Upload 22 files
Browse files- README.md +60 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +49 -0
- trainer_state.json +1147 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
|
| 31 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 32 |
+
- quant_method: bitsandbytes
|
| 33 |
+
- load_in_8bit: False
|
| 34 |
+
- load_in_4bit: True
|
| 35 |
+
- llm_int8_threshold: 6.0
|
| 36 |
+
- llm_int8_skip_modules: None
|
| 37 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 38 |
+
- llm_int8_has_fp16_weight: False
|
| 39 |
+
- bnb_4bit_quant_type: nf4
|
| 40 |
+
- bnb_4bit_use_double_quant: False
|
| 41 |
+
- bnb_4bit_compute_dtype: float16
|
| 42 |
+
|
| 43 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 44 |
+
- quant_method: bitsandbytes
|
| 45 |
+
- load_in_8bit: False
|
| 46 |
+
- load_in_4bit: True
|
| 47 |
+
- llm_int8_threshold: 6.0
|
| 48 |
+
- llm_int8_skip_modules: None
|
| 49 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 50 |
+
- llm_int8_has_fp16_weight: False
|
| 51 |
+
- bnb_4bit_quant_type: nf4
|
| 52 |
+
- bnb_4bit_use_double_quant: False
|
| 53 |
+
- bnb_4bit_compute_dtype: float16
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- PEFT 0.5.0
|
| 57 |
+
- PEFT 0.5.0
|
| 58 |
+
- PEFT 0.5.0
|
| 59 |
+
|
| 60 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "marianbasti/Llama-2-13b-fp16-alpaca-spanish",
|
| 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 sha256:6b0a357d14ea89de0e10590f0bbf23cc33aa935c7bdae86681c7ed3a2dcf95c6
|
| 3 |
+
size 52486922
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f36e253772b5e4bb94b670a1783b356ceb99bef9a3ca99570c6d7d6a216640f
|
| 3 |
+
size 52450328
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<PAD>": 32000
|
| 3 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4d4f927619a6e4aa3569961ca6bdb32f7133027c7f29c720a29b7af4b18f2c7
|
| 3 |
+
size 104992698
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:049c26b844b79121ddd8379f7f69194e63f6fbf6aa007eeac0c66f17eebb8893
|
| 3 |
+
size 888
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2935d18b7f9e319974e1ca34aee6f8f9851f9327531dd0e1216412fbe057c482
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70dbd4a599c84e98da1bbc039e487b0f78d7d7e8f6fe0a5094db76267ad93456
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:375239a1bd1d554228f0522a695405a11a57eb766d9ba0bf4774cb85f957fba0
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8462be7c3f3d64c89fd677986bad41220ab6a4b11275ebb4c382f4f5acd346b4
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9de57136f81ca7baa71782d99d7edadd7ef8ffdc54d673f7e5146f76484a261
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3b1f5312cc33642302f1249c8516e63e634c2885391f85553153cad11b60c45
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f6d571ca0dfa6439738bf16305a427d0504ff20c6630372d69d5efd7de709df
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce67da411b96051d5a21550b5cf27aea4740dd346c74aa095ded72c59c3c2743
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de4fdaa2e76eb96129e89560b765cc716fab1fa0fbf3453b88c8e90b4883c07b
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": {
|
| 17 |
+
"content": "<PAD>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<unk>",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
}
|
| 30 |
+
}
|
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 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"0": {
|
| 6 |
+
"content": "<unk>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"32000": {
|
| 30 |
+
"content": "<PAD>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
}
|
| 37 |
+
},
|
| 38 |
+
"bos_token": "<s>",
|
| 39 |
+
"clean_up_tokenization_spaces": false,
|
| 40 |
+
"eos_token": "</s>",
|
| 41 |
+
"legacy": true,
|
| 42 |
+
"model_max_length": 1024,
|
| 43 |
+
"pad_token": "<PAD>",
|
| 44 |
+
"sp_model_kwargs": {},
|
| 45 |
+
"spaces_between_special_tokens": false,
|
| 46 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 47 |
+
"unk_token": "<unk>",
|
| 48 |
+
"use_default_system_prompt": false
|
