David Roy Nelson
commited on
Upload 13 files
Browse files- README.md +24 -3
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +50 -0
- trainer_state.json +2833 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,24 @@
|
|
| 1 |
-
---
|
| 2 |
-
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: QuantizationMethod.BITS_AND_BYTES
|
| 9 |
+
- _load_in_8bit: False
|
| 10 |
+
- _load_in_4bit: False
|
| 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: True
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
- bnb_4bit_quant_storage: uint8
|
| 19 |
+
- load_in_4bit: False
|
| 20 |
+
- load_in_8bit: False
|
| 21 |
+
### Framework versions
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- PEFT 0.4.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 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": 16,
|
| 11 |
+
"lora_dropout": 0.0,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"o_proj",
|
| 18 |
+
"up_proj",
|
| 19 |
+
"v_proj",
|
| 20 |
+
"q_proj",
|
| 21 |
+
"k_proj",
|
| 22 |
+
"down_proj",
|
| 23 |
+
"gate_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74ed02120ba5b3cf1bb9b3c3d4d4d8565e32520f19898b628d6efcc8ed25960a
|
| 3 |
+
size 671149168
|
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:f9138b193b74ec811ba88d08014c940aaec00653cf3e6e32ce23be7530282669
|
| 3 |
+
size 1342453434
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e03d046ba2c285f63dbb723bd51c24de7856654009666f83a753346ada93f438
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2f94ab3093689b2db0b2d07dc25e44d3330771cf99326fbd3567c6ef72dd65ce
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 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": false,
|
| 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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,50 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"1": {
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"2": {
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 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 |
+
"additional_special_tokens": [],
|
| 39 |
+
"bos_token": "<s>",
|
| 40 |
+
"clean_up_tokenization_spaces": false,
|
| 41 |
+
"eos_token": "</s>",
|
| 42 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 43 |
+
"pad_token": "[PAD]",
|
| 44 |
+
"padding_side": "right",
|
| 45 |
+
"sp_model_kwargs": {},
|
| 46 |
+
"spaces_between_special_tokens": false,
|
| 47 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 48 |
+
"unk_token": "<unk>",
|
| 49 |
+
"use_default_system_prompt": false
|
| 50 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5514959327174962,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0013787398317937406,
|
| 13 |
+
"grad_norm": 1.0734721422195435,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 2.8003,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.002757479663587481,
|
| 20 |
+
"grad_norm": 0.19643057882785797,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 0.3727,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.004136219495381221,
|
| 27 |
+
"grad_norm": 0.8137874007225037,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 0.3519,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.005514959327174962,
|
| 34 |
+
"grad_norm": 0.4064357578754425,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.357,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.0068936991589687024,
|
| 41 |
+
"grad_norm": 1.0673978328704834,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.3515,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.008272438990762443,
|
| 48 |
+
"grad_norm": 2.2639453411102295,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.4068,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.009651178822556184,
|
| 55 |
+
"grad_norm": 1.2247616052627563,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.5108,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.011029918654349925,
|
| 62 |
+
"grad_norm": 0.07231716066598892,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.3644,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.012408658486143665,
|
| 69 |
+
"grad_norm": 1.4329577684402466,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.3571,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.013787398317937405,
|
| 76 |
+
"grad_norm": 0.8798255920410156,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.3521,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.015166138149731145,
|
| 83 |
+
"grad_norm": 0.06499180942773819,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 0.3597,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.016544877981524885,
|
| 90 |
+
"grad_norm": 0.284839928150177,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.4099,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.017923617813318627,
|
| 97 |
+
"grad_norm": 0.12186373770236969,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 0.3572,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.01930235764511237,
|
| 104 |
+
"grad_norm": 0.21747085452079773,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.3497,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.020681097476906107,
|
| 111 |
+
"grad_norm": 0.22812429070472717,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.3778,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.02205983730869985,
|
| 118 |
+
"grad_norm": 1.1110987663269043,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 0.3607,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.023438577140493588,
|
| 125 |
+
"grad_norm": 0.8457236886024475,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 0.9183,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.02481731697228733,
|
| 132 |
+
"grad_norm": 0.46427470445632935,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 0.3503,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.02619605680408107,
|
| 139 |
+
"grad_norm": 2.4730632305145264,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.3824,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.02757479663587481,
|
| 146 |
+
"grad_norm": 0.3589227497577667,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 1.0105,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.02895353646766855,
|
| 153 |
+
"grad_norm": 3.5308260917663574,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 0.3605,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.03033227629946229,
|
| 160 |
+
"grad_norm": 0.5237946510314941,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 0.3983,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.031711016131256035,
|
| 167 |
+
"grad_norm": 0.5702632665634155,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 0.3521,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.03308975596304977,
|
| 174 |
+
"grad_norm": 1.1318608522415161,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.3617,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.03446849579484351,
|
| 181 |
+
"grad_norm": 0.536571741104126,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 0.3555,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.035847235626637254,
|
| 188 |
+
"grad_norm": 0.12125778943300247,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.3733,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.037225975458430996,
|
| 195 |
+
"grad_norm": 0.045536063611507416,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 0.3514,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.03860471529022474,
|
| 202 |
+
"grad_norm": 0.31765612959861755,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.3536,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.03998345512201847,
|
| 209 |
+
"grad_norm": 0.27900660037994385,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 0.3495,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.041362194953812215,
|
| 216 |
+
"grad_norm": 0.15112566947937012,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 0.355,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.04274093478560596,
|
| 223 |
+
"grad_norm": 0.2682303786277771,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 0.3609,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.0441196746173997,
|
| 230 |
+
"grad_norm": 1.0106860399246216,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 0.3697,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.04549841444919344,
|
| 237 |
+
"grad_norm": 1.0782426595687866,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 0.3594,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.046877154280987175,
|
| 244 |
+
"grad_norm": 2.294581651687622,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.3676,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.04825589411278092,
|
| 251 |
+
"grad_norm": 0.6223801970481873,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 0.3741,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.04963463394457466,
|
| 258 |
+
"grad_norm": 0.2735952138900757,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 0.3628,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.0510133737763684,
|
| 265 |
+
"grad_norm": 0.7569056153297424,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 1.1827,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.05239211360816214,
|
| 272 |
+
"grad_norm": 0.6536706686019897,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 0.3543,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.05377085343995588,
|
| 279 |
+
"grad_norm": 0.3573110103607178,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 0.3529,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.05514959327174962,
|
| 286 |
+
"grad_norm": 0.8121228218078613,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 0.3566,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.05652833310354336,
|
| 293 |
+
"grad_norm": 0.7444269061088562,
|
| 294 |
+
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 0.7803,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.0579070729353371,
|
| 300 |
+
"grad_norm": 0.5015038847923279,
|
| 301 |
+
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 0.6134,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.059285812767130845,
|
| 307 |
+
"grad_norm": 0.08748292177915573,
|
