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 +1433 -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 sha256:0d2d983be819e141d612f328ed8d7cee3f4cfa74b41beca98c5ae13731abb89a
|
| 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 sha256:5f097e1afe0dd8c67ad3c8f38696709b8494274193373754e8955a3dff639673
|
| 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 sha256:164ad263cf59cc624144a74c59cd955e51d010e0528a883568b5d16baa44d608
|
| 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 +1,1433 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2757479663587481,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 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 |
+
"logging_steps": 10,
|
| 1413 |
+
"max_steps": 100000,
|
| 1414 |
+
"num_input_tokens_seen": 0,
|
| 1415 |
+
"num_train_epochs": 14,
|
| 1416 |
+
"save_steps": 1000,
|
| 1417 |
+
"stateful_callbacks": {
|
| 1418 |
+
"TrainerControl": {
|
| 1419 |
+
"args": {
|
| 1420 |
+
"should_epoch_stop": false,
|
| 1421 |
+
"should_evaluate": false,
|
| 1422 |
+
"should_log": false,
|
| 1423 |
+
"should_save": true,
|
| 1424 |
+
"should_training_stop": false
|
| 1425 |
+
},
|
| 1426 |
+
"attributes": {}
|
| 1427 |
+
}
|
| 1428 |
+
},
|
| 1429 |
+
"total_flos": 4.09149951218339e+18,
|
| 1430 |
+
"train_batch_size": 16,
|
| 1431 |
+
"trial_name": null,
|
| 1432 |
+
"trial_params": null
|
| 1433 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4261b3dcd8c59f12f210ebb5db510f5460754a7eb15daa19a88b8813bb250abd
|
| 3 |
+
size 7224
|