| 49 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1147 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9998673212153376,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3768,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 2.6525198938992043e-06,
|
| 14 |
+
"loss": 1.3287,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 5.305039787798409e-06,
|
| 20 |
+
"loss": 1.2877,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 7.957559681697613e-06,
|
| 26 |
+
"loss": 1.2194,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 1.0610079575596817e-05,
|
| 32 |
+
"loss": 1.0738,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 1.3262599469496024e-05,
|
| 38 |
+
"loss": 0.9618,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 1.5915119363395225e-05,
|
| 44 |
+
"loss": 0.8582,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 1.856763925729443e-05,
|
| 50 |
+
"loss": 0.7276,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 2.1220159151193635e-05,
|
| 56 |
+
"loss": 0.5857,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.05,
|
| 61 |
+
"learning_rate": 2.3872679045092838e-05,
|
| 62 |
+
"loss": 0.4838,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 2.6525198938992047e-05,
|
| 68 |
+
"loss": 0.3778,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.06,
|
| 73 |
+
"learning_rate": 2.9177718832891247e-05,
|
| 74 |
+
"loss": 0.3352,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 3.183023872679045e-05,
|
| 80 |
+
"loss": 0.3077,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.07,
|
| 85 |
+
"learning_rate": 3.4482758620689657e-05,
|
| 86 |
+
"loss": 0.2823,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 3.713527851458886e-05,
|
| 92 |
+
"loss": 0.2651,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.08,
|
| 97 |
+
"learning_rate": 3.978779840848806e-05,
|
| 98 |
+
"loss": 0.2411,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 4.244031830238727e-05,
|
| 104 |
+
"loss": 0.2261,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.09,
|
| 109 |
+
"learning_rate": 4.5092838196286476e-05,
|
| 110 |
+
"loss": 0.214,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.1,
|
| 115 |
+
"learning_rate": 4.7745358090185675e-05,
|
| 116 |
+
"loss": 0.2055,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.1,
|
| 121 |
+
"learning_rate": 5.039787798408488e-05,
|
| 122 |
+
"loss": 0.2032,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.11,
|
| 127 |
+
"learning_rate": 5.3050397877984095e-05,
|
| 128 |
+
"loss": 0.1882,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.11,
|
| 133 |
+
"learning_rate": 5.570291777188329e-05,
|
| 134 |
+
"loss": 0.1831,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.12,
|
| 139 |
+
"learning_rate": 5.8355437665782494e-05,
|
| 140 |
+
"loss": 0.1768,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.12,
|
| 145 |
+
"learning_rate": 6.100795755968171e-05,
|
| 146 |
+
"loss": 0.1634,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.13,
|
| 151 |
+
"learning_rate": 6.36604774535809e-05,
|
| 152 |
+
"loss": 0.1598,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.13,
|
| 157 |
+
"learning_rate": 6.631299734748011e-05,
|
| 158 |
+
"loss": 0.1546,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.14,
|
| 163 |
+
"learning_rate": 6.896551724137931e-05,
|
| 164 |
+
"loss": 0.1538,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.14,
|
| 169 |
+
"learning_rate": 7.161803713527851e-05,
|
| 170 |
+
"loss": 0.1575,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.15,
|
| 175 |
+
"learning_rate": 7.427055702917773e-05,
|
| 176 |
+
"loss": 0.1464,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.15,
|
| 181 |
+
"learning_rate": 7.692307692307693e-05,
|
| 182 |
+
"loss": 0.147,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.16,
|
| 187 |
+
"learning_rate": 7.957559681697613e-05,
|
| 188 |
+
"loss": 0.1446,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.16,
|
| 193 |
+
"learning_rate": 8.222811671087534e-05,
|
| 194 |
+
"loss": 0.1417,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.17,
|
| 199 |
+
"learning_rate": 8.488063660477454e-05,
|
| 200 |
+
