Upload folder using huggingface_hub
Browse files- README.md +34 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +32 -0
- trainer_state.json +4447 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float16
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: False
|
22 |
+
- load_in_4bit: True
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: nf4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float16
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.6.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.6.0.dev0
|
adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:818cd5ef272767adbc6f2346305bfbe5fc9ba58b087284172cdfa582df7e51cf
|
3 |
+
size 33600461
|
optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:afa76d55162236f79291a83db817b2b14252b2fef18b1ad5b7ebce191f57b237
|
3 |
+
size 67216581
|
rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b279e8d4c1d9ebd6ff60079c2af9249e8b34b6637fe4ac5fdabd2076009dda5
|
3 |
+
size 15607
|
rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc17c54d3e115e77227ed37aab1e6cf82e460539c37cca5d7392af265ed74cb7
|
3 |
+
size 15607
|
scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0690f3bd7ad7e2ac9ef3993fda1ea1ed587211a3d643ae14167cea41d6493026
|
3 |
+
size 627
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "</s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"eos_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"model_max_length": 2048,
|
20 |
+
"pad_token": null,
|
21 |
+
"sp_model_kwargs": {},
|
22 |
+
"tokenizer_class": "LlamaTokenizer",
|
23 |
+
"unk_token": {
|
24 |
+
"__type": "AddedToken",
|
25 |
+
"content": "<unk>",
|
26 |
+
"lstrip": false,
|
27 |
+
"normalized": true,
|
28 |
+
"rstrip": false,
|
29 |
+
"single_word": false
|
30 |
+
},
|
31 |
+
"use_default_system_prompt": true
|
32 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,4447 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.1179438864315028,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 7386,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.0,
|
13 |
+
"learning_rate": 4.790036723614881e-07,
|
14 |
+
"loss": 1.5083,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.0,
|
19 |
+
"learning_rate": 9.580073447229762e-07,
|
20 |
+
"loss": 1.4983,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.0,
|
25 |
+
"learning_rate": 1.437011017084464e-06,
|
26 |
+
"loss": 1.4938,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.0,
|
31 |
+
"learning_rate": 1.9160146894459524e-06,
|
32 |
+
"loss": 1.4914,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.0,
|
37 |
+
"learning_rate": 2.3950183618074405e-06,
|
38 |
+
"loss": 1.4758,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.0,
|
43 |
+
"learning_rate": 2.874022034168928e-06,
|
44 |
+
"loss": 1.4549,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.0,
|
49 |
+
"learning_rate": 3.3530257065304165e-06,
|
50 |
+
"loss": 1.4589,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.0,
|
55 |
+
"learning_rate": 3.832029378891905e-06,
|
56 |
+
"loss": 1.423,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.0,
|
61 |
+
"learning_rate": 4.311033051253392e-06,
|
62 |
+
"loss": 1.39,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.0,
|
67 |
+
"learning_rate": 4.790036723614881e-06,
|
68 |
+
"loss": 1.3579,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.0,
|
73 |
+
"learning_rate": 5.269040395976369e-06,
|
74 |
+
"loss": 1.3309,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.0,
|
79 |
+
"learning_rate": 5.748044068337856e-06,
|
80 |
+
"loss": 1.3144,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.0,
|
85 |
+
"learning_rate": 6.227047740699345e-06,
|
86 |
+
"loss": 1.3007,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.0,
|
91 |
+
"learning_rate": 6.706051413060833e-06,
|
92 |
+
"loss": 1.2618,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.0,
|
97 |
+
"learning_rate": 7.185055085422321e-06,
|
98 |
+
"loss": 1.2586,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.0,
|
103 |
+
"learning_rate": 7.66405875778381e-06,
|
104 |
+
"loss": 1.2345,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.0,
|
109 |
+
"learning_rate": 8.143062430145297e-06,
|
110 |
+
"loss": 1.2088,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.0,
|
115 |
+
"learning_rate": 8.622066102506784e-06,
|
116 |
+
"loss": 1.1936,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.0,
|
121 |
+
"learning_rate": 9.101069774868273e-06,
|
122 |
+
"loss": 1.1791,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.0,
|
127 |
+
"learning_rate": 9.580073447229762e-06,
|
128 |
+
"loss": 1.1724,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.0,
|
133 |
+
"learning_rate": 1.0059077119591249e-05,
|
134 |
+
"loss": 1.1602,
|
135 |
+
"step": 210
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.0,
|
139 |
+
"learning_rate": 1.0538080791952738e-05,
|
140 |
+
"loss": 1.1546,
|
141 |
+
"step": 220
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.0,
|
145 |
+
"learning_rate": 1.1017084464314227e-05,
|
146 |
+
"loss": 1.1434,
|
147 |
+
"step": 230
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.0,
|
151 |
+
"learning_rate": 1.1496088136675712e-05,
|
152 |
+
"loss": 1.1119,
|
153 |
+
"step": 240
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.0,
|
157 |
+
"learning_rate": 1.1975091809037201e-05,
|
158 |
+
"loss": 1.0983,
|
159 |
+
"step": 250
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.0,
|
163 |
+
"learning_rate": 1.245409548139869e-05,
|
164 |
+
"loss": 1.0826,
|
165 |
+
"step": 260
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.0,
|
169 |
+
"learning_rate": 1.2933099153760177e-05,
|
170 |
+
"loss": 1.0324,
|
171 |
+
"step": 270
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.0,
|
175 |
+
"learning_rate": 1.3412102826121666e-05,
|
176 |
+
"loss": 1.0157,
|
177 |
+
"step": 280
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.0,
|
181 |
+
"learning_rate": 1.3891106498483155e-05,
|
182 |
+
"loss": 0.9962,
|
183 |
+
"step": 290
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.0,
|
187 |
+
"learning_rate": 1.4370110170844642e-05,
|
188 |
+
"loss": 0.9938,
|
189 |
+
"step": 300
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.0,
|
193 |
+
"learning_rate": 1.484911384320613e-05,
|
194 |
+
"loss": 1.0055,
|
195 |
+
"step": 310
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.01,
|
199 |
+
"learning_rate": 1.532811751556762e-05,
|
200 |
+
"loss": 0.9723,
|
201 |
+
"step": 320
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.01,
|
205 |
+
"learning_rate": 1.5807121187929107e-05,
|
206 |
+
"loss": 1.0011,
|
207 |
+
"step": 330
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.01,
|
211 |
+
"learning_rate": 1.6286124860290594e-05,
|
212 |
+
"loss": 0.9864,
|
213 |
+
"step": 340
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.01,
|
217 |
+
"learning_rate": 1.676512853265208e-05,
|
218 |
+
"loss": 0.9877,
|
219 |
+
"step": 350
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.01,
|
223 |
+
"learning_rate": 1.7244132205013568e-05,
|
224 |
+
"loss": 0.9937,
|
225 |
+
"step": 360
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.01,
|
229 |
+
"learning_rate": 1.772313587737506e-05,
|
230 |
+
"loss": 0.99,
|
231 |
+
"step": 370
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.01,
|
235 |
+
"learning_rate": 1.8202139549736546e-05,
|
236 |
+
"loss": 0.9943,
|
237 |
+
"step": 380
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.01,
|
241 |
+
"learning_rate": 1.8681143222098033e-05,
|
242 |
+
"loss": 0.9744,
|
243 |
+
"step": 390
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 0.01,
|
247 |
+
"learning_rate": 1.9160146894459524e-05,
|
248 |
+
"loss": 0.9678,
|
249 |
+
"step": 400
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.01,
|
253 |
+
"learning_rate": 1.9639150566821007e-05,
|
254 |
+
"loss": 0.9756,
|
255 |
+
"step": 410
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 0.01,
|
259 |
+
"learning_rate": 2.0118154239182498e-05,
|
260 |
+
"loss": 0.9665,
|
261 |
+
"step": 420
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 0.01,
|
265 |
+
"learning_rate": 2.0597157911543985e-05,
|
266 |
+
"loss": 0.9528,
|
267 |
+
"step": 430
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 0.01,
|
271 |
+
"learning_rate": 2.1076161583905476e-05,
|
272 |
+
"loss": 0.9609,
|
273 |
+
"step": 440
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 0.01,
|
277 |
+
"learning_rate": 2.1555165256266963e-05,
|
278 |
+
"loss": 0.9616,
|
279 |
+
"step": 450
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 0.01,
|
283 |
+
"learning_rate": 2.2034168928628453e-05,
|
284 |
+
"loss": 0.9685,
|
285 |
+
"step": 460
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 0.01,
|
289 |
+
"learning_rate": 2.2513172600989937e-05,
|
290 |
+
"loss": 0.9523,
|
291 |
+
"step": 470
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.01,
|
295 |
+
"learning_rate": 2.2992176273351424e-05,
|
296 |
+
"loss": 0.9581,
|
297 |
+
"step": 480
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 0.01,
|
301 |
+
"learning_rate": 2.3471179945712915e-05,
|
302 |
+
"loss": 0.9551,
|
303 |
+
"step": 490
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 0.01,
|
307 |
+
"learning_rate": 2.3950183618074402e-05,
|
308 |
+
"loss": 0.9697,
|
309 |
+
"step": 500
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 0.01,
|
313 |
+
"learning_rate": 2.4429187290435893e-05,
|
314 |
+
"loss": 0.9729,
|
315 |
+
"step": 510
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 0.01,
|
319 |
+
"learning_rate": 2.490819096279738e-05,
|
320 |
+
"loss": 0.9724,
|
321 |
+
"step": 520
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.01,
|
325 |
+
"learning_rate": 2.5387194635158867e-05,
|
326 |
+
"loss": 0.9709,
|
327 |
+
"step": 530
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 0.01,
|
331 |
+
"learning_rate": 2.5866198307520354e-05,
|
332 |
+
"loss": 0.9707,
|
333 |
+
"step": 540
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 0.01,
|
337 |
+
"learning_rate": 2.634520197988184e-05,
|
338 |
+
"loss": 0.9615,
|
339 |
+
"step": 550
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 0.01,
|
343 |
+
"learning_rate": 2.6824205652243332e-05,
|
344 |
+
"loss": 0.9586,
|
345 |
+
"step": 560
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 0.01,
|
349 |
+
"learning_rate": 2.730320932460482e-05,
|
350 |
+
"loss": 0.9723,
|
351 |
+
"step": 570
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 0.01,
|
355 |
+
"learning_rate": 2.778221299696631e-05,
|
356 |
+
"loss": 0.9537,
|
357 |
+
"step": 580
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 0.01,
|
361 |
+
"learning_rate": 2.8261216669327797e-05,
|
362 |
+
"loss": 0.9701,
|
363 |
+
"step": 590
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.01,
|
367 |
+
"learning_rate": 2.8740220341689284e-05,
|
368 |
+
"loss": 0.9648,
|
369 |
+
"step": 600
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 0.01,
|
373 |
+
"learning_rate": 2.921922401405077e-05,
|
374 |
+
"loss": 0.9469,
|
375 |
+
"step": 610
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 0.01,
|
379 |
+
"learning_rate": 2.969822768641226e-05,
|
380 |
+
"loss": 0.9543,
|
381 |
+
"step": 620
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 0.01,
|
385 |
+
"learning_rate": 3.017723135877375e-05,
|
386 |
+
"loss": 0.9705,
|
387 |
+
"step": 630
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 0.01,
|
391 |
+
"learning_rate": 3.065623503113524e-05,
|
392 |
+
"loss": 0.9661,
|
393 |
+
"step": 640
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.01,
|
397 |
+
"learning_rate": 3.1135238703496726e-05,
|
398 |
+
"loss": 0.979,
|
399 |
+
"step": 650
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.01,
|
403 |
+
"learning_rate": 3.1614242375858214e-05,
|
404 |
+
"loss": 0.9702,
|
405 |
+
"step": 660
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.01,
|
409 |
+
"learning_rate": 3.20932460482197e-05,
|
410 |
+
"loss": 0.9859,
|
411 |
+
"step": 670
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.01,
|
415 |
+
"learning_rate": 3.257224972058119e-05,
|
416 |
+
"loss": 0.9815,
|
417 |
+
"step": 680
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.01,
|
421 |
+
"learning_rate": 3.3051253392942675e-05,
|
422 |
+
"loss": 0.9949,
|
423 |
+
"step": 690
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.01,
|
427 |
+
"learning_rate": 3.353025706530416e-05,
|
428 |
+
"loss": 0.9808,
|
429 |
+
"step": 700
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.01,
|
433 |
+
"learning_rate": 3.4009260737665656e-05,
|
434 |
+
"loss": 0.9637,
|
435 |
+
"step": 710
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.01,
|
439 |
+
"learning_rate": 3.4488264410027136e-05,
|
440 |
+
"loss": 0.9975,
|
441 |
+
"step": 720
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.01,
|
445 |
+
"learning_rate": 3.496726808238863e-05,
|
446 |
+
"loss": 1.0081,
|
447 |
+
"step": 730
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.01,
|
451 |
+
"learning_rate": 3.544627175475012e-05,
|
452 |
+
"loss": 1.006,
|
453 |
+
"step": 740
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.01,
|
457 |
+
"learning_rate": 3.5925275427111605e-05,
|
458 |
+
"loss": 0.9949,
|
459 |
+
"step": 750
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.01,
|
463 |
+
"learning_rate": 3.640427909947309e-05,
|
464 |
+
"loss": 0.9723,
|
465 |
+
"step": 760
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.01,
|
469 |
+
"learning_rate": 3.6883282771834586e-05,
|
470 |
+
"loss": 0.9761,
|
471 |
+
"step": 770
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.01,
|
475 |
+
"learning_rate": 3.7362286444196066e-05,
|
476 |
+
"loss": 0.9877,
|
477 |
+
"step": 780
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.01,
|
481 |
+
"learning_rate": 3.784129011655756e-05,
|
482 |
+
"loss": 0.9878,
|
483 |
+
"step": 790
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.01,
|
487 |
+
"learning_rate": 3.832029378891905e-05,
|
488 |
+
"loss": 0.9703,
|
489 |
+
"step": 800
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.01,
|
493 |
+
"learning_rate": 3.879929746128053e-05,
|
494 |
+
"loss": 0.9863,
|
495 |
+
"step": 810
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.01,
|
499 |
+
"learning_rate": 3.9278301133642015e-05,
|
500 |
+
"loss": 0.9522,
|
501 |
+
"step": 820
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.01,
|
505 |
+
"learning_rate": 3.975730480600351e-05,
|
506 |
+
"loss": 0.9087,
|
507 |
+
"step": 830
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.01,
|
511 |
+
"learning_rate": 4.0236308478364996e-05,
|
512 |
+
"loss": 0.9289,
|
513 |
+
