460adf429ab02faa7f3dc17bc8045bb8f4ed
|
3 |
+
size 17655
|
rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7bcfa77ac3f110a56f5914fd49f553e576595821af996b9820eab55077fd731
|
3 |
+
size 17655
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:085050153143f6636a80966bb11d5d14a8cb33bc1ebe86a86fd01b02f1b1efdc
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7dc4c393423b76e4373e5157ddc34803a0189ba96b21ddbb40269d31468a6f2
|
3 |
+
size 1018370
|
tokenizer_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_map": {
|
3 |
+
"AutoTokenizer": [
|
4 |
+
"tokenization_chatglm.ChatGLMTokenizer",
|
5 |
+
null
|
6 |
+
]
|
7 |
+
},
|
8 |
+
"clean_up_tokenization_spaces": true,
|
9 |
+
"do_lower_case": false,
|
10 |
+
"model_max_length": 1000000000000000019884624838656,
|
11 |
+
"padding_side": "left",
|
12 |
+
"remove_space": false,
|
13 |
+
"tokenizer_class": "ChatGLMTokenizer"
|
14 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1216 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.722126929674099,
|
5 |
+
"global_step": 2000,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.07,
|
12 |
+
"learning_rate": 0.00995,
|
13 |
+
"loss": 3.247,
|
14 |
+
"step": 10
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.14,
|
18 |
+
"learning_rate": 0.0099,
|
19 |
+
"loss": 2.397,
|
20 |
+
"step": 20
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.21,
|
24 |
+
"learning_rate": 0.00985,
|
25 |
+
"loss": 2.1303,
|
26 |
+
"step": 30
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.27,
|
30 |
+
"learning_rate": 0.0098,
|
31 |
+
"loss": 1.9873,
|
32 |
+
"step": 40
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.34,
|
36 |
+
"learning_rate": 0.00975,
|
37 |
+
"loss": 1.8902,
|
38 |
+
"step": 50
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.41,
|
42 |
+
"learning_rate": 0.0097,
|
43 |
+
"loss": 1.7747,
|
44 |
+
"step": 60
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.48,
|
48 |
+
"learning_rate": 0.00965,
|
49 |
+
"loss": 1.711,
|
50 |
+
"step": 70
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.55,
|
54 |
+
"learning_rate": 0.0096,
|
55 |
+
"loss": 1.6649,
|
56 |
+
"step": 80
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.62,
|
60 |
+
"learning_rate": 0.00955,
|
61 |
+
"loss": 1.6457,
|
62 |
+
"step": 90
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.69,
|
66 |
+
"learning_rate": 0.0095,
|
67 |
+
"loss": 1.5889,
|
68 |
+
"step": 100
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.75,
|
72 |
+
"learning_rate": 0.00945,
|
73 |
+
"loss": 1.602,
|
74 |
+
"step": 110
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.82,
|
78 |
+
"learning_rate": 0.0094,
|
79 |
+
"loss": 1.5384,
|
80 |
+
"step": 120
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.89,
|
84 |
+
"learning_rate": 0.00935,
|
85 |
+
"loss": 1.5033,
|
86 |
+
"step": 130
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.96,
|
90 |
+
"learning_rate": 0.009300000000000001,
|
91 |
+
"loss": 1.5284,
|
92 |
+
"step": 140
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 1.03,
|
96 |
+
"learning_rate": 0.009250000000000001,
|
97 |
+
"loss": 1.4809,
|
98 |
+
"step": 150
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 1.1,
|
102 |
+
"learning_rate": 0.0092,
|
103 |
+
"loss": 1.4795,
|
104 |
+
"step": 160
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 1.17,
|
108 |
+
"learning_rate": 0.00915,
|
109 |
+
"loss": 1.4555,
|
110 |
+
"step": 170
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 1.23,
|
114 |
+
"learning_rate": 0.0091,
|
115 |
+
"loss": 1.4335,
|
116 |
+
"step": 180
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 1.3,
|
120 |
+
"learning_rate": 0.00905,
|
121 |
+
"loss": 1.4275,
|
122 |
+
"step": 190
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.37,
|
126 |