"loss": 0.1413,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.18,
|
| 205 |
+
"learning_rate": 8.753315649867374e-05,
|
| 206 |
+
"loss": 0.1356,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.18,
|
| 211 |
+
"learning_rate": 9.018567639257295e-05,
|
| 212 |
+
"loss": 0.1352,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.19,
|
| 217 |
+
"learning_rate": 9.283819628647215e-05,
|
| 218 |
+
"loss": 0.1345,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.19,
|
| 223 |
+
"learning_rate": 9.549071618037135e-05,
|
| 224 |
+
"loss": 0.1357,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.2,
|
| 229 |
+
"learning_rate": 9.814323607427056e-05,
|
| 230 |
+
"loss": 0.1308,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.2,
|
| 235 |
+
"learning_rate": 0.00010079575596816976,
|
| 236 |
+
"loss": 0.1327,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.21,
|
| 241 |
+
"learning_rate": 0.00010344827586206898,
|
| 242 |
+
"loss": 0.1296,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.21,
|
| 247 |
+
"learning_rate": 0.00010610079575596819,
|
| 248 |
+
"loss": 0.1233,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.22,
|
| 253 |
+
"learning_rate": 0.00010875331564986738,
|
| 254 |
+
"loss": 0.1273,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.22,
|
| 259 |
+
"learning_rate": 0.00011140583554376658,
|
| 260 |
+
"loss": 0.1247,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.23,
|
| 265 |
+
"learning_rate": 0.00011405835543766579,
|
| 266 |
+
"loss": 0.1235,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.23,
|
| 271 |
+
"learning_rate": 0.00011671087533156499,
|
| 272 |
+
"loss": 0.1228,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.24,
|
| 277 |
+
"learning_rate": 0.0001193633952254642,
|
| 278 |
+
"loss": 0.1221,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.24,
|
| 283 |
+
"learning_rate": 0.00012201591511936341,
|
| 284 |
+
"loss": 0.1219,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.25,
|
| 289 |
+
"learning_rate": 0.0001246684350132626,
|
| 290 |
+
"loss": 0.1212,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.25,
|
| 295 |
+
"learning_rate": 0.0001273209549071618,
|
| 296 |
+
"loss": 0.1213,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.26,
|
| 301 |
+
"learning_rate": 0.00012997347480106101,
|
| 302 |
+
"loss": 0.1198,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.27,
|
| 307 |
+
"learning_rate": 0.00013262599469496023,
|
| 308 |
+
"loss": 0.1188,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.27,
|
| 313 |
+
"learning_rate": 0.00013527851458885944,
|
| 314 |
+
"loss": 0.1199,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.28,
|
| 319 |
+
"learning_rate": 0.00013793103448275863,
|
| 320 |
+
"loss": 0.1165,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.28,
|
| 325 |
+
"learning_rate": 0.0001405835543766578,
|
| 326 |
+
"loss": 0.1173,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.29,
|
| 331 |
+
"learning_rate": 0.00014323607427055703,
|
| 332 |
+
"loss": 0.1146,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.29,
|
| 337 |
+
"learning_rate": 0.00014588859416445624,
|
| 338 |
+
"loss": 0.1123,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.3,
|
| 343 |
+
"learning_rate": 0.00014854111405835545,
|
| 344 |
+
"loss": 0.1113,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.3,
|
| 349 |
+
"learning_rate": 0.00015119363395225467,
|
| 350 |
+
"loss": 0.1146,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.31,
|
| 355 |
+
"learning_rate": 0.00015384615384615385,
|
| 356 |
+
"loss": 0.1134,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.31,
|
| 361 |
+
"learning_rate": 0.00015649867374005304,
|
| 362 |
+
"loss": 0.1124,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.32,
|
| 367 |
+
"learning_rate": 0.00015915119363395225,
|
| 368 |
+
"loss": 0.1127,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.32,
|
| 373 |
+
"learning_rate": 0.00016180371352785146,
|
| 374 |
+
"loss": 0.1125,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.33,
|
| 379 |
+
"learning_rate": 0.00016445623342175068,
|
| 380 |
+