"step": 840
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.01,
|
517 |
+
"learning_rate": 4.071531215072648e-05,
|
518 |
+
"loss": 0.9115,
|
519 |
+
"step": 850
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.01,
|
523 |
+
"learning_rate": 4.119431582308797e-05,
|
524 |
+
"loss": 0.931,
|
525 |
+
"step": 860
|
526 |
+
},
|
527 |
+
{
|
528 |
+
"epoch": 0.01,
|
529 |
+
"learning_rate": 4.1673319495449464e-05,
|
530 |
+
"loss": 0.909,
|
531 |
+
"step": 870
|
532 |
+
},
|
533 |
+
{
|
534 |
+
"epoch": 0.01,
|
535 |
+
"learning_rate": 4.215232316781095e-05,
|
536 |
+
"loss": 0.9239,
|
537 |
+
"step": 880
|
538 |
+
},
|
539 |
+
{
|
540 |
+
"epoch": 0.01,
|
541 |
+
"learning_rate": 4.263132684017244e-05,
|
542 |
+
"loss": 0.9346,
|
543 |
+
"step": 890
|
544 |
+
},
|
545 |
+
{
|
546 |
+
"epoch": 0.01,
|
547 |
+
"learning_rate": 4.3110330512533926e-05,
|
548 |
+
"loss": 0.9121,
|
549 |
+
"step": 900
|
550 |
+
},
|
551 |
+
{
|
552 |
+
"epoch": 0.01,
|
553 |
+
"learning_rate": 4.358933418489542e-05,
|
554 |
+
"loss": 0.9179,
|
555 |
+
"step": 910
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 0.01,
|
559 |
+
"learning_rate": 4.406833785725691e-05,
|
560 |
+
"loss": 0.9212,
|
561 |
+
"step": 920
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.01,
|
565 |
+
"learning_rate": 4.4547341529618394e-05,
|
566 |
+
"loss": 0.9025,
|
567 |
+
"step": 930
|
568 |
+
},
|
569 |
+
{
|
570 |
+
"epoch": 0.02,
|
571 |
+
"learning_rate": 4.5026345201979874e-05,
|
572 |
+
"loss": 0.9307,
|
573 |
+
"step": 940
|
574 |
+
},
|
575 |
+
{
|
576 |
+
"epoch": 0.02,
|
577 |
+
"learning_rate": 4.550534887434136e-05,
|
578 |
+
"loss": 0.9262,
|
579 |
+
"step": 950
|
580 |
+
},
|
581 |
+
{
|
582 |
+
"epoch": 0.02,
|
583 |
+
"learning_rate": 4.598435254670285e-05,
|
584 |
+
"loss": 0.9053,
|
585 |
+
"step": 960
|
586 |
+
},
|
587 |
+
{
|
588 |
+
"epoch": 0.02,
|
589 |
+
"learning_rate": 4.646335621906434e-05,
|
590 |
+
"loss": 0.9079,
|
591 |
+
"step": 970
|
592 |
+
},
|
593 |
+
{
|
594 |
+
"epoch": 0.02,
|
595 |
+
"learning_rate": 4.694235989142583e-05,
|
596 |
+
"loss": 0.9104,
|
597 |
+
"step": 980
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 0.02,
|
601 |
+
"learning_rate": 4.742136356378732e-05,
|
602 |
+
"loss": 0.9131,
|
603 |
+
"step": 990
|
604 |
+
},
|
605 |
+
{
|
606 |
+
"epoch": 0.02,
|
607 |
+
"learning_rate": 4.7900367236148804e-05,
|
608 |
+
"loss": 0.9434,
|
609 |
+
"step": 1000
|
610 |
+
},
|
611 |
+
{
|
612 |
+
"epoch": 0.02,
|
613 |
+
"learning_rate": 4.83793709085103e-05,
|
614 |
+
"loss": 0.9321,
|
615 |
+
"step": 1010
|
616 |
+
},
|
617 |
+
{
|
618 |
+
"epoch": 0.02,
|
619 |
+
"learning_rate": 4.8858374580871785e-05,
|
620 |
+
"loss": 0.9411,
|
621 |
+
"step": 1020
|
622 |
+
},
|
623 |
+
{
|
624 |
+
"epoch": 0.02,
|
625 |
+
"learning_rate": 4.933737825323327e-05,
|
626 |
+
"loss": 0.9419,
|
627 |
+
"step": 1030
|
628 |
+
},
|
629 |
+
{
|
630 |
+
"epoch": 0.02,
|
631 |
+
"learning_rate": 4.981638192559476e-05,
|
632 |
+
"loss": 0.9285,
|
633 |
+
"step": 1040
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.02,
|
637 |
+
"learning_rate": 5.029538559795625e-05,
|
638 |
+
"loss": 0.9529,
|
639 |
+
"step": 1050
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 0.02,
|
643 |
+
"learning_rate": 5.0774389270317734e-05,
|
644 |
+
"loss": 0.9518,
|
645 |
+
"step": 1060
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 0.02,
|
649 |
+
"learning_rate": 5.125339294267922e-05,
|
650 |
+
"loss": 0.941,
|
651 |
+
"step": 1070
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 0.02,
|
655 |
+
"learning_rate": 5.173239661504071e-05,
|
656 |
+
"loss": 0.9399,
|
657 |
+
"step": 1080
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 0.02,
|
661 |
+
"learning_rate": 5.2211400287402195e-05,
|
662 |
+
"loss": 0.9463,
|
663 |
+
"step": 1090
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 0.02,
|
667 |
+
"learning_rate": 5.269040395976368e-05,
|
668 |
+
"loss": 0.922,
|
669 |
+
"step": 1100
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 0.02,
|
673 |
+
"learning_rate": 5.3169407632125176e-05,
|
674 |
+
"loss": 0.9496,
|
675 |
+
"step": 1110
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.02,
|
679 |
+
"learning_rate": 5.3648411304486663e-05,
|
680 |
+
"loss": 0.9239,
|
681 |
+
"step": 1120
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 0.02,
|
685 |
+
"learning_rate": 5.412741497684815e-05,
|
686 |
+
"loss": 0.941,
|
687 |
+
"step": 1130
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 0.02,
|
691 |
+
"learning_rate": 5.460641864920964e-05,
|
692 |
+
"loss": 0.9189,
|
693 |
+
"step": 1140
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 0.02,
|
697 |
+
"learning_rate": 5.508542232157113e-05,
|
698 |
+
"loss": 0.9228,
|
699 |
+
"step": 1150
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 0.02,
|
703 |
+
"learning_rate": 5.556442599393262e-05,
|
704 |
+
"loss": 0.9792,
|
705 |
+
"step": 1160
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 0.02,
|
709 |
+
"learning_rate": 5.6043429666294106e-05,
|
710 |
+
"loss": 0.9682,
|
711 |
+
"step": 1170
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 0.02,
|
715 |
+
"learning_rate": 5.652243333865559e-05,
|
716 |
+
"loss": 0.9293,
|
717 |
+
"step": 1180
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.02,
|
721 |
+
"learning_rate": 5.7001437011017074e-05,
|
722 |
+
"loss": 0.96,
|
723 |
+
"step": 1190
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 0.02,
|
727 |
+
"learning_rate": 5.748044068337857e-05,
|
728 |
+
"loss": 0.9288,
|
729 |
+
"step": 1200
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 0.02,
|
733 |
+
"learning_rate": 5.7959444355740055e-05,
|
734 |
+
"loss": 0.955,
|
735 |
+
"step": 1210
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 0.02,
|
739 |
+
"learning_rate": 5.843844802810154e-05,
|
740 |
+
"loss": 0.9591,
|
741 |
+
"step": 1220
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 0.02,
|
745 |
+
"learning_rate": 5.891745170046303e-05,
|
746 |
+
"loss": 0.9684,
|
747 |
+
"step": 1230
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 0.02,
|
751 |
+
"learning_rate": 5.939645537282452e-05,
|
752 |
+
"loss": 0.9338,
|
753 |
+
"step": 1240
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 0.02,
|
757 |
+
"learning_rate": 5.987545904518601e-05,
|
758 |
+
"loss": 0.9663,
|
759 |
+
"step": 1250
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 0.02,
|
763 |
+
"learning_rate": 6.03544627175475e-05,
|
764 |
+
"loss": 0.9623,
|
765 |
+
"step": 1260
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 0.02,
|
769 |
+
"learning_rate": 6.0833466389908984e-05,
|
770 |
+
"loss": 0.9567,
|
771 |
+
"step": 1270
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 0.02,
|
775 |
+
"learning_rate": 6.131247006227048e-05,
|
776 |
+
"loss": 0.9332,
|
777 |
+
"step": 1280
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.02,
|
781 |
+
"learning_rate": 6.179147373463196e-05,
|
782 |
+
"loss": 0.9558,
|
783 |
+
"step": 1290
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.02,
|
787 |
+
"learning_rate": 6.227047740699345e-05,
|
788 |
+
"loss": 0.9696,
|
789 |
+
"step": 1300
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.02,
|
793 |
+
"learning_rate": 6.274948107935493e-05,
|
794 |
+
"loss": 0.955,
|
795 |
+
"step": 1310
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.02,
|
799 |
+
"learning_rate": 6.322848475171643e-05,
|
800 |
+
"loss": 0.9765,
|
801 |
+
"step": 1320
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.02,
|
805 |
+
"learning_rate": 6.370748842407791e-05,
|
806 |
+
"loss": 1.0007,
|
807 |
+
"step": 1330
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.02,
|
811 |
+
"learning_rate": 6.41864920964394e-05,
|
812 |
+
"loss": 1.0083,
|
813 |
+
"step": 1340
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.02,
|
817 |
+
"learning_rate": 6.466549576880088e-05,
|
818 |
+
"loss": 0.9953,
|
819 |
+
"step": 1350
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.02,
|
823 |
+
"learning_rate": 6.514449944116238e-05,
|
824 |
+
"loss": 0.9801,
|
825 |
+
"step": 1360
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.02,
|
829 |
+
"learning_rate": 6.562350311352387e-05,
|
830 |
+
"loss": 0.996,
|
831 |
+
"step": 1370
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.02,
|
835 |
+
"learning_rate": 6.610250678588535e-05,
|
836 |
+
"loss": 1.0034,
|
837 |
+
"step": 1380
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.02,
|
841 |
+
"learning_rate": 6.658151045824684e-05,
|
842 |
+
"loss": 1.0063,
|
843 |
+
"step": 1390
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.02,
|
847 |
+
"learning_rate": 6.706051413060832e-05,
|
848 |
+
"loss": 0.9886,
|
849 |
+
"step": 1400
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.02,
|
853 |
+
"learning_rate": 6.753951780296982e-05,
|
854 |
+
"loss": 1.0168,
|
855 |
+
"step": 1410
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.02,
|
859 |
+
"learning_rate": 6.801852147533131e-05,
|
860 |
+
"loss": 0.9977,
|
861 |
+
"step": 1420
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.02,
|
865 |
+
"learning_rate": 6.849752514769279e-05,
|
866 |
+
"loss": 0.9931,
|
867 |
+
"step": 1430
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.02,
|
871 |
+
"learning_rate": 6.897652882005427e-05,
|
872 |
+
"loss": 0.9978,
|
873 |
+
"step": 1440
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.02,
|
877 |
+
"learning_rate": 6.945553249241577e-05,
|
878 |
+
"loss": 0.9907,
|
879 |
+
"step": 1450
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.02,
|
883 |
+
"learning_rate": 6.993453616477726e-05,
|
884 |
+
"loss": 0.989,
|
885 |
+
"step": 1460
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.02,
|
889 |
+
"learning_rate": 7.041353983713874e-05,
|
890 |
+
"loss": 0.9947,
|
891 |
+
"step": 1470
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.02,
|
895 |
+
"learning_rate": 7.089254350950024e-05,
|
896 |
+
"loss": 1.0033,
|
897 |
+
"step": 1480
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.02,
|
901 |
+
"learning_rate": 7.137154718186172e-05,
|
902 |
+
"loss": 0.9806,
|
903 |
+
"step": 1490
|
904 |
+
},
|
905 |
+
{
|
906 |
+
"epoch": 0.02,
|
907 |
+
"learning_rate": 7.185055085422321e-05,
|
908 |
+
"loss": 0.999,
|
909 |
+
"step": 1500
|
910 |
+
},
|
911 |
+
{
|
912 |
+
"epoch": 0.02,
|
913 |
+
"learning_rate": 7.23295545265847e-05,
|
914 |
+
"loss": 0.9932,
|
915 |
+
"step": 1510
|
916 |
+
},
|
917 |
+
{
|
918 |
+
"epoch": 0.02,
|
919 |
+
"learning_rate": 7.280855819894618e-05,
|
920 |
+
"loss": 0.9771,
|
921 |
+
"step": 1520
|
922 |
+
},
|
923 |
+
{
|
924 |
+
"epoch": 0.02,
|
925 |
+
"learning_rate": 7.328756187130768e-05,
|
926 |
+
"loss": 0.9791,
|
927 |
+
"step": 1530
|
928 |
+
},
|
929 |
+
{
|
930 |
+
"epoch": 0.02,
|
931 |
+
"learning_rate": 7.376656554366917e-05,
|
932 |
+
"loss": 0.978,
|
933 |
+
"step": 1540
|
934 |
+
},
|
935 |
+
{
|
936 |
+
"epoch": 0.02,
|
937 |
+
"learning_rate": 7.424556921603065e-05,
|
938 |
+
"loss": 0.9864,
|
939 |
+
"step": 1550
|
940 |
+
},
|
941 |
+
{
|
942 |
+
"epoch": 0.02,
|
943 |
+
"learning_rate": 7.472457288839213e-05,
|
944 |
+
"loss": 0.9846,
|
945 |
+
"step": 1560
|
946 |
+
},
|
947 |
+
{
|
948 |
+
"epoch": 0.03,
|
949 |
+
"learning_rate": 7.520357656075363e-05,
|
950 |
+
"loss": 0.9796,
|
951 |
+
"step": 1570
|
952 |
+
},
|
953 |
+
{
|
954 |
+
"epoch": 0.03,
|
955 |
+
"learning_rate": 7.568258023311512e-05,
|
956 |
+
"loss": 0.9704,
|
957 |
+
"step": 1580
|
958 |
+
},
|
959 |
+
{
|
960 |
+
"epoch": 0.03,
|
961 |
+
"learning_rate": 7.616158390547661e-05,
|
962 |
+
"loss": 0.983,
|
963 |
+
"step": 1590
|
964 |
+
},
|
965 |
+
{
|
966 |
+
"epoch": 0.03,
|
967 |
+
"learning_rate": 7.66405875778381e-05,
|
968 |
+
"loss": 0.982,
|
969 |
+
"step": 1600
|
970 |
+
},
|
971 |
+
{
|
972 |
+
"epoch": 0.03,
|
973 |
+
"learning_rate": 7.711959125019959e-05,
|
974 |
+
"loss": 0.9753,
|
975 |
+
"step": 1610
|
976 |
+
},
|
977 |
+
{
|
978 |
+
"epoch": 0.03,
|
979 |
+
"learning_rate": 7.759859492256106e-05,
|
980 |
+
"loss": 0.9864,
|
981 |
+
"step": 1620
|
982 |
+
},
|
983 |
+
{
|
984 |
+
"epoch": 0.03,
|
985 |
+
"learning_rate": 7.807759859492255e-05,
|
986 |
+
"loss": 0.983,
|
987 |
+
"step": 1630
|
988 |
+
},
|
989 |
+
{
|
990 |
+
"epoch": 0.03,
|
991 |
+
"learning_rate": 7.855660226728403e-05,
|
992 |
+
"loss": 0.9886,
|
993 |
+
"step": 1640
|
994 |
+
},
|
995 |
+
{
|
996 |
+
"epoch": 0.03,
|
997 |
+
"learning_rate": 7.903560593964552e-05,
|
998 |
+
"loss": 0.9821,
|
999 |
+
"step": 1650
|
1000 |
+
},
|
1001 |
+
{
|
1002 |
+
"epoch": 0.03,
|
1003 |
+
"learning_rate": 7.951460961200702e-05,
|
1004 |
+
"loss": 0.9844,
|
1005 |
+
"step": 1660
|
1006 |
+
},
|
1007 |
+
{
|
1008 |
+
"epoch": 0.03,
|
1009 |
+
"learning_rate": 7.99936132843685e-05,
|
1010 |
+
"loss": 0.9787,
|
1011 |
+
"step": 1670
|
1012 |
+
},
|
1013 |
+
{
|
1014 |
+
"epoch": 0.03,
|
1015 |
+
"learning_rate": 8.047261695672999e-05,
|
1016 |
+
"loss": 0.9659,
|
1017 |
+
"step": 1680
|
1018 |
+
},
|
1019 |
+
{
|
1020 |
+
"epoch": 0.03,
|
1021 |
+
"learning_rate": 8.095162062909149e-05,
|
1022 |
+
"loss": 0.9648,
|
1023 |
+
"step": 1690
|
1024 |
+
},
|
1025 |
+
{
|
1026 |
+
"epoch": 0.03,
|
1027 |
+
"learning_rate": 8.143062430145297e-05,
|
1028 |
+
"loss": 0.9602,
|
1029 |
+
"step": 1700
|
1030 |
+
},
|
1031 |
+
{
|
1032 |
+
"epoch": 0.03,
|
1033 |
+
"learning_rate": 8.190962797381446e-05,
|
1034 |
+
"loss": 0.9656,
|
1035 |
+
"step": 1710
|
1036 |
+
},
|
1037 |
+
{
|
1038 |
+
"epoch": 0.03,
|
1039 |
+
"learning_rate": 8.238863164617594e-05,
|
1040 |
+
"loss": 0.9728,
|
1041 |
+
"step": 1720
|
1042 |
+
},
|
1043 |
+
{
|
1044 |
+
"epoch": 0.03,
|
1045 |
+
"learning_rate": 8.286763531853743e-05,
|
1046 |
+
"loss": 0.959,
|
1047 |
+
"step": 1730
|
1048 |
+
},
|
1049 |
+
{
|
1050 |
+
"epoch": 0.03,
|
1051 |
+
"learning_rate": 8.334663899089893e-05,
|
1052 |
+
"loss": 0.9482,
|
1053 |
+
"step": 1740
|
1054 |
+
},
|
1055 |
+
{
|
1056 |
+
"epoch": 0.03,
|
1057 |
+
"learning_rate": 8.382564266326041e-05,
|
1058 |
+
"loss": 0.9641,
|
1059 |
+
"step": 1750
|
1060 |
+
},
|
1061 |
+
{
|
1062 |
+
"epoch": 0.03,
|
1063 |
+
"learning_rate": 8.43046463356219e-05,
|
1064 |
+
"loss": 0.9603,
|
1065 |
+
"step": 1760
|
1066 |
+
},
|
1067 |
+
{
|
1068 |
+
"epoch": 0.03,
|
1069 |
+
"learning_rate": 8.478365000798338e-05,
|
1070 |
+
"loss": 0.9799,
|
1071 |
+
"step": 1770
|
1072 |
+
},
|
1073 |
+
{
|
1074 |
+
"epoch": 0.03,
|
1075 |
+
"learning_rate": 8.526265368034488e-05,
|
1076 |
+
"loss": 0.9651,
|
1077 |
+
"step": 1780
|
1078 |
+
},
|
1079 |
+
{
|
1080 |
+
"epoch": 0.03,
|
1081 |
+
"learning_rate": 8.574165735270637e-05,
|
1082 |
+
"loss": 0.9652,
