David Roy Nelson commited on
Upload 11 files
Browse files- README.md +24 -3
- adapter_config.json +23 -0
- adapter_model.safetensors +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_config.json +215 -0
- trainer_state.json +1608 -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 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "state-spaces/mamba-2.8b-hf",
|
| 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 |
+
"x_proj",
|
| 18 |
+
"in_proj",
|
| 19 |
+
"dt_proj",
|
| 20 |
+
"out_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7e2362510bcb162a7a045b4ab043b8987ed34476e3c21692f1814f965acf1777
|
| 3 |
+
size 509153456
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b10d4855a7b205966d2a568c3bd650b5a4e9ed877edb53e3dd900e85584eef3a
|
| 3 |
+
size 1018480722
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3af285a76b3712b289951955fed90d44c8f005858287a3848975dedb5ec20e4f
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa6ae9b63d734aff1f04d6a5fbb455d3c71c36714eec1bf556549db996fddb67
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"unk_token": {
|
| 24 |
+
"content": "<|endoftext|>",
|
| 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_config.json
ADDED
|
@@ -0,0 +1,215 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": false,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"0": {
|
| 7 |
+
"content": "<|endoftext|>",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": false,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": true
|
| 13 |
+
},
|
| 14 |
+
"1": {
|
| 15 |
+
"content": "<|padding|>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": true
|
| 21 |
+
},
|
| 22 |
+
"50254": {
|
| 23 |
+
"content": " ",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"50255": {
|
| 31 |
+
"content": " ",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"50256": {
|
| 39 |
+
"content": " ",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"50257": {
|
| 47 |
+
"content": " ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"50258": {
|
| 55 |
+
"content": " ",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"50259": {
|
| 63 |
+
"content": " ",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"50260": {
|
| 71 |
+
"content": " ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"50261": {
|
| 79 |
+
"content": " ",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"50262": {
|
| 87 |
+
"content": " ",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"50263": {
|
| 95 |
+
"content": " ",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"50264": {
|
| 103 |
+
"content": " ",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"50265": {
|
| 111 |
+
"content": " ",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": false
|
| 117 |
+
},
|
| 118 |
+
"50266": {
|
| 119 |
+
"content": " ",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": false
|
| 125 |
+
},
|
| 126 |
+
"50267": {
|
| 127 |
+
"content": " ",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"50268": {
|
| 135 |
+
"content": " ",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"50269": {
|
| 143 |
+
"content": " ",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"50270": {
|
| 151 |
+
"content": " ",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"50271": {
|
| 159 |
+
"content": " ",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"50272": {
|
| 167 |
+
"content": " ",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"50273": {
|
| 175 |
+
"content": " ",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
},
|
| 182 |
+
"50274": {
|
| 183 |
+
"content": " ",
|
| 184 |
+
"lstrip": false,
|
| 185 |
+
"normalized": true,
|
| 186 |
+
"rstrip": false,
|
| 187 |
+
"single_word": false,
|
| 188 |
+
"special": false
|
| 189 |
+
},
|
| 190 |
+
"50275": {
|
| 191 |
+
"content": " ",
|
| 192 |
+
"lstrip": false,
|