"loss": 0.1103,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.33,
|
| 385 |
+
"learning_rate": 0.0001671087533156499,
|
| 386 |
+
"loss": 0.1111,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.34,
|
| 391 |
+
"learning_rate": 0.00016976127320954908,
|
| 392 |
+
"loss": 0.1096,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.34,
|
| 397 |
+
"learning_rate": 0.00017241379310344826,
|
| 398 |
+
"loss": 0.1104,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.35,
|
| 403 |
+
"learning_rate": 0.00017506631299734748,
|
| 404 |
+
"loss": 0.1112,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.36,
|
| 409 |
+
"learning_rate": 0.0001777188328912467,
|
| 410 |
+
"loss": 0.1076,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.36,
|
| 415 |
+
"learning_rate": 0.0001803713527851459,
|
| 416 |
+
"loss": 0.1093,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.37,
|
| 421 |
+
"learning_rate": 0.00018302387267904512,
|
| 422 |
+
"loss": 0.1086,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.37,
|
| 427 |
+
"learning_rate": 0.0001856763925729443,
|
| 428 |
+
"loss": 0.1068,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.38,
|
| 433 |
+
"learning_rate": 0.00018832891246684351,
|
| 434 |
+
"loss": 0.107,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.38,
|
| 439 |
+
"learning_rate": 0.0001909814323607427,
|
| 440 |
+
"loss": 0.1091,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.39,
|
| 445 |
+
"learning_rate": 0.00019363395225464191,
|
| 446 |
+
"loss": 0.1069,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.39,
|
| 451 |
+
"learning_rate": 0.00019628647214854113,
|
| 452 |
+
"loss": 0.1048,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.4,
|
| 457 |
+
"learning_rate": 0.00019893899204244034,
|
| 458 |
+
"loss": 0.1062,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.4,
|
| 463 |
+
"learning_rate": 0.00019982306104393983,
|
| 464 |
+
"loss": 0.1076,
|
| 465 |
+
"step": 1520
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.41,
|
| 469 |
+
"learning_rate": 0.00019952816278383958,
|
| 470 |
+
"loss": 0.1026,
|
| 471 |
+
"step": 1540
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.41,
|
| 475 |
+
"learning_rate": 0.0001992332645237393,
|
| 476 |
+
"loss": 0.1064,
|
| 477 |
+
"step": 1560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.42,
|
| 481 |
+
"learning_rate": 0.00019893836626363906,
|
| 482 |
+
"loss": 0.1065,
|
| 483 |
+
"step": 1580
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.42,
|
| 487 |
+
"learning_rate": 0.00019864346800353878,
|
| 488 |
+
"loss": 0.1079,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.43,
|
| 493 |
+
"learning_rate": 0.0001983485697434385,
|
| 494 |
+
"loss": 0.1067,
|
| 495 |
+
"step": 1620
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.44,
|
| 499 |
+
"learning_rate": 0.00019805367148333826,
|
| 500 |
+
"loss": 0.1023,
|
| 501 |
+
"step": 1640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.44,
|
| 505 |
+
"learning_rate": 0.000197758773223238,
|
| 506 |
+
"loss": 0.1038,
|
| 507 |
+
"step": 1660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.45,
|
| 511 |
+
"learning_rate": 0.0001974638749631377,
|
| 512 |
+
"loss": 0.1033,
|
| 513 |
+
"step": 1680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.45,
|
| 517 |
+
"learning_rate": 0.00019716897670303746,
|
| 518 |
+
"loss": 0.1024,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.46,
|
| 523 |
+
"learning_rate": 0.0001968740784429372,
|
| 524 |
+
"loss": 0.1035,
|
| 525 |
+
"step": 1720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.46,
|
| 529 |
+
"learning_rate": 0.00019657918018283694,
|
| 530 |
+
"loss": 0.1025,
|
| 531 |
+
"step": 1740
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.47,
|
| 535 |
+
"learning_rate": 0.00019628428192273667,
|
| 536 |
+
"loss": 0.1003,
|
| 537 |
+
"step": 1760
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.47,
|
| 541 |
+
"learning_rate": 0.0001959893836626364,
|
| 542 |
+
"loss": 0.1009,
|
| 543 |
+
"step": 1780
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.48,
|
| 547 |
+