| 308 |
+
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 0.3501,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.06066455259892458,
|
| 314 |
+
"grad_norm": 0.3987080156803131,
|
| 315 |
+
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 0.3484,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.06204329243071832,
|
| 321 |
+
"grad_norm": 347.7005920410156,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 0.8413,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.06342203226251207,
|
| 328 |
+
"grad_norm": 88.2750473022461,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 2.8013,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.0648007720943058,
|
| 335 |
+
"grad_norm": 0.8716701865196228,
|
| 336 |
+
"learning_rate": 0.0002,
|
| 337 |
+
"loss": 0.8356,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.06617951192609954,
|
| 342 |
+
"grad_norm": 0.8243119120597839,
|
| 343 |
+
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.3616,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.06755825175789329,
|
| 349 |
+
"grad_norm": 1.1744294166564941,
|
| 350 |
+
"learning_rate": 0.0002,
|
| 351 |
+
"loss": 0.3998,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.06893699158968702,
|
| 356 |
+
"grad_norm": 0.03163053095340729,
|
| 357 |
+
"learning_rate": 0.0002,
|
| 358 |
+
"loss": 0.3549,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.07031573142148077,
|
| 363 |
+
"grad_norm": 3.4403915405273438,
|
| 364 |
+
"learning_rate": 0.0002,
|
| 365 |
+
"loss": 0.3722,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.07169447125327451,
|
| 370 |
+
"grad_norm": 1.0608879327774048,
|
| 371 |
+
"learning_rate": 0.0002,
|
| 372 |
+
"loss": 0.3701,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.07307321108506824,
|
| 377 |
+
"grad_norm": 1.2809940576553345,
|
| 378 |
+
"learning_rate": 0.0002,
|
| 379 |
+
"loss": 0.3602,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.07445195091686199,
|
| 384 |
+
"grad_norm": 0.40460118651390076,
|
| 385 |
+
"learning_rate": 0.0002,
|
| 386 |
+
"loss": 0.3532,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.07583069074865573,
|
| 391 |
+
"grad_norm": 0.6290703415870667,
|
| 392 |
+
"learning_rate": 0.0002,
|
| 393 |
+
"loss": 0.3477,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.07720943058044948,
|
| 398 |
+
"grad_norm": 0.2159261256456375,
|
| 399 |
+
"learning_rate": 0.0002,
|
| 400 |
+
"loss": 0.405,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.07858817041224321,
|
| 405 |
+
"grad_norm": 0.37101301550865173,
|
| 406 |
+
"learning_rate": 0.0002,
|
| 407 |
+
"loss": 0.3752,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.07996691024403695,
|
| 412 |
+
"grad_norm": 1.3007190227508545,
|
| 413 |
+
"learning_rate": 0.0002,
|
| 414 |
+
"loss": 0.3503,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.0813456500758307,
|
| 419 |
+
"grad_norm": 0.4508918225765228,
|
| 420 |
+
"learning_rate": 0.0002,
|
| 421 |
+
"loss": 0.3531,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.08272438990762443,
|
| 426 |
+
"grad_norm": 0.46898791193962097,
|
| 427 |
+
"learning_rate": 0.0002,
|
| 428 |
+
"loss": 0.347,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.08410312973941818,
|
| 433 |
+
"grad_norm": 0.8449831604957581,
|
| 434 |
+
"learning_rate": 0.0002,
|
| 435 |
+
"loss": 0.3546,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.08548186957121191,
|
| 440 |
+
"grad_norm": 0.7988163232803345,
|
| 441 |
+
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.3505,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.08686060940300565,
|
| 447 |
+
"grad_norm": 0.4426226317882538,
|
| 448 |
+
"learning_rate": 0.0002,
|
| 449 |
+
"loss": 0.3649,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.0882393492347994,
|
| 454 |
+
"grad_norm": 0.2260913848876953,
|
| 455 |
+
"learning_rate": 0.0002,
|
| 456 |
+
"loss": 0.3499,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.08961808906659313,
|
| 461 |
+
"grad_norm": 1.476747751235962,
|
| 462 |
+
"learning_rate": 0.0002,
|
| 463 |
+
"loss": 0.3546,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.09099682889838688,
|
| 468 |
+
"grad_norm": 0.7640777230262756,
|
| 469 |
+
"learning_rate": 0.0002,
|
| 470 |
+
"loss": 0.3568,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.09237556873018062,
|
| 475 |
+
"grad_norm": 0.8559088706970215,
|
| 476 |
+
"learning_rate": 0.0002,
|
| 477 |
+
"loss": 0.3507,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.09375430856197435,
|
| 482 |
+
"grad_norm": 0.20833595097064972,
|
| 483 |
+
"learning_rate": 0.0002,
|
| 484 |
+
"loss": 0.3556,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0951330483937681,
|
| 489 |
+
"grad_norm": 1.1485021114349365,
|
| 490 |
+
"learning_rate": 0.0002,
|
| 491 |
+
"loss": 0.3516,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.09651178822556183,
|
| 496 |
+
"grad_norm": 1.0206815004348755,
|
| 497 |
+
"learning_rate": 0.0002,
|
| 498 |
+
"loss": 0.3591,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.09789052805735558,
|
| 503 |
+
"grad_norm": 0.9966775178909302,
|
| 504 |
+
"learning_rate": 0.0002,
|
| 505 |
+
"loss": 0.359,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.09926926788914932,
|
| 510 |
+
"grad_norm": 0.8833585977554321,
|
| 511 |
+
"learning_rate": 0.0002,
|
| 512 |
+
"loss": 0.3546,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.10064800772094305,
|
| 517 |
+
"grad_norm": 1.0842584371566772,
|
| 518 |
+
"learning_rate": 0.0002,
|
| 519 |
+
"loss": 0.3556,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.1020267475527368,
|
| 524 |
+
"grad_norm": 0.3791511058807373,
|
| 525 |
+
"learning_rate": 0.0002,
|
| 526 |
+
"loss": 0.3571,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.10340548738453054,
|
| 531 |
+
"grad_norm": 0.24666732549667358,
|
| 532 |
+
"learning_rate": 0.0002,
|
| 533 |
+
"loss": 0.3502,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.10478422721632429,
|
| 538 |
+
"grad_norm": 0.21794968843460083,
|
| 539 |
+
"learning_rate": 0.0002,
|
| 540 |
+
"loss": 0.3483,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.10616296704811802,
|
| 545 |
+
"grad_norm": 0.47017499804496765,
|
| 546 |
+
"learning_rate": 0.0002,
|
| 547 |
+
"loss": 0.3499,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.10754170687991176,
|
| 552 |
+
"grad_norm": 0.2813131809234619,
|
| 553 |
+
"learning_rate": 0.0002,
|
| 554 |
+
"loss": 0.3482,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.1089204467117055,
|
| 559 |
+
"grad_norm": 1.2175363302230835,
|
| 560 |
+
"learning_rate": 0.0002,
|
| 561 |
+
"loss": 0.3524,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.11029918654349924,
|
| 566 |
+
"grad_norm": 0.2712210416793823,
|
| 567 |
+
"learning_rate": 0.0002,
|
| 568 |
+
"loss": 0.3526,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.11167792637529299,
|
| 573 |
+
"grad_norm": 0.1428445726633072,
|
| 574 |
+
"learning_rate": 0.0002,
|
| 575 |
+
"loss": 0.3518,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.11305666620708672,
|
| 580 |
+
"grad_norm": 0.23716595768928528,
|
| 581 |
+
"learning_rate": 0.0002,
|
| 582 |
+
"loss": 0.3501,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.11443540603888046,
|
| 587 |
+
"grad_norm": 0.07993923872709274,
|
| 588 |
+
"learning_rate": 0.0002,
|
| 589 |
+
"loss": 0.349,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.1158141458706742,
|
| 594 |
+
"grad_norm": 1.2958595752716064,
|
| 595 |
+
"learning_rate": 0.0002,
|
| 596 |
+
"loss": 0.352,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.11719288570246794,
|
| 601 |
+
"grad_norm": 1.6257132291793823,
|
| 602 |
+
"learning_rate": 0.0002,
|
| 603 |
+
"loss": 0.3589,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.11857162553426169,
|
| 608 |
+
"grad_norm": 0.20367591083049774,
|
| 609 |
+
"learning_rate": 0.0002,
|
| 610 |
+
"loss": 0.3602,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.11995036536605543,
|
| 615 |
+
"grad_norm": 1.147210955619812,
|
| 616 |
+
"learning_rate": 0.0002,
|
| 617 |
+
"loss": 0.3619,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.12132910519784916,
|
| 622 |
+
"grad_norm": 0.19706425070762634,
|
| 623 |
+
"learning_rate": 0.0002,
|
| 624 |
+
"loss": 0.3536,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.12270784502964291,
|
| 629 |
+
"grad_norm": 0.17990930378437042,
|
| 630 |
+
"learning_rate": 0.0002,
|
| 631 |
+
"loss": 0.3501,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.12408658486143664,
|
| 636 |
+
"grad_norm": 0.5770463943481445,
|
| 637 |
+
"learning_rate": 0.0002,
|
| 638 |
+
"loss": 0.3509,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.12546532469323038,
|
| 643 |
+
"grad_norm": 0.24645955860614777,
|
| 644 |
+
"learning_rate": 0.0002,
|
| 645 |
+
"loss": 0.3526,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.12684406452502414,
|
| 650 |
+
"grad_norm": 0.15745119750499725,
|
| 651 |
+
"learning_rate": 0.0002,
|
| 652 |
+
"loss": 0.3503,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.12822280435681788,
|
| 657 |
+
"grad_norm": 0.054484590888023376,
|
| 658 |
+
"learning_rate": 0.0002,
|
| 659 |
+
"loss": 0.3508,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.1296015441886116,
|
| 664 |
+
"grad_norm": 0.30564025044441223,
|
| 665 |
+
"learning_rate": 0.0002,
|
| 666 |
+
"loss": 0.3489,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.13098028402040535,
|
| 671 |
+
"grad_norm": 0.3614678382873535,
|
| 672 |
+
"learning_rate": 0.0002,
|
| 673 |
+
"loss": 0.3477,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.13235902385219908,
|
| 678 |
+
"grad_norm": 0.703029990196228,
|
| 679 |
+
"learning_rate": 0.0002,
|
| 680 |
+
"loss": 0.3552,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.13373776368399284,
|
| 685 |
+
"grad_norm": 1.1954560279846191,
|
| 686 |
+
"learning_rate": 0.0002,
|
| 687 |
+
"loss": 0.3528,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.13511650351578658,
|
| 692 |
+
"grad_norm": 0.8106504678726196,
|
| 693 |
+
"learning_rate": 0.0002,
|
| 694 |
+
"loss": 0.3586,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.13649524334758031,
|
| 699 |
+
"grad_norm": 0.40758854150772095,
|
| 700 |