|
1083 |
+
"step": 1790
|
1084 |
+
},
|
1085 |
+
{
|
1086 |
+
"epoch": 0.03,
|
1087 |
+
"learning_rate": 8.622066102506785e-05,
|
1088 |
+
"loss": 0.9668,
|
1089 |
+
"step": 1800
|
1090 |
+
},
|
1091 |
+
{
|
1092 |
+
"epoch": 0.03,
|
1093 |
+
"learning_rate": 8.669966469742935e-05,
|
1094 |
+
"loss": 0.9676,
|
1095 |
+
"step": 1810
|
1096 |
+
},
|
1097 |
+
{
|
1098 |
+
"epoch": 0.03,
|
1099 |
+
"learning_rate": 8.717866836979084e-05,
|
1100 |
+
"loss": 0.9762,
|
1101 |
+
"step": 1820
|
1102 |
+
},
|
1103 |
+
{
|
1104 |
+
"epoch": 0.03,
|
1105 |
+
"learning_rate": 8.765767204215232e-05,
|
1106 |
+
"loss": 0.9732,
|
1107 |
+
"step": 1830
|
1108 |
+
},
|
1109 |
+
{
|
1110 |
+
"epoch": 0.03,
|
1111 |
+
"learning_rate": 8.813667571451381e-05,
|
1112 |
+
"loss": 0.9772,
|
1113 |
+
"step": 1840
|
1114 |
+
},
|
1115 |
+
{
|
1116 |
+
"epoch": 0.03,
|
1117 |
+
"learning_rate": 8.86156793868753e-05,
|
1118 |
+
"loss": 0.9786,
|
1119 |
+
"step": 1850
|
1120 |
+
},
|
1121 |
+
{
|
1122 |
+
"epoch": 0.03,
|
1123 |
+
"learning_rate": 8.909468305923679e-05,
|
1124 |
+
"loss": 0.9826,
|
1125 |
+
"step": 1860
|
1126 |
+
},
|
1127 |
+
{
|
1128 |
+
"epoch": 0.03,
|
1129 |
+
"learning_rate": 8.957368673159825e-05,
|
1130 |
+
"loss": 0.952,
|
1131 |
+
"step": 1870
|
1132 |
+
},
|
1133 |
+
{
|
1134 |
+
"epoch": 0.03,
|
1135 |
+
"learning_rate": 9.005269040395975e-05,
|
1136 |
+
"loss": 0.9508,
|
1137 |
+
"step": 1880
|
1138 |
+
},
|
1139 |
+
{
|
1140 |
+
"epoch": 0.03,
|
1141 |
+
"learning_rate": 9.053169407632124e-05,
|
1142 |
+
"loss": 0.9569,
|
1143 |
+
"step": 1890
|
1144 |
+
},
|
1145 |
+
{
|
1146 |
+
"epoch": 0.03,
|
1147 |
+
"learning_rate": 9.101069774868272e-05,
|
1148 |
+
"loss": 0.9701,
|
1149 |
+
"step": 1900
|
1150 |
+
},
|
1151 |
+
{
|
1152 |
+
"epoch": 0.03,
|
1153 |
+
"learning_rate": 9.148970142104422e-05,
|
1154 |
+
"loss": 0.9704,
|
1155 |
+
"step": 1910
|
1156 |
+
},
|
1157 |
+
{
|
1158 |
+
"epoch": 0.03,
|
1159 |
+
"learning_rate": 9.19687050934057e-05,
|
1160 |
+
"loss": 0.9765,
|
1161 |
+
"step": 1920
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 0.03,
|
1165 |
+
"learning_rate": 9.244770876576719e-05,
|
1166 |
+
"loss": 0.9759,
|
1167 |
+
"step": 1930
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 0.03,
|
1171 |
+
"learning_rate": 9.292671243812869e-05,
|
1172 |
+
"loss": 0.969,
|
1173 |
+
"step": 1940
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 0.03,
|
1177 |
+
"learning_rate": 9.340571611049017e-05,
|
1178 |
+
"loss": 0.9616,
|
1179 |
+
"step": 1950
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 0.03,
|
1183 |
+
"learning_rate": 9.388471978285166e-05,
|
1184 |
+
"loss": 0.9539,
|
1185 |
+
"step": 1960
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 0.03,
|
1189 |
+
"learning_rate": 9.436372345521315e-05,
|
1190 |
+
"loss": 0.9596,
|
1191 |
+
"step": 1970
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 0.03,
|
1195 |
+
"learning_rate": 9.484272712757463e-05,
|
1196 |
+
"loss": 0.9699,
|
1197 |
+
"step": 1980
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 0.03,
|
1201 |
+
"learning_rate": 9.532173079993613e-05,
|
1202 |
+
"loss": 0.9642,
|
1203 |
+
"step": 1990
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 0.03,
|
1207 |
+
"learning_rate": 9.580073447229761e-05,
|
1208 |
+
"loss": 0.9636,
|
1209 |
+
"step": 2000
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 0.03,
|
1213 |
+
"learning_rate": 9.62797381446591e-05,
|
1214 |
+
"loss": 0.9776,
|
1215 |
+
"step": 2010
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 0.03,
|
1219 |
+
"learning_rate": 9.67587418170206e-05,
|
1220 |
+
"loss": 0.9632,
|
1221 |
+
"step": 2020
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 0.03,
|
1225 |
+
"learning_rate": 9.723774548938208e-05,
|
1226 |
+
"loss": 0.9675,
|
1227 |
+
"step": 2030
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 0.03,
|
1231 |
+
"learning_rate": 9.771674916174357e-05,
|
1232 |
+
"loss": 0.9642,
|
1233 |
+
"step": 2040
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 0.03,
|
1237 |
+
"learning_rate": 9.819575283410505e-05,
|
1238 |
+
"loss": 0.9616,
|
1239 |
+
"step": 2050
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 0.03,
|
1243 |
+
"learning_rate": 9.867475650646654e-05,
|
1244 |
+
"loss": 0.9667,
|
1245 |
+
"step": 2060
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 0.03,
|
1249 |
+
"learning_rate": 9.915376017882804e-05,
|
1250 |
+
"loss": 0.9635,
|
1251 |
+
"step": 2070
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 0.03,
|
1255 |
+
"learning_rate": 9.963276385118952e-05,
|
1256 |
+
"loss": 0.941,
|
1257 |
+
"step": 2080
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 0.03,
|
1261 |
+
"learning_rate": 0.00010011176752355101,
|
1262 |
+
"loss": 0.9553,
|
1263 |
+
"step": 2090
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 0.03,
|
1267 |
+
"learning_rate": 0.0001005907711959125,
|
1268 |
+
"loss": 0.9669,
|
1269 |
+
"step": 2100
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 0.03,
|
1273 |
+
"learning_rate": 0.00010106977486827399,
|
1274 |
+
"loss": 0.9673,
|
1275 |
+
"step": 2110
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 0.03,
|
1279 |
+
"learning_rate": 0.00010154877854063547,
|
1280 |
+
"loss": 0.9783,
|
1281 |
+
"step": 2120
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 0.03,
|
1285 |
+
"learning_rate": 0.00010202778221299695,
|
1286 |
+
"loss": 0.9594,
|
1287 |
+
"step": 2130
|
1288 |
+
},
|
1289 |
+
{
|
1290 |
+
"epoch": 0.03,
|
1291 |
+
"learning_rate": 0.00010250678588535844,
|
1292 |
+
"loss": 0.9636,
|
1293 |
+
"step": 2140
|
1294 |
+
},
|
1295 |
+
{
|
1296 |
+
"epoch": 0.03,
|
1297 |
+
"learning_rate": 0.00010298578955771992,
|
1298 |
+
"loss": 0.963,
|
1299 |
+
"step": 2150
|
1300 |
+
},
|
1301 |
+
{
|
1302 |
+
"epoch": 0.03,
|
1303 |
+
"learning_rate": 0.00010346479323008142,
|
1304 |
+
"loss": 0.9771,
|
1305 |
+
"step": 2160
|
1306 |
+
},
|
1307 |
+
{
|
1308 |
+
"epoch": 0.03,
|
1309 |
+
"learning_rate": 0.00010394379690244291,
|
1310 |
+
"loss": 0.9802,
|
1311 |
+
"step": 2170
|
1312 |
+
},
|
1313 |
+
{
|
1314 |
+
"epoch": 0.03,
|
1315 |
+
"learning_rate": 0.00010442280057480439,
|
1316 |
+
"loss": 0.96,
|
1317 |
+
"step": 2180
|
1318 |
+
},
|
1319 |
+
{
|
1320 |
+
"epoch": 0.03,
|
1321 |
+
"learning_rate": 0.00010490180424716588,
|
1322 |
+
"loss": 0.9759,
|
1323 |
+
"step": 2190
|
1324 |
+
},
|
1325 |
+
{
|
1326 |
+
"epoch": 0.04,
|
1327 |
+
"learning_rate": 0.00010538080791952736,
|
1328 |
+
"loss": 0.978,
|
1329 |
+
"step": 2200
|
1330 |
+
},
|
1331 |
+
{
|
1332 |
+
"epoch": 0.04,
|
1333 |
+
"learning_rate": 0.00010585981159188886,
|
1334 |
+
"loss": 0.9755,
|
1335 |
+
"step": 2210
|
1336 |
+
},
|
1337 |
+
{
|
1338 |
+
"epoch": 0.04,
|
1339 |
+
"learning_rate": 0.00010633881526425035,
|
1340 |
+
"loss": 0.9742,
|
1341 |
+
"step": 2220
|
1342 |
+
},
|
1343 |
+
{
|
1344 |
+
"epoch": 0.04,
|
1345 |
+
"learning_rate": 0.00010681781893661183,
|
1346 |
+
"loss": 0.9685,
|
1347 |
+
"step": 2230
|
1348 |
+
},
|
1349 |
+
{
|
1350 |
+
"epoch": 0.04,
|
1351 |
+
"learning_rate": 0.00010729682260897333,
|
1352 |
+
"loss": 0.9637,
|
1353 |
+
"step": 2240
|
1354 |
+
},
|
1355 |
+
{
|
1356 |
+
"epoch": 0.04,
|
1357 |
+
"learning_rate": 0.00010777582628133482,
|
1358 |
+
"loss": 0.9647,
|
1359 |
+
"step": 2250
|
1360 |
+
},
|
1361 |
+
{
|
1362 |
+
"epoch": 0.04,
|
1363 |
+
"learning_rate": 0.0001082548299536963,
|
1364 |
+
"loss": 0.9566,
|
1365 |
+
"step": 2260
|
1366 |
+
},
|
1367 |
+
{
|
1368 |
+
"epoch": 0.04,
|
1369 |
+
"learning_rate": 0.0001087338336260578,
|
1370 |
+
"loss": 0.9579,
|
1371 |
+
"step": 2270
|
1372 |
+
},
|
1373 |
+
{
|
1374 |
+
"epoch": 0.04,
|
1375 |
+
"learning_rate": 0.00010921283729841928,
|
1376 |
+
"loss": 0.9746,
|
1377 |
+
"step": 2280
|
1378 |
+
},
|
1379 |
+
{
|
1380 |
+
"epoch": 0.04,
|
1381 |
+
"learning_rate": 0.00010969184097078077,
|
1382 |
+
"loss": 0.967,
|
1383 |
+
"step": 2290
|
1384 |
+
},
|
1385 |
+
{
|
1386 |
+
"epoch": 0.04,
|
1387 |
+
"learning_rate": 0.00011017084464314226,
|
1388 |
+
"loss": 0.9884,
|
1389 |
+
"step": 2300
|
1390 |
+
},
|
1391 |
+
{
|
1392 |
+
"epoch": 0.04,
|
1393 |
+
"learning_rate": 0.00011064984831550374,
|
1394 |
+
"loss": 0.9649,
|
1395 |
+
"step": 2310
|
1396 |
+
},
|
1397 |
+
{
|
1398 |
+
"epoch": 0.04,
|
1399 |
+
"learning_rate": 0.00011112885198786524,
|
1400 |
+
"loss": 0.9534,
|
1401 |
+
"step": 2320
|
1402 |
+
},
|
1403 |
+
{
|
1404 |
+
"epoch": 0.04,
|
1405 |
+
"learning_rate": 0.00011160785566022672,
|
1406 |
+
"loss": 0.9706,
|
1407 |
+
"step": 2330
|
1408 |
+
},
|
1409 |
+
{
|
1410 |
+
"epoch": 0.04,
|
1411 |
+
"learning_rate": 0.00011208685933258821,
|
1412 |
+
"loss": 0.9747,
|
1413 |
+
"step": 2340
|
1414 |
+
},
|
1415 |
+
{
|
1416 |
+
"epoch": 0.04,
|
1417 |
+
"learning_rate": 0.0001125658630049497,
|
1418 |
+
"loss": 0.9532,
|
1419 |
+
"step": 2350
|
1420 |
+
},
|
1421 |
+
{
|
1422 |
+
"epoch": 0.04,
|
1423 |
+
"learning_rate": 0.00011304486667731119,
|
1424 |
+
"loss": 0.9733,
|
1425 |
+
"step": 2360
|
1426 |
+
},
|
1427 |
+
{
|
1428 |
+
"epoch": 0.04,
|
1429 |
+
"learning_rate": 0.00011352387034967267,
|
1430 |
+
"loss": 0.9648,
|
1431 |
+
"step": 2370
|
1432 |
+
},
|
1433 |
+
{
|
1434 |
+
"epoch": 0.04,
|
1435 |
+
"learning_rate": 0.00011400287402203415,
|
1436 |
+
"loss": 0.9651,
|
1437 |
+
"step": 2380
|
1438 |
+
},
|
1439 |
+
{
|
1440 |
+
"epoch": 0.04,
|
1441 |
+
"learning_rate": 0.00011448187769439564,
|
1442 |
+
"loss": 0.9597,
|
1443 |
+
"step": 2390
|
1444 |
+
},
|
1445 |
+
{
|
1446 |
+
"epoch": 0.04,
|
1447 |
+
"learning_rate": 0.00011496088136675714,
|
1448 |
+
"loss": 0.9757,
|
1449 |
+
"step": 2400
|
1450 |
+
},
|
1451 |
+
{
|
1452 |
+
"epoch": 0.04,
|
1453 |
+
"learning_rate": 0.00011543988503911862,
|
1454 |
+
"loss": 0.9621,
|
1455 |
+
"step": 2410
|
1456 |
+
},
|
1457 |
+
{
|
1458 |
+
"epoch": 0.04,
|
1459 |
+
"learning_rate": 0.00011591888871148011,
|
1460 |
+
"loss": 0.9515,
|
1461 |
+
"step": 2420
|
1462 |
+
},
|
1463 |
+
{
|
1464 |
+
"epoch": 0.04,
|
1465 |
+
"learning_rate": 0.00011639789238384159,
|
1466 |
+
"loss": 0.952,
|
1467 |
+
"step": 2430
|
1468 |
+
},
|
1469 |
+
{
|
1470 |
+
"epoch": 0.04,
|
1471 |
+
"learning_rate": 0.00011687689605620308,
|
1472 |
+
"loss": 0.9683,
|
1473 |
+
"step": 2440
|
1474 |
+
},
|
1475 |
+
{
|
1476 |
+
"epoch": 0.04,
|
1477 |
+
"learning_rate": 0.00011735589972856458,
|
1478 |
+
"loss": 0.9534,
|
1479 |
+
"step": 2450
|
1480 |
+
},
|
1481 |
+
{
|
1482 |
+
"epoch": 0.04,
|
1483 |
+
"learning_rate": 0.00011783490340092606,
|
1484 |
+
"loss": 0.9654,
|
1485 |
+
"step": 2460
|
1486 |
+
},
|
1487 |
+
{
|
1488 |
+
"epoch": 0.04,
|
1489 |
+
"learning_rate": 0.00011831390707328755,
|
1490 |
+
"loss": 0.9595,
|
1491 |
+
"step": 2470
|
1492 |
+
},
|
1493 |
+
{
|
1494 |
+
"epoch": 0.04,
|
1495 |
+
"learning_rate": 0.00011879291074564905,
|
1496 |
+
"loss": 0.987,
|
1497 |
+
"step": 2480
|
1498 |
+
},
|
1499 |
+
{
|
1500 |
+
"epoch": 0.04,
|
1501 |
+
"learning_rate": 0.00011927191441801053,
|
1502 |
+
"loss": 0.9746,
|
1503 |
+
"step": 2490
|
1504 |
+
},
|
1505 |
+
{
|
1506 |
+
"epoch": 0.04,
|
1507 |
+
"learning_rate": 0.00011975091809037202,
|
1508 |
+
"loss": 0.9632,
|
1509 |
+
"step": 2500
|
1510 |
+
},
|
1511 |
+
{
|
1512 |
+
"epoch": 0.04,
|
1513 |
+
"learning_rate": 0.0001202299217627335,
|
1514 |
+
"loss": 0.9565,
|
1515 |
+
"step": 2510
|
1516 |
+
},
|
1517 |
+
{
|
1518 |
+
"epoch": 0.04,
|
1519 |
+
"learning_rate": 0.000120708925435095,
|
1520 |
+
"loss": 0.9493,
|
1521 |
+
"step": 2520
|
1522 |
+
},
|
1523 |
+
{
|
1524 |
+
"epoch": 0.04,
|
1525 |
+
"learning_rate": 0.00012118792910745649,
|
1526 |
+
"loss": 0.9449,
|
1527 |
+
"step": 2530
|
1528 |
+
},
|
1529 |
+
{
|
1530 |
+
"epoch": 0.04,
|
1531 |
+
"learning_rate": 0.00012166693277981797,
|
1532 |
+
"loss": 0.9456,
|
1533 |
+
"step": 2540
|
1534 |
+
},
|
1535 |
+
{
|
1536 |
+
"epoch": 0.04,
|
1537 |
+
"learning_rate": 0.00012214593645217946,
|
1538 |
+
"loss": 0.9386,
|
1539 |
+
"step": 2550
|
1540 |
+
},
|
1541 |
+
{
|
1542 |
+
"epoch": 0.04,
|
1543 |
+
"learning_rate": 0.00012262494012454096,
|
1544 |
+
"loss": 0.938,
|
1545 |
+
"step": 2560
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 0.04,
|
1549 |
+
"learning_rate": 0.00012310394379690245,
|
1550 |
+
"loss": 0.9372,
|
1551 |
+
"step": 2570
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 0.04,
|
1555 |
+
"learning_rate": 0.00012358294746926392,
|
1556 |
+
"loss": 0.9377,
|
1557 |
+
"step": 2580
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 0.04,
|
1561 |
+
"learning_rate": 0.0001240619511416254,
|
1562 |
+
"loss": 0.9312,
|
1563 |
+
"step": 2590
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 0.04,
|
1567 |
+
"learning_rate": 0.0001245409548139869,
|
1568 |
+
"loss": 0.9323,
|
1569 |
+
"step": 2600
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 0.04,
|
1573 |
+
"learning_rate": 0.00012501995848634837,
|
1574 |
+
"loss": 0.9278,
|
1575 |
+
"step": 2610
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 0.04,
|
1579 |
+
"learning_rate": 0.00012549896215870987,
|
1580 |
+
"loss": 0.9291,
|
1581 |
+
"step": 2620
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 0.04,
|
1585 |
+
"learning_rate": 0.00012597796583107136,
|
1586 |
+
"loss": 0.93,
|
1587 |
+
"step": 2630
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 0.04,
|
1591 |
+
"learning_rate": 0.00012645696950343285,
|
1592 |
+
"loss": 0.9262,
|
1593 |
+
"step": 2640
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 0.04,
|
1597 |
+
"learning_rate": 0.00012693597317579432,
|
1598 |
+
"loss": 0.9385,
|
1599 |
+
"step": 2650
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 0.04,
|
1603 |
+
"learning_rate": 0.00012741497684815581,
|
1604 |
+
"loss": 0.9323,
|
1605 |
+
"step": 2660
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 0.04,
|
1609 |
+
"learning_rate": 0.0001278939805205173,
|
1610 |
+
"loss": 0.9129,
|
1611 |
+
"step": 2670
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 0.04,
|
1615 |
+
"learning_rate": 0.0001283729841928788,
|
1616 |
+
"loss": 0.924,
|
1617 |
+
"step": 2680
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 0.04,
|
1621 |
+
"learning_rate": 0.0001288519878652403,
|
1622 |
+
"loss": 0.928,
|
1623 |
+
"step": 2690
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 0.04,
|
1627 |
+
"learning_rate": 0.00012933099153760176,
|
1628 |
+
"loss": 0.9291,
|
1629 |
+
"step": 2700
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 0.04,
|
1633 |
+
"learning_rate": 0.00012980999520996326,
|
1634 |
+
"loss": 0.9111,
|
1635 |
+
"step": 2710
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 0.04,
|
1639 |