"learning_rate": 0.00019569448540253615,
|
| 548 |
+
"loss": 0.0994,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.48,
|
| 553 |
+
"learning_rate": 0.00019539958714243587,
|
| 554 |
+
"loss": 0.1026,
|
| 555 |
+
"step": 1820
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.49,
|
| 559 |
+
"learning_rate": 0.0001951046888823356,
|
| 560 |
+
"loss": 0.1008,
|
| 561 |
+
"step": 1840
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.49,
|
| 565 |
+
"learning_rate": 0.00019480979062223535,
|
| 566 |
+
"loss": 0.1012,
|
| 567 |
+
"step": 1860
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.5,
|
| 571 |
+
"learning_rate": 0.00019451489236213507,
|
| 572 |
+
"loss": 0.0977,
|
| 573 |
+
"step": 1880
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.5,
|
| 577 |
+
"learning_rate": 0.0001942199941020348,
|
| 578 |
+
"loss": 0.0995,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.51,
|
| 583 |
+
"learning_rate": 0.00019392509584193455,
|
| 584 |
+
"loss": 0.1003,
|
| 585 |
+
"step": 1920
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.51,
|
| 589 |
+
"learning_rate": 0.00019363019758183428,
|
| 590 |
+
"loss": 0.0985,
|
| 591 |
+
"step": 1940
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.52,
|
| 595 |
+
"learning_rate": 0.00019333529932173403,
|
| 596 |
+
"loss": 0.0976,
|
| 597 |
+
"step": 1960
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.53,
|
| 601 |
+
"learning_rate": 0.00019304040106163375,
|
| 602 |
+
"loss": 0.1009,
|
| 603 |
+
"step": 1980
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.53,
|
| 607 |
+
"learning_rate": 0.00019274550280153348,
|
| 608 |
+
"loss": 0.0986,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.54,
|
| 613 |
+
"learning_rate": 0.00019245060454143323,
|
| 614 |
+
"loss": 0.1004,
|
| 615 |
+
"step": 2020
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.54,
|
| 619 |
+
"learning_rate": 0.00019215570628133296,
|
| 620 |
+
"loss": 0.1007,
|
| 621 |
+
"step": 2040
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.55,
|
| 625 |
+
"learning_rate": 0.00019186080802123268,
|
| 626 |
+
"loss": 0.0976,
|
| 627 |
+
"step": 2060
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.55,
|
| 631 |
+
"learning_rate": 0.00019156590976113244,
|
| 632 |
+
"loss": 0.0979,
|
| 633 |
+
"step": 2080
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.56,
|
| 637 |
+
"learning_rate": 0.00019127101150103216,
|
| 638 |
+
"loss": 0.0984,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.56,
|
| 643 |
+
"learning_rate": 0.00019097611324093189,
|
| 644 |
+
"loss": 0.0978,
|
| 645 |
+
"step": 2120
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.57,
|
| 649 |
+
"learning_rate": 0.0001906812149808316,
|
| 650 |
+
"loss": 0.1001,
|
| 651 |
+
"step": 2140
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.57,
|
| 655 |
+
"learning_rate": 0.00019038631672073136,
|
| 656 |
+
"loss": 0.0989,
|
| 657 |
+
"step": 2160
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.58,
|
| 661 |
+
"learning_rate": 0.0001900914184606311,
|
| 662 |
+
"loss": 0.0999,
|
| 663 |
+
"step": 2180
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.58,
|
| 667 |
+
"learning_rate": 0.00018979652020053081,
|
| 668 |
+
"loss": 0.0967,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.59,
|
| 673 |
+
"learning_rate": 0.00018950162194043054,
|
| 674 |
+
"loss": 0.0944,
|
| 675 |
+
"step": 2220
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.59,
|
| 679 |
+
"learning_rate": 0.0001892067236803303,
|
| 680 |
+
"loss": 0.0971,
|
| 681 |
+
"step": 2240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.6,
|
| 685 |
+
"learning_rate": 0.00018891182542023002,
|
| 686 |
+
"loss": 0.0974,
|
| 687 |
+
"step": 2260
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.61,
|
| 691 |
+
"learning_rate": 0.00018861692716012977,
|
| 692 |
+
"loss": 0.0968,
|
| 693 |
+
"step": 2280
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.61,
|
| 697 |
+
"learning_rate": 0.0001883220289000295,
|
| 698 |
+
"loss": 0.0946,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.62,
|
| 703 |
+