+
"learning_rate": 0.0002,
|
| 701 |
+
"loss": 0.3908,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.13787398317937405,
|
| 706 |
+
"grad_norm": 0.613096296787262,
|
| 707 |
+
"learning_rate": 0.0002,
|
| 708 |
+
"loss": 0.3519,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.13925272301116778,
|
| 713 |
+
"grad_norm": 0.38185614347457886,
|
| 714 |
+
"learning_rate": 0.0002,
|
| 715 |
+
"loss": 0.3506,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.14063146284296155,
|
| 720 |
+
"grad_norm": 0.07220327854156494,
|
| 721 |
+
"learning_rate": 0.0002,
|
| 722 |
+
"loss": 0.3472,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.14201020267475528,
|
| 727 |
+
"grad_norm": 0.1451689898967743,
|
| 728 |
+
"learning_rate": 0.0002,
|
| 729 |
+
"loss": 0.3534,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.14338894250654902,
|
| 734 |
+
"grad_norm": 0.08052591234445572,
|
| 735 |
+
"learning_rate": 0.0002,
|
| 736 |
+
"loss": 0.3476,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.14476768233834275,
|
| 741 |
+
"grad_norm": 1.0108163356781006,
|
| 742 |
+
"learning_rate": 0.0002,
|
| 743 |
+
"loss": 0.3508,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.1461464221701365,
|
| 748 |
+
"grad_norm": 0.5895722508430481,
|
| 749 |
+
"learning_rate": 0.0002,
|
| 750 |
+
"loss": 0.3541,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.14752516200193025,
|
| 755 |
+
"grad_norm": 0.6988415718078613,
|
| 756 |
+
"learning_rate": 0.0002,
|
| 757 |
+
"loss": 0.3512,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.14890390183372398,
|
| 762 |
+
"grad_norm": 0.54078608751297,
|
| 763 |
+
"learning_rate": 0.0002,
|
| 764 |
+
"loss": 0.3479,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.15028264166551772,
|
| 769 |
+
"grad_norm": 0.19162333011627197,
|
| 770 |
+
"learning_rate": 0.0002,
|
| 771 |
+
"loss": 0.3518,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.15166138149731145,
|
| 776 |
+
"grad_norm": 0.36928215622901917,
|
| 777 |
+
"learning_rate": 0.0002,
|
| 778 |
+
"loss": 0.3505,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.1530401213291052,
|
| 783 |
+
"grad_norm": 0.572607696056366,
|
| 784 |
+
"learning_rate": 0.0002,
|
| 785 |
+
"loss": 0.355,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.15441886116089895,
|
| 790 |
+
"grad_norm": 0.20841191709041595,
|
| 791 |
+
"learning_rate": 0.0002,
|
| 792 |
+
"loss": 0.348,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.1557976009926927,
|
| 797 |
+
"grad_norm": 0.04682110995054245,
|
| 798 |
+
"learning_rate": 0.0002,
|
| 799 |
+
"loss": 0.3502,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.15717634082448642,
|
| 804 |
+
"grad_norm": 0.867899477481842,
|
| 805 |
+
"learning_rate": 0.0002,
|
| 806 |
+
"loss": 0.3476,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.15855508065628016,
|
| 811 |
+
"grad_norm": 0.2828502655029297,
|
| 812 |
+
"learning_rate": 0.0002,
|
| 813 |
+
"loss": 0.3525,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.1599338204880739,
|
| 818 |
+
"grad_norm": 0.44510889053344727,
|
| 819 |
+
"learning_rate": 0.0002,
|
| 820 |
+
"loss": 0.35,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.16131256031986765,
|
| 825 |
+
"grad_norm": 0.1896822154521942,
|
| 826 |
+
"learning_rate": 0.0002,
|
| 827 |
+
"loss": 0.3493,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.1626913001516614,
|
| 832 |
+
"grad_norm": 0.15781590342521667,
|
| 833 |
+
"learning_rate": 0.0002,
|
| 834 |
+
"loss": 0.3477,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.16407003998345512,
|
| 839 |
+
"grad_norm": 0.2315225899219513,
|
| 840 |
+
"learning_rate": 0.0002,
|
| 841 |
+
"loss": 0.3498,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.16544877981524886,
|
| 846 |
+
"grad_norm": 0.2198018729686737,
|
| 847 |
+
"learning_rate": 0.0002,
|
| 848 |
+
"loss": 0.3484,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.1668275196470426,
|
| 853 |
+
"grad_norm": 0.2039571851491928,
|
| 854 |
+
"learning_rate": 0.0002,
|
| 855 |
+
"loss": 0.348,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.16820625947883636,
|
| 860 |
+
"grad_norm": 0.009352603927254677,
|
| 861 |
+
"learning_rate": 0.0002,
|
| 862 |
+
"loss": 0.3481,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.1695849993106301,
|
| 867 |
+
"grad_norm": 0.2558707892894745,
|
| 868 |
+
"learning_rate": 0.0002,
|
| 869 |
+
"loss": 0.3475,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.17096373914242383,
|
| 874 |
+
"grad_norm": 0.07278712838888168,
|
| 875 |
+
"learning_rate": 0.0002,
|
| 876 |
+
"loss": 0.3471,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.17234247897421756,
|
| 881 |
+
"grad_norm": 0.4133436381816864,
|
| 882 |
+
"learning_rate": 0.0002,
|
| 883 |
+
"loss": 0.3453,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.1737212188060113,
|
| 888 |
+
"grad_norm": 0.16729828715324402,
|
| 889 |
+
"learning_rate": 0.0002,
|
| 890 |
+
"loss": 0.3527,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.17509995863780506,
|
| 895 |
+
"grad_norm": 0.33326980471611023,
|
| 896 |
+
"learning_rate": 0.0002,
|
| 897 |
+
"loss": 0.3463,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.1764786984695988,
|
| 902 |
+
"grad_norm": 0.7140666246414185,
|
| 903 |
+
"learning_rate": 0.0002,
|
| 904 |
+
"loss": 0.3627,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.17785743830139253,
|
| 909 |
+
"grad_norm": 0.17751634120941162,
|
| 910 |
+
"learning_rate": 0.0002,
|
| 911 |
+
"loss": 0.3506,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.17923617813318626,
|
| 916 |
+
"grad_norm": 0.44009125232696533,
|
| 917 |
+
"learning_rate": 0.0002,
|
| 918 |
+
"loss": 0.3516,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.18061491796498,
|
| 923 |
+
"grad_norm": 0.07371579110622406,
|
| 924 |
+
"learning_rate": 0.0002,
|
| 925 |
+
"loss": 0.3479,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.18199365779677376,
|
| 930 |
+
"grad_norm": 0.6804266571998596,
|
| 931 |
+
"learning_rate": 0.0002,
|
| 932 |
+
"loss": 0.3476,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.1833723976285675,
|
| 937 |
+
"grad_norm": 0.19634029269218445,
|
| 938 |
+
"learning_rate": 0.0002,
|
| 939 |
+
"loss": 0.354,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.18475113746036123,
|
| 944 |
+
"grad_norm": 0.34020882844924927,
|
| 945 |
+
"learning_rate": 0.0002,
|
| 946 |
+
"loss": 0.3481,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.18612987729215497,
|
| 951 |
+
"grad_norm": 0.38502731919288635,
|
| 952 |
+
"learning_rate": 0.0002,
|
| 953 |
+
"loss": 0.3501,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.1875086171239487,
|
| 958 |
+
"grad_norm": 0.0810522586107254,
|
| 959 |
+
"learning_rate": 0.0002,
|
| 960 |
+
"loss": 0.3473,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.18888735695574246,
|
| 965 |
+
"grad_norm": 0.4057389497756958,
|
| 966 |
+
"learning_rate": 0.0002,
|
| 967 |
+
"loss": 0.3489,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.1902660967875362,
|
| 972 |
+
"grad_norm": 0.17514599859714508,
|
| 973 |
+
"learning_rate": 0.0002,
|
| 974 |
+
"loss": 0.3472,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.19164483661932993,
|
| 979 |
+
"grad_norm": 0.10964088141918182,
|
| 980 |
+
"learning_rate": 0.0002,
|
| 981 |
+
"loss": 0.3479,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.19302357645112367,
|
| 986 |
+
"grad_norm": 0.20920871198177338,
|
| 987 |
+
"learning_rate": 0.0002,
|
| 988 |
+
"loss": 0.3488,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.1944023162829174,
|
| 993 |
+
"grad_norm": 1.149121880531311,
|
| 994 |
+
"learning_rate": 0.0002,
|
| 995 |
+
"loss": 0.3548,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.19578105611471117,
|
| 1000 |
+
"grad_norm": 1.3394649028778076,
|
| 1001 |
+
"learning_rate": 0.0002,
|
| 1002 |
+
"loss": 0.3495,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.1971597959465049,
|
| 1007 |
+
"grad_norm": 1.2763960361480713,
|
| 1008 |
+
"learning_rate": 0.0002,
|
| 1009 |
+
"loss": 0.3679,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.19853853577829864,
|
| 1014 |
+
"grad_norm": 0.5421571731567383,
|
| 1015 |
+
"learning_rate": 0.0002,
|
| 1016 |
+
"loss": 0.3538,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.19991727561009237,
|
| 1021 |
+
"grad_norm": 0.22273503243923187,
|
| 1022 |
+
"learning_rate": 0.0002,
|
| 1023 |
+
"loss": 0.3518,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.2012960154418861,
|
| 1028 |
+
"grad_norm": 0.6335702538490295,
|
| 1029 |
+
"learning_rate": 0.0002,
|
| 1030 |
+
"loss": 0.3481,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.20267475527367987,
|
| 1035 |
+
"grad_norm": 0.7090324759483337,
|
| 1036 |
+
"learning_rate": 0.0002,
|
| 1037 |
+
"loss": 0.3486,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.2040534951054736,
|
| 1042 |
+
"grad_norm": 0.011333847418427467,
|
| 1043 |
+
"learning_rate": 0.0002,
|
| 1044 |
+
"loss": 0.3476,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.20543223493726734,
|
| 1049 |
+
"grad_norm": 0.24088676273822784,
|
| 1050 |
+
"learning_rate": 0.0002,
|
| 1051 |
+
"loss": 0.3569,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.20681097476906107,
|
| 1056 |
+
"grad_norm": 0.8654371500015259,
|
| 1057 |
+
"learning_rate": 0.0002,
|
| 1058 |
+
"loss": 0.3528,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.2081897146008548,
|
| 1063 |
+
"grad_norm": 0.06135034188628197,
|
| 1064 |
+
"learning_rate": 0.0002,
|
| 1065 |
+
"loss": 0.3509,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.20956845443264857,
|
| 1070 |
+
"grad_norm": 0.38141730427742004,
|
| 1071 |
+
"learning_rate": 0.0002,
|
| 1072 |
+
"loss": 0.3474,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.2109471942644423,
|
| 1077 |
+
"grad_norm": 1.1622456312179565,
|
| 1078 |
+
"learning_rate": 0.0002,
|
| 1079 |
+
"loss": 0.353,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.21232593409623604,
|
| 1084 |
+
"grad_norm": 0.5747712254524231,
|
| 1085 |
+
"learning_rate": 0.0002,
|
| 1086 |
+
"loss": 0.3513,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.21370467392802978,
|
| 1091 |
+
"grad_norm": 0.09723293781280518,