+
"learning_rate": 0.00013028899888232475,
|
1640 |
+
"loss": 0.9201,
|
1641 |
+
"step": 2720
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 0.04,
|
1645 |
+
"learning_rate": 0.00013076800255468625,
|
1646 |
+
"loss": 0.9274,
|
1647 |
+
"step": 2730
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 0.04,
|
1651 |
+
"learning_rate": 0.00013124700622704774,
|
1652 |
+
"loss": 0.9095,
|
1653 |
+
"step": 2740
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 0.04,
|
1657 |
+
"learning_rate": 0.0001317260098994092,
|
1658 |
+
"loss": 0.9146,
|
1659 |
+
"step": 2750
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 0.04,
|
1663 |
+
"learning_rate": 0.0001322050135717707,
|
1664 |
+
"loss": 0.9186,
|
1665 |
+
"step": 2760
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 0.04,
|
1669 |
+
"learning_rate": 0.0001326840172441322,
|
1670 |
+
"loss": 0.9149,
|
1671 |
+
"step": 2770
|
1672 |
+
},
|
1673 |
+
{
|
1674 |
+
"epoch": 0.04,
|
1675 |
+
"learning_rate": 0.0001331630209164937,
|
1676 |
+
"loss": 0.9221,
|
1677 |
+
"step": 2780
|
1678 |
+
},
|
1679 |
+
{
|
1680 |
+
"epoch": 0.04,
|
1681 |
+
"learning_rate": 0.00013364202458885518,
|
1682 |
+
"loss": 0.9153,
|
1683 |
+
"step": 2790
|
1684 |
+
},
|
1685 |
+
{
|
1686 |
+
"epoch": 0.04,
|
1687 |
+
"learning_rate": 0.00013412102826121665,
|
1688 |
+
"loss": 0.9145,
|
1689 |
+
"step": 2800
|
1690 |
+
},
|
1691 |
+
{
|
1692 |
+
"epoch": 0.04,
|
1693 |
+
"learning_rate": 0.00013460003193357814,
|
1694 |
+
"loss": 0.9252,
|
1695 |
+
"step": 2810
|
1696 |
+
},
|
1697 |
+
{
|
1698 |
+
"epoch": 0.05,
|
1699 |
+
"learning_rate": 0.00013507903560593964,
|
1700 |
+
"loss": 0.9038,
|
1701 |
+
"step": 2820
|
1702 |
+
},
|
1703 |
+
{
|
1704 |
+
"epoch": 0.05,
|
1705 |
+
"learning_rate": 0.00013555803927830113,
|
1706 |
+
"loss": 0.9119,
|
1707 |
+
"step": 2830
|
1708 |
+
},
|
1709 |
+
{
|
1710 |
+
"epoch": 0.05,
|
1711 |
+
"learning_rate": 0.00013603704295066262,
|
1712 |
+
"loss": 0.9126,
|
1713 |
+
"step": 2840
|
1714 |
+
},
|
1715 |
+
{
|
1716 |
+
"epoch": 0.05,
|
1717 |
+
"learning_rate": 0.00013651604662302412,
|
1718 |
+
"loss": 0.9093,
|
1719 |
+
"step": 2850
|
1720 |
+
},
|
1721 |
+
{
|
1722 |
+
"epoch": 0.05,
|
1723 |
+
"learning_rate": 0.00013699505029538559,
|
1724 |
+
"loss": 0.9104,
|
1725 |
+
"step": 2860
|
1726 |
+
},
|
1727 |
+
{
|
1728 |
+
"epoch": 0.05,
|
1729 |
+
"learning_rate": 0.00013747405396774708,
|
1730 |
+
"loss": 0.916,
|
1731 |
+
"step": 2870
|
1732 |
+
},
|
1733 |
+
{
|
1734 |
+
"epoch": 0.05,
|
1735 |
+
"learning_rate": 0.00013795305764010855,
|
1736 |
+
"loss": 0.9114,
|
1737 |
+
"step": 2880
|
1738 |
+
},
|
1739 |
+
{
|
1740 |
+
"epoch": 0.05,
|
1741 |
+
"learning_rate": 0.00013843206131247004,
|
1742 |
+
"loss": 0.9037,
|
1743 |
+
"step": 2890
|
1744 |
+
},
|
1745 |
+
{
|
1746 |
+
"epoch": 0.05,
|
1747 |
+
"learning_rate": 0.00013891106498483153,
|
1748 |
+
"loss": 0.9133,
|
1749 |
+
"step": 2900
|
1750 |
+
},
|
1751 |
+
{
|
1752 |
+
"epoch": 0.05,
|
1753 |
+
"learning_rate": 0.00013939006865719303,
|
1754 |
+
"loss": 0.9001,
|
1755 |
+
"step": 2910
|
1756 |
+
},
|
1757 |
+
{
|
1758 |
+
"epoch": 0.05,
|
1759 |
+
"learning_rate": 0.00013986907232955452,
|
1760 |
+
"loss": 0.9088,
|
1761 |
+
"step": 2920
|
1762 |
+
},
|
1763 |
+
{
|
1764 |
+
"epoch": 0.05,
|
1765 |
+
"learning_rate": 0.000140348076001916,
|
1766 |
+
"loss": 0.9102,
|
1767 |
+
"step": 2930
|
1768 |
+
},
|
1769 |
+
{
|
1770 |
+
"epoch": 0.05,
|
1771 |
+
"learning_rate": 0.00014082707967427748,
|
1772 |
+
"loss": 0.9181,
|
1773 |
+
"step": 2940
|
1774 |
+
},
|
1775 |
+
{
|
1776 |
+
"epoch": 0.05,
|
1777 |
+
"learning_rate": 0.00014130608334663898,
|
1778 |
+
"loss": 0.8853,
|
1779 |
+
"step": 2950
|
1780 |
+
},
|
1781 |
+
{
|
1782 |
+
"epoch": 0.05,
|
1783 |
+
"learning_rate": 0.00014178508701900047,
|
1784 |
+
"loss": 0.8549,
|
1785 |
+
"step": 2960
|
1786 |
+
},
|
1787 |
+
{
|
1788 |
+
"epoch": 0.05,
|
1789 |
+
"learning_rate": 0.00014226409069136196,
|
1790 |
+
"loss": 0.8592,
|
1791 |
+
"step": 2970
|
1792 |
+
},
|
1793 |
+
{
|
1794 |
+
"epoch": 0.05,
|
1795 |
+
"learning_rate": 0.00014274309436372343,
|
1796 |
+
"loss": 0.8436,
|
1797 |
+
"step": 2980
|
1798 |
+
},
|
1799 |
+
{
|
1800 |
+
"epoch": 0.05,
|
1801 |
+
"learning_rate": 0.00014322209803608492,
|
1802 |
+
"loss": 0.8454,
|
1803 |
+
"step": 2990
|
1804 |
+
},
|
1805 |
+
{
|
1806 |
+
"epoch": 0.05,
|
1807 |
+
"learning_rate": 0.00014370110170844642,
|
1808 |
+
"loss": 0.8489,
|
1809 |
+
"step": 3000
|
1810 |
+
},
|
1811 |
+
{
|
1812 |
+
"epoch": 0.05,
|
1813 |
+
"learning_rate": 0.0001441801053808079,
|
1814 |
+
"loss": 0.8522,
|
1815 |
+
"step": 3010
|
1816 |
+
},
|
1817 |
+
{
|
1818 |
+
"epoch": 0.05,
|
1819 |
+
"learning_rate": 0.0001446591090531694,
|
1820 |
+
"loss": 0.8418,
|
1821 |
+
"step": 3020
|
1822 |
+
},
|
1823 |
+
{
|
1824 |
+
"epoch": 0.05,
|
1825 |
+
"learning_rate": 0.00014513811272553087,
|
1826 |
+
"loss": 0.8377,
|
1827 |
+
"step": 3030
|
1828 |
+
},
|
1829 |
+
{
|
1830 |
+
"epoch": 0.05,
|
1831 |
+
"learning_rate": 0.00014561711639789237,
|
1832 |
+
"loss": 0.8273,
|
1833 |
+
"step": 3040
|
1834 |
+
},
|
1835 |
+
{
|
1836 |
+
"epoch": 0.05,
|
1837 |
+
"learning_rate": 0.00014609612007025386,
|
1838 |
+
"loss": 0.8356,
|
1839 |
+
"step": 3050
|
1840 |
+
},
|
1841 |
+
{
|
1842 |
+
"epoch": 0.05,
|
1843 |
+
"learning_rate": 0.00014657512374261536,
|
1844 |
+
"loss": 0.8503,
|
1845 |
+
"step": 3060
|
1846 |
+
},
|
1847 |
+
{
|
1848 |
+
"epoch": 0.05,
|
1849 |
+
"learning_rate": 0.00014705412741497685,
|
1850 |
+
"loss": 0.8378,
|
1851 |
+
"step": 3070
|
1852 |
+
},
|
1853 |
+
{
|
1854 |
+
"epoch": 0.05,
|
1855 |
+
"learning_rate": 0.00014753313108733834,
|
1856 |
+
"loss": 0.8313,
|
1857 |
+
"step": 3080
|
1858 |
+
},
|
1859 |
+
{
|
1860 |
+
"epoch": 0.05,
|
1861 |
+
"learning_rate": 0.0001480121347596998,
|
1862 |
+
"loss": 0.8395,
|
1863 |
+
"step": 3090
|
1864 |
+
},
|
1865 |
+
{
|
1866 |
+
"epoch": 0.05,
|
1867 |
+
"learning_rate": 0.0001484911384320613,
|
1868 |
+
"loss": 0.8229,
|
1869 |
+
"step": 3100
|
1870 |
+
},
|
1871 |
+
{
|
1872 |
+
"epoch": 0.05,
|
1873 |
+
"learning_rate": 0.00014897014210442277,
|
1874 |
+
"loss": 0.7687,
|
1875 |
+
"step": 3110
|
1876 |
+
},
|
1877 |
+
{
|
1878 |
+
"epoch": 0.05,
|
1879 |
+
"learning_rate": 0.00014944914577678426,
|
1880 |
+
"loss": 0.7637,
|
1881 |
+
"step": 3120
|
1882 |
+
},
|
1883 |
+
{
|
1884 |
+
"epoch": 0.05,
|
1885 |
+
"learning_rate": 0.00014992814944914576,
|
1886 |
+
"loss": 0.7688,
|
1887 |
+
"step": 3130
|
1888 |
+
},
|
1889 |
+
{
|
1890 |
+
"epoch": 0.05,
|
1891 |
+
"learning_rate": 0.00015040715312150725,
|
1892 |
+
"loss": 0.7523,
|
1893 |
+
"step": 3140
|
1894 |
+
},
|
1895 |
+
{
|
1896 |
+
"epoch": 0.05,
|
1897 |
+
"learning_rate": 0.00015088615679386875,
|
1898 |
+
"loss": 0.7575,
|
1899 |
+
"step": 3150
|
1900 |
+
},
|
1901 |
+
{
|
1902 |
+
"epoch": 0.05,
|
1903 |
+
"learning_rate": 0.00015136516046623024,
|
1904 |
+
"loss": 0.7491,
|
1905 |
+
"step": 3160
|
1906 |
+
},
|
1907 |
+
{
|
1908 |
+
"epoch": 0.05,
|
1909 |
+
"learning_rate": 0.00015184416413859173,
|
1910 |
+
"loss": 0.7557,
|
1911 |
+
"step": 3170
|
1912 |
+
},
|
1913 |
+
{
|
1914 |
+
"epoch": 0.05,
|
1915 |
+
"learning_rate": 0.00015232316781095323,
|
1916 |
+
"loss": 0.7449,
|
1917 |
+
"step": 3180
|
1918 |
+
},
|
1919 |
+
{
|
1920 |
+
"epoch": 0.05,
|
1921 |
+
"learning_rate": 0.0001528021714833147,
|
1922 |
+
"loss": 0.7556,
|
1923 |
+
"step": 3190
|
1924 |
+
},
|
1925 |
+
{
|
1926 |
+
"epoch": 0.05,
|
1927 |
+
"learning_rate": 0.0001532811751556762,
|
1928 |
+
"loss": 0.744,
|
1929 |
+
"step": 3200
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 0.05,
|
1933 |
+
"learning_rate": 0.00015376017882803768,
|
1934 |
+
"loss": 0.74,
|
1935 |
+
"step": 3210
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 0.05,
|
1939 |
+
"learning_rate": 0.00015423918250039918,
|
1940 |
+
"loss": 0.7443,
|
1941 |
+
"step": 3220
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 0.05,
|
1945 |
+
"learning_rate": 0.00015471818617276067,
|
1946 |
+
"loss": 0.7399,
|
1947 |
+
"step": 3230
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 0.05,
|
1951 |
+
"learning_rate": 0.0001551971898451221,
|
1952 |
+
"loss": 0.7388,
|
1953 |
+
"step": 3240
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 0.05,
|
1957 |
+
"learning_rate": 0.0001556761935174836,
|
1958 |
+
"loss": 0.7432,
|
1959 |
+
"step": 3250
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 0.05,
|
1963 |
+
"learning_rate": 0.0001561551971898451,
|
1964 |
+
"loss": 0.7448,
|
1965 |
+
"step": 3260
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 0.05,
|
1969 |
+
"learning_rate": 0.0001566342008622066,
|
1970 |
+
"loss": 0.7394,
|
1971 |
+
"step": 3270
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 0.05,
|
1975 |
+
"learning_rate": 0.00015711320453456806,
|
1976 |
+
"loss": 0.7402,
|
1977 |
+
"step": 3280
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 0.05,
|
1981 |
+
"learning_rate": 0.00015759220820692955,
|
1982 |
+
"loss": 0.7484,
|
1983 |
+
"step": 3290
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 0.05,
|
1987 |
+
"learning_rate": 0.00015807121187929105,
|
1988 |
+
"loss": 0.7378,
|
1989 |
+
"step": 3300
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 0.05,
|
1993 |
+
"learning_rate": 0.00015855021555165254,
|
1994 |
+
"loss": 0.7319,
|
1995 |
+
"step": 3310
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 0.05,
|
1999 |
+
"learning_rate": 0.00015902921922401404,
|
2000 |
+
"loss": 0.73,
|
2001 |
+
"step": 3320
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 0.05,
|
2005 |
+
"learning_rate": 0.0001595082228963755,
|
2006 |
+
"loss": 0.7327,
|
2007 |
+
"step": 3330
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 0.05,
|
2011 |
+
"learning_rate": 0.000159987226568737,
|
2012 |
+
"loss": 0.7346,
|
2013 |
+
"step": 3340
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 0.05,
|
2017 |
+
"learning_rate": 0.0001604662302410985,
|
2018 |
+
"loss": 0.7285,
|
2019 |
+
"step": 3350
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 0.05,
|
2023 |
+
"learning_rate": 0.00016094523391345998,
|
2024 |
+
"loss": 0.7335,
|
2025 |
+
"step": 3360
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 0.05,
|
2029 |
+
"learning_rate": 0.00016142423758582148,
|
2030 |
+
"loss": 0.7379,
|
2031 |
+
"step": 3370
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 0.05,
|
2035 |
+
"learning_rate": 0.00016190324125818297,
|
2036 |
+
"loss": 0.7285,
|
2037 |
+
"step": 3380
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 0.05,
|
2041 |
+
"learning_rate": 0.00016238224493054444,
|
2042 |
+
"loss": 0.7344,
|
2043 |
+
"step": 3390
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 0.05,
|
2047 |
+
"learning_rate": 0.00016286124860290593,
|
2048 |
+
"loss": 0.7179,
|
2049 |
+
"step": 3400
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 0.05,
|
2053 |
+
"learning_rate": 0.00016334025227526743,
|
2054 |
+
"loss": 0.7285,
|
2055 |
+
"step": 3410
|
2056 |
+
},
|
2057 |
+
{
|
2058 |
+
"epoch": 0.05,
|
2059 |
+
"learning_rate": 0.00016381925594762892,
|
2060 |
+
"loss": 0.7282,
|
2061 |
+
"step": 3420
|
2062 |
+
},
|
2063 |
+
{
|
2064 |
+
"epoch": 0.05,
|
2065 |
+
"learning_rate": 0.00016429825961999041,
|
2066 |
+
"loss": 0.7149,
|
2067 |
+
"step": 3430
|
2068 |
+
},
|
2069 |
+
{
|
2070 |
+
"epoch": 0.05,
|
2071 |
+
"learning_rate": 0.00016477726329235188,
|
2072 |
+
"loss": 0.7404,
|
2073 |
+
"step": 3440
|
2074 |
+
},
|
2075 |
+
{
|
2076 |
+
"epoch": 0.06,
|
2077 |
+
"learning_rate": 0.00016525626696471337,
|
2078 |
+
"loss": 0.7565,
|
2079 |
+
"step": 3450
|
2080 |
+
},
|
2081 |
+
{
|
2082 |
+
"epoch": 0.06,
|
2083 |
+
"learning_rate": 0.00016573527063707487,
|
2084 |
+
"loss": 0.7382,
|
2085 |
+
"step": 3460
|
2086 |
+
},
|
2087 |
+
{
|
2088 |
+
"epoch": 0.06,
|
2089 |
+
"learning_rate": 0.00016621427430943636,
|
2090 |
+
"loss": 0.7543,
|
2091 |
+
"step": 3470
|
2092 |
+
},
|
2093 |
+
{
|
2094 |
+
"epoch": 0.06,
|
2095 |
+
"learning_rate": 0.00016669327798179786,
|
2096 |
+
"loss": 0.7501,
|
2097 |
+
"step": 3480
|
2098 |
+
},
|
2099 |
+
{
|
2100 |
+
"epoch": 0.06,
|
2101 |
+
"learning_rate": 0.00016717228165415932,
|
2102 |
+
"loss": 0.74,
|
2103 |
+
"step": 3490
|
2104 |
+
},
|
2105 |
+
{
|
2106 |
+
"epoch": 0.06,
|
2107 |
+
"learning_rate": 0.00016765128532652082,
|
2108 |
+
"loss": 0.747,
|
2109 |
+
"step": 3500
|
2110 |
+
},
|
2111 |
+
{
|
2112 |
+
"epoch": 0.06,
|
2113 |
+
"learning_rate": 0.0001681302889988823,
|
2114 |
+
"loss": 0.7308,
|
2115 |
+
"step": 3510
|
2116 |
+
},
|
2117 |
+
{
|
2118 |
+
"epoch": 0.06,
|
2119 |
+
"learning_rate": 0.0001686092926712438,
|
2120 |
+
"loss": 0.7444,
|
2121 |
+
"step": 3520
|
2122 |
+
},
|
2123 |
+
{
|
2124 |
+
"epoch": 0.06,
|
2125 |
+
"learning_rate": 0.0001690882963436053,
|
2126 |
+
"loss": 0.732,
|
2127 |
+
"step": 3530
|
2128 |
+
},
|
2129 |
+
{
|
2130 |
+
"epoch": 0.06,
|
2131 |
+
"learning_rate": 0.00016956730001596677,
|
2132 |
+
"loss": 0.7448,
|
2133 |
+
"step": 3540
|
2134 |
+
},
|
2135 |
+
{
|
2136 |
+
"epoch": 0.06,
|
2137 |
+
"learning_rate": 0.00017004630368832826,
|
2138 |
+
"loss": 0.7336,
|
2139 |
+
"step": 3550
|
2140 |
+
},
|
2141 |
+
{
|
2142 |
+
"epoch": 0.06,
|
2143 |
+
"learning_rate": 0.00017052530736068975,
|
2144 |
+
"loss": 0.7263,
|
2145 |
+
"step": 3560
|
2146 |
+
},
|
2147 |
+
{
|
2148 |
+
"epoch": 0.06,
|
2149 |
+
"learning_rate": 0.00017100431103305125,
|
2150 |
+
"loss": 0.7273,
|
2151 |
+
"step": 3570
|
2152 |
+
},
|
2153 |
+
{
|
2154 |
+
"epoch": 0.06,
|
2155 |
+
"learning_rate": 0.00017148331470541274,
|
2156 |
+
"loss": 0.7248,
|
2157 |
+
"step": 3580
|
2158 |
+
},
|
2159 |
+
{
|
2160 |
+
"epoch": 0.06,
|
2161 |
+
"learning_rate": 0.0001719623183777742,
|
2162 |
+
"loss": 0.7319,
|
2163 |
+
"step": 3590
|
2164 |
+
},
|
2165 |
+
{
|
2166 |
+
"epoch": 0.06,
|
2167 |
+
"learning_rate": 0.0001724413220501357,
|
2168 |
+
"loss": 0.7584,
|
2169 |
+
"step": 3600
|
2170 |
+
},
|
2171 |
+
{
|
2172 |
+
"epoch": 0.06,
|
2173 |
+
"learning_rate": 0.0001729203257224972,
|
2174 |
+
"loss": 0.8264,
|
2175 |
+
"step": 3610
|
2176 |
+
},
|
2177 |
+
{
|
2178 |
+
"epoch": 0.06,
|
2179 |
+
"learning_rate": 0.0001733993293948587,
|
2180 |
+
"loss": 0.8127,
|
2181 |
+
"step": 3620
|
2182 |
+
},
|
2183 |
+
{
|
2184 |
+
"epoch": 0.06,
|
2185 |
+
"learning_rate": 0.00017387833306722018,
|
2186 |
+
"loss": 0.8102,
|
2187 |
+
"step": 3630
|
2188 |
+
},
|
2189 |
+
{
|
2190 |
+
"epoch": 0.06,
|
2191 |
+
"learning_rate": 0.00017435733673958168,
|
2192 |
+
"loss": 0.8068,
|
2193 |
+
"step": 3640
|
2194 |
+
},
|
2195 |
+
{
|
2196 |
+
"epoch": 0.06,