| 193 |
+
"normalized": true,
|
| 194 |
+
"rstrip": false,
|
| 195 |
+
"single_word": false,
|
| 196 |
+
"special": false
|
| 197 |
+
},
|
| 198 |
+
"50276": {
|
| 199 |
+
"content": " ",
|
| 200 |
+
"lstrip": false,
|
| 201 |
+
"normalized": true,
|
| 202 |
+
"rstrip": false,
|
| 203 |
+
"single_word": false,
|
| 204 |
+
"special": false
|
| 205 |
+
}
|
| 206 |
+
},
|
| 207 |
+
"bos_token": "<|endoftext|>",
|
| 208 |
+
"clean_up_tokenization_spaces": true,
|
| 209 |
+
"eos_token": "<|endoftext|>",
|
| 210 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 211 |
+
"pad_token": "<|endoftext|>",
|
| 212 |
+
"padding_side": "right",
|
| 213 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
| 214 |
+
"unk_token": "<|endoftext|>"
|
| 215 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1608 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.004092034400369192,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.818681955719641e-05,
|
| 13 |
+
"grad_norm": 1.608859896659851,
|
| 14 |
+
"learning_rate": 0.0002,
|
| 15 |
+
"loss": 3.3372,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 3.637363911439282e-05,
|
| 20 |
+
"grad_norm": 0.9594001770019531,
|
| 21 |
+
"learning_rate": 0.0002,
|
| 22 |
+
"loss": 0.1895,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 5.4560458671589234e-05,
|
| 27 |
+
"grad_norm": 0.7858404517173767,
|
| 28 |
+
"learning_rate": 0.0002,
|
| 29 |
+
"loss": 0.1819,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 7.274727822878565e-05,
|
| 34 |
+
"grad_norm": 0.05236278474330902,
|
| 35 |
+
"learning_rate": 0.0002,
|
| 36 |
+
"loss": 0.0967,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 9.093409778598205e-05,
|
| 41 |
+
"grad_norm": 0.00239331996999681,
|
| 42 |
+
"learning_rate": 0.0002,
|
| 43 |
+
"loss": 0.0001,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.00010912091734317847,
|
| 48 |
+
"grad_norm": 0.6015797853469849,
|
| 49 |
+
"learning_rate": 0.0002,
|
| 50 |
+
"loss": 0.9137,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.00012730773690037487,
|
| 55 |
+
"grad_norm": 0.2916141152381897,
|
| 56 |
+
"learning_rate": 0.0002,
|
| 57 |
+
"loss": 0.1584,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0001454945564575713,
|
| 62 |
+
"grad_norm": 0.22034427523612976,
|
| 63 |
+
"learning_rate": 0.0002,
|
| 64 |
+
"loss": 0.1212,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.0001636813760147677,
|
| 69 |
+
"grad_norm": 0.05342680215835571,
|
| 70 |
+
"learning_rate": 0.0002,
|
| 71 |
+
"loss": 0.0933,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0001818681955719641,
|
| 76 |
+
"grad_norm": 0.0009122246992774308,
|
| 77 |
+
"learning_rate": 0.0002,
|
| 78 |
+
"loss": 0.0002,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.00020005501512916052,
|
| 83 |
+
"grad_norm": 0.30845287442207336,
|
| 84 |
+
"learning_rate": 0.0002,
|
| 85 |
+
"loss": 0.8141,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.00021824183468635694,
|
| 90 |
+
"grad_norm": 0.1849660873413086,
|
| 91 |
+
"learning_rate": 0.0002,
|
| 92 |
+
"loss": 0.1604,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.00023642865424355333,
|
| 97 |
+
"grad_norm": 0.09605516493320465,
|
| 98 |
+
"learning_rate": 0.0002,
|
| 99 |
+
"loss": 0.1163,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.00025461547380074975,
|
| 104 |
+
"grad_norm": 0.4438878893852234,
|
| 105 |
+
"learning_rate": 0.0002,
|
| 106 |
+
"loss": 0.1043,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.00027280229335794617,
|
| 111 |
+
"grad_norm": 0.0012718827929347754,
|
| 112 |
+
"learning_rate": 0.0002,
|
| 113 |
+
"loss": 0.0018,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0002909891129151426,
|
| 118 |
+
"grad_norm": 0.19092628359794617,
|
| 119 |
+
"learning_rate": 0.0002,
|
| 120 |
+
"loss": 0.6226,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.000309175932472339,