+
"learning_rate": 0.009000000000000001,
|
127 |
+
"loss": 1.4365,
|
128 |
+
"step": 200
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.44,
|
132 |
+
"learning_rate": 0.00895,
|
133 |
+
"loss": 1.4345,
|
134 |
+
"step": 210
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 1.51,
|
138 |
+
"learning_rate": 0.0089,
|
139 |
+
"loss": 1.4284,
|
140 |
+
"step": 220
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.58,
|
144 |
+
"learning_rate": 0.00885,
|
145 |
+
"loss": 1.4069,
|
146 |
+
"step": 230
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.65,
|
150 |
+
"learning_rate": 0.0088,
|
151 |
+
"loss": 1.4395,
|
152 |
+
"step": 240
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 1.72,
|
156 |
+
"learning_rate": 0.00875,
|
157 |
+
"loss": 1.3858,
|
158 |
+
"step": 250
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.78,
|
162 |
+
"learning_rate": 0.0087,
|
163 |
+
"loss": 1.3875,
|
164 |
+
"step": 260
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 1.85,
|
168 |
+
"learning_rate": 0.00865,
|
169 |
+
"loss": 1.3721,
|
170 |
+
"step": 270
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 1.92,
|
174 |
+
"learning_rate": 0.0086,
|
175 |
+
"loss": 1.374,
|
176 |
+
"step": 280
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.99,
|
180 |
+
"learning_rate": 0.00855,
|
181 |
+
"loss": 1.348,
|
182 |
+
"step": 290
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 2.06,
|
186 |
+
"learning_rate": 0.0085,
|
187 |
+
"loss": 1.358,
|
188 |
+
"step": 300
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 2.13,
|
192 |
+
"learning_rate": 0.00845,
|
193 |
+
"loss": 1.3352,
|
194 |
+
"step": 310
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 2.2,
|
198 |
+
"learning_rate": 0.0084,
|
199 |
+
"loss": 1.3385,
|
200 |
+
"step": 320
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.26,
|
204 |
+
"learning_rate": 0.00835,
|
205 |
+
"loss": 1.3546,
|
206 |
+
"step": 330
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 2.33,
|
210 |
+
"learning_rate": 0.0083,
|
211 |
+
"loss": 1.3472,
|
212 |
+
"step": 340
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 2.4,
|
216 |
+
"learning_rate": 0.00825,
|
217 |
+
"loss": 1.3179,
|
218 |
+
"step": 350
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 2.47,
|
222 |
+
"learning_rate": 0.008199999999999999,
|
223 |
+
"loss": 1.2895,
|
224 |
+
"step": 360
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 2.54,
|
228 |
+
"learning_rate": 0.00815,
|
229 |
+
"loss": 1.303,
|
230 |
+
"step": 370
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 2.61,
|
234 |
+
"learning_rate": 0.008100000000000001,
|
235 |
+
"loss": 1.3066,
|
236 |
+
"step": 380
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 2.68,
|
240 |
+
"learning_rate": 0.00805,
|
241 |
+
"loss": 1.3264,
|
242 |
+
"step": 390
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 2.74,
|
246 |
+
"learning_rate": 0.008,
|
247 |
+
"loss": 1.3202,
|
248 |
+
"step": 400
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 2.81,
|
252 |
+
"learning_rate": 0.00795,
|
253 |
+
"loss": 1.2923,
|
254 |
+
"step": 410
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 2.88,
|
258 |
+
"learning_rate": 0.0079,
|
259 |
+
"loss": 1.2711,
|
260 |
+
"step": 420
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 2.95,
|
264 |
+
"learning_rate": 0.007850000000000001,
|
265 |
+
"loss": 1.313,
|
266 |
+
"step": 430
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 3.02,
|
270 |
+
"learning_rate": 0.0078000000000000005,
|
271 |
+
"loss": 1.2948,
|
272 |
+
"step": 440
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 3.09,
|
276 |
+
"learning_rate": 0.007750000000000001,
|
277 |
+
"loss": 1.2596,
|
278 |
+
"step": 450
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 3.16,