|
2197 |
+
"learning_rate": 0.00017483634041194315,
|
2198 |
+
"loss": 0.8134,
|
2199 |
+
"step": 3650
|
2200 |
+
},
|
2201 |
+
{
|
2202 |
+
"epoch": 0.06,
|
2203 |
+
"learning_rate": 0.00017531534408430464,
|
2204 |
+
"loss": 0.7994,
|
2205 |
+
"step": 3660
|
2206 |
+
},
|
2207 |
+
{
|
2208 |
+
"epoch": 0.06,
|
2209 |
+
"learning_rate": 0.00017579434775666613,
|
2210 |
+
"loss": 0.8169,
|
2211 |
+
"step": 3670
|
2212 |
+
},
|
2213 |
+
{
|
2214 |
+
"epoch": 0.06,
|
2215 |
+
"learning_rate": 0.00017627335142902763,
|
2216 |
+
"loss": 0.8135,
|
2217 |
+
"step": 3680
|
2218 |
+
},
|
2219 |
+
{
|
2220 |
+
"epoch": 0.06,
|
2221 |
+
"learning_rate": 0.00017675235510138912,
|
2222 |
+
"loss": 0.8074,
|
2223 |
+
"step": 3690
|
2224 |
+
},
|
2225 |
+
{
|
2226 |
+
"epoch": 0.06,
|
2227 |
+
"learning_rate": 0.0001772313587737506,
|
2228 |
+
"loss": 0.7948,
|
2229 |
+
"step": 3700
|
2230 |
+
},
|
2231 |
+
{
|
2232 |
+
"epoch": 0.06,
|
2233 |
+
"learning_rate": 0.00017771036244611208,
|
2234 |
+
"loss": 0.7862,
|
2235 |
+
"step": 3710
|
2236 |
+
},
|
2237 |
+
{
|
2238 |
+
"epoch": 0.06,
|
2239 |
+
"learning_rate": 0.00017818936611847358,
|
2240 |
+
"loss": 0.7942,
|
2241 |
+
"step": 3720
|
2242 |
+
},
|
2243 |
+
{
|
2244 |
+
"epoch": 0.06,
|
2245 |
+
"learning_rate": 0.00017866836979083504,
|
2246 |
+
"loss": 0.782,
|
2247 |
+
"step": 3730
|
2248 |
+
},
|
2249 |
+
{
|
2250 |
+
"epoch": 0.06,
|
2251 |
+
"learning_rate": 0.0001791473734631965,
|
2252 |
+
"loss": 0.8037,
|
2253 |
+
"step": 3740
|
2254 |
+
},
|
2255 |
+
{
|
2256 |
+
"epoch": 0.06,
|
2257 |
+
"learning_rate": 0.000179626377135558,
|
2258 |
+
"loss": 0.7926,
|
2259 |
+
"step": 3750
|
2260 |
+
},
|
2261 |
+
{
|
2262 |
+
"epoch": 0.06,
|
2263 |
+
"learning_rate": 0.0001801053808079195,
|
2264 |
+
"loss": 0.7788,
|
2265 |
+
"step": 3760
|
2266 |
+
},
|
2267 |
+
{
|
2268 |
+
"epoch": 0.06,
|
2269 |
+
"learning_rate": 0.000180584384480281,
|
2270 |
+
"loss": 0.7084,
|
2271 |
+
"step": 3770
|
2272 |
+
},
|
2273 |
+
{
|
2274 |
+
"epoch": 0.06,
|
2275 |
+
"learning_rate": 0.00018106338815264249,
|
2276 |
+
"loss": 0.6898,
|
2277 |
+
"step": 3780
|
2278 |
+
},
|
2279 |
+
{
|
2280 |
+
"epoch": 0.06,
|
2281 |
+
"learning_rate": 0.00018154239182500395,
|
2282 |
+
"loss": 0.6993,
|
2283 |
+
"step": 3790
|
2284 |
+
},
|
2285 |
+
{
|
2286 |
+
"epoch": 0.06,
|
2287 |
+
"learning_rate": 0.00018202139549736545,
|
2288 |
+
"loss": 0.6843,
|
2289 |
+
"step": 3800
|
2290 |
+
},
|
2291 |
+
{
|
2292 |
+
"epoch": 0.06,
|
2293 |
+
"learning_rate": 0.00018250039916972694,
|
2294 |
+
"loss": 0.6912,
|
2295 |
+
"step": 3810
|
2296 |
+
},
|
2297 |
+
{
|
2298 |
+
"epoch": 0.06,
|
2299 |
+
"learning_rate": 0.00018297940284208843,
|
2300 |
+
"loss": 0.6959,
|
2301 |
+
"step": 3820
|
2302 |
+
},
|
2303 |
+
{
|
2304 |
+
"epoch": 0.06,
|
2305 |
+
"learning_rate": 0.00018345840651444993,
|
2306 |
+
"loss": 0.6788,
|
2307 |
+
"step": 3830
|
2308 |
+
},
|
2309 |
+
{
|
2310 |
+
"epoch": 0.06,
|
2311 |
+
"learning_rate": 0.0001839374101868114,
|
2312 |
+
"loss": 0.6802,
|
2313 |
+
"step": 3840
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 0.06,
|
2317 |
+
"learning_rate": 0.0001844164138591729,
|
2318 |
+
"loss": 0.6682,
|
2319 |
+
"step": 3850
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 0.06,
|
2323 |
+
"learning_rate": 0.00018489541753153438,
|
2324 |
+
"loss": 0.6739,
|
2325 |
+
"step": 3860
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 0.06,
|
2329 |
+
"learning_rate": 0.00018537442120389588,
|
2330 |
+
"loss": 0.667,
|
2331 |
+
"step": 3870
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 0.06,
|
2335 |
+
"learning_rate": 0.00018585342487625737,
|
2336 |
+
"loss": 0.6771,
|
2337 |
+
"step": 3880
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 0.06,
|
2341 |
+
"learning_rate": 0.00018633242854861886,
|
2342 |
+
"loss": 0.6815,
|
2343 |
+
"step": 3890
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 0.06,
|
2347 |
+
"learning_rate": 0.00018681143222098033,
|
2348 |
+
"loss": 0.6649,
|
2349 |
+
"step": 3900
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 0.06,
|
2353 |
+
"learning_rate": 0.00018729043589334182,
|
2354 |
+
"loss": 0.6694,
|
2355 |
+
"step": 3910
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 0.06,
|
2359 |
+
"learning_rate": 0.00018776943956570332,
|
2360 |
+
"loss": 0.6558,
|
2361 |
+
"step": 3920
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 0.06,
|
2365 |
+
"learning_rate": 0.0001882484432380648,
|
2366 |
+
"loss": 0.6611,
|
2367 |
+
"step": 3930
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 0.06,
|
2371 |
+
"learning_rate": 0.0001887274469104263,
|
2372 |
+
"loss": 0.6879,
|
2373 |
+
"step": 3940
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 0.06,
|
2377 |
+
"learning_rate": 0.00018920645058278777,
|
2378 |
+
"loss": 0.6766,
|
2379 |
+
"step": 3950
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 0.06,
|
2383 |
+
"learning_rate": 0.00018968545425514927,
|
2384 |
+
"loss": 0.6872,
|
2385 |
+
"step": 3960
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 0.06,
|
2389 |
+
"learning_rate": 0.00019016445792751076,
|
2390 |
+
"loss": 0.6774,
|
2391 |
+
"step": 3970
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 0.06,
|
2395 |
+
"learning_rate": 0.00019064346159987226,
|
2396 |
+
"loss": 0.682,
|
2397 |
+
"step": 3980
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 0.06,
|
2401 |
+
"learning_rate": 0.00019112246527223375,
|
2402 |
+
"loss": 0.6762,
|
2403 |
+
"step": 3990
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 0.06,
|
2407 |
+
"learning_rate": 0.00019160146894459522,
|
2408 |
+
"loss": 0.676,
|
2409 |
+
"step": 4000
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 0.06,
|
2413 |
+
"learning_rate": 0.0001920804726169567,
|
2414 |
+
"loss": 0.6767,
|
2415 |
+
"step": 4010
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 0.06,
|
2419 |
+
"learning_rate": 0.0001925594762893182,
|
2420 |
+
"loss": 0.6728,
|
2421 |
+
"step": 4020
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 0.06,
|
2425 |
+
"learning_rate": 0.0001930384799616797,
|
2426 |
+
"loss": 0.6719,
|
2427 |
+
"step": 4030
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 0.06,
|
2431 |
+
"learning_rate": 0.0001935174836340412,
|
2432 |
+
"loss": 0.663,
|
2433 |
+
"step": 4040
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 0.06,
|
2437 |
+
"learning_rate": 0.00019399648730640266,
|
2438 |
+
"loss": 0.6789,
|
2439 |
+
"step": 4050
|
2440 |
+
},
|
2441 |
+
{
|
2442 |
+
"epoch": 0.06,
|
2443 |
+
"learning_rate": 0.00019447549097876415,
|
2444 |
+
"loss": 0.6626,
|
2445 |
+
"step": 4060
|
2446 |
+
},
|
2447 |
+
{
|
2448 |
+
"epoch": 0.06,
|
2449 |
+
"learning_rate": 0.00019495449465112565,
|
2450 |
+
"loss": 0.6738,
|
2451 |
+
"step": 4070
|
2452 |
+
},
|
2453 |
+
{
|
2454 |
+
"epoch": 0.07,
|
2455 |
+
"learning_rate": 0.00019543349832348714,
|
2456 |
+
"loss": 0.6737,
|
2457 |
+
"step": 4080
|
2458 |
+
},
|
2459 |
+
{
|
2460 |
+
"epoch": 0.07,
|
2461 |
+
"learning_rate": 0.00019591250199584863,
|
2462 |
+
"loss": 0.6771,
|
2463 |
+
"step": 4090
|
2464 |
+
},
|
2465 |
+
{
|
2466 |
+
"epoch": 0.07,
|
2467 |
+
"learning_rate": 0.0001963915056682101,
|
2468 |
+
"loss": 0.6779,
|
2469 |
+
"step": 4100
|
2470 |
+
},
|
2471 |
+
{
|
2472 |
+
"epoch": 0.07,
|
2473 |
+
"learning_rate": 0.0001968705093405716,
|
2474 |
+
"loss": 0.6969,
|
2475 |
+
"step": 4110
|
2476 |
+
},
|
2477 |
+
{
|
2478 |
+
"epoch": 0.07,
|
2479 |
+
"learning_rate": 0.0001973495130129331,
|
2480 |
+
"loss": 0.68,
|
2481 |
+
"step": 4120
|
2482 |
+
},
|
2483 |
+
{
|
2484 |
+
"epoch": 0.07,
|
2485 |
+
"learning_rate": 0.00019782851668529458,
|
2486 |
+
"loss": 0.6753,
|
2487 |
+
"step": 4130
|
2488 |
+
},
|
2489 |
+
{
|
2490 |
+
"epoch": 0.07,
|
2491 |
+
"learning_rate": 0.00019830752035765608,
|
2492 |
+
"loss": 0.6769,
|
2493 |
+
"step": 4140
|
2494 |
+
},
|
2495 |
+
{
|
2496 |
+
"epoch": 0.07,
|
2497 |
+
"learning_rate": 0.00019878652403001757,
|
2498 |
+
"loss": 0.6719,
|
2499 |
+
"step": 4150
|
2500 |
+
},
|
2501 |
+
{
|
2502 |
+
"epoch": 0.07,
|
2503 |
+
"learning_rate": 0.00019926552770237904,
|
2504 |
+
"loss": 0.674,
|
2505 |
+
"step": 4160
|
2506 |
+
},
|
2507 |
+
{
|
2508 |
+
"epoch": 0.07,
|
2509 |
+
"learning_rate": 0.00019974453137474053,
|
2510 |
+
"loss": 0.6635,
|
2511 |
+
"step": 4170
|
2512 |
+
},
|
2513 |
+
{
|
2514 |
+
"epoch": 0.07,
|
2515 |
+
"learning_rate": 0.00020022353504710203,
|
2516 |
+
"loss": 0.6671,
|
2517 |
+
"step": 4180
|
2518 |
+
},
|
2519 |
+
{
|
2520 |
+
"epoch": 0.07,
|
2521 |
+
"learning_rate": 0.00020070253871946352,
|
2522 |
+
"loss": 0.668,
|
2523 |
+
"step": 4190
|
2524 |
+
},
|
2525 |
+
{
|
2526 |
+
"epoch": 0.07,
|
2527 |
+
"learning_rate": 0.000201181542391825,
|
2528 |
+
"loss": 0.6654,
|
2529 |
+
"step": 4200
|
2530 |
+
},
|
2531 |
+
{
|
2532 |
+
"epoch": 0.07,
|
2533 |
+
"learning_rate": 0.00020166054606418648,
|
2534 |
+
"loss": 0.6505,
|
2535 |
+
"step": 4210
|
2536 |
+
},
|
2537 |
+
{
|
2538 |
+
"epoch": 0.07,
|
2539 |
+
"learning_rate": 0.00020213954973654797,
|
2540 |
+
"loss": 0.6583,
|
2541 |
+
"step": 4220
|
2542 |
+
},
|
2543 |
+
{
|
2544 |
+
"epoch": 0.07,
|
2545 |
+
"learning_rate": 0.00020261855340890944,
|
2546 |
+
"loss": 0.6616,
|
2547 |
+
"step": 4230
|
2548 |
+
},
|
2549 |
+
{
|
2550 |
+
"epoch": 0.07,
|
2551 |
+
"learning_rate": 0.00020309755708127094,
|
2552 |
+
"loss": 0.6618,
|
2553 |
+
"step": 4240
|
2554 |
+
},
|
2555 |
+
{
|
2556 |
+
"epoch": 0.07,
|
2557 |
+
"learning_rate": 0.0002035765607536324,
|
2558 |
+
"loss": 0.6524,
|
2559 |
+
"step": 4250
|
2560 |
+
},
|
2561 |
+
{
|
2562 |
+
"epoch": 0.07,
|
2563 |
+
"learning_rate": 0.0002040555644259939,
|
2564 |
+
"loss": 0.662,
|
2565 |
+
"step": 4260
|
2566 |
+
},
|
2567 |
+
{
|
2568 |
+
"epoch": 0.07,
|
2569 |
+
"learning_rate": 0.0002045345680983554,
|
2570 |
+
"loss": 0.647,
|
2571 |
+
"step": 4270
|
2572 |
+
},
|
2573 |
+
{
|
2574 |
+
"epoch": 0.07,
|
2575 |
+
"learning_rate": 0.00020501357177071688,
|
2576 |
+
"loss": 0.6381,
|
2577 |
+
"step": 4280
|
2578 |
+
},
|
2579 |
+
{
|
2580 |
+
"epoch": 0.07,
|
2581 |
+
"learning_rate": 0.00020549257544307838,
|
2582 |
+
"loss": 0.6357,
|
2583 |
+
"step": 4290
|
2584 |
+
},
|
2585 |
+
{
|
2586 |
+
"epoch": 0.07,
|
2587 |
+
"learning_rate": 0.00020597157911543984,
|
2588 |
+
"loss": 0.6382,
|
2589 |
+
"step": 4300
|
2590 |
+
},
|
2591 |
+
{
|
2592 |
+
"epoch": 0.07,
|
2593 |
+
"learning_rate": 0.00020645058278780134,
|
2594 |
+
"loss": 0.6332,
|
2595 |
+
"step": 4310
|
2596 |
+
},
|
2597 |
+
{
|
2598 |
+
"epoch": 0.07,
|
2599 |
+
"learning_rate": 0.00020692958646016283,
|
2600 |
+
"loss": 0.6315,
|
2601 |
+
"step": 4320
|
2602 |
+
},
|
2603 |
+
{
|
2604 |
+
"epoch": 0.07,
|
2605 |
+
"learning_rate": 0.00020740859013252433,
|
2606 |
+
"loss": 0.6352,
|
2607 |
+
"step": 4330
|
2608 |
+
},
|
2609 |
+
{
|
2610 |
+
"epoch": 0.07,
|
2611 |
+
"learning_rate": 0.00020788759380488582,
|
2612 |
+
"loss": 0.6309,
|
2613 |
+
"step": 4340
|
2614 |
+
},
|
2615 |
+
{
|
2616 |
+
"epoch": 0.07,
|
2617 |
+
"learning_rate": 0.0002083665974772473,
|
2618 |
+
"loss": 0.6198,
|
2619 |
+
"step": 4350
|
2620 |
+
},
|
2621 |
+
{
|
2622 |
+
"epoch": 0.07,
|
2623 |
+
"learning_rate": 0.00020884560114960878,
|
2624 |
+
"loss": 0.6222,
|
2625 |
+
"step": 4360
|
2626 |
+
},
|
2627 |
+
{
|
2628 |
+
"epoch": 0.07,
|
2629 |
+
"learning_rate": 0.00020932460482197027,
|
2630 |
+
"loss": 0.6282,
|
2631 |
+
"step": 4370
|
2632 |
+
},
|
2633 |
+
{
|
2634 |
+
"epoch": 0.07,
|
2635 |
+
"learning_rate": 0.00020980360849433177,
|
2636 |
+
"loss": 0.6213,
|
2637 |
+
"step": 4380
|
2638 |
+
},
|
2639 |
+
{
|
2640 |
+
"epoch": 0.07,
|
2641 |
+
"learning_rate": 0.00021028261216669326,
|
2642 |
+
"loss": 0.6237,
|
2643 |
+
"step": 4390
|
2644 |
+
},
|
2645 |
+
{
|
2646 |
+
"epoch": 0.07,
|
2647 |
+
"learning_rate": 0.00021076161583905473,
|
2648 |
+
"loss": 0.6325,
|
2649 |
+
"step": 4400
|
2650 |
+
},
|
2651 |
+
{
|
2652 |
+
"epoch": 0.07,
|
2653 |
+
"learning_rate": 0.00021124061951141622,
|
2654 |
+
"loss": 0.6247,
|
2655 |
+
"step": 4410
|
2656 |
+
},
|
2657 |
+
{
|
2658 |
+
"epoch": 0.07,
|
2659 |
+
"learning_rate": 0.00021171962318377772,
|
2660 |
+
"loss": 0.6229,
|
2661 |
+
"step": 4420
|
2662 |
+
},
|
2663 |
+
{
|
2664 |
+
"epoch": 0.07,
|
2665 |
+
"learning_rate": 0.0002121986268561392,
|
2666 |
+
"loss": 0.672,
|
2667 |
+
"step": 4430
|
2668 |
+
},
|
2669 |
+
{
|
2670 |
+
"epoch": 0.07,
|
2671 |
+
"learning_rate": 0.0002126776305285007,
|
2672 |
+
"loss": 0.958,
|
2673 |
+
"step": 4440
|
2674 |
+
},
|
2675 |
+
{
|
2676 |
+
"epoch": 0.07,
|
2677 |
+
"learning_rate": 0.0002131566342008622,
|
2678 |
+
"loss": 0.9283,
|
2679 |
+
"step": 4450
|
2680 |
+
},
|
2681 |
+
{
|
2682 |
+
"epoch": 0.07,
|
2683 |
+
"learning_rate": 0.00021363563787322367,
|
2684 |
+
"loss": 0.8836,
|
2685 |
+
"step": 4460
|
2686 |
+
},
|
2687 |
+
{
|
2688 |
+
"epoch": 0.07,
|
2689 |
+
"learning_rate": 0.00021411464154558516,
|
2690 |
+
"loss": 0.9024,
|
2691 |
+
"step": 4470
|
2692 |
+
},
|
2693 |
+
{
|
2694 |
+
"epoch": 0.07,
|
2695 |
+
"learning_rate": 0.00021459364521794665,
|
2696 |
+
"loss": 0.8943,
|
2697 |
+
"step": 4480
|
2698 |
+
},
|
2699 |
+
{
|
2700 |
+
"epoch": 0.07,
|
2701 |
+
"learning_rate": 0.00021507264889030815,
|
2702 |
+
"loss": 0.8709,
|
2703 |
+
"step": 4490
|
2704 |
+
},
|
2705 |
+
{
|
2706 |
+
"epoch": 0.07,
|
2707 |
+
"learning_rate": 0.00021555165256266964,
|
2708 |
+
"loss": 0.8923,
|
2709 |
+
"step": 4500
|
2710 |
+
},
|
2711 |
+
{
|
2712 |
+
"epoch": 0.07,
|
2713 |
+
"learning_rate": 0.0002160306562350311,
|
2714 |
+
"loss": 0.8864,
|
2715 |
+
"step": 4510
|
2716 |
+
},
|
2717 |
+
{
|
2718 |
+
"epoch": 0.07,
|
2719 |
+
"learning_rate": 0.0002165096599073926,
|
2720 |
+
"loss": 0.8725,
|
2721 |
+
"step": 4520
|
2722 |
+
},
|
2723 |
+
{
|
2724 |
+
"epoch": 0.07,
|
2725 |
+
"learning_rate": 0.0002169886635797541,
|
2726 |
+
"loss": 0.8794,
|
2727 |
+
"step": 4530
|
2728 |
+
},
|
2729 |
+
{
|
2730 |
+
"epoch": 0.07,
|
2731 |
+
"learning_rate": 0.0002174676672521156,
|
2732 |
+
"loss": 0.8599,
|
2733 |
+
"step": 4540
|
2734 |
+
},
|
2735 |
+
{
|
2736 |
+
"epoch": 0.07,
|
2737 |
+
"learning_rate": 0.00021794667092447708,
|
2738 |
+
"loss": 0.883,
|
2739 |
+
"step": 4550
|
2740 |
+
},
|
2741 |
+
{
|
2742 |
+
"epoch": 0.07,
|
2743 |
+
"learning_rate": 0.00021842567459683855,
|
2744 |
+
"loss": 0.8507,
|
2745 |
+
"step": 4560
|
2746 |
+
},
|
2747 |
+
{
|
2748 |
+
"epoch": 0.07,
|
2749 |
+
"learning_rate": 0.00021890467826920005,
|
2750 |
+
"loss": 0.8668,
|
2751 |
+
"step": 4570
|
2752 |
+
},
|
2753 |
+
{
|
2754 |
+
"epoch": 0.07,
|
2755 |
+