|
| 125 |
+
"grad_norm": 0.04102358967065811,
|
| 126 |
+
"learning_rate": 0.0002,
|
| 127 |
+
"loss": 0.1575,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.0003273627520295354,
|
| 132 |
+
"grad_norm": 0.06057624891400337,
|
| 133 |
+
"learning_rate": 0.0002,
|
| 134 |
+
"loss": 0.1119,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.0003455495715867318,
|
| 139 |
+
"grad_norm": 0.13942261040210724,
|
| 140 |
+
"learning_rate": 0.0002,
|
| 141 |
+
"loss": 0.0781,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.0003637363911439282,
|
| 146 |
+
"grad_norm": 0.005650315433740616,
|
| 147 |
+
"learning_rate": 0.0002,
|
| 148 |
+
"loss": 0.0013,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.0003819232107011246,
|
| 153 |
+
"grad_norm": 0.6245204210281372,
|
| 154 |
+
"learning_rate": 0.0002,
|
| 155 |
+
"loss": 0.7091,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.00040011003025832104,
|
| 160 |
+
"grad_norm": 0.058550119400024414,
|
| 161 |
+
"learning_rate": 0.0002,
|
| 162 |
+
"loss": 0.1411,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.00041829684981551746,
|
| 167 |
+
"grad_norm": 0.08625461906194687,
|
| 168 |
+
"learning_rate": 0.0002,
|
| 169 |
+
"loss": 0.1138,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.0004364836693727139,
|
| 174 |
+
"grad_norm": 0.06455521285533905,
|
| 175 |
+
"learning_rate": 0.0002,
|
| 176 |
+
"loss": 0.0805,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.0004546704889299103,
|
| 181 |
+
"grad_norm": 0.0020822149235755205,
|
| 182 |
+
"learning_rate": 0.0002,
|
| 183 |
+
"loss": 0.0013,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.00047285730848710666,
|
| 188 |
+
"grad_norm": 0.1977258324623108,
|
| 189 |
+
"learning_rate": 0.0002,
|
| 190 |
+
"loss": 0.5558,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.0004910441280443031,
|
| 195 |
+
"grad_norm": 0.20794034004211426,
|
| 196 |
+
"learning_rate": 0.0002,
|
| 197 |
+
"loss": 0.1263,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.0005092309476014995,
|
| 202 |
+
"grad_norm": 0.08760973066091537,
|
| 203 |
+
"learning_rate": 0.0002,
|
| 204 |
+
"loss": 0.1118,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.0005274177671586959,
|
| 209 |
+
"grad_norm": 0.299059122800827,
|
| 210 |
+
"learning_rate": 0.0002,
|
| 211 |
+
"loss": 0.0804,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.0005456045867158923,
|
| 216 |
+
"grad_norm": 0.002420844743028283,
|
| 217 |
+
"learning_rate": 0.0002,
|
| 218 |
+
"loss": 0.0022,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.0005637914062730887,
|
| 223 |
+
"grad_norm": 2.2061026096343994,
|
| 224 |
+
"learning_rate": 0.0002,
|
| 225 |
+
"loss": 0.5624,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.0005819782258302852,
|
| 230 |
+
"grad_norm": 0.7011717557907104,
|
| 231 |
+
"learning_rate": 0.0002,
|
| 232 |
+
"loss": 0.1177,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.0006001650453874816,
|
| 237 |
+
"grad_norm": 0.37657421827316284,
|
| 238 |
+
"learning_rate": 0.0002,
|
| 239 |
+
"loss": 0.1005,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.000618351864944678,
|
| 244 |
+
"grad_norm": 0.048011403530836105,
|
| 245 |
+
"learning_rate": 0.0002,
|
| 246 |
+
"loss": 0.079,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.0006365386845018744,
|
| 251 |
+
"grad_norm": 0.002076848642900586,
|
| 252 |
+
"learning_rate": 0.0002,
|
| 253 |
+
"loss": 0.0018,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.0006547255040590708,
|
| 258 |
+
"grad_norm": 0.721218466758728,
|
| 259 |
+
"learning_rate": 0.0002,
|
| 260 |
+
"loss": 0.5647,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.0006729123236162671,
|
| 265 |
+
"grad_norm": 0.09965512156486511,
|
| 266 |
+
"learning_rate": 0.0002,
|
| 267 |
+