|
282 |
+
"learning_rate": 0.0077,
|
283 |
+
"loss": 1.2505,
|
284 |
+
"step": 460
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 3.22,
|
288 |
+
"learning_rate": 0.0076500000000000005,
|
289 |
+
"loss": 1.2581,
|
290 |
+
"step": 470
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 3.29,
|
294 |
+
"learning_rate": 0.0076,
|
295 |
+
"loss": 1.2829,
|
296 |
+
"step": 480
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 3.36,
|
300 |
+
"learning_rate": 0.00755,
|
301 |
+
"loss": 1.2487,
|
302 |
+
"step": 490
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 3.43,
|
306 |
+
"learning_rate": 0.0075,
|
307 |
+
"loss": 1.2927,
|
308 |
+
"step": 500
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 3.5,
|
312 |
+
"learning_rate": 0.00745,
|
313 |
+
"loss": 1.263,
|
314 |
+
"step": 510
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 3.57,
|
318 |
+
"learning_rate": 0.0074,
|
319 |
+
"loss": 1.2565,
|
320 |
+
"step": 520
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 3.64,
|
324 |
+
"learning_rate": 0.00735,
|
325 |
+
"loss": 1.2842,
|
326 |
+
"step": 530
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 3.7,
|
330 |
+
"learning_rate": 0.0073,
|
331 |
+
"loss": 1.2506,
|
332 |
+
"step": 540
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 3.77,
|
336 |
+
"learning_rate": 0.0072499999999999995,
|
337 |
+
"loss": 1.2436,
|
338 |
+
"step": 550
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 3.84,
|
342 |
+
"learning_rate": 0.0072,
|
343 |
+
"loss": 1.2752,
|
344 |
+
"step": 560
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 3.91,
|
348 |
+
"learning_rate": 0.00715,
|
349 |
+
"loss": 1.2366,
|
350 |
+
"step": 570
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 3.98,
|
354 |
+
"learning_rate": 0.0070999999999999995,
|
355 |
+
"loss": 1.2681,
|
356 |
+
"step": 580
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 4.05,
|
360 |
+
"learning_rate": 0.00705,
|
361 |
+
"loss": 1.2076,
|
362 |
+
"step": 590
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 4.12,
|
366 |
+
"learning_rate": 0.006999999999999999,
|
367 |
+
"loss": 1.2311,
|
368 |
+
"step": 600
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 4.19,
|
372 |
+
"learning_rate": 0.00695,
|
373 |
+
"loss": 1.2203,
|
374 |
+
"step": 610
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 4.25,
|
378 |
+
"learning_rate": 0.0069,
|
379 |
+
"loss": 1.2084,
|
380 |
+
"step": 620
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 4.32,
|
384 |
+
"learning_rate": 0.006850000000000001,
|
385 |
+
"loss": 1.2243,
|
386 |
+
"step": 630
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 4.39,
|
390 |
+
"learning_rate": 0.0068000000000000005,
|
391 |
+
"loss": 1.2382,
|
392 |
+
"step": 640
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 4.46,
|
396 |
+
"learning_rate": 0.006750000000000001,
|
397 |
+
"loss": 1.206,
|
398 |
+
"step": 650
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 4.53,
|
402 |
+
"learning_rate": 0.0067,
|
403 |
+
"loss": 1.2301,
|
404 |
+
"step": 660
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 4.6,
|
408 |
+
"learning_rate": 0.0066500000000000005,
|
409 |
+
"loss": 1.2079,
|
410 |
+
"step": 670
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 4.67,
|
414 |
+
"learning_rate": 0.006600000000000001,
|
415 |
+
"loss": 1.2072,
|
416 |
+
"step": 680
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 4.73,
|
420 |
+
"learning_rate": 0.00655,
|
421 |
+
"loss": 1.169,
|
422 |
+
"step": 690
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 4.8,
|
426 |
+
"learning_rate": 0.006500000000000001,
|
427 |
+
"loss": 1.2034,
|
428 |
+
"step": 700
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 4.87,
|
432 |
+
"learning_rate": 0.00645,
|
433 |
+
"loss": 1.2168,