"learning_rate": 0.00021938368194156154,
|
2756 |
+
"loss": 0.8604,
|
2757 |
+
"step": 4580
|
2758 |
+
},
|
2759 |
+
{
|
2760 |
+
"epoch": 0.07,
|
2761 |
+
"learning_rate": 0.00021986268561392303,
|
2762 |
+
"loss": 0.9212,
|
2763 |
+
"step": 4590
|
2764 |
+
},
|
2765 |
+
{
|
2766 |
+
"epoch": 0.07,
|
2767 |
+
"learning_rate": 0.00022034168928628453,
|
2768 |
+
"loss": 0.9333,
|
2769 |
+
"step": 4600
|
2770 |
+
},
|
2771 |
+
{
|
2772 |
+
"epoch": 0.07,
|
2773 |
+
"learning_rate": 0.000220820692958646,
|
2774 |
+
"loss": 0.9508,
|
2775 |
+
"step": 4610
|
2776 |
+
},
|
2777 |
+
{
|
2778 |
+
"epoch": 0.07,
|
2779 |
+
"learning_rate": 0.0002212996966310075,
|
2780 |
+
"loss": 0.9529,
|
2781 |
+
"step": 4620
|
2782 |
+
},
|
2783 |
+
{
|
2784 |
+
"epoch": 0.07,
|
2785 |
+
"learning_rate": 0.00022177870030336898,
|
2786 |
+
"loss": 0.937,
|
2787 |
+
"step": 4630
|
2788 |
+
},
|
2789 |
+
{
|
2790 |
+
"epoch": 0.07,
|
2791 |
+
"learning_rate": 0.00022225770397573048,
|
2792 |
+
"loss": 0.9439,
|
2793 |
+
"step": 4640
|
2794 |
+
},
|
2795 |
+
{
|
2796 |
+
"epoch": 0.07,
|
2797 |
+
"learning_rate": 0.00022273670764809197,
|
2798 |
+
"loss": 0.9287,
|
2799 |
+
"step": 4650
|
2800 |
+
},
|
2801 |
+
{
|
2802 |
+
"epoch": 0.07,
|
2803 |
+
"learning_rate": 0.00022321571132045344,
|
2804 |
+
"loss": 0.9313,
|
2805 |
+
"step": 4660
|
2806 |
+
},
|
2807 |
+
{
|
2808 |
+
"epoch": 0.07,
|
2809 |
+
"learning_rate": 0.00022369471499281493,
|
2810 |
+
"loss": 0.9196,
|
2811 |
+
"step": 4670
|
2812 |
+
},
|
2813 |
+
{
|
2814 |
+
"epoch": 0.07,
|
2815 |
+
"learning_rate": 0.00022417371866517642,
|
2816 |
+
"loss": 0.9217,
|
2817 |
+
"step": 4680
|
2818 |
+
},
|
2819 |
+
{
|
2820 |
+
"epoch": 0.07,
|
2821 |
+
"learning_rate": 0.00022465272233753792,
|
2822 |
+
"loss": 0.9251,
|
2823 |
+
"step": 4690
|
2824 |
+
},
|
2825 |
+
{
|
2826 |
+
"epoch": 0.08,
|
2827 |
+
"learning_rate": 0.0002251317260098994,
|
2828 |
+
"loss": 0.9357,
|
2829 |
+
"step": 4700
|
2830 |
+
},
|
2831 |
+
{
|
2832 |
+
"epoch": 0.08,
|
2833 |
+
"learning_rate": 0.0002256107296822609,
|
2834 |
+
"loss": 0.9199,
|
2835 |
+
"step": 4710
|
2836 |
+
},
|
2837 |
+
{
|
2838 |
+
"epoch": 0.08,
|
2839 |
+
"learning_rate": 0.00022608973335462237,
|
2840 |
+
"loss": 0.9208,
|
2841 |
+
"step": 4720
|
2842 |
+
},
|
2843 |
+
{
|
2844 |
+
"epoch": 0.08,
|
2845 |
+
"learning_rate": 0.00022656873702698384,
|
2846 |
+
"loss": 0.924,
|
2847 |
+
"step": 4730
|
2848 |
+
},
|
2849 |
+
{
|
2850 |
+
"epoch": 0.08,
|
2851 |
+
"learning_rate": 0.00022704774069934533,
|
2852 |
+
"loss": 0.9353,
|
2853 |
+
"step": 4740
|
2854 |
+
},
|
2855 |
+
{
|
2856 |
+
"epoch": 0.08,
|
2857 |
+
"learning_rate": 0.00022752674437170683,
|
2858 |
+
"loss": 1.0033,
|
2859 |
+
"step": 4750
|
2860 |
+
},
|
2861 |
+
{
|
2862 |
+
"epoch": 0.08,
|
2863 |
+
"learning_rate": 0.0002280057480440683,
|
2864 |
+
"loss": 0.9979,
|
2865 |
+
"step": 4760
|
2866 |
+
},
|
2867 |
+
{
|
2868 |
+
"epoch": 0.08,
|
2869 |
+
"learning_rate": 0.0002284847517164298,
|
2870 |
+
"loss": 0.9915,
|
2871 |
+
"step": 4770
|
2872 |
+
},
|
2873 |
+
{
|
2874 |
+
"epoch": 0.08,
|
2875 |
+
"learning_rate": 0.00022896375538879128,
|
2876 |
+
"loss": 0.9785,
|
2877 |
+
"step": 4780
|
2878 |
+
},
|
2879 |
+
{
|
2880 |
+
"epoch": 0.08,
|
2881 |
+
"learning_rate": 0.00022944275906115278,
|
2882 |
+
"loss": 0.9813,
|
2883 |
+
"step": 4790
|
2884 |
+
},
|
2885 |
+
{
|
2886 |
+
"epoch": 0.08,
|
2887 |
+
"learning_rate": 0.00022992176273351427,
|
2888 |
+
"loss": 0.9785,
|
2889 |
+
"step": 4800
|
2890 |
+
},
|
2891 |
+
{
|
2892 |
+
"epoch": 0.08,
|
2893 |
+
"learning_rate": 0.00023040076640587574,
|
2894 |
+
"loss": 0.984,
|
2895 |
+
"step": 4810
|
2896 |
+
},
|
2897 |
+
{
|
2898 |
+
"epoch": 0.08,
|
2899 |
+
"learning_rate": 0.00023087977007823723,
|
2900 |
+
"loss": 0.9657,
|
2901 |
+
"step": 4820
|
2902 |
+
},
|
2903 |
+
{
|
2904 |
+
"epoch": 0.08,
|
2905 |
+
"learning_rate": 0.00023135877375059872,
|
2906 |
+
"loss": 0.9531,
|
2907 |
+
"step": 4830
|
2908 |
+
},
|
2909 |
+
{
|
2910 |
+
"epoch": 0.08,
|
2911 |
+
"learning_rate": 0.00023183777742296022,
|
2912 |
+
"loss": 0.9606,
|
2913 |
+
"step": 4840
|
2914 |
+
},
|
2915 |
+
{
|
2916 |
+
"epoch": 0.08,
|
2917 |
+
"learning_rate": 0.0002323167810953217,
|
2918 |
+
"loss": 0.9686,
|
2919 |
+
"step": 4850
|
2920 |
+
},
|
2921 |
+
{
|
2922 |
+
"epoch": 0.08,
|
2923 |
+
"learning_rate": 0.00023279578476768318,
|
2924 |
+
"loss": 0.968,
|
2925 |
+
"step": 4860
|
2926 |
+
},
|
2927 |
+
{
|
2928 |
+
"epoch": 0.08,
|
2929 |
+
"learning_rate": 0.00023327478844004467,
|
2930 |
+
"loss": 0.9517,
|
2931 |
+
"step": 4870
|
2932 |
+
},
|
2933 |
+
{
|
2934 |
+
"epoch": 0.08,
|
2935 |
+
"learning_rate": 0.00023375379211240617,
|
2936 |
+
"loss": 0.9517,
|
2937 |
+
"step": 4880
|
2938 |
+
},
|
2939 |
+
{
|
2940 |
+
"epoch": 0.08,
|
2941 |
+
"learning_rate": 0.00023423279578476766,
|
2942 |
+
"loss": 0.9465,
|
2943 |
+
"step": 4890
|
2944 |
+
},
|
2945 |
+
{
|
2946 |
+
"epoch": 0.08,
|
2947 |
+
"learning_rate": 0.00023471179945712916,
|
2948 |
+
"loss": 0.9635,
|
2949 |
+
"step": 4900
|
2950 |
+
},
|
2951 |
+
{
|
2952 |
+
"epoch": 0.08,
|
2953 |
+
"learning_rate": 0.00023519080312949062,
|
2954 |
+
"loss": 0.9523,
|
2955 |
+
"step": 4910
|
2956 |
+
},
|
2957 |
+
{
|
2958 |
+
"epoch": 0.08,
|
2959 |
+
"learning_rate": 0.00023566980680185212,
|
2960 |
+
"loss": 0.953,
|
2961 |
+
"step": 4920
|
2962 |
+
},
|
2963 |
+
{
|
2964 |
+
"epoch": 0.08,
|
2965 |
+
"learning_rate": 0.0002361488104742136,
|
2966 |
+
"loss": 0.9455,
|
2967 |
+
"step": 4930
|
2968 |
+
},
|
2969 |
+
{
|
2970 |
+
"epoch": 0.08,
|
2971 |
+
"learning_rate": 0.0002366278141465751,
|
2972 |
+
"loss": 0.9318,
|
2973 |
+
"step": 4940
|
2974 |
+
},
|
2975 |
+
{
|
2976 |
+
"epoch": 0.08,
|
2977 |
+
"learning_rate": 0.0002371068178189366,
|
2978 |
+
"loss": 0.9487,
|
2979 |
+
"step": 4950
|
2980 |
+
},
|
2981 |
+
{
|
2982 |
+
"epoch": 0.08,
|
2983 |
+
"learning_rate": 0.0002375858214912981,
|
2984 |
+
"loss": 0.9319,
|
2985 |
+
"step": 4960
|
2986 |
+
},
|
2987 |
+
{
|
2988 |
+
"epoch": 0.08,
|
2989 |
+
"learning_rate": 0.00023806482516365956,
|
2990 |
+
"loss": 0.9357,
|
2991 |
+
"step": 4970
|
2992 |
+
},
|
2993 |
+
{
|
2994 |
+
"epoch": 0.08,
|
2995 |
+
"learning_rate": 0.00023854382883602105,
|
2996 |
+
"loss": 0.9402,
|
2997 |
+
"step": 4980
|
2998 |
+
},
|
2999 |
+
{
|
3000 |
+
"epoch": 0.08,
|
3001 |
+
"learning_rate": 0.00023902283250838255,
|
3002 |
+
"loss": 0.9298,
|
3003 |
+
"step": 4990
|
3004 |
+
},
|
3005 |
+
{
|
3006 |
+
"epoch": 0.08,
|
3007 |
+
"learning_rate": 0.00023950183618074404,
|
3008 |
+
"loss": 0.9387,
|
3009 |
+
"step": 5000
|
3010 |
+
},
|
3011 |
+
{
|
3012 |
+
"epoch": 0.08,
|
3013 |
+
"learning_rate": 0.00023998083985310553,
|
3014 |
+
"loss": 0.9283,
|
3015 |
+
"step": 5010
|
3016 |
+
},
|
3017 |
+
{
|
3018 |
+
"epoch": 0.08,
|
3019 |
+
"learning_rate": 0.000240459843525467,
|
3020 |
+
"loss": 0.9295,
|
3021 |
+
"step": 5020
|
3022 |
+
},
|
3023 |
+
{
|
3024 |
+
"epoch": 0.08,
|
3025 |
+
"learning_rate": 0.0002409388471978285,
|
3026 |
+
"loss": 0.9248,
|
3027 |
+
"step": 5030
|
3028 |
+
},
|
3029 |
+
{
|
3030 |
+
"epoch": 0.08,
|
3031 |
+
"learning_rate": 0.00024141785087019,
|
3032 |
+
"loss": 0.92,
|
3033 |
+
"step": 5040
|
3034 |
+
},
|
3035 |
+
{
|
3036 |
+
"epoch": 0.08,
|
3037 |
+
"learning_rate": 0.00024189685454255148,
|
3038 |
+
"loss": 0.9262,
|
3039 |
+
"step": 5050
|
3040 |
+
},
|
3041 |
+
{
|
3042 |
+
"epoch": 0.08,
|
3043 |
+
"learning_rate": 0.00024237585821491298,
|
3044 |
+
"loss": 0.9404,
|
3045 |
+
"step": 5060
|
3046 |
+
},
|
3047 |
+
{
|
3048 |
+
"epoch": 0.08,
|
3049 |
+
"learning_rate": 0.00024285486188727444,
|
3050 |
+
"loss": 0.9296,
|
3051 |
+
"step": 5070
|
3052 |
+
},
|
3053 |
+
{
|
3054 |
+
"epoch": 0.08,
|
3055 |
+
"learning_rate": 0.00024333386555963594,
|
3056 |
+
"loss": 0.9182,
|
3057 |
+
"step": 5080
|
3058 |
+
},
|
3059 |
+
{
|
3060 |
+
"epoch": 0.08,
|
3061 |
+
"learning_rate": 0.00024381286923199743,
|
3062 |
+
"loss": 0.9129,
|
3063 |
+
"step": 5090
|
3064 |
+
},
|
3065 |
+
{
|
3066 |
+
"epoch": 0.08,
|
3067 |
+
"learning_rate": 0.0002442918729043589,
|
3068 |
+
"loss": 0.9244,
|
3069 |
+
"step": 5100
|
3070 |
+
},
|
3071 |
+
{
|
3072 |
+
"epoch": 0.08,
|
3073 |
+
"learning_rate": 0.0002447708765767204,
|
3074 |
+
"loss": 0.9113,
|
3075 |
+
"step": 5110
|
3076 |
+
},
|
3077 |
+
{
|
3078 |
+
"epoch": 0.08,
|
3079 |
+
"learning_rate": 0.0002452498802490819,
|
3080 |
+
"loss": 0.8955,
|
3081 |
+
"step": 5120
|
3082 |
+
},
|
3083 |
+
{
|
3084 |
+
"epoch": 0.08,
|
3085 |
+
"learning_rate": 0.0002457288839214434,
|
3086 |
+
"loss": 0.901,
|
3087 |
+
"step": 5130
|
3088 |
+
},
|
3089 |
+
{
|
3090 |
+
"epoch": 0.08,
|
3091 |
+
"learning_rate": 0.0002462078875938049,
|
3092 |
+
"loss": 0.9069,
|
3093 |
+
"step": 5140
|
3094 |
+
},
|
3095 |
+
{
|
3096 |
+
"epoch": 0.08,
|
3097 |
+
"learning_rate": 0.00024668689126616637,
|
3098 |
+
"loss": 0.8934,
|
3099 |
+
"step": 5150
|
3100 |
+
},
|
3101 |
+
{
|
3102 |
+
"epoch": 0.08,
|
3103 |
+
"learning_rate": 0.00024716589493852784,
|
3104 |
+
"loss": 0.8879,
|
3105 |
+
"step": 5160
|
3106 |
+
},
|
3107 |
+
{
|
3108 |
+
"epoch": 0.08,
|
3109 |
+
"learning_rate": 0.00024764489861088936,
|
3110 |
+
"loss": 0.8909,
|
3111 |
+
"step": 5170
|
3112 |
+
},
|
3113 |
+
{
|
3114 |
+
"epoch": 0.08,
|
3115 |
+
"learning_rate": 0.0002481239022832508,
|
3116 |
+
"loss": 0.9004,
|
3117 |
+
"step": 5180
|
3118 |
+
},
|
3119 |
+
{
|
3120 |
+
"epoch": 0.08,
|
3121 |
+
"learning_rate": 0.00024860290595561234,
|
3122 |
+
"loss": 0.8819,
|
3123 |
+
"step": 5190
|
3124 |
+
},
|
3125 |
+
{
|
3126 |
+
"epoch": 0.08,
|
3127 |
+
"learning_rate": 0.0002490819096279738,
|
3128 |
+
"loss": 0.8925,
|
3129 |
+
"step": 5200
|
3130 |
+
},
|
3131 |
+
{
|
3132 |
+
"epoch": 0.08,
|
3133 |
+
"learning_rate": 0.0002495609133003353,
|
3134 |
+
"loss": 0.8959,
|
3135 |
+
"step": 5210
|
3136 |
+
},
|
3137 |
+
{
|
3138 |
+
"epoch": 0.08,
|
3139 |
+
"learning_rate": 0.00025003991697269674,
|
3140 |
+
"loss": 0.9681,
|
3141 |
+
"step": 5220
|
3142 |
+
},
|
3143 |
+
{
|
3144 |
+
"epoch": 0.08,
|
3145 |
+
"learning_rate": 0.00025051892064505827,
|
3146 |
+
"loss": 0.9684,
|
3147 |
+
"step": 5230
|
3148 |
+
},
|
3149 |
+
{
|
3150 |
+
"epoch": 0.08,
|
3151 |
+
"learning_rate": 0.00025099792431741973,
|
3152 |
+
"loss": 0.9552,
|
3153 |
+
"step": 5240
|
3154 |
+
},
|
3155 |
+
{
|
3156 |
+
"epoch": 0.08,
|
3157 |
+
"learning_rate": 0.0002514769279897812,
|
3158 |
+
"loss": 0.9704,
|
3159 |
+
"step": 5250
|
3160 |
+
},
|
3161 |
+
{
|
3162 |
+
"epoch": 0.08,
|
3163 |
+
"learning_rate": 0.0002519559316621427,
|
3164 |
+
"loss": 0.9671,
|
3165 |
+
"step": 5260
|
3166 |
+
},
|
3167 |
+
{
|
3168 |
+
"epoch": 0.08,
|
3169 |
+
"learning_rate": 0.0002524349353345042,
|
3170 |
+
"loss": 0.963,
|
3171 |
+
"step": 5270
|
3172 |
+
},
|
3173 |
+
{
|
3174 |
+
"epoch": 0.08,
|
3175 |
+
"learning_rate": 0.0002529139390068657,
|
3176 |
+
"loss": 0.9612,
|
3177 |
+
"step": 5280
|
3178 |
+
},
|
3179 |
+
{
|
3180 |
+
"epoch": 0.08,
|
3181 |
+
"learning_rate": 0.0002533929426792272,
|
3182 |
+
"loss": 0.9592,
|
3183 |
+
"step": 5290
|
3184 |
+
},
|
3185 |
+
{
|
3186 |
+
"epoch": 0.08,
|
3187 |
+
"learning_rate": 0.00025387194635158864,
|
3188 |
+
"loss": 0.9516,
|
3189 |
+
"step": 5300
|
3190 |
+
},
|
3191 |
+
{
|
3192 |
+
"epoch": 0.08,
|
3193 |
+
"learning_rate": 0.00025435095002395016,
|
3194 |
+
"loss": 0.9569,
|
3195 |
+
"step": 5310
|
3196 |
+
},
|
3197 |
+
{
|
3198 |
+
"epoch": 0.08,
|
3199 |
+
"learning_rate": 0.00025482995369631163,
|
3200 |
+
"loss": 0.9553,
|
3201 |
+
"step": 5320
|
3202 |
+
},
|
3203 |
+
{
|
3204 |
+
"epoch": 0.09,
|
3205 |
+
"learning_rate": 0.00025530895736867315,
|
3206 |
+
"loss": 0.9678,
|
3207 |
+
"step": 5330
|
3208 |
+
},
|
3209 |
+
{
|
3210 |
+
"epoch": 0.09,
|
3211 |
+
"learning_rate": 0.0002557879610410346,
|
3212 |
+
"loss": 0.9645,
|
3213 |
+
"step": 5340
|
3214 |
+
},
|
3215 |
+
{
|
3216 |
+
"epoch": 0.09,
|
3217 |
+
"learning_rate": 0.0002562669647133961,
|
3218 |
+
"loss": 0.9569,
|
3219 |
+
"step": 5350
|
3220 |
+
},
|
3221 |
+
{
|
3222 |
+
"epoch": 0.09,
|
3223 |
+
"learning_rate": 0.0002567459683857576,
|
3224 |
+
"loss": 0.9448,
|
3225 |
+
"step": 5360
|
3226 |
+
},
|
3227 |
+
{
|
3228 |
+
"epoch": 0.09,
|
3229 |
+
"learning_rate": 0.00025722497205811907,
|
3230 |
+
"loss": 0.9755,
|
3231 |
+
"step": 5370
|
3232 |
+
},
|
3233 |
+
{
|
3234 |
+
"epoch": 0.09,
|
3235 |
+
"learning_rate": 0.0002577039757304806,
|
3236 |
+
"loss": 0.9914,
|
3237 |
+
"step": 5380
|
3238 |
+
},
|
3239 |
+
{
|
3240 |
+
"epoch": 0.09,
|
3241 |
+
"learning_rate": 0.00025818297940284206,
|
3242 |
+
"loss": 0.9916,
|
3243 |
+
"step": 5390
|
3244 |
+
},
|
3245 |
+
{
|
3246 |
+
"epoch": 0.09,
|
3247 |
+
"learning_rate": 0.0002586619830752035,
|
3248 |
+
"loss": 0.9896,
|
3249 |
+
"step": 5400
|
3250 |
+
},
|
3251 |
+
{
|
3252 |
+
"epoch": 0.09,
|
3253 |
+
"learning_rate": 0.00025914098674756505,
|
3254 |
+
"loss": 0.9998,
|
3255 |
+
"step": 5410
|
3256 |
+
},
|
3257 |
+
{
|
3258 |
+
"epoch": 0.09,
|
3259 |
+
"learning_rate": 0.0002596199904199265,
|
3260 |
+
"loss": 0.9861,
|
3261 |
+
"step": 5420
|
3262 |
+
},
|
3263 |
+
{
|
3264 |
+
"epoch": 0.09,
|
3265 |
+
"learning_rate": 0.00026009899409228804,
|
3266 |
+
"loss": 0.9857,
|
3267 |
+
"step": 5430
|
3268 |
+
},
|
3269 |
+
{
|
3270 |
+
"epoch": 0.09,
|
3271 |
+
"learning_rate": 0.0002605779977646495,
|
3272 |
+
"loss": 0.9788,
|
3273 |
+
"step": 5440
|
3274 |
+
},
|
3275 |
+
{
|
3276 |
+
"epoch": 0.09,
|
3277 |
+
"learning_rate": 0.00026105700143701097,
|
3278 |
+
"loss": 0.9827,
|
3279 |
+
"step": 5450
|
3280 |
+
},
|
3281 |
+
{
|
3282 |
+
"epoch": 0.09,
|
3283 |
+
"learning_rate": 0.0002615360051093725,
|
3284 |
+
"loss": 0.995,
|
3285 |
+
"step": 5460
|
3286 |
+
},
|
3287 |
+
{
|
3288 |
+
"epoch": 0.09,
|
3289 |
+
"learning_rate": 0.00026201500878173396,
|
3290 |
+
"loss": 0.9898,
|
3291 |
+
"step": 5470
|
3292 |
+
},
|
3293 |
+
{
|
3294 |
+
"epoch": 0.09,
|
3295 |
+
"learning_rate": 0.0002624940124540955,
|
3296 |
+
"loss": 0.9771,
|
3297 |
+
"step": 5480
|
3298 |
+
},
|
3299 |
+
{
|
3300 |
+
"epoch": 0.09,
|
3301 |
+
"learning_rate": 0.00026297301612645695,
|
3302 |
+
"loss": 0.9728,
|
3303 |
+
"step": 5490
|
3304 |
+
},
|
3305 |
+
{
|
3306 |
+
"epoch": 0.09,
|
3307 |
+
"learning_rate": 0.0002634520197988184,
|
3308 |
+
"loss": 0.9766,
|
3309 |
+
"step": 5500
|
3310 |
+
},
|
3311 |
+
{
|
3312 |
+
"epoch": 0.09,
|
3313 |
+
"learning_rate": 0.00026393102347117993,
|
3314 |
+
"loss": 0.9803,
|
3315 |
+
"step": 5510
|
3316 |
+
},
|
3317 |
+
{
|
3318 |
+
"epoch": 0.09,
|
3319 |
+
"learning_rate": 0.0002644100271435414,
|
3320 |