"learning_rate": 0.00018802713063992922,
|
| 704 |
+
"loss": 0.0965,
|
| 705 |
+
"step": 2320
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.62,
|
| 709 |
+
"learning_rate": 0.00018773223237982897,
|
| 710 |
+
"loss": 0.0946,
|
| 711 |
+
"step": 2340
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.63,
|
| 715 |
+
"learning_rate": 0.0001874373341197287,
|
| 716 |
+
"loss": 0.0941,
|
| 717 |
+
"step": 2360
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.63,
|
| 721 |
+
"learning_rate": 0.00018714243585962842,
|
| 722 |
+
"loss": 0.0947,
|
| 723 |
+
"step": 2380
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.64,
|
| 727 |
+
"learning_rate": 0.00018684753759952818,
|
| 728 |
+
"loss": 0.0953,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.64,
|
| 733 |
+
"learning_rate": 0.0001865526393394279,
|
| 734 |
+
"loss": 0.095,
|
| 735 |
+
"step": 2420
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.65,
|
| 739 |
+
"learning_rate": 0.00018625774107932763,
|
| 740 |
+
"loss": 0.0938,
|
| 741 |
+
"step": 2440
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.65,
|
| 745 |
+
"learning_rate": 0.00018596284281922738,
|
| 746 |
+
"loss": 0.094,
|
| 747 |
+
"step": 2460
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.66,
|
| 751 |
+
"learning_rate": 0.0001856679445591271,
|
| 752 |
+
"loss": 0.0951,
|
| 753 |
+
"step": 2480
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.66,
|
| 757 |
+
"learning_rate": 0.00018537304629902686,
|
| 758 |
+
"loss": 0.0946,
|
| 759 |
+
"step": 2500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.67,
|
| 763 |
+
"learning_rate": 0.00018507814803892658,
|
| 764 |
+
"loss": 0.0937,
|
| 765 |
+
"step": 2520
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.67,
|
| 769 |
+
"learning_rate": 0.0001847832497788263,
|
| 770 |
+
"loss": 0.0931,
|
| 771 |
+
"step": 2540
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.68,
|
| 775 |
+
"learning_rate": 0.00018448835151872606,
|
| 776 |
+
"loss": 0.0942,
|
| 777 |
+
"step": 2560
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.68,
|
| 781 |
+
"learning_rate": 0.00018419345325862579,
|
| 782 |
+
"loss": 0.0925,
|
| 783 |
+
"step": 2580
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.69,
|
| 787 |
+
"learning_rate": 0.0001838985549985255,
|
| 788 |
+
"loss": 0.0938,
|
| 789 |
+
"step": 2600
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.7,
|
| 793 |
+
"learning_rate": 0.00018360365673842526,
|
| 794 |
+
"loss": 0.093,
|
| 795 |
+
"step": 2620
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.7,
|
| 799 |
+
"learning_rate": 0.000183308758478325,
|
| 800 |
+
"loss": 0.0919,
|
| 801 |
+
"step": 2640
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.71,
|
| 805 |
+
"learning_rate": 0.00018301386021822474,
|
| 806 |
+
"loss": 0.0951,
|
| 807 |
+
"step": 2660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.71,
|
| 811 |
+
"learning_rate": 0.00018271896195812447,
|
| 812 |
+
"loss": 0.0943,
|
| 813 |
+
"step": 2680
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.72,
|
| 817 |
+
"learning_rate": 0.0001824240636980242,
|
| 818 |
+
"loss": 0.0946,
|
| 819 |
+
"step": 2700
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.72,
|
| 823 |
+
"learning_rate": 0.00018212916543792394,
|
| 824 |
+
"loss": 0.094,
|
| 825 |
+
"step": 2720
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.73,
|
| 829 |
+
"learning_rate": 0.00018183426717782367,
|
| 830 |
+
"loss": 0.0954,
|
| 831 |
+
"step": 2740
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.73,
|
| 835 |
+
"learning_rate": 0.0001815393689177234,
|
| 836 |
+
"loss": 0.0912,
|
| 837 |
+
"step": 2760
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.74,
|
| 841 |
+
"learning_rate": 0.00018124447065762315,
|
| 842 |
+
"loss": 0.0925,
|
| 843 |
+
"step": 2780
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.74,
|
| 847 |
+
"learning_rate": 0.00018094957239752287,
|
| 848 |
+
"loss": 0.0928,
|
| 849 |
+
"step": 2800
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.75,
|
| 853 |
+
"learning_rate": 0.0001806546741374226,
|
| 854 |
+
"loss": 0.0908,