|
434 |
+
"step": 710
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 4.94,
|
438 |
+
"learning_rate": 0.0064,
|
439 |
+
"loss": 1.2131,
|
440 |
+
"step": 720
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 5.01,
|
444 |
+
"learning_rate": 0.006350000000000001,
|
445 |
+
"loss": 1.2044,
|
446 |
+
"step": 730
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 5.08,
|
450 |
+
"learning_rate": 0.0063,
|
451 |
+
"loss": 1.1908,
|
452 |
+
"step": 740
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 5.15,
|
456 |
+
"learning_rate": 0.00625,
|
457 |
+
"loss": 1.1594,
|
458 |
+
"step": 750
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 5.21,
|
462 |
+
"learning_rate": 0.0062,
|
463 |
+
"loss": 1.1371,
|
464 |
+
"step": 760
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 5.28,
|
468 |
+
"learning_rate": 0.00615,
|
469 |
+
"loss": 1.1905,
|
470 |
+
"step": 770
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 5.35,
|
474 |
+
"learning_rate": 0.0061,
|
475 |
+
"loss": 1.1684,
|
476 |
+
"step": 780
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 5.42,
|
480 |
+
"learning_rate": 0.00605,
|
481 |
+
"loss": 1.1942,
|
482 |
+
"step": 790
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 5.49,
|
486 |
+
"learning_rate": 0.006,
|
487 |
+
"loss": 1.1848,
|
488 |
+
"step": 800
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 5.56,
|
492 |
+
"learning_rate": 0.0059499999999999996,
|
493 |
+
"loss": 1.1786,
|
494 |
+
"step": 810
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 5.63,
|
498 |
+
"learning_rate": 0.0059,
|
499 |
+
"loss": 1.1686,
|
500 |
+
"step": 820
|
501 |
+
},
|
502 |
+
{
|
503 |
+
"epoch": 5.69,
|
504 |
+
"learning_rate": 0.00585,
|
505 |
+
"loss": 1.1852,
|
506 |
+
"step": 830
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 5.76,
|
510 |
+
"learning_rate": 0.0058,
|
511 |
+
"loss": 1.198,
|
512 |
+
"step": 840
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 5.83,
|
516 |
+
"learning_rate": 0.00575,
|
517 |
+
"loss": 1.1738,
|
518 |
+
"step": 850
|
519 |
+
},
|
520 |
+
{
|
521 |
+
"epoch": 5.9,
|
522 |
+
"learning_rate": 0.005699999999999999,
|
523 |
+
"loss": 1.1808,
|
524 |
+
"step": 860
|
525 |
+
},
|
526 |
+
{
|
527 |
+
"epoch": 5.97,
|
528 |
+
"learning_rate": 0.00565,
|
529 |
+
"loss": 1.1655,
|
530 |
+
"step": 870
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 6.04,
|
534 |
+
"learning_rate": 0.005600000000000001,
|
535 |
+
"loss": 1.1467,
|
536 |
+
"step": 880
|
537 |
+
},
|
538 |
+
{
|
539 |
+
"epoch": 6.11,
|
540 |
+
"learning_rate": 0.00555,
|
541 |
+
"loss": 1.1559,
|
542 |
+
"step": 890
|
543 |
+
},
|
544 |
+
{
|
545 |
+
"epoch": 6.17,
|
546 |
+
"learning_rate": 0.0055000000000000005,
|
547 |
+
"loss": 1.1497,
|
548 |
+
"step": 900
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 6.24,
|
552 |
+
"learning_rate": 0.005450000000000001,
|
553 |
+
"loss": 1.1473,
|
554 |
+
"step": 910
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 6.31,
|
558 |
+
"learning_rate": 0.0054,
|
559 |
+
"loss": 1.184,
|
560 |
+
"step": 920
|
561 |
+
},
|
562 |
+
{
|
563 |
+
"epoch": 6.38,
|
564 |
+
"learning_rate": 0.005350000000000001,
|
565 |
+
"loss": 1.1053,
|
566 |
+
"step": 930
|
567 |
+
},
|
568 |
+
{
|
569 |
+
"epoch": 6.45,
|
570 |
+
"learning_rate": 0.0053,
|
571 |
+
"loss": 1.1721,
|
572 |
+
"step": 940
|
573 |
+
},
|
574 |
+
{
|
575 |
+
"epoch": 6.52,
|
576 |
+
"learning_rate": 0.00525,
|
577 |
+
"loss": 1.1418,
|
578 |
+
"step": 950
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 6.59,
|
582 |
+
"learning_rate": 0.005200000000000001,
|
583 |
+
"loss": 1.1243,
|
584 |
+
"step": 960
|
585 |
+
},
|
586 |
+
{
|
587 |
+
"epoch": 6.66,
|
588 |
+
"learning_rate": 0.00515,
|
589 |
+
"loss": 1.1386,
|
590 |
+
"step": 970