+
"loss": 0.9785,
|
3321 |
+
"step": 5520
|
3322 |
+
},
|
3323 |
+
{
|
3324 |
+
"epoch": 0.09,
|
3325 |
+
"learning_rate": 0.0002648890308159029,
|
3326 |
+
"loss": 0.9898,
|
3327 |
+
"step": 5530
|
3328 |
+
},
|
3329 |
+
{
|
3330 |
+
"epoch": 0.09,
|
3331 |
+
"learning_rate": 0.0002653680344882644,
|
3332 |
+
"loss": 0.9976,
|
3333 |
+
"step": 5540
|
3334 |
+
},
|
3335 |
+
{
|
3336 |
+
"epoch": 0.09,
|
3337 |
+
"learning_rate": 0.00026584703816062585,
|
3338 |
+
"loss": 0.9993,
|
3339 |
+
"step": 5550
|
3340 |
+
},
|
3341 |
+
{
|
3342 |
+
"epoch": 0.09,
|
3343 |
+
"learning_rate": 0.0002663260418329874,
|
3344 |
+
"loss": 1.0075,
|
3345 |
+
"step": 5560
|
3346 |
+
},
|
3347 |
+
{
|
3348 |
+
"epoch": 0.09,
|
3349 |
+
"learning_rate": 0.00026680504550534884,
|
3350 |
+
"loss": 1.0011,
|
3351 |
+
"step": 5570
|
3352 |
+
},
|
3353 |
+
{
|
3354 |
+
"epoch": 0.09,
|
3355 |
+
"learning_rate": 0.00026728404917771036,
|
3356 |
+
"loss": 1.0041,
|
3357 |
+
"step": 5580
|
3358 |
+
},
|
3359 |
+
{
|
3360 |
+
"epoch": 0.09,
|
3361 |
+
"learning_rate": 0.00026776305285007183,
|
3362 |
+
"loss": 0.9964,
|
3363 |
+
"step": 5590
|
3364 |
+
},
|
3365 |
+
{
|
3366 |
+
"epoch": 0.09,
|
3367 |
+
"learning_rate": 0.0002682420565224333,
|
3368 |
+
"loss": 0.9956,
|
3369 |
+
"step": 5600
|
3370 |
+
},
|
3371 |
+
{
|
3372 |
+
"epoch": 0.09,
|
3373 |
+
"learning_rate": 0.0002687210601947948,
|
3374 |
+
"loss": 0.9928,
|
3375 |
+
"step": 5610
|
3376 |
+
},
|
3377 |
+
{
|
3378 |
+
"epoch": 0.09,
|
3379 |
+
"learning_rate": 0.0002692000638671563,
|
3380 |
+
"loss": 0.9877,
|
3381 |
+
"step": 5620
|
3382 |
+
},
|
3383 |
+
{
|
3384 |
+
"epoch": 0.09,
|
3385 |
+
"learning_rate": 0.0002696790675395178,
|
3386 |
+
"loss": 0.9948,
|
3387 |
+
"step": 5630
|
3388 |
+
},
|
3389 |
+
{
|
3390 |
+
"epoch": 0.09,
|
3391 |
+
"learning_rate": 0.00027015807121187927,
|
3392 |
+
"loss": 0.9955,
|
3393 |
+
"step": 5640
|
3394 |
+
},
|
3395 |
+
{
|
3396 |
+
"epoch": 0.09,
|
3397 |
+
"learning_rate": 0.0002706370748842408,
|
3398 |
+
"loss": 0.986,
|
3399 |
+
"step": 5650
|
3400 |
+
},
|
3401 |
+
{
|
3402 |
+
"epoch": 0.09,
|
3403 |
+
"learning_rate": 0.00027111607855660226,
|
3404 |
+
"loss": 0.9942,
|
3405 |
+
"step": 5660
|
3406 |
+
},
|
3407 |
+
{
|
3408 |
+
"epoch": 0.09,
|
3409 |
+
"learning_rate": 0.00027159508222896373,
|
3410 |
+
"loss": 0.9883,
|
3411 |
+
"step": 5670
|
3412 |
+
},
|
3413 |
+
{
|
3414 |
+
"epoch": 0.09,
|
3415 |
+
"learning_rate": 0.00027207408590132525,
|
3416 |
+
"loss": 1.0043,
|
3417 |
+
"step": 5680
|
3418 |
+
},
|
3419 |
+
{
|
3420 |
+
"epoch": 0.09,
|
3421 |
+
"learning_rate": 0.0002725530895736867,
|
3422 |
+
"loss": 0.997,
|
3423 |
+
"step": 5690
|
3424 |
+
},
|
3425 |
+
{
|
3426 |
+
"epoch": 0.09,
|
3427 |
+
"learning_rate": 0.00027303209324604824,
|
3428 |
+
"loss": 1.0037,
|
3429 |
+
"step": 5700
|
3430 |
+
},
|
3431 |
+
{
|
3432 |
+
"epoch": 0.09,
|
3433 |
+
"learning_rate": 0.0002735110969184097,
|
3434 |
+
"loss": 1.0123,
|
3435 |
+
"step": 5710
|
3436 |
+
},
|
3437 |
+
{
|
3438 |
+
"epoch": 0.09,
|
3439 |
+
"learning_rate": 0.00027399010059077117,
|
3440 |
+
"loss": 1.0016,
|
3441 |
+
"step": 5720
|
3442 |
+
},
|
3443 |
+
{
|
3444 |
+
"epoch": 0.09,
|
3445 |
+
"learning_rate": 0.00027446910426313264,
|
3446 |
+
"loss": 1.0128,
|
3447 |
+
"step": 5730
|
3448 |
+
},
|
3449 |
+
{
|
3450 |
+
"epoch": 0.09,
|
3451 |
+
"learning_rate": 0.00027494810793549416,
|
3452 |
+
"loss": 0.9919,
|
3453 |
+
"step": 5740
|
3454 |
+
},
|
3455 |
+
{
|
3456 |
+
"epoch": 0.09,
|
3457 |
+
"learning_rate": 0.0002754271116078556,
|
3458 |
+
"loss": 0.9995,
|
3459 |
+
"step": 5750
|
3460 |
+
},
|
3461 |
+
{
|
3462 |
+
"epoch": 0.09,
|
3463 |
+
"learning_rate": 0.0002759061152802171,
|
3464 |
+
"loss": 1.0071,
|
3465 |
+
"step": 5760
|
3466 |
+
},
|
3467 |
+
{
|
3468 |
+
"epoch": 0.09,
|
3469 |
+
"learning_rate": 0.0002763851189525786,
|
3470 |
+
"loss": 0.9988,
|
3471 |
+
"step": 5770
|
3472 |
+
},
|
3473 |
+
{
|
3474 |
+
"epoch": 0.09,
|
3475 |
+
"learning_rate": 0.0002768641226249401,
|
3476 |
+
"loss": 1.0016,
|
3477 |
+
"step": 5780
|
3478 |
+
},
|
3479 |
+
{
|
3480 |
+
"epoch": 0.09,
|
3481 |
+
"learning_rate": 0.0002773431262973016,
|
3482 |
+
"loss": 1.0005,
|
3483 |
+
"step": 5790
|
3484 |
+
},
|
3485 |
+
{
|
3486 |
+
"epoch": 0.09,
|
3487 |
+
"learning_rate": 0.00027782212996966307,
|
3488 |
+
"loss": 0.9998,
|
3489 |
+
"step": 5800
|
3490 |
+
},
|
3491 |
+
{
|
3492 |
+
"epoch": 0.09,
|
3493 |
+
"learning_rate": 0.00027830113364202453,
|
3494 |
+
"loss": 0.9881,
|
3495 |
+
"step": 5810
|
3496 |
+
},
|
3497 |
+
{
|
3498 |
+
"epoch": 0.09,
|
3499 |
+
"learning_rate": 0.00027878013731438606,
|
3500 |
+
"loss": 0.9985,
|
3501 |
+
"step": 5820
|
3502 |
+
},
|
3503 |
+
{
|
3504 |
+
"epoch": 0.09,
|
3505 |
+
"learning_rate": 0.0002792591409867475,
|
3506 |
+
"loss": 1.0091,
|
3507 |
+
"step": 5830
|
3508 |
+
},
|
3509 |
+
{
|
3510 |
+
"epoch": 0.09,
|
3511 |
+
"learning_rate": 0.00027973814465910904,
|
3512 |
+
"loss": 1.005,
|
3513 |
+
"step": 5840
|
3514 |
+
},
|
3515 |
+
{
|
3516 |
+
"epoch": 0.09,
|
3517 |
+
"learning_rate": 0.0002802171483314705,
|
3518 |
+
"loss": 0.9998,
|
3519 |
+
"step": 5850
|
3520 |
+
},
|
3521 |
+
{
|
3522 |
+
"epoch": 0.09,
|
3523 |
+
"learning_rate": 0.000280696152003832,
|
3524 |
+
"loss": 1.0121,
|
3525 |
+
"step": 5860
|
3526 |
+
},
|
3527 |
+
{
|
3528 |
+
"epoch": 0.09,
|
3529 |
+
"learning_rate": 0.0002811751556761935,
|
3530 |
+
"loss": 1.0055,
|
3531 |
+
"step": 5870
|
3532 |
+
},
|
3533 |
+
{
|
3534 |
+
"epoch": 0.09,
|
3535 |
+
"learning_rate": 0.00028165415934855496,
|
3536 |
+
"loss": 1.0139,
|
3537 |
+
"step": 5880
|
3538 |
+
},
|
3539 |
+
{
|
3540 |
+
"epoch": 0.09,
|
3541 |
+
"learning_rate": 0.0002821331630209165,
|
3542 |
+
"loss": 0.9987,
|
3543 |
+
"step": 5890
|
3544 |
+
},
|
3545 |
+
{
|
3546 |
+
"epoch": 0.09,
|
3547 |
+
"learning_rate": 0.00028261216669327795,
|
3548 |
+
"loss": 1.0034,
|
3549 |
+
"step": 5900
|
3550 |
+
},
|
3551 |
+
{
|
3552 |
+
"epoch": 0.09,
|
3553 |
+
"learning_rate": 0.0002830911703656394,
|
3554 |
+
"loss": 1.0107,
|
3555 |
+
"step": 5910
|
3556 |
+
},
|
3557 |
+
{
|
3558 |
+
"epoch": 0.09,
|
3559 |
+
"learning_rate": 0.00028357017403800094,
|
3560 |
+
"loss": 1.0041,
|
3561 |
+
"step": 5920
|
3562 |
+
},
|
3563 |
+
{
|
3564 |
+
"epoch": 0.09,
|
3565 |
+
"learning_rate": 0.0002840491777103624,
|
3566 |
+
"loss": 1.0114,
|
3567 |
+
"step": 5930
|
3568 |
+
},
|
3569 |
+
{
|
3570 |
+
"epoch": 0.09,
|
3571 |
+
"learning_rate": 0.00028452818138272393,
|
3572 |
+
"loss": 1.0142,
|
3573 |
+
"step": 5940
|
3574 |
+
},
|
3575 |
+
{
|
3576 |
+
"epoch": 0.1,
|
3577 |
+
"learning_rate": 0.0002850071850550854,
|
3578 |
+
"loss": 0.9973,
|
3579 |
+
"step": 5950
|
3580 |
+
},
|
3581 |
+
{
|
3582 |
+
"epoch": 0.1,
|
3583 |
+
"learning_rate": 0.00028548618872744686,
|
3584 |
+
"loss": 0.9952,
|
3585 |
+
"step": 5960
|
3586 |
+
},
|
3587 |
+
{
|
3588 |
+
"epoch": 0.1,
|
3589 |
+
"learning_rate": 0.0002859651923998084,
|
3590 |
+
"loss": 0.9993,
|
3591 |
+
"step": 5970
|
3592 |
+
},
|
3593 |
+
{
|
3594 |
+
"epoch": 0.1,
|
3595 |
+
"learning_rate": 0.00028644419607216985,
|
3596 |
+
"loss": 1.0018,
|
3597 |
+
"step": 5980
|
3598 |
+
},
|
3599 |
+
{
|
3600 |
+
"epoch": 0.1,
|
3601 |
+
"learning_rate": 0.00028692319974453137,
|
3602 |
+
"loss": 0.9958,
|
3603 |
+
"step": 5990
|
3604 |
+
},
|
3605 |
+
{
|
3606 |
+
"epoch": 0.1,
|
3607 |
+
"learning_rate": 0.00028740220341689284,
|
3608 |
+
"loss": 0.999,
|
3609 |
+
"step": 6000
|
3610 |
+
},
|
3611 |
+
{
|
3612 |
+
"epoch": 0.1,
|
3613 |
+
"learning_rate": 0.0002878812070892543,
|
3614 |
+
"loss": 1.018,
|
3615 |
+
"step": 6010
|
3616 |
+
},
|
3617 |
+
{
|
3618 |
+
"epoch": 0.1,
|
3619 |
+
"learning_rate": 0.0002883602107616158,
|
3620 |
+
"loss": 1.0012,
|
3621 |
+
"step": 6020
|
3622 |
+
},
|
3623 |
+
{
|
3624 |
+
"epoch": 0.1,
|
3625 |
+
"learning_rate": 0.0002888392144339773,
|
3626 |
+
"loss": 0.9982,
|
3627 |
+
"step": 6030
|
3628 |
+
},
|
3629 |
+
{
|
3630 |
+
"epoch": 0.1,
|
3631 |
+
"learning_rate": 0.0002893182181063388,
|
3632 |
+
"loss": 1.0085,
|
3633 |
+
"step": 6040
|
3634 |
+
},
|
3635 |
+
{
|
3636 |
+
"epoch": 0.1,
|
3637 |
+
"learning_rate": 0.0002897972217787003,
|
3638 |
+
"loss": 0.9975,
|
3639 |
+
"step": 6050
|
3640 |
+
},
|
3641 |
+
{
|
3642 |
+
"epoch": 0.1,
|
3643 |
+
"learning_rate": 0.00029027622545106175,
|
3644 |
+
"loss": 1.0067,
|
3645 |
+
"step": 6060
|
3646 |
+
},
|
3647 |
+
{
|
3648 |
+
"epoch": 0.1,
|
3649 |
+
"learning_rate": 0.00029075522912342327,
|
3650 |
+
"loss": 1.0052,
|
3651 |
+
"step": 6070
|
3652 |
+
},
|
3653 |
+
{
|
3654 |
+
"epoch": 0.1,
|
3655 |
+
"learning_rate": 0.00029123423279578473,
|
3656 |
+
"loss": 0.997,
|
3657 |
+
"step": 6080
|
3658 |
+
},
|
3659 |
+
{
|
3660 |
+
"epoch": 0.1,
|
3661 |
+
"learning_rate": 0.00029171323646814626,
|
3662 |
+
"loss": 0.9969,
|
3663 |
+
"step": 6090
|
3664 |
+
},
|
3665 |
+
{
|
3666 |
+
"epoch": 0.1,
|
3667 |
+
"learning_rate": 0.0002921922401405077,
|
3668 |
+
"loss": 0.9922,
|
3669 |
+
"step": 6100
|
3670 |
+
},
|
3671 |
+
{
|
3672 |
+
"epoch": 0.1,
|
3673 |
+
"learning_rate": 0.0002926712438128692,
|
3674 |
+
"loss": 0.9941,
|
3675 |
+
"step": 6110
|
3676 |
+
},
|
3677 |
+
{
|
3678 |
+
"epoch": 0.1,
|
3679 |
+
"learning_rate": 0.0002931502474852307,
|
3680 |
+
"loss": 1.0063,
|
3681 |
+
"step": 6120
|
3682 |
+
},
|
3683 |
+
{
|
3684 |
+
"epoch": 0.1,
|
3685 |
+
"learning_rate": 0.0002936292511575922,
|
3686 |
+
"loss": 1.0138,
|
3687 |
+
"step": 6130
|
3688 |
+
},
|
3689 |
+
{
|
3690 |
+
"epoch": 0.1,
|
3691 |
+
"learning_rate": 0.0002941082548299537,
|
3692 |
+
"loss": 1.0033,
|
3693 |
+
"step": 6140
|
3694 |
+
},
|
3695 |
+
{
|
3696 |
+
"epoch": 0.1,
|
3697 |
+
"learning_rate": 0.00029458725850231517,
|
3698 |
+
"loss": 1.0086,
|
3699 |
+
"step": 6150
|
3700 |
+
},
|
3701 |
+
{
|
3702 |
+
"epoch": 0.1,
|
3703 |
+
"learning_rate": 0.0002950662621746767,
|
3704 |
+
"loss": 1.0169,
|
3705 |
+
"step": 6160
|
3706 |
+
},
|
3707 |
+
{
|
3708 |
+
"epoch": 0.1,
|
3709 |
+
"learning_rate": 0.00029554526584703815,
|
3710 |
+
"loss": 1.02,
|
3711 |
+
"step": 6170
|
3712 |
+
},
|
3713 |
+
{
|
3714 |
+
"epoch": 0.1,
|
3715 |
+
"learning_rate": 0.0002960242695193996,
|
3716 |
+
"loss": 1.0146,
|
3717 |
+
"step": 6180
|
3718 |
+
},
|
3719 |
+
{
|
3720 |
+
"epoch": 0.1,
|
3721 |
+
"learning_rate": 0.00029650327319176114,
|
3722 |
+
"loss": 1.0217,
|
3723 |
+
"step": 6190
|
3724 |
+
},
|
3725 |
+
{
|
3726 |
+
"epoch": 0.1,
|
3727 |
+
"learning_rate": 0.0002969822768641226,
|
3728 |
+
"loss": 1.0076,
|
3729 |
+
"step": 6200
|
3730 |
+
},
|
3731 |
+
{
|
3732 |
+
"epoch": 0.1,
|
3733 |
+
"learning_rate": 0.00029746128053648413,
|
3734 |
+
"loss": 1.0176,
|
3735 |
+
"step": 6210
|
3736 |
+
},
|
3737 |
+
{
|
3738 |
+
"epoch": 0.1,
|
3739 |
+
"learning_rate": 0.00029794028420884554,
|
3740 |
+
"loss": 0.9997,
|
3741 |
+
"step": 6220
|
3742 |
+
},
|
3743 |
+
{
|
3744 |
+
"epoch": 0.1,
|
3745 |
+
"learning_rate": 0.00029841928788120706,
|
3746 |
+
"loss": 1.0161,
|
3747 |
+
"step": 6230
|
3748 |
+
},
|
3749 |
+
{
|
3750 |
+
"epoch": 0.1,
|
3751 |
+
"learning_rate": 0.00029889829155356853,
|
3752 |
+
"loss": 1.0054,
|
3753 |
+
"step": 6240
|
3754 |
+
},
|
3755 |
+
{
|
3756 |
+
"epoch": 0.1,
|
3757 |
+
"learning_rate": 0.00029937729522593005,
|
3758 |
+
"loss": 1.0074,
|
3759 |
+
"step": 6250
|
3760 |
+
},
|
3761 |
+
{
|
3762 |
+
"epoch": 0.1,
|
3763 |
+
"learning_rate": 0.0002998562988982915,
|
3764 |
+
"loss": 1.0096,
|
3765 |
+
"step": 6260
|
3766 |
+
},
|
3767 |
+
{
|
3768 |
+
"epoch": 0.1,
|
3769 |
+
"learning_rate": 0.00029996273953158265,
|
3770 |
+
"loss": 1.0126,
|
3771 |
+
"step": 6270
|
3772 |
+
},
|
3773 |
+
{
|
3774 |
+
"epoch": 0.1,
|
3775 |
+
"learning_rate": 0.0002999095102909865,
|
3776 |
+
"loss": 1.0195,
|
3777 |
+
"step": 6280
|
3778 |
+
},
|
3779 |
+
{
|
3780 |
+
"epoch": 0.1,
|
3781 |
+
"learning_rate": 0.0002998562810503903,
|
3782 |
+
"loss": 1.0131,
|
3783 |
+
"step": 6290
|
3784 |
+
},
|
3785 |
+
{
|
3786 |
+
"epoch": 0.1,
|
3787 |
+
"learning_rate": 0.00029980305180979416,
|
3788 |
+
"loss": 1.0222,
|
3789 |
+
"step": 6300
|
3790 |
+
},
|
3791 |
+
{
|
3792 |
+
"epoch": 0.1,
|
3793 |
+
"learning_rate": 0.000299749822569198,
|
3794 |
+
"loss": 1.0131,
|
3795 |
+
"step": 6310
|
3796 |
+
},
|
3797 |
+
{
|
3798 |
+
"epoch": 0.1,
|
3799 |
+
"learning_rate": 0.0002996965933286018,
|
3800 |
+
"loss": 1.0123,
|
3801 |
+
"step": 6320
|
3802 |
+
},
|
3803 |
+
{
|
3804 |
+
"epoch": 0.1,
|
3805 |
+
"learning_rate": 0.00029964336408800567,
|
3806 |
+
"loss": 1.0195,
|
3807 |
+
"step": 6330
|
3808 |
+
},
|
3809 |
+
{
|
3810 |
+
"epoch": 0.1,
|
3811 |
+
"learning_rate": 0.00029959013484740947,
|
3812 |
+
"loss": 1.0154,
|
3813 |
+
"step": 6340
|
3814 |
+
},
|
3815 |
+
{
|
3816 |
+
"epoch": 0.1,
|
3817 |
+
"learning_rate": 0.0002995369056068133,
|
3818 |
+
"loss": 1.0246,
|
3819 |
+
"step": 6350
|
3820 |
+
},
|
3821 |
+
{
|
3822 |
+
"epoch": 0.1,
|
3823 |
+
"learning_rate": 0.0002994836763662172,
|
3824 |
+
"loss": 1.0102,
|
3825 |
+
"step": 6360
|
3826 |
+
},
|
3827 |
+
{
|
3828 |
+
"epoch": 0.1,
|
3829 |
+
"learning_rate": 0.000299430447125621,
|
3830 |
+
"loss": 1.001,
|
3831 |
+
"step": 6370
|
3832 |
+
},
|
3833 |
+
{
|
3834 |
+
"epoch": 0.1,
|
3835 |
+
"learning_rate": 0.00029937721788502483,
|
3836 |
+
"loss": 1.0246,
|
3837 |
+
"step": 6380
|
3838 |
+
},
|
3839 |
+
{
|
3840 |
+
"epoch": 0.1,
|
3841 |
+
"learning_rate": 0.00029932398864442863,
|
3842 |
+
"loss": 1.0219,
|
3843 |
+
"step": 6390
|
3844 |
+
},
|
3845 |
+
{
|
3846 |
+
"epoch": 0.1,
|
3847 |
+
"learning_rate": 0.0002992707594038325,
|
3848 |
+
"loss": 1.012,
|
3849 |
+
"step": 6400
|
3850 |
+
},
|
3851 |
+
{
|
3852 |
+
"epoch": 0.1,
|
3853 |
+
"learning_rate": 0.00029921753016323634,
|
3854 |
+
"loss": 1.0151,
|
3855 |
+
"step": 6410
|
3856 |
+
},
|
3857 |
+
{
|
3858 |
+
"epoch": 0.1,
|
3859 |
+
"learning_rate": 0.00029916430092264014,
|
3860 |
+
"loss": 1.0256,
|
3861 |
+
"step": 6420
|
3862 |
+
},
|
3863 |
+
{
|
3864 |
+
"epoch": 0.1,
|
3865 |
+
"learning_rate": 0.000299111071682044,
|
3866 |
+
"loss": 1.0214,
|
3867 |
+
"step": 6430
|
3868 |
+
},
|
3869 |
+
{
|
3870 |
+
"epoch": 0.1,
|
3871 |
+
"learning_rate": 0.0002990578424414478,
|
3872 |
+
"loss": 1.0275,
|
3873 |
+
"step": 6440
|
3874 |
+
},
|
3875 |
+
{
|
3876 |
+
"epoch": 0.1,
|
3877 |
+
"learning_rate": 0.00029900461320085165,
|
3878 |
+
"loss": 1.0189,
|
3879 |
+
"step": 6450
|
3880 |
+
},
|
3881 |
+
{
|
3882 |
+
"epoch": 0.1,
|
3883 |
+
"learning_rate": 0.0002989513839602555,
|
3884 |
+
"loss": 1.0078,
|
3885 |
+
"step": 6460
|
3886 |
+
},
|
3887 |
+
{
|
3888 |
+
"epoch": 0.1,