"loss": 0.1403,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.0006910991431734636,
|
| 272 |
+
"grad_norm": 0.21733985841274261,
|
| 273 |
+
"learning_rate": 0.0002,
|
| 274 |
+
"loss": 0.1024,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.00070928596273066,
|
| 279 |
+
"grad_norm": 0.003134253202006221,
|
| 280 |
+
"learning_rate": 0.0002,
|
| 281 |
+
"loss": 0.0707,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.0007274727822878564,
|
| 286 |
+
"grad_norm": 0.0011866611894220114,
|
| 287 |
+
"learning_rate": 0.0002,
|
| 288 |
+
"loss": 0.0003,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.0007456596018450528,
|
| 293 |
+
"grad_norm": 0.37573525309562683,
|
| 294 |
+
"learning_rate": 0.0002,
|
| 295 |
+
"loss": 0.6122,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.0007638464214022492,
|
| 300 |
+
"grad_norm": 0.34029653668403625,
|
| 301 |
+
"learning_rate": 0.0002,
|
| 302 |
+
"loss": 0.1149,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.0007820332409594457,
|
| 307 |
+
"grad_norm": 0.35701191425323486,
|
| 308 |
+
"learning_rate": 0.0002,
|
| 309 |
+
"loss": 0.0972,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.0008002200605166421,
|
| 314 |
+
"grad_norm": 0.06324547529220581,
|
| 315 |
+
"learning_rate": 0.0002,
|
| 316 |
+
"loss": 0.0722,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.0008184068800738385,
|
| 321 |
+
"grad_norm": 0.0011920438846573234,
|
| 322 |
+
"learning_rate": 0.0002,
|
| 323 |
+
"loss": 0.0011,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.0008365936996310349,
|
| 328 |
+
"grad_norm": 0.861393392086029,
|
| 329 |
+
"learning_rate": 0.0002,
|
| 330 |
+
"loss": 0.4433,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.0008547805191882313,
|
| 335 |
+
"grad_norm": 0.16104361414909363,
|
| 336 |
+
"learning_rate": 0.0002,
|
| 337 |
+
"loss": 0.1176,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.0008729673387454278,
|
| 342 |
+
"grad_norm": 0.28712376952171326,
|
| 343 |
+
"learning_rate": 0.0002,
|
| 344 |
+
"loss": 0.0983,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.0008911541583026242,
|
| 349 |
+
"grad_norm": 0.07980292290449142,
|
| 350 |
+
"learning_rate": 0.0002,
|
| 351 |
+
"loss": 0.0721,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.0009093409778598206,
|
| 356 |
+
"grad_norm": 0.0018368292367085814,
|
| 357 |
+
"learning_rate": 0.0002,
|
| 358 |
+
"loss": 0.0019,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.000927527797417017,
|
| 363 |
+
"grad_norm": 0.05152284353971481,
|
| 364 |
+
"learning_rate": 0.0002,
|
| 365 |
+
"loss": 0.2823,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.0009457146169742133,
|
| 370 |
+
"grad_norm": 0.04693318158388138,
|
| 371 |
+
"learning_rate": 0.0002,
|
| 372 |
+
"loss": 0.1179,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.0009639014365314097,
|
| 377 |
+
"grad_norm": 0.10586889833211899,
|
| 378 |
+
"learning_rate": 0.0002,
|
| 379 |
+
"loss": 0.1094,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.0009820882560886062,
|
| 384 |
+
"grad_norm": 0.006325385998934507,
|
| 385 |
+
"learning_rate": 0.0002,
|
| 386 |
+
"loss": 0.0706,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.0010002750756458027,
|
| 391 |
+
"grad_norm": 4.665973028750159e-05,
|
| 392 |
+
"learning_rate": 0.0002,
|
| 393 |
+
"loss": 0.0002,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.001018461895202999,
|
| 398 |
+
"grad_norm": 0.293944776058197,
|
| 399 |
+
"learning_rate": 0.0002,
|
| 400 |
+
"loss": 0.732,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.0010366487147601955,
|
| 405 |
+
"grad_norm": 0.22614754736423492,
|
| 406 |
+
"learning_rate": 0.0002,
|
| 407 |
+
"loss": 0.1226,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.0010548355343173918,
|
| 412 |
+
"grad_norm": 0.10801248252391815,
|
| 413 |
+