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 6.72,
|
594 |
+
"learning_rate": 0.0051,
|
595 |
+
"loss": 1.1743,
|
596 |
+
"step": 980
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 6.79,
|
600 |
+
"learning_rate": 0.00505,
|
601 |
+
"loss": 1.1201,
|
602 |
+
"step": 990
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 6.86,
|
606 |
+
"learning_rate": 0.005,
|
607 |
+
"loss": 1.1224,
|
608 |
+
"step": 1000
|
609 |
+
},
|
610 |
+
{
|
611 |
+
"epoch": 6.93,
|
612 |
+
"learning_rate": 0.00495,
|
613 |
+
"loss": 1.1464,
|
614 |
+
"step": 1010
|
615 |
+
},
|
616 |
+
{
|
617 |
+
"epoch": 7.0,
|
618 |
+
"learning_rate": 0.0049,
|
619 |
+
"loss": 1.1547,
|
620 |
+
"step": 1020
|
621 |
+
},
|
622 |
+
{
|
623 |
+
"epoch": 7.07,
|
624 |
+
"learning_rate": 0.00485,
|
625 |
+
"loss": 1.145,
|
626 |
+
"step": 1030
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 7.14,
|
630 |
+
"learning_rate": 0.0048,
|
631 |
+
"loss": 1.1261,
|
632 |
+
"step": 1040
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 7.2,
|
636 |
+
"learning_rate": 0.00475,
|
637 |
+
"loss": 1.1422,
|
638 |
+
"step": 1050
|
639 |
+
},
|
640 |
+
{
|
641 |
+
"epoch": 7.27,
|
642 |
+
"learning_rate": 0.0047,
|
643 |
+
"loss": 1.1115,
|
644 |
+
"step": 1060
|
645 |
+
},
|
646 |
+
{
|
647 |
+
"epoch": 7.34,
|
648 |
+
"learning_rate": 0.0046500000000000005,
|
649 |
+
"loss": 1.0921,
|
650 |
+
"step": 1070
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 7.41,
|
654 |
+
"learning_rate": 0.0046,
|
655 |
+
"loss": 1.1041,
|
656 |
+
"step": 1080
|
657 |
+
},
|
658 |
+
{
|
659 |
+
"epoch": 7.48,
|
660 |
+
"learning_rate": 0.00455,
|
661 |
+
"loss": 1.1196,
|
662 |
+
"step": 1090
|
663 |
+
},
|
664 |
+
{
|
665 |
+
"epoch": 7.55,
|
666 |
+
"learning_rate": 0.0045000000000000005,
|
667 |
+
"loss": 1.133,
|
668 |
+
"step": 1100
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 7.62,
|
672 |
+
"learning_rate": 0.00445,
|
673 |
+
"loss": 1.1133,
|
674 |
+
"step": 1110
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 7.68,
|
678 |
+
"learning_rate": 0.0044,
|
679 |
+
"loss": 1.1034,
|
680 |
+
"step": 1120
|
681 |
+
},
|
682 |
+
{
|
683 |
+
"epoch": 7.75,
|
684 |
+
"learning_rate": 0.00435,
|
685 |
+
"loss": 1.118,
|
686 |
+
"step": 1130
|
687 |
+
},
|
688 |
+
{
|
689 |
+
"epoch": 7.82,
|
690 |
+
"learning_rate": 0.0043,
|
691 |
+
"loss": 1.128,
|
692 |
+
"step": 1140
|
693 |
+
},
|
694 |
+
{
|
695 |
+
"epoch": 7.89,
|
696 |
+
"learning_rate": 0.00425,
|
697 |
+
"loss": 1.1316,
|
698 |
+
"step": 1150
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 7.96,
|
702 |
+
"learning_rate": 0.0042,
|
703 |
+
"loss": 1.129,
|
704 |
+
"step": 1160
|
705 |
+
},
|
706 |
+
{
|
707 |
+
"epoch": 8.03,
|
708 |
+
"learning_rate": 0.00415,
|
709 |
+
"loss": 1.0815,
|
710 |
+
"step": 1170
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 8.1,
|
714 |
+
"learning_rate": 0.0040999999999999995,
|
715 |
+
"loss": 1.091,
|
716 |
+
"step": 1180
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 8.16,
|
720 |
+
"learning_rate": 0.004050000000000001,
|
721 |
+
"loss": 1.0751,
|
722 |
+
"step": 1190
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 8.23,
|
726 |
+
"learning_rate": 0.004,
|
727 |
+
"loss": 1.1042,
|
728 |
+
"step": 1200
|
729 |
+
},
|
730 |
+
{
|
731 |
+
"epoch": 8.3,
|
732 |
+
"learning_rate": 0.00395,
|
733 |
+
"loss": 1.0957,
|
734 |
+
"step": 1210
|
735 |
+
},
|
736 |
+
{
|
737 |
+
"epoch": 8.37,
|
738 |
+
"learning_rate": 0.0039000000000000003,
|
739 |
+
"loss": 1.1186,
|
740 |
+
"step": 1220
|
741 |
+
},
|
742 |
+
{
|
743 |
+
"epoch": 8.44,
|
744 |
+
"learning_rate": 0.00385,
|
745 |
+
"loss": 1.101,
|
746 |
+
"step": 1230
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 8.51,
|
750 |
+
"learning_rate": 0.0038,
|
751 |
+
"loss": 1.0889,