|
3889 |
+
"learning_rate": 0.0002988981547196593,
|
3890 |
+
"loss": 1.0091,
|
3891 |
+
"step": 6470
|
3892 |
+
},
|
3893 |
+
{
|
3894 |
+
"epoch": 0.1,
|
3895 |
+
"learning_rate": 0.00029884492547906316,
|
3896 |
+
"loss": 1.0082,
|
3897 |
+
"step": 6480
|
3898 |
+
},
|
3899 |
+
{
|
3900 |
+
"epoch": 0.1,
|
3901 |
+
"learning_rate": 0.00029879169623846696,
|
3902 |
+
"loss": 1.0128,
|
3903 |
+
"step": 6490
|
3904 |
+
},
|
3905 |
+
{
|
3906 |
+
"epoch": 0.1,
|
3907 |
+
"learning_rate": 0.0002987384669978708,
|
3908 |
+
"loss": 1.0299,
|
3909 |
+
"step": 6500
|
3910 |
+
},
|
3911 |
+
{
|
3912 |
+
"epoch": 0.1,
|
3913 |
+
"learning_rate": 0.0002986852377572746,
|
3914 |
+
"loss": 1.0142,
|
3915 |
+
"step": 6510
|
3916 |
+
},
|
3917 |
+
{
|
3918 |
+
"epoch": 0.1,
|
3919 |
+
"learning_rate": 0.0002986320085166785,
|
3920 |
+
"loss": 1.009,
|
3921 |
+
"step": 6520
|
3922 |
+
},
|
3923 |
+
{
|
3924 |
+
"epoch": 0.1,
|
3925 |
+
"learning_rate": 0.00029857877927608233,
|
3926 |
+
"loss": 1.0204,
|
3927 |
+
"step": 6530
|
3928 |
+
},
|
3929 |
+
{
|
3930 |
+
"epoch": 0.1,
|
3931 |
+
"learning_rate": 0.00029852555003548613,
|
3932 |
+
"loss": 1.0201,
|
3933 |
+
"step": 6540
|
3934 |
+
},
|
3935 |
+
{
|
3936 |
+
"epoch": 0.1,
|
3937 |
+
"learning_rate": 0.00029847232079489,
|
3938 |
+
"loss": 1.0111,
|
3939 |
+
"step": 6550
|
3940 |
+
},
|
3941 |
+
{
|
3942 |
+
"epoch": 0.1,
|
3943 |
+
"learning_rate": 0.0002984190915542938,
|
3944 |
+
"loss": 1.0296,
|
3945 |
+
"step": 6560
|
3946 |
+
},
|
3947 |
+
{
|
3948 |
+
"epoch": 0.1,
|
3949 |
+
"learning_rate": 0.00029836586231369764,
|
3950 |
+
"loss": 1.0169,
|
3951 |
+
"step": 6570
|
3952 |
+
},
|
3953 |
+
{
|
3954 |
+
"epoch": 0.11,
|
3955 |
+
"learning_rate": 0.00029831263307310144,
|
3956 |
+
"loss": 1.0175,
|
3957 |
+
"step": 6580
|
3958 |
+
},
|
3959 |
+
{
|
3960 |
+
"epoch": 0.11,
|
3961 |
+
"learning_rate": 0.0002982594038325053,
|
3962 |
+
"loss": 1.0181,
|
3963 |
+
"step": 6590
|
3964 |
+
},
|
3965 |
+
{
|
3966 |
+
"epoch": 0.11,
|
3967 |
+
"learning_rate": 0.00029820617459190915,
|
3968 |
+
"loss": 1.0091,
|
3969 |
+
"step": 6600
|
3970 |
+
},
|
3971 |
+
{
|
3972 |
+
"epoch": 0.11,
|
3973 |
+
"learning_rate": 0.00029815294535131295,
|
3974 |
+
"loss": 1.0253,
|
3975 |
+
"step": 6610
|
3976 |
+
},
|
3977 |
+
{
|
3978 |
+
"epoch": 0.11,
|
3979 |
+
"learning_rate": 0.0002980997161107168,
|
3980 |
+
"loss": 1.0158,
|
3981 |
+
"step": 6620
|
3982 |
+
},
|
3983 |
+
{
|
3984 |
+
"epoch": 0.11,
|
3985 |
+
"learning_rate": 0.0002980464868701206,
|
3986 |
+
"loss": 1.0082,
|
3987 |
+
"step": 6630
|
3988 |
+
},
|
3989 |
+
{
|
3990 |
+
"epoch": 0.11,
|
3991 |
+
"learning_rate": 0.00029799325762952446,
|
3992 |
+
"loss": 1.023,
|
3993 |
+
"step": 6640
|
3994 |
+
},
|
3995 |
+
{
|
3996 |
+
"epoch": 0.11,
|
3997 |
+
"learning_rate": 0.00029794002838892826,
|
3998 |
+
"loss": 1.0094,
|
3999 |
+
"step": 6650
|
4000 |
+
},
|
4001 |
+
{
|
4002 |
+
"epoch": 0.11,
|
4003 |
+
"learning_rate": 0.0002978867991483321,
|
4004 |
+
"loss": 1.0106,
|
4005 |
+
"step": 6660
|
4006 |
+
},
|
4007 |
+
{
|
4008 |
+
"epoch": 0.11,
|
4009 |
+
"learning_rate": 0.00029783356990773597,
|
4010 |
+
"loss": 1.0131,
|
4011 |
+
"step": 6670
|
4012 |
+
},
|
4013 |
+
{
|
4014 |
+
"epoch": 0.11,
|
4015 |
+
"learning_rate": 0.0002977803406671398,
|
4016 |
+
"loss": 1.0325,
|
4017 |
+
"step": 6680
|
4018 |
+
},
|
4019 |
+
{
|
4020 |
+
"epoch": 0.11,
|
4021 |
+
"learning_rate": 0.00029772711142654363,
|
4022 |
+
"loss": 1.021,
|
4023 |
+
"step": 6690
|
4024 |
+
},
|
4025 |
+
{
|
4026 |
+
"epoch": 0.11,
|
4027 |
+
"learning_rate": 0.00029767388218594743,
|
4028 |
+
"loss": 1.022,
|
4029 |
+
"step": 6700
|
4030 |
+
},
|
4031 |
+
{
|
4032 |
+
"epoch": 0.11,
|
4033 |
+
"learning_rate": 0.0002976206529453513,
|
4034 |
+
"loss": 1.0157,
|
4035 |
+
"step": 6710
|
4036 |
+
},
|
4037 |
+
{
|
4038 |
+
"epoch": 0.11,
|
4039 |
+
"learning_rate": 0.0002975674237047551,
|
4040 |
+
"loss": 1.0253,
|
4041 |
+
"step": 6720
|
4042 |
+
},
|
4043 |
+
{
|
4044 |
+
"epoch": 0.11,
|
4045 |
+
"learning_rate": 0.00029751419446415894,
|
4046 |
+
"loss": 1.0178,
|
4047 |
+
"step": 6730
|
4048 |
+
},
|
4049 |
+
{
|
4050 |
+
"epoch": 0.11,
|
4051 |
+
"learning_rate": 0.0002974609652235628,
|
4052 |
+
"loss": 1.0079,
|
4053 |
+
"step": 6740
|
4054 |
+
},
|
4055 |
+
{
|
4056 |
+
"epoch": 0.11,
|
4057 |
+
"learning_rate": 0.0002974077359829666,
|
4058 |
+
"loss": 1.0097,
|
4059 |
+
"step": 6750
|
4060 |
+
},
|
4061 |
+
{
|
4062 |
+
"epoch": 0.11,
|
4063 |
+
"learning_rate": 0.00029735450674237045,
|
4064 |
+
"loss": 1.0082,
|
4065 |
+
"step": 6760
|
4066 |
+
},
|
4067 |
+
{
|
4068 |
+
"epoch": 0.11,
|
4069 |
+
"learning_rate": 0.00029730127750177425,
|
4070 |
+
"loss": 1.0111,
|
4071 |
+
"step": 6770
|
4072 |
+
},
|
4073 |
+
{
|
4074 |
+
"epoch": 0.11,
|
4075 |
+
"learning_rate": 0.0002972480482611781,
|
4076 |
+
"loss": 1.028,
|
4077 |
+
"step": 6780
|
4078 |
+
},
|
4079 |
+
{
|
4080 |
+
"epoch": 0.11,
|
4081 |
+
"learning_rate": 0.0002971948190205819,
|
4082 |
+
"loss": 1.0176,
|
4083 |
+
"step": 6790
|
4084 |
+
},
|
4085 |
+
{
|
4086 |
+
"epoch": 0.11,
|
4087 |
+
"learning_rate": 0.00029714158977998576,
|
4088 |
+
"loss": 1.0292,
|
4089 |
+
"step": 6800
|
4090 |
+
},
|
4091 |
+
{
|
4092 |
+
"epoch": 0.11,
|
4093 |
+
"learning_rate": 0.0002970883605393896,
|
4094 |
+
"loss": 1.0249,
|
4095 |
+
"step": 6810
|
4096 |
+
},
|
4097 |
+
{
|
4098 |
+
"epoch": 0.11,
|
4099 |
+
"learning_rate": 0.0002970351312987934,
|
4100 |
+
"loss": 1.0161,
|
4101 |
+
"step": 6820
|
4102 |
+
},
|
4103 |
+
{
|
4104 |
+
"epoch": 0.11,
|
4105 |
+
"learning_rate": 0.00029698190205819727,
|
4106 |
+
"loss": 1.0332,
|
4107 |
+
"step": 6830
|
4108 |
+
},
|
4109 |
+
{
|
4110 |
+
"epoch": 0.11,
|
4111 |
+
"learning_rate": 0.00029692867281760107,
|
4112 |
+
"loss": 1.0401,
|
4113 |
+
"step": 6840
|
4114 |
+
},
|
4115 |
+
{
|
4116 |
+
"epoch": 0.11,
|
4117 |
+
"learning_rate": 0.0002968754435770049,
|
4118 |
+
"loss": 1.0431,
|
4119 |
+
"step": 6850
|
4120 |
+
},
|
4121 |
+
{
|
4122 |
+
"epoch": 0.11,
|
4123 |
+
"learning_rate": 0.0002968222143364088,
|
4124 |
+
"loss": 1.0207,
|
4125 |
+
"step": 6860
|
4126 |
+
},
|
4127 |
+
{
|
4128 |
+
"epoch": 0.11,
|
4129 |
+
"learning_rate": 0.0002967689850958126,
|
4130 |
+
"loss": 1.0405,
|
4131 |
+
"step": 6870
|
4132 |
+
},
|
4133 |
+
{
|
4134 |
+
"epoch": 0.11,
|
4135 |
+
"learning_rate": 0.00029671575585521644,
|
4136 |
+
"loss": 1.0123,
|
4137 |
+
"step": 6880
|
4138 |
+
},
|
4139 |
+
{
|
4140 |
+
"epoch": 0.11,
|
4141 |
+
"learning_rate": 0.0002966625266146203,
|
4142 |
+
"loss": 1.0382,
|
4143 |
+
"step": 6890
|
4144 |
+
},
|
4145 |
+
{
|
4146 |
+
"epoch": 0.11,
|
4147 |
+
"learning_rate": 0.0002966092973740241,
|
4148 |
+
"loss": 1.0264,
|
4149 |
+
"step": 6900
|
4150 |
+
},
|
4151 |
+
{
|
4152 |
+
"epoch": 0.11,
|
4153 |
+
"learning_rate": 0.00029655606813342795,
|
4154 |
+
"loss": 1.0187,
|
4155 |
+
"step": 6910
|
4156 |
+
},
|
4157 |
+
{
|
4158 |
+
"epoch": 0.11,
|
4159 |
+
"learning_rate": 0.00029650283889283175,
|
4160 |
+
"loss": 1.0317,
|
4161 |
+
"step": 6920
|
4162 |
+
},
|
4163 |
+
{
|
4164 |
+
"epoch": 0.11,
|
4165 |
+
"learning_rate": 0.0002964496096522356,
|
4166 |
+
"loss": 1.0163,
|
4167 |
+
"step": 6930
|
4168 |
+
},
|
4169 |
+
{
|
4170 |
+
"epoch": 0.11,
|
4171 |
+
"learning_rate": 0.00029639638041163946,
|
4172 |
+
"loss": 1.0273,
|
4173 |
+
"step": 6940
|
4174 |
+
},
|
4175 |
+
{
|
4176 |
+
"epoch": 0.11,
|
4177 |
+
"learning_rate": 0.00029634315117104326,
|
4178 |
+
"loss": 1.0163,
|
4179 |
+
"step": 6950
|
4180 |
+
},
|
4181 |
+
{
|
4182 |
+
"epoch": 0.11,
|
4183 |
+
"learning_rate": 0.0002962899219304471,
|
4184 |
+
"loss": 1.1661,
|
4185 |
+
"step": 6960
|
4186 |
+
},
|
4187 |
+
{
|
4188 |
+
"epoch": 0.11,
|
4189 |
+
"learning_rate": 0.0002962366926898509,
|
4190 |
+
"loss": 1.1242,
|
4191 |
+
"step": 6970
|
4192 |
+
},
|
4193 |
+
{
|
4194 |
+
"epoch": 0.11,
|
4195 |
+
"learning_rate": 0.00029618346344925477,
|
4196 |
+
"loss": 1.0727,
|
4197 |
+
"step": 6980
|
4198 |
+
},
|
4199 |
+
{
|
4200 |
+
"epoch": 0.11,
|
4201 |
+
"learning_rate": 0.0002961302342086586,
|
4202 |
+
"loss": 1.0681,
|
4203 |
+
"step": 6990
|
4204 |
+
},
|
4205 |
+
{
|
4206 |
+
"epoch": 0.11,
|
4207 |
+
"learning_rate": 0.0002960770049680624,
|
4208 |
+
"loss": 1.0341,
|
4209 |
+
"step": 7000
|
4210 |
+
},
|
4211 |
+
{
|
4212 |
+
"epoch": 0.11,
|
4213 |
+
"learning_rate": 0.0002960237757274663,
|
4214 |
+
"loss": 1.0658,
|
4215 |
+
"step": 7010
|
4216 |
+
},
|
4217 |
+
{
|
4218 |
+
"epoch": 0.11,
|
4219 |
+
"learning_rate": 0.00029597054648687013,
|
4220 |
+
"loss": 1.0571,
|
4221 |
+
"step": 7020
|
4222 |
+
},
|
4223 |
+
{
|
4224 |
+
"epoch": 0.11,
|
4225 |
+
"learning_rate": 0.00029591731724627393,
|
4226 |
+
"loss": 1.0424,
|
4227 |
+
"step": 7030
|
4228 |
+
},
|
4229 |
+
{
|
4230 |
+
"epoch": 0.11,
|
4231 |
+
"learning_rate": 0.0002958640880056778,
|
4232 |
+
"loss": 1.0132,
|
4233 |
+
"step": 7040
|
4234 |
+
},
|
4235 |
+
{
|
4236 |
+
"epoch": 0.11,
|
4237 |
+
"learning_rate": 0.0002958108587650816,
|
4238 |
+
"loss": 1.013,
|
4239 |
+
"step": 7050
|
4240 |
+
},
|
4241 |
+
{
|
4242 |
+
"epoch": 0.11,
|
4243 |
+
"learning_rate": 0.00029575762952448545,
|
4244 |
+
"loss": 1.0305,
|
4245 |
+
"step": 7060
|
4246 |
+
},
|
4247 |
+
{
|
4248 |
+
"epoch": 0.11,
|
4249 |
+
"learning_rate": 0.00029570440028388925,
|
4250 |
+
"loss": 1.0169,
|
4251 |
+
"step": 7070
|
4252 |
+
},
|
4253 |
+
{
|
4254 |
+
"epoch": 0.11,
|
4255 |
+
"learning_rate": 0.0002956511710432931,
|
4256 |
+
"loss": 1.0077,
|
4257 |
+
"step": 7080
|
4258 |
+
},
|
4259 |
+
{
|
4260 |
+
"epoch": 0.11,
|
4261 |
+
"learning_rate": 0.00029559794180269696,
|
4262 |
+
"loss": 1.0245,
|
4263 |
+
"step": 7090
|
4264 |
+
},
|
4265 |
+
{
|
4266 |
+
"epoch": 0.11,
|
4267 |
+
"learning_rate": 0.00029554471256210076,
|
4268 |
+
"loss": 0.9795,
|
4269 |
+
"step": 7100
|
4270 |
+
},
|
4271 |
+
{
|
4272 |
+
"epoch": 0.11,
|
4273 |
+
"learning_rate": 0.0002954914833215046,
|
4274 |
+
"loss": 0.9896,
|
4275 |
+
"step": 7110
|
4276 |
+
},
|
4277 |
+
{
|
4278 |
+
"epoch": 0.11,
|
4279 |
+
"learning_rate": 0.0002954382540809084,
|
4280 |
+
"loss": 1.0317,
|
4281 |
+
"step": 7120
|
4282 |
+
},
|
4283 |
+
{
|
4284 |
+
"epoch": 0.11,
|
4285 |
+
"learning_rate": 0.00029538502484031227,
|
4286 |
+
"loss": 1.0483,
|
4287 |
+
"step": 7130
|
4288 |
+
},
|
4289 |
+
{
|
4290 |
+
"epoch": 0.11,
|
4291 |
+
"learning_rate": 0.00029533179559971607,
|
4292 |
+
"loss": 1.081,
|
4293 |
+
"step": 7140
|
4294 |
+
},
|
4295 |
+
{
|
4296 |
+
"epoch": 0.11,
|
4297 |
+
"learning_rate": 0.0002952785663591199,
|
4298 |
+
"loss": 1.0491,
|
4299 |
+
"step": 7150
|
4300 |
+
},
|
4301 |
+
{
|
4302 |
+
"epoch": 0.11,
|
4303 |
+
"learning_rate": 0.0002952253371185238,
|
4304 |
+
"loss": 1.0396,
|
4305 |
+
"step": 7160
|
4306 |
+
},
|
4307 |
+
{
|
4308 |
+
"epoch": 0.11,
|
4309 |
+
"learning_rate": 0.0002951721078779276,
|
4310 |
+
"loss": 1.0584,
|
4311 |
+
"step": 7170
|
4312 |
+
},
|
4313 |
+
{
|
4314 |
+
"epoch": 0.11,
|
4315 |
+
"learning_rate": 0.00029511887863733143,
|
4316 |
+
"loss": 1.0595,
|
4317 |
+
"step": 7180
|
4318 |
+
},
|
4319 |
+
{
|
4320 |
+
"epoch": 0.11,
|
4321 |
+
"learning_rate": 0.00029506564939673523,
|
4322 |
+
"loss": 1.0468,
|
4323 |
+
"step": 7190
|
4324 |
+
},
|
4325 |
+
{
|
4326 |
+
"epoch": 0.11,
|
4327 |
+
"learning_rate": 0.0002950124201561391,
|
4328 |
+
"loss": 1.0235,
|
4329 |
+
"step": 7200
|
4330 |
+
},
|
4331 |
+
{
|
4332 |
+
"epoch": 0.12,
|
4333 |
+
"learning_rate": 0.0002949591909155429,
|
4334 |
+
"loss": 1.0191,
|
4335 |
+
"step": 7210
|
4336 |
+
},
|
4337 |
+
{
|
4338 |
+
"epoch": 0.12,
|
4339 |
+
"learning_rate": 0.00029490596167494674,
|
4340 |
+
"loss": 1.0417,
|
4341 |
+
"step": 7220
|
4342 |
+
},
|
4343 |
+
{
|
4344 |
+
"epoch": 0.12,
|
4345 |
+
"learning_rate": 0.0002948527324343506,
|
4346 |
+
"loss": 1.0059,
|
4347 |
+
"step": 7230
|
4348 |
+
},
|
4349 |
+
{
|
4350 |
+
"epoch": 0.12,
|
4351 |
+
"learning_rate": 0.0002947995031937544,
|
4352 |
+
"loss": 1.0449,
|
4353 |
+
"step": 7240
|
4354 |
+
},
|
4355 |
+
{
|
4356 |
+
"epoch": 0.12,
|
4357 |
+
"learning_rate": 0.00029474627395315825,
|
4358 |
+
"loss": 0.9896,
|
4359 |
+
"step": 7250
|
4360 |
+
},
|
4361 |
+
{
|
4362 |
+
"epoch": 0.12,
|
4363 |
+
"learning_rate": 0.00029469304471256205,
|
4364 |
+
"loss": 1.0022,
|
4365 |
+
"step": 7260
|
4366 |
+
},
|
4367 |
+
{
|
4368 |
+
"epoch": 0.12,
|
4369 |
+
"learning_rate": 0.0002946398154719659,
|
4370 |
+
"loss": 1.0225,
|
4371 |
+
"step": 7270
|
4372 |
+
},
|
4373 |
+
{
|
4374 |
+
"epoch": 0.12,
|
4375 |
+
"learning_rate": 0.0002945865862313697,
|
4376 |
+
"loss": 1.0086,
|
4377 |
+
"step": 7280
|
4378 |
+
},
|
4379 |
+
{
|
4380 |
+
"epoch": 0.12,
|
4381 |
+
"learning_rate": 0.00029453335699077357,
|
4382 |
+
"loss": 1.0692,
|
4383 |
+
"step": 7290
|
4384 |
+
},
|
4385 |
+
{
|
4386 |
+
"epoch": 0.12,
|
4387 |
+
"learning_rate": 0.0002944801277501774,
|
4388 |
+
"loss": 1.0995,
|
4389 |
+
"step": 7300
|
4390 |
+
},
|
4391 |
+
{
|
4392 |
+
"epoch": 0.12,
|
4393 |
+
"learning_rate": 0.0002944268985095812,
|
4394 |
+
"loss": 1.0794,
|
4395 |
+
"step": 7310
|
4396 |
+
},
|
4397 |
+
{
|
4398 |
+
"epoch": 0.12,
|
4399 |
+
"learning_rate": 0.0002943736692689851,
|
4400 |
+
"loss": 1.0765,
|
4401 |
+
"step": 7320
|
4402 |
+
},
|
4403 |
+
{
|
4404 |
+
"epoch": 0.12,
|
4405 |
+
"learning_rate": 0.0002943204400283889,
|
4406 |
+
"loss": 1.0532,
|
4407 |
+
"step": 7330
|
4408 |
+
},
|
4409 |
+
{
|
4410 |
+
"epoch": 0.12,
|
4411 |
+
"learning_rate": 0.00029426721078779273,
|
4412 |
+
"loss": 1.0671,
|
4413 |
+
"step": 7340
|
4414 |
+
},
|
4415 |
+
{
|
4416 |
+
"epoch": 0.12,
|
4417 |
+
"learning_rate": 0.00029421398154719653,
|
4418 |
+
"loss": 1.0371,
|
4419 |
+
"step": 7350
|
4420 |
+
},
|
4421 |
+
{
|
4422 |
+
"epoch": 0.12,
|
4423 |
+
"learning_rate": 0.0002941607523066004,
|
4424 |
+
"loss": 1.0449,
|
4425 |
+
"step": 7360
|
4426 |
+
},
|
4427 |
+
{
|
4428 |
+
"epoch": 0.12,
|
4429 |
+
"learning_rate": 0.00029410752306600424,
|
4430 |
+
"loss": 1.0338,
|
4431 |
+
"step": 7370
|
4432 |
+
},
|
4433 |
+
{
|
4434 |
+
"epoch": 0.12,
|
4435 |
+
"learning_rate": 0.00029405429382540804,
|
4436 |
+
"loss": 1.0312,
|
4437 |
+
"step": 7380
|
4438 |
+
}
|
4439 |
+
],
|
4440 |
+
"logging_steps": 10,
|
4441 |
+
"max_steps": 62623,
|
4442 |
+
"num_train_epochs": 1,
|
4443 |
+
"save_steps": 500,
|
4444 |
+
"total_flos": 4.80334442885913e+18,
|
4445 |
+
"trial_name": null,
|
4446 |
+
"trial_params": null
|
4447 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60cd401cfd61b28c28109fd89489bb9a177b957b914b200a720d6cf74d4187a4
|
3 |
+
size 4091
|