|
| 1092 |
+
"learning_rate": 0.0002,
|
| 1093 |
+
"loss": 0.3482,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.2150834137598235,
|
| 1098 |
+
"grad_norm": 0.18574804067611694,
|
| 1099 |
+
"learning_rate": 0.0002,
|
| 1100 |
+
"loss": 0.3512,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.21646215359161727,
|
| 1105 |
+
"grad_norm": 0.33651217818260193,
|
| 1106 |
+
"learning_rate": 0.0002,
|
| 1107 |
+
"loss": 0.349,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.217840893423411,
|
| 1112 |
+
"grad_norm": 0.07309216260910034,
|
| 1113 |
+
"learning_rate": 0.0002,
|
| 1114 |
+
"loss": 0.3493,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.21921963325520474,
|
| 1119 |
+
"grad_norm": 0.19346486032009125,
|
| 1120 |
+
"learning_rate": 0.0002,
|
| 1121 |
+
"loss": 0.3478,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.22059837308699848,
|
| 1126 |
+
"grad_norm": 0.3398933708667755,
|
| 1127 |
+
"learning_rate": 0.0002,
|
| 1128 |
+
"loss": 0.3496,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.2219771129187922,
|
| 1133 |
+
"grad_norm": 0.34032130241394043,
|
| 1134 |
+
"learning_rate": 0.0002,
|
| 1135 |
+
"loss": 0.3488,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.22335585275058598,
|
| 1140 |
+
"grad_norm": 0.901030421257019,
|
| 1141 |
+
"learning_rate": 0.0002,
|
| 1142 |
+
"loss": 0.3531,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.2247345925823797,
|
| 1147 |
+
"grad_norm": 0.500088632106781,
|
| 1148 |
+
"learning_rate": 0.0002,
|
| 1149 |
+
"loss": 0.3516,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.22611333241417345,
|
| 1154 |
+
"grad_norm": 0.3230324387550354,
|
| 1155 |
+
"learning_rate": 0.0002,
|
| 1156 |
+
"loss": 0.3546,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.22749207224596718,
|
| 1161 |
+
"grad_norm": 1.2476601600646973,
|
| 1162 |
+
"learning_rate": 0.0002,
|
| 1163 |
+
"loss": 0.3512,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.22887081207776092,
|
| 1168 |
+
"grad_norm": 0.23318485915660858,
|
| 1169 |
+
"learning_rate": 0.0002,
|
| 1170 |
+
"loss": 0.3456,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.23024955190955468,
|
| 1175 |
+
"grad_norm": 0.472400963306427,
|
| 1176 |
+
"learning_rate": 0.0002,
|
| 1177 |
+
"loss": 0.3551,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.2316282917413484,
|
| 1182 |
+
"grad_norm": 0.04836912825703621,
|
| 1183 |
+
"learning_rate": 0.0002,
|
| 1184 |
+
"loss": 0.3505,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.23300703157314215,
|
| 1189 |
+
"grad_norm": 0.34590113162994385,
|
| 1190 |
+
"learning_rate": 0.0002,
|
| 1191 |
+
"loss": 0.3507,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.23438577140493588,
|
| 1196 |
+
"grad_norm": 0.23341989517211914,
|
| 1197 |
+
"learning_rate": 0.0002,
|
| 1198 |
+
"loss": 0.3478,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.23576451123672962,
|
| 1203 |
+
"grad_norm": 0.001271920627914369,
|
| 1204 |
+
"learning_rate": 0.0002,
|
| 1205 |
+
"loss": 0.3562,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.23714325106852338,
|
| 1210 |
+
"grad_norm": 0.20549911260604858,
|
| 1211 |
+
"learning_rate": 0.0002,
|
| 1212 |
+
"loss": 0.3479,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.23852199090031712,
|
| 1217 |
+
"grad_norm": 0.3825775384902954,
|
| 1218 |
+
"learning_rate": 0.0002,
|
| 1219 |
+
"loss": 0.3482,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.23990073073211085,
|
| 1224 |
+
"grad_norm": 0.028804048895835876,
|
| 1225 |
+
"learning_rate": 0.0002,
|
| 1226 |
+
"loss": 0.3481,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.24127947056390459,
|
| 1231 |
+
"grad_norm": 0.04462611302733421,
|
| 1232 |
+
"learning_rate": 0.0002,
|
| 1233 |
+
"loss": 0.3477,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.24265821039569832,
|
| 1238 |
+
"grad_norm": 0.6634818315505981,
|
| 1239 |
+
"learning_rate": 0.0002,
|
| 1240 |
+
"loss": 0.3501,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.24403695022749208,
|
| 1245 |
+
"grad_norm": 1.3807406425476074,
|
| 1246 |
+
"learning_rate": 0.0002,
|
| 1247 |
+
"loss": 0.3547,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.24541569005928582,
|
| 1252 |
+
"grad_norm": 0.24347831308841705,
|
| 1253 |
+
"learning_rate": 0.0002,
|
| 1254 |
+
"loss": 0.3473,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.24679442989107955,
|
| 1259 |
+
"grad_norm": 0.61258465051651,
|
| 1260 |
+
"learning_rate": 0.0002,
|
| 1261 |
+
"loss": 0.3492,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.2481731697228733,
|
| 1266 |
+
"grad_norm": 0.011543272994458675,
|
| 1267 |
+
"learning_rate": 0.0002,
|
| 1268 |
+
"loss": 0.347,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.24955190955466702,
|
| 1273 |
+
"grad_norm": 0.09996844828128815,
|
| 1274 |
+
"learning_rate": 0.0002,
|
| 1275 |
+
"loss": 0.3474,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.25093064938646076,
|
| 1280 |
+
"grad_norm": 0.17044603824615479,
|
| 1281 |
+
"learning_rate": 0.0002,
|
| 1282 |
+
"loss": 0.3471,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.2523093892182545,
|
| 1287 |
+
"grad_norm": 0.17940489947795868,
|
| 1288 |
+
"learning_rate": 0.0002,
|
| 1289 |
+
"loss": 0.3478,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.2536881290500483,
|
| 1294 |
+
"grad_norm": 0.21834205090999603,
|
| 1295 |
+
"learning_rate": 0.0002,
|
| 1296 |
+
"loss": 0.3461,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.255066868881842,
|
| 1301 |
+
"grad_norm": 0.2272634655237198,
|
| 1302 |
+
"learning_rate": 0.0002,
|
| 1303 |
+
"loss": 0.347,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.25644560871363575,
|
| 1308 |
+
"grad_norm": 0.18734070658683777,
|
| 1309 |
+
"learning_rate": 0.0002,
|
| 1310 |
+
"loss": 0.3497,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.25782434854542946,
|
| 1315 |
+
"grad_norm": 0.04078834876418114,
|
| 1316 |
+
"learning_rate": 0.0002,
|
| 1317 |
+
"loss": 0.3493,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.2592030883772232,
|
| 1322 |
+
"grad_norm": 0.3463903069496155,
|
| 1323 |
+
"learning_rate": 0.0002,
|
| 1324 |
+
"loss": 0.3494,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.260581828209017,
|
| 1329 |
+
"grad_norm": 0.3256634771823883,
|
| 1330 |
+
"learning_rate": 0.0002,
|
| 1331 |
+
"loss": 0.3488,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.2619605680408107,
|
| 1336 |
+
"grad_norm": 0.04404434189200401,
|
| 1337 |
+
"learning_rate": 0.0002,
|
| 1338 |
+
"loss": 0.3509,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.26333930787260446,
|
| 1343 |
+
"grad_norm": 0.20446011424064636,
|
| 1344 |
+
"learning_rate": 0.0002,
|
| 1345 |
+
"loss": 0.3526,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.26471804770439816,
|
| 1350 |
+
"grad_norm": 0.06089179962873459,
|
| 1351 |
+
"learning_rate": 0.0002,
|
| 1352 |
+
"loss": 0.3491,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.2660967875361919,
|
| 1357 |
+
"grad_norm": 0.32661405205726624,
|
| 1358 |
+
"learning_rate": 0.0002,
|
| 1359 |
+
"loss": 0.35,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.2674755273679857,
|
| 1364 |
+
"grad_norm": 0.09823151677846909,
|
| 1365 |
+
"learning_rate": 0.0002,
|
| 1366 |
+
"loss": 0.3482,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.2688542671997794,
|
| 1371 |
+
"grad_norm": 0.11397412419319153,
|
| 1372 |
+
"learning_rate": 0.0002,
|
| 1373 |
+
"loss": 0.347,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.27023300703157316,
|
| 1378 |
+
"grad_norm": 0.2632172703742981,
|
| 1379 |
+
"learning_rate": 0.0002,
|
| 1380 |
+
"loss": 0.352,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.27161174686336687,
|
| 1385 |
+
"grad_norm": 0.27215296030044556,
|
| 1386 |
+
"learning_rate": 0.0002,
|
| 1387 |
+
"loss": 0.3482,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.27299048669516063,
|
| 1392 |
+
"grad_norm": 0.20016005635261536,
|
| 1393 |
+
"learning_rate": 0.0002,
|
| 1394 |
+
"loss": 0.3489,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.2743692265269544,
|
| 1399 |
+
"grad_norm": 0.3071637749671936,
|
| 1400 |
+
"learning_rate": 0.0002,
|
| 1401 |
+
"loss": 0.354,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.2757479663587481,
|
| 1406 |
+
"grad_norm": 1.0373337268829346,
|
| 1407 |
+
"learning_rate": 0.0002,
|
| 1408 |
+
"loss": 0.3481,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.27712670619054186,
|
| 1413 |
+
"grad_norm": 0.49023887515068054,
|
| 1414 |
+
"learning_rate": 0.0002,
|
| 1415 |
+
"loss": 0.3501,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.27850544602233557,
|
| 1420 |
+
"grad_norm": 0.7107551097869873,
|
| 1421 |
+
"learning_rate": 0.0002,
|
| 1422 |
+
"loss": 0.3515,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.27988418585412933,
|
| 1427 |
+
"grad_norm": 1.5392403602600098,
|
| 1428 |
+
"learning_rate": 0.0002,
|
| 1429 |
+
"loss": 0.3468,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.2812629256859231,
|
| 1434 |
+
"grad_norm": 2.7259292602539062,
|
| 1435 |
+
"learning_rate": 0.0002,
|
| 1436 |
+
"loss": 0.3585,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.2826416655177168,
|
| 1441 |
+
"grad_norm": 2.783911943435669,
|
| 1442 |
+
"learning_rate": 0.0002,
|
| 1443 |
+
"loss": 0.3703,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.28402040534951056,
|
| 1448 |
+
"grad_norm": 0.015472312457859516,
|
| 1449 |
+
"learning_rate": 0.0002,
|
| 1450 |
+
"loss": 0.3506,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.28539914518130427,
|
| 1455 |
+
"grad_norm": 0.7833682298660278,
|
| 1456 |
+
"learning_rate": 0.0002,
|
| 1457 |
+
"loss": 0.3483,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.28677788501309803,
|
| 1462 |
+
"grad_norm": 0.4828648269176483,
|
| 1463 |
+
"learning_rate": 0.0002,
|
| 1464 |
+
"loss": 0.3479,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.2881566248448918,
|
| 1469 |
+
"grad_norm": 1.035452961921692,
|
| 1470 |
+
"learning_rate": 0.0002,
|
| 1471 |
+
"loss": 0.348,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.2895353646766855,
|
| 1476 |
+
"grad_norm": 0.14552044868469238,
|
| 1477 |
+
"learning_rate": 0.0002,
|
| 1478 |