|
752 |
+
"step": 1240
|
753 |
+
},
|
754 |
+
{
|
755 |
+
"epoch": 8.58,
|
756 |
+
"learning_rate": 0.00375,
|
757 |
+
"loss": 1.1111,
|
758 |
+
"step": 1250
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 8.64,
|
762 |
+
"learning_rate": 0.0037,
|
763 |
+
"loss": 1.1158,
|
764 |
+
"step": 1260
|
765 |
+
},
|
766 |
+
{
|
767 |
+
"epoch": 8.71,
|
768 |
+
"learning_rate": 0.00365,
|
769 |
+
"loss": 1.0982,
|
770 |
+
"step": 1270
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 8.78,
|
774 |
+
"learning_rate": 0.0036,
|
775 |
+
"loss": 1.1002,
|
776 |
+
"step": 1280
|
777 |
+
},
|
778 |
+
{
|
779 |
+
"epoch": 8.85,
|
780 |
+
"learning_rate": 0.0035499999999999998,
|
781 |
+
"loss": 1.0892,
|
782 |
+
"step": 1290
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 8.92,
|
786 |
+
"learning_rate": 0.0034999999999999996,
|
787 |
+
"loss": 1.0698,
|
788 |
+
"step": 1300
|
789 |
+
},
|
790 |
+
{
|
791 |
+
"epoch": 8.99,
|
792 |
+
"learning_rate": 0.00345,
|
793 |
+
"loss": 1.0703,
|
794 |
+
"step": 1310
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 9.06,
|
798 |
+
"learning_rate": 0.0034000000000000002,
|
799 |
+
"loss": 1.0602,
|
800 |
+
"step": 1320
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 9.13,
|
804 |
+
"learning_rate": 0.00335,
|
805 |
+
"loss": 1.0611,
|
806 |
+
"step": 1330
|
807 |
+
},
|
808 |
+
{
|
809 |
+
"epoch": 9.19,
|
810 |
+
"learning_rate": 0.0033000000000000004,
|
811 |
+
"loss": 1.0886,
|
812 |
+
"step": 1340
|
813 |
+
},
|
814 |
+
{
|
815 |
+
"epoch": 9.26,
|
816 |
+
"learning_rate": 0.0032500000000000003,
|
817 |
+
"loss": 1.1028,
|
818 |
+
"step": 1350
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 9.33,
|
822 |
+
"learning_rate": 0.0032,
|
823 |
+
"loss": 1.0727,
|
824 |
+
"step": 1360
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 9.4,
|
828 |
+
"learning_rate": 0.00315,
|
829 |
+
"loss": 1.074,
|
830 |
+
"step": 1370
|
831 |
+
},
|
832 |
+
{
|
833 |
+
"epoch": 9.47,
|
834 |
+
"learning_rate": 0.0031,
|
835 |
+
"loss": 1.0605,
|
836 |
+
"step": 1380
|
837 |
+
},
|
838 |
+
{
|
839 |
+
"epoch": 9.54,
|
840 |
+
"learning_rate": 0.00305,
|
841 |
+
"loss": 1.0896,
|
842 |
+
"step": 1390
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 9.61,
|
846 |
+
"learning_rate": 0.003,
|
847 |
+
"loss": 1.0674,
|
848 |
+
"step": 1400
|
849 |
+
},
|
850 |
+
{
|
851 |
+
"epoch": 9.67,
|
852 |
+
"learning_rate": 0.00295,
|
853 |
+
"loss": 1.0894,
|
854 |
+
"step": 1410
|
855 |
+
},
|
856 |
+
{
|
857 |
+
"epoch": 9.74,
|
858 |
+
"learning_rate": 0.0029,
|
859 |
+
"loss": 1.0782,
|
860 |
+
"step": 1420
|
861 |
+
},
|
862 |
+
{
|
863 |
+
"epoch": 9.81,
|
864 |
+
"learning_rate": 0.0028499999999999997,
|
865 |
+
"loss": 1.0905,
|
866 |
+
"step": 1430
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 9.88,
|
870 |
+
"learning_rate": 0.0028000000000000004,
|
871 |
+
"loss": 1.0713,
|
872 |
+
"step": 1440
|
873 |
+
},
|
874 |
+
{
|
875 |
+
"epoch": 9.95,
|
876 |
+
"learning_rate": 0.0027500000000000003,
|
877 |
+
"loss": 1.0694,
|
878 |
+
"step": 1450
|
879 |
+
},
|
880 |
+
{
|
881 |
+
"epoch": 10.02,
|
882 |
+
"learning_rate": 0.0027,
|
883 |
+
"loss": 1.0734,
|
884 |
+
"step": 1460
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 10.09,
|
888 |
+
"learning_rate": 0.00265,
|
889 |
+
"loss": 1.0836,
|
890 |
+
"step": 1470
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 10.15,
|
894 |
+
"learning_rate": 0.0026000000000000003,
|
895 |
+
"loss": 1.033,
|
896 |
+
"step": 1480
|
897 |
+
},
|
898 |
+
{
|
899 |
+
"epoch": 10.22,
|
900 |
+
"learning_rate": 0.00255,
|
901 |
+
"loss": 1.0646,
|
902 |
+
"step": 1490
|
903 |
+
},
|
904 |
+
{
|
905 |
+
"epoch": 10.29,
|
906 |
+
"learning_rate": 0.0025,
|
907 |
+
"loss": 1.0718,
|
908 |
+
"step": 1500
|
909 |
+
},
|
910 |