|
| 855 |
+
"step": 2820
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.75,
|
| 859 |
+
"learning_rate": 0.00018035977587732232,
|
| 860 |
+
"loss": 0.0926,
|
| 861 |
+
"step": 2840
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.76,
|
| 865 |
+
"learning_rate": 0.00018006487761722205,
|
| 866 |
+
"loss": 0.0958,
|
| 867 |
+
"step": 2860
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.76,
|
| 871 |
+
"learning_rate": 0.0001797699793571218,
|
| 872 |
+
"loss": 0.0927,
|
| 873 |
+
"step": 2880
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.77,
|
| 877 |
+
"learning_rate": 0.00017947508109702153,
|
| 878 |
+
"loss": 0.0912,
|
| 879 |
+
"step": 2900
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.77,
|
| 883 |
+
"learning_rate": 0.00017918018283692125,
|
| 884 |
+
"loss": 0.0936,
|
| 885 |
+
"step": 2920
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.78,
|
| 889 |
+
"learning_rate": 0.000178885284576821,
|
| 890 |
+
"loss": 0.0931,
|
| 891 |
+
"step": 2940
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.79,
|
| 895 |
+
"learning_rate": 0.00017859038631672073,
|
| 896 |
+
"loss": 0.0927,
|
| 897 |
+
"step": 2960
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.79,
|
| 901 |
+
"learning_rate": 0.00017829548805662048,
|
| 902 |
+
"loss": 0.0913,
|
| 903 |
+
"step": 2980
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.8,
|
| 907 |
+
"learning_rate": 0.0001780005897965202,
|
| 908 |
+
"loss": 0.0908,
|
| 909 |
+
"step": 3000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.8,
|
| 913 |
+
"learning_rate": 0.00017770569153641993,
|
| 914 |
+
"loss": 0.0928,
|
| 915 |
+
"step": 3020
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.81,
|
| 919 |
+
"learning_rate": 0.00017741079327631968,
|
| 920 |
+
"loss": 0.0911,
|
| 921 |
+
"step": 3040
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.81,
|
| 925 |
+
"learning_rate": 0.0001771158950162194,
|
| 926 |
+
"loss": 0.0898,
|
| 927 |
+
"step": 3060
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.82,
|
| 931 |
+
"learning_rate": 0.00017682099675611913,
|
| 932 |
+
"loss": 0.0887,
|
| 933 |
+
"step": 3080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.82,
|
| 937 |
+
"learning_rate": 0.0001765260984960189,
|
| 938 |
+
"loss": 0.0918,
|
| 939 |
+
"step": 3100
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.83,
|
| 943 |
+
"learning_rate": 0.0001762312002359186,
|
| 944 |
+
"loss": 0.0911,
|
| 945 |
+
"step": 3120
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.83,
|
| 949 |
+
"learning_rate": 0.00017593630197581834,
|
| 950 |
+
"loss": 0.0925,
|
| 951 |
+
"step": 3140
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.84,
|
| 955 |
+
"learning_rate": 0.0001756414037157181,
|
| 956 |
+
"loss": 0.0901,
|
| 957 |
+
"step": 3160
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.84,
|
| 961 |
+
"learning_rate": 0.00017534650545561782,
|
| 962 |
+
"loss": 0.0931,
|
| 963 |
+
"step": 3180
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.85,
|
| 967 |
+
"learning_rate": 0.00017505160719551757,
|
| 968 |
+
"loss": 0.0889,
|
| 969 |
+
"step": 3200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.85,
|
| 973 |
+
"learning_rate": 0.0001747567089354173,
|
| 974 |
+
"loss": 0.0892,
|
| 975 |
+
"step": 3220
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.86,
|
| 979 |
+
"learning_rate": 0.00017446181067531702,
|
| 980 |
+
"loss": 0.0926,
|
| 981 |
+
"step": 3240
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.87,
|
| 985 |
+
"learning_rate": 0.00017416691241521677,
|
| 986 |
+
"loss": 0.0898,
|
| 987 |
+
"step": 3260
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.87,
|
| 991 |
+
"learning_rate": 0.0001738720141551165,
|
| 992 |
+
"loss": 0.0899,
|
| 993 |
+
"step": 3280
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.88,
|
| 997 |
+
"learning_rate": 0.00017357711589501622,
|
| 998 |
+
"loss": 0.088,
|
| 999 |
+
"step": 3300
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.88,
|
| 1003 |
+
"learning_rate": 0.00017328221763491597,
|
| 1004 |
+
"loss": 0.0912,
|
| 1005 |