+
"loss": 0.3478,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.29091410450847927,
|
| 1483 |
+
"grad_norm": 0.9040600061416626,
|
| 1484 |
+
"learning_rate": 0.0002,
|
| 1485 |
+
"loss": 0.3508,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.292292844340273,
|
| 1490 |
+
"grad_norm": 0.36334726214408875,
|
| 1491 |
+
"learning_rate": 0.0002,
|
| 1492 |
+
"loss": 0.3472,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.29367158417206674,
|
| 1497 |
+
"grad_norm": 0.6746371984481812,
|
| 1498 |
+
"learning_rate": 0.0002,
|
| 1499 |
+
"loss": 0.3546,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.2950503240038605,
|
| 1504 |
+
"grad_norm": 0.49551185965538025,
|
| 1505 |
+
"learning_rate": 0.0002,
|
| 1506 |
+
"loss": 0.3464,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.2964290638356542,
|
| 1511 |
+
"grad_norm": 0.04471205919981003,
|
| 1512 |
+
"learning_rate": 0.0002,
|
| 1513 |
+
"loss": 0.347,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.29780780366744797,
|
| 1518 |
+
"grad_norm": 0.12050581723451614,
|
| 1519 |
+
"learning_rate": 0.0002,
|
| 1520 |
+
"loss": 0.3475,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.2991865434992417,
|
| 1525 |
+
"grad_norm": 0.04496219381690025,
|
| 1526 |
+
"learning_rate": 0.0002,
|
| 1527 |
+
"loss": 0.346,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.30056528333103544,
|
| 1532 |
+
"grad_norm": 0.11529727280139923,
|
| 1533 |
+
"learning_rate": 0.0002,
|
| 1534 |
+
"loss": 0.3475,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.3019440231628292,
|
| 1539 |
+
"grad_norm": 0.12811416387557983,
|
| 1540 |
+
"learning_rate": 0.0002,
|
| 1541 |
+
"loss": 0.3466,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.3033227629946229,
|
| 1546 |
+
"grad_norm": 0.0471930056810379,
|
| 1547 |
+
"learning_rate": 0.0002,
|
| 1548 |
+
"loss": 0.3468,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.30470150282641667,
|
| 1553 |
+
"grad_norm": 2.6910486221313477,
|
| 1554 |
+
"learning_rate": 0.0002,
|
| 1555 |
+
"loss": 0.351,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.3060802426582104,
|
| 1560 |
+
"grad_norm": 0.3302823305130005,
|
| 1561 |
+
"learning_rate": 0.0002,
|
| 1562 |
+
"loss": 0.3498,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.30745898249000414,
|
| 1567 |
+
"grad_norm": 10.41483211517334,
|
| 1568 |
+
"learning_rate": 0.0002,
|
| 1569 |
+
"loss": 0.3694,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.3088377223217979,
|
| 1574 |
+
"grad_norm": 12.485153198242188,
|
| 1575 |
+
"learning_rate": 0.0002,
|
| 1576 |
+
"loss": 0.3816,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.3102164621535916,
|
| 1581 |
+
"grad_norm": 1.1303633451461792,
|
| 1582 |
+
"learning_rate": 0.0002,
|
| 1583 |
+
"loss": 0.3554,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
},
|
| 1586 |
+
{
|
| 1587 |
+
"epoch": 0.3115952019853854,
|
| 1588 |
+
"grad_norm": 0.08931141346693039,
|
| 1589 |
+
"learning_rate": 0.0002,
|
| 1590 |
+
"loss": 0.3824,
|
| 1591 |
+
"step": 2260
|
| 1592 |
+
},
|
| 1593 |
+
{
|
| 1594 |
+
"epoch": 0.3129739418171791,
|
| 1595 |
+
"grad_norm": 0.20106171071529388,
|
| 1596 |
+
"learning_rate": 0.0002,
|
| 1597 |
+
"loss": 0.3483,
|
| 1598 |
+
"step": 2270
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 0.31435268164897284,
|
| 1602 |
+
"grad_norm": 1.7839974164962769,
|
| 1603 |
+
"learning_rate": 0.0002,
|
| 1604 |
+
"loss": 0.354,
|
| 1605 |
+
"step": 2280
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.3157314214807666,
|
| 1609 |
+
"grad_norm": 0.6848243474960327,
|
| 1610 |
+
"learning_rate": 0.0002,
|
| 1611 |
+
"loss": 0.356,
|
| 1612 |
+
"step": 2290
|
| 1613 |
+
},
|
| 1614 |
+
{
|
| 1615 |
+
"epoch": 0.3171101613125603,
|
| 1616 |
+
"grad_norm": 1.5771201848983765,
|
| 1617 |
+
"learning_rate": 0.0002,
|
| 1618 |
+
"loss": 0.35,
|
| 1619 |
+
"step": 2300
|
| 1620 |
+
},
|
| 1621 |
+
{
|
| 1622 |
+
"epoch": 0.3184889011443541,
|
| 1623 |
+
"grad_norm": 1.2237290143966675,
|
| 1624 |
+
"learning_rate": 0.0002,
|
| 1625 |
+
"loss": 0.3521,
|
| 1626 |
+
"step": 2310
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 0.3198676409761478,
|
| 1630 |
+
"grad_norm": 0.04607740044593811,
|
| 1631 |
+
"learning_rate": 0.0002,
|
| 1632 |
+
"loss": 0.3455,
|
| 1633 |
+
"step": 2320
|
| 1634 |
+
},
|
| 1635 |
+
{
|
| 1636 |
+
"epoch": 0.32124638080794155,
|
| 1637 |
+
"grad_norm": 0.0691566988825798,
|
| 1638 |
+
"learning_rate": 0.0002,
|
| 1639 |
+
"loss": 0.6835,
|
| 1640 |
+
"step": 2330
|
| 1641 |
+
},
|
| 1642 |
+
{
|
| 1643 |
+
"epoch": 0.3226251206397353,
|
| 1644 |
+
"grad_norm": 0.17569975554943085,
|
| 1645 |
+
"learning_rate": 0.0002,
|
| 1646 |
+
"loss": 0.3471,
|
| 1647 |
+
"step": 2340
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.324003860471529,
|
| 1651 |
+
"grad_norm": 0.23300354182720184,
|
| 1652 |
+
"learning_rate": 0.0002,
|
| 1653 |
+
"loss": 0.3496,
|
| 1654 |
+
"step": 2350
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 0.3253826003033228,
|
| 1658 |
+
"grad_norm": 0.2859944999217987,
|
| 1659 |
+
"learning_rate": 0.0002,
|
| 1660 |
+
"loss": 0.3544,
|
| 1661 |
+
"step": 2360
|
| 1662 |
+
},
|
| 1663 |
+
{
|
| 1664 |
+
"epoch": 0.3267613401351165,
|
| 1665 |
+
"grad_norm": 140.8813018798828,
|
| 1666 |
+
"learning_rate": 0.0002,
|
| 1667 |
+
"loss": 0.5267,
|
| 1668 |
+
"step": 2370
|
| 1669 |
+
},
|
| 1670 |
+
{
|
| 1671 |
+
"epoch": 0.32814007996691025,
|
| 1672 |
+
"grad_norm": 0.4637663960456848,
|
| 1673 |
+
"learning_rate": 0.0002,
|
| 1674 |
+
"loss": 0.3538,
|
| 1675 |
+
"step": 2380
|
| 1676 |
+
},
|
| 1677 |
+
{
|
| 1678 |
+
"epoch": 0.329518819798704,
|
| 1679 |
+
"grad_norm": 0.2639578580856323,
|
| 1680 |
+
"learning_rate": 0.0002,
|
| 1681 |
+
"loss": 0.3482,
|
| 1682 |
+
"step": 2390
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 0.3308975596304977,
|
| 1686 |
+
"grad_norm": 0.02536751516163349,
|
| 1687 |
+
"learning_rate": 0.0002,
|
| 1688 |
+
"loss": 0.3468,
|
| 1689 |
+
"step": 2400
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.3322762994622915,
|
| 1693 |
+
"grad_norm": 0.20604869723320007,
|
| 1694 |
+
"learning_rate": 0.0002,
|
| 1695 |
+
"loss": 0.3494,
|
| 1696 |
+
"step": 2410
|
| 1697 |
+
},
|
| 1698 |
+
{
|
| 1699 |
+
"epoch": 0.3336550392940852,
|
| 1700 |
+
"grad_norm": 0.3395155668258667,
|
| 1701 |
+
"learning_rate": 0.0002,
|
| 1702 |
+
"loss": 0.3492,
|
| 1703 |
+
"step": 2420
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 0.33503377912587895,
|
| 1707 |
+
"grad_norm": 0.07880198955535889,
|
| 1708 |
+
"learning_rate": 0.0002,
|
| 1709 |
+
"loss": 0.3474,
|
| 1710 |
+
"step": 2430
|
| 1711 |
+
},
|
| 1712 |
+
{
|
| 1713 |
+
"epoch": 0.3364125189576727,
|
| 1714 |
+
"grad_norm": 0.18549232184886932,
|
| 1715 |
+
"learning_rate": 0.0002,
|
| 1716 |
+
"loss": 0.3515,
|
| 1717 |
+
"step": 2440
|
| 1718 |
+
},
|
| 1719 |
+
{
|
| 1720 |
+
"epoch": 0.3377912587894664,
|
| 1721 |
+
"grad_norm": 0.030663492158055305,
|
| 1722 |
+
"learning_rate": 0.0002,
|
| 1723 |
+
"loss": 0.3475,
|
| 1724 |
+
"step": 2450
|
| 1725 |
+
},
|
| 1726 |
+
{
|
| 1727 |
+
"epoch": 0.3391699986212602,
|
| 1728 |
+
"grad_norm": 0.2116040587425232,
|
| 1729 |
+
"learning_rate": 0.0002,
|
| 1730 |
+
"loss": 0.3484,
|
| 1731 |
+
"step": 2460
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.3405487384530539,
|
| 1735 |
+
"grad_norm": 0.06269362568855286,
|
| 1736 |
+
"learning_rate": 0.0002,
|
| 1737 |
+
"loss": 0.3476,
|
| 1738 |
+
"step": 2470
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 0.34192747828484765,
|
| 1742 |
+
"grad_norm": 0.13339760899543762,
|
| 1743 |
+
"learning_rate": 0.0002,
|
| 1744 |
+
"loss": 0.3477,
|
| 1745 |
+
"step": 2480
|
| 1746 |
+
},
|
| 1747 |
+
{
|
| 1748 |
+
"epoch": 0.3433062181166414,
|
| 1749 |
+
"grad_norm": 0.3202485740184784,
|
| 1750 |
+
"learning_rate": 0.0002,
|
| 1751 |
+
"loss": 0.3477,
|
| 1752 |
+
"step": 2490
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 0.3446849579484351,
|
| 1756 |
+
"grad_norm": 0.2552681565284729,
|
| 1757 |
+
"learning_rate": 0.0002,
|
| 1758 |
+
"loss": 0.3488,
|
| 1759 |
+
"step": 2500
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 0.3460636977802289,
|
| 1763 |
+
"grad_norm": 0.5942317247390747,
|
| 1764 |
+
"learning_rate": 0.0002,
|
| 1765 |
+
"loss": 0.3513,
|
| 1766 |
+
"step": 2510
|
| 1767 |
+
},
|
| 1768 |
+
{
|
| 1769 |
+
"epoch": 0.3474424376120226,
|
| 1770 |
+
"grad_norm": 0.865836501121521,
|
| 1771 |
+
"learning_rate": 0.0002,
|
| 1772 |
+
"loss": 0.3517,
|
| 1773 |
+
"step": 2520
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.34882117744381635,
|
| 1777 |
+
"grad_norm": 0.47955092787742615,
|
| 1778 |
+
"learning_rate": 0.0002,
|
| 1779 |
+
"loss": 0.3508,
|
| 1780 |
+
"step": 2530
|
| 1781 |
+
},
|
| 1782 |
+
{
|
| 1783 |
+
"epoch": 0.3501999172756101,
|
| 1784 |
+
"grad_norm": 0.07025259733200073,
|
| 1785 |
+
"learning_rate": 0.0002,
|
| 1786 |
+
"loss": 0.3476,
|
| 1787 |
+
"step": 2540
|
| 1788 |
+
},
|
| 1789 |
+
{
|
| 1790 |
+
"epoch": 0.3515786571074038,
|
| 1791 |
+
"grad_norm": 0.08550610393285751,
|
| 1792 |
+
"learning_rate": 0.0002,
|
| 1793 |
+
"loss": 0.3483,
|
| 1794 |
+
"step": 2550
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 0.3529573969391976,
|
| 1798 |
+
"grad_norm": 0.07628582417964935,
|
| 1799 |
+
"learning_rate": 0.0002,
|
| 1800 |
+
"loss": 0.3503,
|
| 1801 |
+
"step": 2560
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 0.3543361367709913,
|
| 1805 |
+
"grad_norm": 0.09870871156454086,
|
| 1806 |
+
"learning_rate": 0.0002,
|
| 1807 |
+
"loss": 0.3506,
|
| 1808 |
+
"step": 2570
|
| 1809 |
+
},
|
| 1810 |
+
{
|
| 1811 |
+
"epoch": 0.35571487660278506,
|
| 1812 |
+
"grad_norm": 0.03877127543091774,
|
| 1813 |
+
"learning_rate": 0.0002,
|
| 1814 |
+
"loss": 0.3477,
|
| 1815 |
+
"step": 2580
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.3570936164345788,
|
| 1819 |
+
"grad_norm": 0.01288803294301033,
|
| 1820 |
+
"learning_rate": 0.0002,
|
| 1821 |
+
"loss": 0.3472,
|
| 1822 |
+
"step": 2590
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.3584723562663725,
|
| 1826 |
+
"grad_norm": 0.2647448778152466,
|
| 1827 |
+
"learning_rate": 0.0002,
|
| 1828 |