+
{
|
911 |
+
"epoch": 10.36,
|
912 |
+
"learning_rate": 0.00245,
|
913 |
+
"loss": 1.0507,
|
914 |
+
"step": 1510
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 10.43,
|
918 |
+
"learning_rate": 0.0024,
|
919 |
+
"loss": 1.057,
|
920 |
+
"step": 1520
|
921 |
+
},
|
922 |
+
{
|
923 |
+
"epoch": 10.5,
|
924 |
+
"learning_rate": 0.00235,
|
925 |
+
"loss": 1.0603,
|
926 |
+
"step": 1530
|
927 |
+
},
|
928 |
+
{
|
929 |
+
"epoch": 10.57,
|
930 |
+
"learning_rate": 0.0023,
|
931 |
+
"loss": 1.0669,
|
932 |
+
"step": 1540
|
933 |
+
},
|
934 |
+
{
|
935 |
+
"epoch": 10.63,
|
936 |
+
"learning_rate": 0.0022500000000000003,
|
937 |
+
"loss": 1.0766,
|
938 |
+
"step": 1550
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 10.7,
|
942 |
+
"learning_rate": 0.0022,
|
943 |
+
"loss": 1.0346,
|
944 |
+
"step": 1560
|
945 |
+
},
|
946 |
+
{
|
947 |
+
"epoch": 10.77,
|
948 |
+
"learning_rate": 0.00215,
|
949 |
+
"loss": 1.0648,
|
950 |
+
"step": 1570
|
951 |
+
},
|
952 |
+
{
|
953 |
+
"epoch": 10.84,
|
954 |
+
"learning_rate": 0.0021,
|
955 |
+
"loss": 1.053,
|
956 |
+
"step": 1580
|
957 |
+
},
|
958 |
+
{
|
959 |
+
"epoch": 10.91,
|
960 |
+
"learning_rate": 0.0020499999999999997,
|
961 |
+
"loss": 1.0558,
|
962 |
+
"step": 1590
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 10.98,
|
966 |
+
"learning_rate": 0.002,
|
967 |
+
"loss": 1.0997,
|
968 |
+
"step": 1600
|
969 |
+
},
|
970 |
+
{
|
971 |
+
"epoch": 11.05,
|
972 |
+
"learning_rate": 0.0019500000000000001,
|
973 |
+
"loss": 1.0345,
|
974 |
+
"step": 1610
|
975 |
+
},
|
976 |
+
{
|
977 |
+
"epoch": 11.11,
|
978 |
+
"learning_rate": 0.0019,
|
979 |
+
"loss": 1.0371,
|
980 |
+
"step": 1620
|
981 |
+
},
|
982 |
+
{
|
983 |
+
"epoch": 11.18,
|
984 |
+
"learning_rate": 0.00185,
|
985 |
+
"loss": 1.0542,
|
986 |
+
"step": 1630
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 11.25,
|
990 |
+
"learning_rate": 0.0018,
|
991 |
+
"loss": 1.0702,
|
992 |
+
"step": 1640
|
993 |
+
},
|
994 |
+
{
|
995 |
+
"epoch": 11.32,
|
996 |
+
"learning_rate": 0.0017499999999999998,
|
997 |
+
"loss": 1.0396,
|
998 |
+
"step": 1650
|
999 |
+
},
|
1000 |
+
{
|
1001 |
+
"epoch": 11.39,
|
1002 |
+
"learning_rate": 0.0017000000000000001,
|
1003 |
+
"loss": 1.0159,
|
1004 |
+
"step": 1660
|
1005 |
+
},
|
1006 |
+
{
|
1007 |
+
"epoch": 11.46,
|
1008 |
+
"learning_rate": 0.0016500000000000002,
|
1009 |
+
"loss": 1.0364,
|
1010 |
+
"step": 1670
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 11.53,
|
1014 |
+
"learning_rate": 0.0016,
|
1015 |
+
"loss": 1.054,
|
1016 |
+
"step": 1680
|
1017 |
+
},
|
1018 |
+
{
|
1019 |
+
"epoch": 11.6,
|
1020 |
+
"learning_rate": 0.00155,
|
1021 |
+
"loss": 1.0384,
|
1022 |
+
"step": 1690
|
1023 |
+
},
|
1024 |
+
{
|
1025 |
+
"epoch": 11.66,
|
1026 |
+
"learning_rate": 0.0015,
|
1027 |
+
"loss": 1.0737,
|
1028 |
+
"step": 1700
|
1029 |
+
},
|
1030 |
+
{
|
1031 |
+
"epoch": 11.73,
|
1032 |
+
"learning_rate": 0.00145,
|
1033 |
+
"loss": 1.0502,
|
1034 |
+
"step": 1710
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 11.8,
|
1038 |
+
"learning_rate": 0.0014000000000000002,
|
1039 |
+
"loss": 1.0762,
|
1040 |
+
"step": 1720
|
1041 |
+
},
|
1042 |
+
{
|
1043 |
+
"epoch": 11.87,
|
1044 |
+
"learning_rate": 0.00135,
|
1045 |
+
"loss": 1.0386,
|
1046 |
+
"step": 1730
|
1047 |
+
},
|
1048 |
+
{
|
1049 |
+
"epoch": 11.94,
|
1050 |
+
"learning_rate": 0.0013000000000000002,
|
1051 |
+
"loss": 1.0463,
|
1052 |
+
"step": 1740
|
1053 |
+
},
|
1054 |
+
{
|
1055 |
+
"epoch": 12.01,
|
1056 |
+
"learning_rate": 0.00125,
|
1057 |
+
"loss": 1.0513,
|
1058 |
+
"step": 1750
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 12.08,
|
1062 |
+
"learning_rate": 0.0012,
|
1063 |
+
"loss": 1.044,
|
1064 |
+
"step": 1760
|
1065 |
+
},
|
1066 |
+
{
|
1067 |
+
"epoch": 12.14,