+
"step": 3320
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.89,
|
| 1009 |
+
"learning_rate": 0.0001729873193748157,
|
| 1010 |
+
"loss": 0.0903,
|
| 1011 |
+
"step": 3340
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.89,
|
| 1015 |
+
"learning_rate": 0.00017269242111471545,
|
| 1016 |
+
"loss": 0.091,
|
| 1017 |
+
"step": 3360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.9,
|
| 1021 |
+
"learning_rate": 0.00017239752285461518,
|
| 1022 |
+
"loss": 0.0893,
|
| 1023 |
+
"step": 3380
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.9,
|
| 1027 |
+
"learning_rate": 0.0001721026245945149,
|
| 1028 |
+
"loss": 0.0883,
|
| 1029 |
+
"step": 3400
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.91,
|
| 1033 |
+
"learning_rate": 0.00017180772633441465,
|
| 1034 |
+
"loss": 0.0884,
|
| 1035 |
+
"step": 3420
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.91,
|
| 1039 |
+
"learning_rate": 0.00017151282807431438,
|
| 1040 |
+
"loss": 0.0878,
|
| 1041 |
+
"step": 3440
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.92,
|
| 1045 |
+
"learning_rate": 0.0001712179298142141,
|
| 1046 |
+
"loss": 0.0908,
|
| 1047 |
+
"step": 3460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.92,
|
| 1051 |
+
"learning_rate": 0.00017092303155411383,
|
| 1052 |
+
"loss": 0.0895,
|
| 1053 |
+
"step": 3480
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.93,
|
| 1057 |
+
"learning_rate": 0.00017062813329401358,
|
| 1058 |
+
"loss": 0.088,
|
| 1059 |
+
"step": 3500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.93,
|
| 1063 |
+
"learning_rate": 0.0001703332350339133,
|
| 1064 |
+
"loss": 0.0883,
|
| 1065 |
+
"step": 3520
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.94,
|
| 1069 |
+
"learning_rate": 0.00017003833677381303,
|
| 1070 |
+
"loss": 0.0886,
|
| 1071 |
+
"step": 3540
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.94,
|
| 1075 |
+
"learning_rate": 0.00016974343851371276,
|
| 1076 |
+
"loss": 0.09,
|
| 1077 |
+
"step": 3560
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.95,
|
| 1081 |
+
"learning_rate": 0.0001694485402536125,
|
| 1082 |
+
"loss": 0.0912,
|
| 1083 |
+
"step": 3580
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.96,
|
| 1087 |
+
"learning_rate": 0.00016915364199351224,
|
| 1088 |
+
"loss": 0.0879,
|
| 1089 |
+
"step": 3600
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.96,
|
| 1093 |
+
"learning_rate": 0.00016885874373341196,
|
| 1094 |
+
"loss": 0.0903,
|
| 1095 |
+
"step": 3620
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.97,
|
| 1099 |
+
"learning_rate": 0.00016856384547331171,
|
| 1100 |
+
"loss": 0.0896,
|
| 1101 |
+
"step": 3640
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.97,
|
| 1105 |
+
"learning_rate": 0.00016826894721321144,
|
| 1106 |
+
"loss": 0.0876,
|
| 1107 |
+
"step": 3660
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.98,
|
| 1111 |
+
"learning_rate": 0.00016797404895311117,
|
| 1112 |
+
"loss": 0.0872,
|
| 1113 |
+
"step": 3680
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.98,
|
| 1117 |
+
"learning_rate": 0.00016767915069301092,
|
| 1118 |
+
"loss": 0.0921,
|
| 1119 |
+
"step": 3700
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.99,
|
| 1123 |
+
"learning_rate": 0.00016738425243291064,
|
| 1124 |
+
"loss": 0.086,
|
| 1125 |
+
"step": 3720
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.99,
|
| 1129 |
+
"learning_rate": 0.0001670893541728104,
|
| 1130 |
+
"loss": 0.0861,
|
| 1131 |
+
"step": 3740
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 1.0,
|
| 1135 |
+
"learning_rate": 0.00016679445591271012,
|
| 1136 |
+
"loss": 0.0882,
|
| 1137 |
+
"step": 3760
|
| 1138 |
+
}
|
| 1139 |
+
],
|
| 1140 |
+
"logging_steps": 20,
|
| 1141 |
+
"max_steps": 15072,
|
| 1142 |
+
"num_train_epochs": 4,
|
| 1143 |
+
"save_steps": 500,
|
| 1144 |
+
"total_flos": 1.9064002664523104e+19,
|
| 1145 |
+
"trial_name": null,
|
| 1146 |
+
"trial_params": null
|
| 1147 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4564a8875f7fc5706f6dfe0ca8f88ef5502642d9197cc4fa0f84497780565666
|
| 3 |
+
size 4536
|