+
"loss": 0.3499,
|
| 1829 |
+
"step": 2600
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.3598510960981663,
|
| 1833 |
+
"grad_norm": 0.5602620840072632,
|
| 1834 |
+
"learning_rate": 0.0002,
|
| 1835 |
+
"loss": 0.3478,
|
| 1836 |
+
"step": 2610
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.36122983592996,
|
| 1840 |
+
"grad_norm": 0.788970947265625,
|
| 1841 |
+
"learning_rate": 0.0002,
|
| 1842 |
+
"loss": 0.3513,
|
| 1843 |
+
"step": 2620
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.36260857576175376,
|
| 1847 |
+
"grad_norm": 0.6836252212524414,
|
| 1848 |
+
"learning_rate": 0.0002,
|
| 1849 |
+
"loss": 0.3502,
|
| 1850 |
+
"step": 2630
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.3639873155935475,
|
| 1854 |
+
"grad_norm": 0.14788776636123657,
|
| 1855 |
+
"learning_rate": 0.0002,
|
| 1856 |
+
"loss": 0.3654,
|
| 1857 |
+
"step": 2640
|
| 1858 |
+
},
|
| 1859 |
+
{
|
| 1860 |
+
"epoch": 0.36536605542534123,
|
| 1861 |
+
"grad_norm": 0.7003443837165833,
|
| 1862 |
+
"learning_rate": 0.0002,
|
| 1863 |
+
"loss": 0.3526,
|
| 1864 |
+
"step": 2650
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"epoch": 0.366744795257135,
|
| 1868 |
+
"grad_norm": 0.600309431552887,
|
| 1869 |
+
"learning_rate": 0.0002,
|
| 1870 |
+
"loss": 0.3475,
|
| 1871 |
+
"step": 2660
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 0.3681235350889287,
|
| 1875 |
+
"grad_norm": 0.10942361503839493,
|
| 1876 |
+
"learning_rate": 0.0002,
|
| 1877 |
+
"loss": 0.3467,
|
| 1878 |
+
"step": 2670
|
| 1879 |
+
},
|
| 1880 |
+
{
|
| 1881 |
+
"epoch": 0.36950227492072246,
|
| 1882 |
+
"grad_norm": 0.2913811504840851,
|
| 1883 |
+
"learning_rate": 0.0002,
|
| 1884 |
+
"loss": 0.3473,
|
| 1885 |
+
"step": 2680
|
| 1886 |
+
},
|
| 1887 |
+
{
|
| 1888 |
+
"epoch": 0.3708810147525162,
|
| 1889 |
+
"grad_norm": 0.11519110947847366,
|
| 1890 |
+
"learning_rate": 0.0002,
|
| 1891 |
+
"loss": 0.3492,
|
| 1892 |
+
"step": 2690
|
| 1893 |
+
},
|
| 1894 |
+
{
|
| 1895 |
+
"epoch": 0.37225975458430993,
|
| 1896 |
+
"grad_norm": 0.04020654037594795,
|
| 1897 |
+
"learning_rate": 0.0002,
|
| 1898 |
+
"loss": 0.3465,
|
| 1899 |
+
"step": 2700
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 0.3736384944161037,
|
| 1903 |
+
"grad_norm": 0.3286079168319702,
|
| 1904 |
+
"learning_rate": 0.0002,
|
| 1905 |
+
"loss": 0.3481,
|
| 1906 |
+
"step": 2710
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 0.3750172342478974,
|
| 1910 |
+
"grad_norm": 0.09239518642425537,
|
| 1911 |
+
"learning_rate": 0.0002,
|
| 1912 |
+
"loss": 0.3478,
|
| 1913 |
+
"step": 2720
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 0.37639597407969116,
|
| 1917 |
+
"grad_norm": 0.18499009311199188,
|
| 1918 |
+
"learning_rate": 0.0002,
|
| 1919 |
+
"loss": 0.3474,
|
| 1920 |
+
"step": 2730
|
| 1921 |
+
},
|
| 1922 |
+
{
|
| 1923 |
+
"epoch": 0.3777747139114849,
|
| 1924 |
+
"grad_norm": 0.031250640749931335,
|
| 1925 |
+
"learning_rate": 0.0002,
|
| 1926 |
+
"loss": 0.3478,
|
| 1927 |
+
"step": 2740
|
| 1928 |
+
},
|
| 1929 |
+
{
|
| 1930 |
+
"epoch": 0.37915345374327863,
|
| 1931 |
+
"grad_norm": 0.013040668331086636,
|
| 1932 |
+
"learning_rate": 0.0002,
|
| 1933 |
+
"loss": 0.3463,
|
| 1934 |
+
"step": 2750
|
| 1935 |
+
},
|
| 1936 |
+
{
|
| 1937 |
+
"epoch": 0.3805321935750724,
|
| 1938 |
+
"grad_norm": 0.11167818307876587,
|
| 1939 |
+
"learning_rate": 0.0002,
|
| 1940 |
+
"loss": 0.35,
|
| 1941 |
+
"step": 2760
|
| 1942 |
+
},
|
| 1943 |
+
{
|
| 1944 |
+
"epoch": 0.3819109334068661,
|
| 1945 |
+
"grad_norm": 0.9923171401023865,
|
| 1946 |
+
"learning_rate": 0.0002,
|
| 1947 |
+
"loss": 0.3483,
|
| 1948 |
+
"step": 2770
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 0.38328967323865987,
|
| 1952 |
+
"grad_norm": 0.7532585263252258,
|
| 1953 |
+
"learning_rate": 0.0002,
|
| 1954 |
+
"loss": 0.3493,
|
| 1955 |
+
"step": 2780
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"epoch": 0.38466841307045363,
|
| 1959 |
+
"grad_norm": 0.17266100645065308,
|
| 1960 |
+
"learning_rate": 0.0002,
|
| 1961 |
+
"loss": 0.3472,
|
| 1962 |
+
"step": 2790
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 0.38604715290224734,
|
| 1966 |
+
"grad_norm": 0.07107715308666229,
|
| 1967 |
+
"learning_rate": 0.0002,
|
| 1968 |
+
"loss": 0.3465,
|
| 1969 |
+
"step": 2800
|
| 1970 |
+
},
|
| 1971 |
+
{
|
| 1972 |
+
"epoch": 0.3874258927340411,
|
| 1973 |
+
"grad_norm": 0.05912484973669052,
|
| 1974 |
+
"learning_rate": 0.0002,
|
| 1975 |
+
"loss": 0.3454,
|
| 1976 |
+
"step": 2810
|
| 1977 |
+
},
|
| 1978 |
+
{
|
| 1979 |
+
"epoch": 0.3888046325658348,
|
| 1980 |
+
"grad_norm": 0.18973538279533386,
|
| 1981 |
+
"learning_rate": 0.0002,
|
| 1982 |
+
"loss": 0.3485,
|
| 1983 |
+
"step": 2820
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 0.39018337239762857,
|
| 1987 |
+
"grad_norm": 0.3309797942638397,
|
| 1988 |
+
"learning_rate": 0.0002,
|
| 1989 |
+
"loss": 0.3477,
|
| 1990 |
+
"step": 2830
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 0.39156211222942233,
|
| 1994 |
+
"grad_norm": 0.1095886304974556,
|
| 1995 |
+
"learning_rate": 0.0002,
|
| 1996 |
+
"loss": 0.3479,
|
| 1997 |
+
"step": 2840
|
| 1998 |
+
},
|
| 1999 |
+
{
|
| 2000 |
+
"epoch": 0.39294085206121604,
|
| 2001 |
+
"grad_norm": 0.7054705619812012,
|
| 2002 |
+
"learning_rate": 0.0002,
|
| 2003 |
+
"loss": 0.3457,
|
| 2004 |
+
"step": 2850
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 0.3943195918930098,
|
| 2008 |
+
"grad_norm": 0.35234084725379944,
|
| 2009 |
+
"learning_rate": 0.0002,
|
| 2010 |
+
"loss": 0.3519,
|
| 2011 |
+
"step": 2860
|
| 2012 |
+
},
|
| 2013 |
+
{
|
| 2014 |
+
"epoch": 0.3956983317248035,
|
| 2015 |
+
"grad_norm": 1.1833308935165405,
|
| 2016 |
+
"learning_rate": 0.0002,
|
| 2017 |
+
"loss": 0.3461,
|
| 2018 |
+
"step": 2870
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 0.39707707155659727,
|
| 2022 |
+
"grad_norm": 0.046266939491033554,
|
| 2023 |
+
"learning_rate": 0.0002,
|
| 2024 |
+
"loss": 0.3478,
|
| 2025 |
+
"step": 2880
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 0.39845581138839103,
|
| 2029 |
+
"grad_norm": 0.47695428133010864,
|
| 2030 |
+
"learning_rate": 0.0002,
|
| 2031 |
+
"loss": 0.3494,
|
| 2032 |
+
"step": 2890
|
| 2033 |
+
},
|
| 2034 |
+
{
|
| 2035 |
+
"epoch": 0.39983455122018474,
|
| 2036 |
+
"grad_norm": 0.14398415386676788,
|
| 2037 |
+
"learning_rate": 0.0002,
|
| 2038 |
+
"loss": 0.347,
|
| 2039 |
+
"step": 2900
|
| 2040 |
+
},
|
| 2041 |
+
{
|
| 2042 |
+
"epoch": 0.4012132910519785,
|
| 2043 |
+
"grad_norm": 0.0672549456357956,
|
| 2044 |
+
"learning_rate": 0.0002,
|
| 2045 |
+
"loss": 0.3446,
|
| 2046 |
+
"step": 2910
|
| 2047 |
+
},
|
| 2048 |
+
{
|
| 2049 |
+
"epoch": 0.4025920308837722,
|
| 2050 |
+
"grad_norm": 0.7201761603355408,
|
| 2051 |
+
"learning_rate": 0.0002,
|
| 2052 |
+
"loss": 0.3536,
|
| 2053 |
+
"step": 2920
|
| 2054 |
+
},
|
| 2055 |
+
{
|
| 2056 |
+
"epoch": 0.403970770715566,
|
| 2057 |
+
"grad_norm": 1.0536067485809326,
|
| 2058 |
+
"learning_rate": 0.0002,
|
| 2059 |
+
"loss": 0.3448,
|
| 2060 |
+
"step": 2930
|
| 2061 |
+
},
|
| 2062 |
+
{
|
| 2063 |
+
"epoch": 0.40534951054735974,
|
| 2064 |
+
"grad_norm": 0.4652802050113678,
|
| 2065 |
+
"learning_rate": 0.0002,
|
| 2066 |
+
"loss": 0.3572,
|
| 2067 |
+
"step": 2940
|
| 2068 |
+
},
|
| 2069 |
+
{
|
| 2070 |
+
"epoch": 0.40672825037915344,
|
| 2071 |
+
"grad_norm": 0.2714202404022217,
|
| 2072 |
+
"learning_rate": 0.0002,
|
| 2073 |
+
"loss": 0.3506,
|
| 2074 |
+
"step": 2950
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 0.4081069902109472,
|
| 2078 |
+
"grad_norm": 0.056970611214637756,
|
| 2079 |
+
"learning_rate": 0.0002,
|
| 2080 |
+
"loss": 0.3466,
|
| 2081 |
+
"step": 2960
|
| 2082 |
+
},
|
| 2083 |
+
{
|
| 2084 |
+
"epoch": 0.4094857300427409,
|
| 2085 |
+
"grad_norm": 0.08109589666128159,
|
| 2086 |
+
"learning_rate": 0.0002,
|
| 2087 |
+
"loss": 0.3478,
|
| 2088 |
+
"step": 2970
|
| 2089 |
+
},
|
| 2090 |
+
{
|
| 2091 |
+
"epoch": 0.4108644698745347,
|
| 2092 |
+
"grad_norm": 0.2987334728240967,
|
| 2093 |
+
"learning_rate": 0.0002,
|
| 2094 |
+
"loss": 0.3482,
|
| 2095 |
+
"step": 2980
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 0.41224320970632844,
|
| 2099 |
+
"grad_norm": 0.3519710898399353,
|
| 2100 |
+
"learning_rate": 0.0002,
|
| 2101 |
+
"loss": 0.351,
|
| 2102 |
+
"step": 2990
|
| 2103 |
+
},
|
| 2104 |
+
{
|
| 2105 |
+
"epoch": 0.41362194953812215,
|
| 2106 |
+
"grad_norm": 0.20754824578762054,
|
| 2107 |
+
"learning_rate": 0.0002,
|
| 2108 |
+
"loss": 0.3455,
|
| 2109 |
+
"step": 3000
|
| 2110 |
+
},
|
| 2111 |
+
{
|
| 2112 |
+
"epoch": 0.4150006893699159,
|
| 2113 |
+
"grad_norm": 0.00901414267718792,
|
| 2114 |
+
"learning_rate": 0.0002,
|
| 2115 |
+
"loss": 0.3497,
|
| 2116 |
+
"step": 3010
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.4163794292017096,
|
| 2120 |
+
"grad_norm": 0.5444782972335815,
|
| 2121 |
+
"learning_rate": 0.0002,
|
| 2122 |
+
"loss": 0.3698,
|
| 2123 |
+
"step": 3020
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.4177581690335034,
|
| 2127 |
+
"grad_norm": 1.026206374168396,
|
| 2128 |
+
"learning_rate": 0.0002,
|
| 2129 |
+
"loss": 0.3516,
|
| 2130 |
+
"step": 3030
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.41913690886529714,
|
| 2134 |
+
"grad_norm": 0.4680636525154114,
|
| 2135 |
+
"learning_rate": 0.0002,
|
| 2136 |
+
"loss": 0.3488,
|
| 2137 |
+
"step": 3040
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.42051564869709085,
|
| 2141 |
+
"grad_norm": 0.07180967926979065,
|
| 2142 |
+
"learning_rate": 0.0002,
|
| 2143 |
+
"loss": 0.3491,
|
| 2144 |
+
"step": 3050
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.4218943885288846,
|
| 2148 |
+
"grad_norm": 1.1045209169387817,
|
| 2149 |
+
"learning_rate": 0.0002,
|
| 2150 |
+
"loss": 0.3497,
|
| 2151 |
+
"step": 3060
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.4232731283606783,
|
| 2155 |
+
"grad_norm": 1.6731029748916626,
|
| 2156 |
+
"learning_rate": 0.0002,
|
| 2157 |
+
"loss": 0.3587,
|
| 2158 |
+
"step": 3070
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.4246518681924721,
|
| 2162 |
+
"grad_norm": 0.44295939803123474,
|
| 2163 |
+
"learning_rate": 0.0002,