|
1068 |
+
"learning_rate": 0.00115,
|
1069 |
+
"loss": 1.0252,
|
1070 |
+
"step": 1770
|
1071 |
+
},
|
1072 |
+
{
|
1073 |
+
"epoch": 12.21,
|
1074 |
+
"learning_rate": 0.0011,
|
1075 |
+
"loss": 1.0311,
|
1076 |
+
"step": 1780
|
1077 |
+
},
|
1078 |
+
{
|
1079 |
+
"epoch": 12.28,
|
1080 |
+
"learning_rate": 0.00105,
|
1081 |
+
"loss": 1.015,
|
1082 |
+
"step": 1790
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 12.35,
|
1086 |
+
"learning_rate": 0.001,
|
1087 |
+
"loss": 1.0654,
|
1088 |
+
"step": 1800
|
1089 |
+
},
|
1090 |
+
{
|
1091 |
+
"epoch": 12.42,
|
1092 |
+
"learning_rate": 0.00095,
|
1093 |
+
"loss": 1.0541,
|
1094 |
+
"step": 1810
|
1095 |
+
},
|
1096 |
+
{
|
1097 |
+
"epoch": 12.49,
|
1098 |
+
"learning_rate": 0.0009,
|
1099 |
+
"loss": 1.0525,
|
1100 |
+
"step": 1820
|
1101 |
+
},
|
1102 |
+
{
|
1103 |
+
"epoch": 12.56,
|
1104 |
+
"learning_rate": 0.0008500000000000001,
|
1105 |
+
"loss": 1.0251,
|
1106 |
+
"step": 1830
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 12.62,
|
1110 |
+
"learning_rate": 0.0008,
|
1111 |
+
"loss": 1.0657,
|
1112 |
+
"step": 1840
|
1113 |
+
},
|
1114 |
+
{
|
1115 |
+
"epoch": 12.69,
|
1116 |
+
"learning_rate": 0.00075,
|
1117 |
+
"loss": 1.041,
|
1118 |
+
"step": 1850
|
1119 |
+
},
|
1120 |
+
{
|
1121 |
+
"epoch": 12.76,
|
1122 |
+
"learning_rate": 0.0007000000000000001,
|
1123 |
+
"loss": 1.025,
|
1124 |
+
"step": 1860
|
1125 |
+
},
|
1126 |
+
{
|
1127 |
+
"epoch": 12.83,
|
1128 |
+
"learning_rate": 0.0006500000000000001,
|
1129 |
+
"loss": 1.0255,
|
1130 |
+
"step": 1870
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 12.9,
|
1134 |
+
"learning_rate": 0.0006,
|
1135 |
+
"loss": 1.0641,
|
1136 |
+
"step": 1880
|
1137 |
+
},
|
1138 |
+
{
|
1139 |
+
"epoch": 12.97,
|
1140 |
+
"learning_rate": 0.00055,
|
1141 |
+
"loss": 1.0529,
|
1142 |
+
"step": 1890
|
1143 |
+
},
|
1144 |
+
{
|
1145 |
+
"epoch": 13.04,
|
1146 |
+
"learning_rate": 0.0005,
|
1147 |
+
"loss": 1.0367,
|
1148 |
+
"step": 1900
|
1149 |
+
},
|
1150 |
+
{
|
1151 |
+
"epoch": 13.1,
|
1152 |
+
"learning_rate": 0.00045,
|
1153 |
+
"loss": 1.0461,
|
1154 |
+
"step": 1910
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 13.17,
|
1158 |
+
"learning_rate": 0.0004,
|
1159 |
+
"loss": 1.0197,
|
1160 |
+
"step": 1920
|
1161 |
+
},
|
1162 |
+
{
|
1163 |
+
"epoch": 13.24,
|
1164 |
+
"learning_rate": 0.00035000000000000005,
|
1165 |
+
"loss": 1.0339,
|
1166 |
+
"step": 1930
|
1167 |
+
},
|
1168 |
+
{
|
1169 |
+
"epoch": 13.31,
|
1170 |
+
"learning_rate": 0.0003,
|
1171 |
+
"loss": 1.0274,
|
1172 |
+
"step": 1940
|
1173 |
+
},
|
1174 |
+
{
|
1175 |
+
"epoch": 13.38,
|
1176 |
+
"learning_rate": 0.00025,
|
1177 |
+
"loss": 1.0222,
|
1178 |
+
"step": 1950
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 13.45,
|
1182 |
+
"learning_rate": 0.0002,
|
1183 |
+
"loss": 1.0174,
|
1184 |
+
"step": 1960
|
1185 |
+
},
|
1186 |
+
{
|
1187 |
+
"epoch": 13.52,
|
1188 |
+
"learning_rate": 0.00015,
|
1189 |
+
"loss": 1.0295,
|
1190 |
+
"step": 1970
|
1191 |
+
},
|
1192 |
+
{
|
1193 |
+
"epoch": 13.58,
|
1194 |
+
"learning_rate": 0.0001,
|
1195 |
+
"loss": 1.0226,
|
1196 |
+
"step": 1980
|
1197 |
+
},
|
1198 |
+
{
|
1199 |
+
"epoch": 13.65,
|
1200 |
+
"learning_rate": 5e-05,
|
1201 |
+
"loss": 1.0655,
|
1202 |
+
"step": 1990
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 13.72,
|
1206 |
+
"learning_rate": 0.0,
|
1207 |
+
"loss": 1.0367,
|
1208 |
+
"step": 2000
|
1209 |
+
}
|
1210 |
+
],
|
1211 |
+
"max_steps": 2000,
|
1212 |
+
"num_train_epochs": 14,
|
1213 |
+
"total_flos": 3.447484134404915e+18,
|
1214 |
+
"trial_name": null,
|
1215 |
+
"trial_params": null
|
1216 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e51401596771f42fd15dd52fcb4c55c4e2a4614e082ab6863e26e1b893c4e8a5
|
3 |
+
size 4091
|