|
| 2164 |
+
"loss": 0.348,
|
| 2165 |
+
"step": 3080
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.42603060802426584,
|
| 2169 |
+
"grad_norm": 0.011876541189849377,
|
| 2170 |
+
"learning_rate": 0.0002,
|
| 2171 |
+
"loss": 0.3471,
|
| 2172 |
+
"step": 3090
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.42740934785605955,
|
| 2176 |
+
"grad_norm": 0.5493383407592773,
|
| 2177 |
+
"learning_rate": 0.0002,
|
| 2178 |
+
"loss": 0.3474,
|
| 2179 |
+
"step": 3100
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.4287880876878533,
|
| 2183 |
+
"grad_norm": 0.013986635021865368,
|
| 2184 |
+
"learning_rate": 0.0002,
|
| 2185 |
+
"loss": 0.3467,
|
| 2186 |
+
"step": 3110
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.430166827519647,
|
| 2190 |
+
"grad_norm": 0.11136174947023392,
|
| 2191 |
+
"learning_rate": 0.0002,
|
| 2192 |
+
"loss": 0.3465,
|
| 2193 |
+
"step": 3120
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.4315455673514408,
|
| 2197 |
+
"grad_norm": 0.18628475069999695,
|
| 2198 |
+
"learning_rate": 0.0002,
|
| 2199 |
+
"loss": 0.347,
|
| 2200 |
+
"step": 3130
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.43292430718323455,
|
| 2204 |
+
"grad_norm": 0.07927969843149185,
|
| 2205 |
+
"learning_rate": 0.0002,
|
| 2206 |
+
"loss": 0.3477,
|
| 2207 |
+
"step": 3140
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.43430304701502825,
|
| 2211 |
+
"grad_norm": 0.32330620288848877,
|
| 2212 |
+
"learning_rate": 0.0002,
|
| 2213 |
+
"loss": 0.3477,
|
| 2214 |
+
"step": 3150
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.435681786846822,
|
| 2218 |
+
"grad_norm": 0.4383370578289032,
|
| 2219 |
+
"learning_rate": 0.0002,
|
| 2220 |
+
"loss": 0.3491,
|
| 2221 |
+
"step": 3160
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.4370605266786157,
|
| 2225 |
+
"grad_norm": 0.5952053070068359,
|
| 2226 |
+
"learning_rate": 0.0002,
|
| 2227 |
+
"loss": 0.3482,
|
| 2228 |
+
"step": 3170
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.4384392665104095,
|
| 2232 |
+
"grad_norm": 1.106527328491211,
|
| 2233 |
+
"learning_rate": 0.0002,
|
| 2234 |
+
"loss": 0.3569,
|
| 2235 |
+
"step": 3180
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.43981800634220325,
|
| 2239 |
+
"grad_norm": 0.6171185970306396,
|
| 2240 |
+
"learning_rate": 0.0002,
|
| 2241 |
+
"loss": 0.3474,
|
| 2242 |
+
"step": 3190
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.44119674617399696,
|
| 2246 |
+
"grad_norm": 0.16300754249095917,
|
| 2247 |
+
"learning_rate": 0.0002,
|
| 2248 |
+
"loss": 0.3474,
|
| 2249 |
+
"step": 3200
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.4425754860057907,
|
| 2253 |
+
"grad_norm": 0.03562415391206741,
|
| 2254 |
+
"learning_rate": 0.0002,
|
| 2255 |
+
"loss": 0.3474,
|
| 2256 |
+
"step": 3210
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.4439542258375844,
|
| 2260 |
+
"grad_norm": 0.30006295442581177,
|
| 2261 |
+
"learning_rate": 0.0002,
|
| 2262 |
+
"loss": 0.3475,
|
| 2263 |
+
"step": 3220
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.4453329656693782,
|
| 2267 |
+
"grad_norm": 0.4837903678417206,
|
| 2268 |
+
"learning_rate": 0.0002,
|
| 2269 |
+
"loss": 0.3618,
|
| 2270 |
+
"step": 3230
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.44671170550117195,
|
| 2274 |
+
"grad_norm": 0.4861944317817688,
|
| 2275 |
+
"learning_rate": 0.0002,
|
| 2276 |
+
"loss": 0.3536,
|
| 2277 |
+
"step": 3240
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.44809044533296566,
|
| 2281 |
+
"grad_norm": 1.048814296722412,
|
| 2282 |
+
"learning_rate": 0.0002,
|
| 2283 |
+
"loss": 0.3538,
|
| 2284 |
+
"step": 3250
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.4494691851647594,
|
| 2288 |
+
"grad_norm": 0.6691413521766663,
|
| 2289 |
+
"learning_rate": 0.0002,
|
| 2290 |
+
"loss": 0.3515,
|
| 2291 |
+
"step": 3260
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.45084792499655313,
|
| 2295 |
+
"grad_norm": 0.24432829022407532,
|
| 2296 |
+
"learning_rate": 0.0002,
|
| 2297 |
+
"loss": 0.3561,
|
| 2298 |
+
"step": 3270
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.4522266648283469,
|
| 2302 |
+
"grad_norm": 0.529619038105011,
|
| 2303 |
+
"learning_rate": 0.0002,
|
| 2304 |
+
"loss": 0.3488,
|
| 2305 |
+
"step": 3280
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.45360540466014065,
|
| 2309 |
+
"grad_norm": 0.10819733142852783,
|
| 2310 |
+
"learning_rate": 0.0002,
|
| 2311 |
+
"loss": 0.3464,
|
| 2312 |
+
"step": 3290
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.45498414449193436,
|
| 2316 |
+
"grad_norm": 0.3517175614833832,
|
| 2317 |
+
"learning_rate": 0.0002,
|
| 2318 |
+
"loss": 0.347,
|
| 2319 |
+
"step": 3300
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.4563628843237281,
|
| 2323 |
+
"grad_norm": 0.23464784026145935,
|
| 2324 |
+
"learning_rate": 0.0002,
|
| 2325 |
+
"loss": 0.3484,
|
| 2326 |
+
"step": 3310
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.45774162415552183,
|
| 2330 |
+
"grad_norm": 0.1873646080493927,
|
| 2331 |
+
"learning_rate": 0.0002,
|
| 2332 |
+
"loss": 0.3517,
|
| 2333 |
+
"step": 3320
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.4591203639873156,
|
| 2337 |
+
"grad_norm": 0.20844773948192596,
|
| 2338 |
+
"learning_rate": 0.0002,
|
| 2339 |
+
"loss": 0.352,
|
| 2340 |
+
"step": 3330
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.46049910381910936,
|
| 2344 |
+
"grad_norm": 0.45384037494659424,
|
| 2345 |
+
"learning_rate": 0.0002,
|
| 2346 |
+
"loss": 0.3492,
|
| 2347 |
+
"step": 3340
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.46187784365090306,
|
| 2351 |
+
"grad_norm": 0.32738834619522095,
|
| 2352 |
+
"learning_rate": 0.0002,
|
| 2353 |
+
"loss": 0.3509,
|
| 2354 |
+
"step": 3350
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.4632565834826968,
|
| 2358 |
+
"grad_norm": 1.4738928079605103,
|
| 2359 |
+
"learning_rate": 0.0002,
|
| 2360 |
+
"loss": 0.3483,
|
| 2361 |
+
"step": 3360
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.46463532331449053,
|
| 2365 |
+
"grad_norm": 0.5815828442573547,
|
| 2366 |
+
"learning_rate": 0.0002,
|
| 2367 |
+
"loss": 0.3509,
|
| 2368 |
+
"step": 3370
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.4660140631462843,
|
| 2372 |
+
"grad_norm": 0.6721034049987793,
|
| 2373 |
+
"learning_rate": 0.0002,
|
| 2374 |
+
"loss": 0.3467,
|
| 2375 |
+
"step": 3380
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.46739280297807806,
|
| 2379 |
+
"grad_norm": 0.8967618346214294,
|
| 2380 |
+
"learning_rate": 0.0002,
|
| 2381 |
+
"loss": 0.3548,
|
| 2382 |
+
"step": 3390
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.46877154280987177,
|
| 2386 |
+
"grad_norm": 2.0388050079345703,
|
| 2387 |
+
"learning_rate": 0.0002,
|
| 2388 |
+
"loss": 0.3612,
|
| 2389 |
+
"step": 3400
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.47015028264166553,
|
| 2393 |
+
"grad_norm": 0.2570609450340271,
|
| 2394 |
+
"learning_rate": 0.0002,
|
| 2395 |
+
"loss": 0.3489,
|
| 2396 |
+
"step": 3410
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.47152902247345924,
|
| 2400 |
+
"grad_norm": 0.6751313209533691,
|
| 2401 |
+
"learning_rate": 0.0002,
|
| 2402 |
+
"loss": 0.3486,
|
| 2403 |
+
"step": 3420
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.472907762305253,
|
| 2407 |
+
"grad_norm": 0.4083470106124878,
|
| 2408 |
+
"learning_rate": 0.0002,
|
| 2409 |
+
"loss": 0.3471,
|
| 2410 |
+
"step": 3430
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.47428650213704676,
|
| 2414 |
+
"grad_norm": 0.09502824395895004,
|
| 2415 |
+
"learning_rate": 0.0002,
|
| 2416 |
+
"loss": 0.3479,
|
| 2417 |
+
"step": 3440
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.47566524196884047,
|
| 2421 |
+
"grad_norm": 0.40624290704727173,
|
| 2422 |
+
"learning_rate": 0.0002,
|
| 2423 |
+
"loss": 0.3484,
|
| 2424 |
+
"step": 3450
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.47704398180063423,
|
| 2428 |
+
"grad_norm": 0.1163792535662651,
|
| 2429 |
+
"learning_rate": 0.0002,
|
| 2430 |
+
"loss": 0.3469,
|
| 2431 |
+
"step": 3460
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.47842272163242794,
|
| 2435 |
+
"grad_norm": 0.06055830419063568,
|
| 2436 |
+
"learning_rate": 0.0002,
|
| 2437 |
+
"loss": 0.3476,
|
| 2438 |
+
"step": 3470
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.4798014614642217,
|
| 2442 |
+
"grad_norm": 0.21893176436424255,
|
| 2443 |
+
"learning_rate": 0.0002,
|
| 2444 |
+
"loss": 0.3465,
|
| 2445 |
+
"step": 3480
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.48118020129601546,
|
| 2449 |
+
"grad_norm": 0.24376049637794495,
|
| 2450 |
+
"learning_rate": 0.0002,
|
| 2451 |
+
"loss": 0.3497,
|
| 2452 |
+
"step": 3490
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.48255894112780917,
|
| 2456 |
+
"grad_norm": 0.14530010521411896,
|
| 2457 |
+
"learning_rate": 0.0002,
|
| 2458 |
+
"loss": 0.3441,
|
| 2459 |
+
"step": 3500
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.48393768095960293,
|
| 2463 |
+
"grad_norm": 0.4784521460533142,
|
| 2464 |
+
"learning_rate": 0.0002,
|
| 2465 |
+
"loss": 0.3585,
|
| 2466 |
+
"step": 3510
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.48531642079139664,
|
| 2470 |
+
"grad_norm": 1.5072555541992188,
|
| 2471 |
+
"learning_rate": 0.0002,
|
| 2472 |
+
"loss": 0.352,
|
| 2473 |
+
"step": 3520
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.4866951606231904,
|
| 2477 |
+
"grad_norm": 1.2513431310653687,
|
| 2478 |
+
"learning_rate": 0.0002,
|
| 2479 |
+
"loss": 0.3495,
|
| 2480 |
+
"step": 3530
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.48807390045498417,
|
| 2484 |
+
"grad_norm": 1.5765403509140015,
|
| 2485 |
+
"learning_rate": 0.0002,
|
| 2486 |
+
"loss": 0.3575,
|
| 2487 |
+
"step": 3540
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.4894526402867779,
|
| 2491 |
+
"grad_norm": 2.110595703125,
|
| 2492 |
+
"learning_rate": 0.0002,
|
| 2493 |
+
"loss": 0.3464,
|
| 2494 |
+
"step": 3550
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.49083138011857164,
|
| 2498 |
+
"grad_norm": 3.3377187252044678,
|
| 2499 |
+
"learning_rate": 0.0002,
|
| 2500 |
+
"loss": 0.3518,
|
| 2501 |
+
"step": 3560
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.49221011995036534,
|
| 2505 |
+
"grad_norm": 1.1348721981048584,
|
| 2506 |
+
"learning_rate": 0.0002,
|
| 2507 |
+
"loss": 0.3461,
|
| 2508 |
+
"step": 3570
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.4935888597821591,
|
| 2512 |
+
"grad_norm": 1.115633249282837,
|
| 2513 |
+
"learning_rate": 0.0002,
|
| 2514 |
+
"loss": 0.3477,
|
| 2515 |
+
"step": 3580
|
| 2516 |
+
},
|
| 2517 |
+
{
|
| 2518 |
+
"epoch": 0.49496759961395287,
|
| 2519 |
+
"grad_norm": 0.46544066071510315,
|
| 2520 |
+
"learning_rate": 0.0002,
|
| 2521 |
+
"loss": 0.3508,
|
| 2522 |
+
"step": 3590
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 0.4963463394457466,
|
| 2526 |
+
"grad_norm": 1.0968178510665894,
|
| 2527 |
+
"learning_rate": 0.0002,
|
| 2528 |
+
"loss": 0.3491,
|
| 2529 |
+
"step": 3600
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"epoch": 0.49772507927754034,
|
| 2533 |
+
"grad_norm": 0.1590128093957901,
|
| 2534 |
+
"learning_rate": 0.0002,
|
| 2535 |
+
"loss": 0.3493,
|
| 2536 |
+
"step": 3610
|
| 2537 |
+
},
|
| 2538 |
+
{
|
| 2539 |
+
"epoch": 0.49910381910933405,
|
| 2540 |
+
"grad_norm": 0.0618724524974823,
|
| 2541 |
+
"learning_rate": 0.0002,
|
| 2542 |
+
"loss": 0.3467,
|
| 2543 |
+
"step": 3620
|
| 2544 |
+
},
|
| 2545 |
+
{
|
| 2546 |
+
"epoch": 0.5004825589411278,
|
| 2547 |
+
"grad_norm": 0.038633331656455994,
|
| 2548 |
+
"learning_rate": 0.0002,
|
| 2549 |
+
"loss": 0.347,
|
| 2550 |
+
"step": 3630
|
| 2551 |
+
},
|
| 2552 |
+
{
|
| 2553 |
+
"epoch": 0.5018612987729215,
|
| 2554 |
+
"grad_norm": 0.08056730031967163,
|
| 2555 |
+
"learning_rate": 0.0002,
|
| 2556 |
+
"loss": 0.3469,
|
| 2557 |
+
"step": 3640
|
| 2558 |
+
},
|
| 2559 |
+
{
|
| 2560 |
+
"epoch": 0.5032400386047153,
|
| 2561 |
+
"grad_norm": 0.07540078461170197,
|
| 2562 |
+
"learning_rate": 0.0002,
|
| 2563 |
+
"loss": 0.347,
|
| 2564 |
+
"step": 3650
|
| 2565 |
+
},
|
| 2566 |
+
{
|
| 2567 |
+
"epoch": 0.504618778436509,
|
| 2568 |
+
"grad_norm": 0.0971425250172615,
|
| 2569 |
+
"learning_rate": 0.0002,
|
| 2570 |
+
"loss": 0.349,
|
| 2571 |
+
"step": 3660
|
| 2572 |
+
},
|
| 2573 |
+
{
|
| 2574 |
+
"epoch": 0.5059975182683027,
|
| 2575 |
+
"grad_norm": 0.1605909764766693,
|
| 2576 |
+
"learning_rate": 0.0002,
|
| 2577 |
+
"loss": 0.3472,
|
| 2578 |
+
"step": 3670
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 0.5073762581000966,
|
| 2582 |
+
"grad_norm": 0.2239840030670166,
|
| 2583 |
+
"learning_rate": 0.0002,
|
| 2584 |
+
"loss": 0.3489,
|
| 2585 |
+
"step": 3680
|
| 2586 |
+
},
|
| 2587 |
+
{
|
| 2588 |
+
"epoch": 0.5087549979318903,
|
| 2589 |
+
"grad_norm": 0.25974148511886597,
|
| 2590 |
+
"learning_rate": 0.0002,
|
| 2591 |
+
"loss": 0.3478,
|
| 2592 |
+
"step": 3690
|
| 2593 |
+
},
|
| 2594 |
+
{
|
| 2595 |
+
"epoch": 0.510133737763684,
|
| 2596 |
+
"grad_norm": 0.7621527314186096,
|
| 2597 |
+
"learning_rate": 0.0002,
|
| 2598 |
+
"loss": 0.3501,
|
| 2599 |
+
"step": 3700
|
| 2600 |
+
},
|
| 2601 |
+
{
|
| 2602 |
+
"epoch": 0.5115124775954777,
|
| 2603 |
+
"grad_norm": 0.6531065702438354,
|
| 2604 |
+
"learning_rate": 0.0002,
|
| 2605 |
+
"loss": 0.3473,
|
| 2606 |
+
"step": 3710
|
| 2607 |
+
},
|
| 2608 |
+
{
|
| 2609 |
+
"epoch": 0.5128912174272715,
|
| 2610 |
+
"grad_norm": 0.0937981903553009,
|
| 2611 |
+
"learning_rate": 0.0002,
|
| 2612 |
+
"loss": 0.3494,
|
| 2613 |
+
"step": 3720
|
| 2614 |
+
},
|
| 2615 |
+
{
|
| 2616 |
+
"epoch": 0.5142699572590652,
|
| 2617 |
+
"grad_norm": 0.353502094745636,
|
| 2618 |
+
"learning_rate": 0.0002,
|
| 2619 |
+
"loss": 0.3487,
|
| 2620 |
+
"step": 3730
|
| 2621 |
+
},
|
| 2622 |
+
{
|
| 2623 |
+
"epoch": 0.5156486970908589,
|
| 2624 |
+
"grad_norm": 0.5151197910308838,
|
| 2625 |
+
"learning_rate": 0.0002,
|
| 2626 |
+
"loss": 0.3485,
|
| 2627 |
+
"step": 3740
|
| 2628 |
+
},
|
| 2629 |
+
{
|
| 2630 |
+
"epoch": 0.5170274369226527,
|
| 2631 |
+
"grad_norm": 0.15747584402561188,
|
| 2632 |
+
"learning_rate": 0.0002,
|
| 2633 |
+
"loss": 0.3473,
|
| 2634 |
+
"step": 3750
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 0.5184061767544464,
|
| 2638 |
+
"grad_norm": 0.18814824521541595,
|
| 2639 |
+
"learning_rate": 0.0002,
|
| 2640 |
+
"loss": 0.3474,
|
| 2641 |
+
"step": 3760
|
| 2642 |
+
},
|
| 2643 |
+
{
|
| 2644 |
+
"epoch": 0.5197849165862402,
|
| 2645 |
+
"grad_norm": 0.040331218391656876,
|
| 2646 |
+
"learning_rate": 0.0002,
|
| 2647 |
+
"loss": 0.3474,
|
| 2648 |
+
"step": 3770
|
| 2649 |
+
},
|
| 2650 |
+
{
|
| 2651 |
+
"epoch": 0.521163656418034,
|
| 2652 |
+
"grad_norm": 0.21510355174541473,
|
| 2653 |
+
"learning_rate": 0.0002,
|
| 2654 |
+
"loss": 0.3471,
|
| 2655 |
+
"step": 3780
|
| 2656 |
+
},
|
| 2657 |
+
{
|
| 2658 |
+
"epoch": 0.5225423962498277,
|
| 2659 |
+
"grad_norm": 0.12755675613880157,
|
| 2660 |
+
"learning_rate": 0.0002,
|
| 2661 |
+
"loss": 0.3477,
|
| 2662 |
+
"step": 3790
|
| 2663 |
+
},
|
| 2664 |
+
{
|
| 2665 |
+
"epoch": 0.5239211360816214,
|
| 2666 |
+
"grad_norm": 0.5592456459999084,
|
| 2667 |
+
"learning_rate": 0.0002,
|
| 2668 |
+
"loss": 0.3509,
|
| 2669 |
+
"step": 3800
|
| 2670 |
+
},
|
| 2671 |
+
{
|
| 2672 |
+
"epoch": 0.5252998759134151,
|
| 2673 |
+
"grad_norm": 0.30668896436691284,
|
| 2674 |
+
"learning_rate": 0.0002,
|
| 2675 |
+
"loss": 0.3475,
|
| 2676 |
+
"step": 3810
|
| 2677 |
+
},
|
| 2678 |
+
{
|
| 2679 |
+
"epoch": 0.5266786157452089,
|
| 2680 |
+
"grad_norm": 0.12264347821474075,
|
| 2681 |
+
"learning_rate": 0.0002,
|
| 2682 |
+
"loss": 0.3691,
|
| 2683 |
+
"step": 3820
|
| 2684 |
+
},
|
| 2685 |
+
{
|
| 2686 |
+
"epoch": 0.5280573555770026,
|
| 2687 |
+
"grad_norm": 0.21281813085079193,
|
| 2688 |
+
"learning_rate": 0.0002,
|
| 2689 |
+
"loss": 0.3493,
|
| 2690 |
+
"step": 3830
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 0.5294360954087963,
|
| 2694 |
+
"grad_norm": 0.547156572341919,
|
| 2695 |
+
"learning_rate": 0.0002,
|
| 2696 |
+
"loss": 0.3485,
|
| 2697 |
+
"step": 3840
|
| 2698 |
+
},
|
| 2699 |
+
{
|
| 2700 |
+
"epoch": 0.5308148352405901,
|
| 2701 |
+
"grad_norm": 0.2829332947731018,
|
| 2702 |
+
"learning_rate": 0.0002,
|
| 2703 |
+
"loss": 0.3459,
|
| 2704 |
+
"step": 3850
|
| 2705 |
+
},
|
| 2706 |
+
{
|
| 2707 |
+
"epoch": 0.5321935750723839,
|
| 2708 |
+
"grad_norm": 0.6659385561943054,
|
| 2709 |
+
"learning_rate": 0.0002,
|
| 2710 |
+
"loss": 0.3492,
|
| 2711 |
+
"step": 3860
|
| 2712 |
+
},
|
| 2713 |
+
{
|
| 2714 |
+
"epoch": 0.5335723149041776,
|
| 2715 |
+
"grad_norm": 0.9354788064956665,
|
| 2716 |
+
"learning_rate": 0.0002,
|
| 2717 |
+
"loss": 0.3501,
|
| 2718 |
+
"step": 3870
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.5349510547359714,
|
| 2722 |
+
"grad_norm": 0.64557945728302,
|
| 2723 |
+
"learning_rate": 0.0002,
|
| 2724 |
+
"loss": 0.3544,
|
| 2725 |
+
"step": 3880
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.5363297945677651,
|
| 2729 |
+
"grad_norm": 0.07203350216150284,
|
| 2730 |
+
"learning_rate": 0.0002,
|
| 2731 |
+
"loss": 0.3485,
|
| 2732 |
+
"step": 3890
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.5377085343995588,
|
| 2736 |
+
"grad_norm": 0.8220388293266296,
|
| 2737 |
+
"learning_rate": 0.0002,
|
| 2738 |
+
"loss": 0.3472,
|
| 2739 |
+
"step": 3900
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.5390872742313525,
|
| 2743 |
+
"grad_norm": 0.2928883135318756,
|
| 2744 |
+
"learning_rate": 0.0002,
|
| 2745 |
+
"loss": 0.3549,
|
| 2746 |
+
"step": 3910
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.5404660140631463,
|
| 2750 |
+
"grad_norm": 0.14233669638633728,
|
| 2751 |
+
"learning_rate": 0.0002,
|
| 2752 |
+
"loss": 0.3465,
|
| 2753 |
+
"step": 3920
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.54184475389494,
|
| 2757 |
+
"grad_norm": 0.3891246020793915,
|
| 2758 |
+
"learning_rate": 0.0002,
|
| 2759 |
+
"loss": 0.3463,
|
| 2760 |
+
"step": 3930
|
| 2761 |
+
},
|
| 2762 |
+
{
|
| 2763 |
+
"epoch": 0.5432234937267337,
|
| 2764 |
+
"grad_norm": 1.5544075965881348,
|
| 2765 |
+
"learning_rate": 0.0002,
|
| 2766 |
+
"loss": 0.357,
|
| 2767 |
+
"step": 3940
|
| 2768 |
+
},
|
| 2769 |
+
{
|
| 2770 |
+
"epoch": 0.5446022335585275,
|
| 2771 |
+
"grad_norm": 0.28166115283966064,
|
| 2772 |
+
"learning_rate": 0.0002,
|
| 2773 |
+
"loss": 0.351,
|
| 2774 |
+
"step": 3950
|
| 2775 |
+
},
|
| 2776 |
+
{
|
| 2777 |
+
"epoch": 0.5459809733903213,
|
| 2778 |
+
"grad_norm": 0.4519428014755249,
|
| 2779 |
+
"learning_rate": 0.0002,
|
| 2780 |
+
"loss": 0.3523,
|
| 2781 |
+
"step": 3960
|
| 2782 |
+
},
|
| 2783 |
+
{
|
| 2784 |
+
"epoch": 0.547359713222115,
|
| 2785 |
+
"grad_norm": 0.05194510146975517,
|
| 2786 |
+
"learning_rate": 0.0002,
|
| 2787 |
+
"loss": 0.3518,
|
| 2788 |
+
"step": 3970
|
| 2789 |
+
},
|
| 2790 |
+
{
|
| 2791 |
+
"epoch": 0.5487384530539088,
|
| 2792 |
+
"grad_norm": 0.5450552105903625,
|
| 2793 |
+
"learning_rate": 0.0002,
|
| 2794 |
+
"loss": 0.3492,
|
| 2795 |
+
"step": 3980
|
| 2796 |
+
},
|
| 2797 |
+
{
|
| 2798 |
+
"epoch": 0.5501171928857025,
|
| 2799 |
+
"grad_norm": 0.24036559462547302,
|
| 2800 |
+
"learning_rate": 0.0002,
|
| 2801 |
+
"loss": 0.3473,
|
| 2802 |
+
"step": 3990
|
| 2803 |
+
},
|
| 2804 |
+
{
|
| 2805 |
+
"epoch": 0.5514959327174962,
|
| 2806 |
+
"grad_norm": 0.15362729132175446,
|
| 2807 |
+
"learning_rate": 0.0002,
|
| 2808 |
+
"loss": 0.3471,
|
| 2809 |
+
"step": 4000
|
| 2810 |
+
}
|
| 2811 |
+
],
|
| 2812 |
+
"logging_steps": 10,
|
| 2813 |
+
"max_steps": 100000,
|
| 2814 |
+
"num_input_tokens_seen": 0,
|
| 2815 |
+
"num_train_epochs": 14,
|
| 2816 |
+
"save_steps": 1000,
|
| 2817 |
+
"stateful_callbacks": {
|
| 2818 |
+
"TrainerControl": {
|
| 2819 |
+
"args": {
|
| 2820 |
+
"should_epoch_stop": false,
|
| 2821 |
+
"should_evaluate": false,
|
| 2822 |
+
"should_log": false,
|
| 2823 |
+
"should_save": true,
|
| 2824 |
+
"should_training_stop": false
|
| 2825 |
+
},
|
| 2826 |
+
"attributes": {}
|
| 2827 |
+
}
|
| 2828 |
+
},
|
| 2829 |
+
"total_flos": 8.182773334612378e+18,
|
| 2830 |
+
"train_batch_size": 16,
|
| 2831 |
+
"trial_name": null,
|
| 2832 |
+
"trial_params": null
|
| 2833 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4261b3dcd8c59f12f210ebb5db510f5460754a7eb15daa19a88b8813bb250abd
|
| 3 |
+
size 7224
|