"learning_rate": 0.0002,
|
| 414 |
+
"loss": 0.1065,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.0010730223538745881,
|
| 419 |
+
"grad_norm": 0.04501640051603317,
|
| 420 |
+
"learning_rate": 0.0002,
|
| 421 |
+
"loss": 0.0759,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.0010912091734317847,
|
| 426 |
+
"grad_norm": 0.00014656950952485204,
|
| 427 |
+
"learning_rate": 0.0002,
|
| 428 |
+
"loss": 0.0001,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.001109395992988981,
|
| 433 |
+
"grad_norm": 0.2490423321723938,
|
| 434 |
+
"learning_rate": 0.0002,
|
| 435 |
+
"loss": 0.4868,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.0011275828125461775,
|
| 440 |
+
"grad_norm": 0.026224857196211815,
|
| 441 |
+
"learning_rate": 0.0002,
|
| 442 |
+
"loss": 0.1242,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.0011457696321033738,
|
| 447 |
+
"grad_norm": 0.11845973134040833,
|
| 448 |
+
"learning_rate": 0.0002,
|
| 449 |
+
"loss": 0.1153,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.0011639564516605703,
|
| 454 |
+
"grad_norm": 0.8349707722663879,
|
| 455 |
+
"learning_rate": 0.0002,
|
| 456 |
+
"loss": 0.1229,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.0011821432712177666,
|
| 461 |
+
"grad_norm": 0.00733955716714263,
|
| 462 |
+
"learning_rate": 0.0002,
|
| 463 |
+
"loss": 0.0016,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.0012003300907749632,
|
| 468 |
+
"grad_norm": 0.3534531891345978,
|
| 469 |
+
"learning_rate": 0.0002,
|
| 470 |
+
"loss": 0.4961,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.0012185169103321595,
|
| 475 |
+
"grad_norm": 0.3938736915588379,
|
| 476 |
+
"learning_rate": 0.0002,
|
| 477 |
+
"loss": 0.126,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.001236703729889356,
|
| 482 |
+
"grad_norm": 0.16779105365276337,
|
| 483 |
+
"learning_rate": 0.0002,
|
| 484 |
+
"loss": 0.1217,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.0012548905494465523,
|
| 489 |
+
"grad_norm": 0.6998353600502014,
|
| 490 |
+
"learning_rate": 0.0002,
|
| 491 |
+
"loss": 0.1171,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.0012730773690037488,
|
| 496 |
+
"grad_norm": 0.0005113715888001025,
|
| 497 |
+
"learning_rate": 0.0002,
|
| 498 |
+
"loss": 0.0143,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.0012912641885609452,
|
| 503 |
+
"grad_norm": 0.4034057557582855,
|
| 504 |
+
"learning_rate": 0.0002,
|
| 505 |
+
"loss": 0.6274,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.0013094510081181417,
|
| 510 |
+
"grad_norm": 0.08985241502523422,
|
| 511 |
+
"learning_rate": 0.0002,
|
| 512 |
+
"loss": 0.1295,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.001327637827675338,
|
| 517 |
+
"grad_norm": 0.20418916642665863,
|
| 518 |
+
"learning_rate": 0.0002,
|
| 519 |
+
"loss": 0.1234,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.0013458246472325343,
|
| 524 |
+
"grad_norm": 1.0206961631774902,
|
| 525 |
+
"learning_rate": 0.0002,
|
| 526 |
+
"loss": 0.1107,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.0013640114667897308,
|
| 531 |
+
"grad_norm": 0.0008244478958658874,
|
| 532 |
+
"learning_rate": 0.0002,
|
| 533 |
+
"loss": 0.0087,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.0013821982863469271,
|
| 538 |
+
"grad_norm": 3.696362018585205,
|
| 539 |
+
"learning_rate": 0.0002,
|
| 540 |
+
"loss": 0.9078,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.0014003851059041237,
|
| 545 |
+
"grad_norm": 0.8782555460929871,
|
| 546 |
+
"learning_rate": 0.0002,
|
| 547 |
+
"loss": 0.1732,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.00141857192546132,
|
| 552 |
+
"grad_norm": 0.18350496888160706,
|
| 553 |
+
"learning_rate": 0.0002,
|
| 554 |
+
"loss": 0.1205,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.0014367587450185165,
|
| 559 |
+
"grad_norm": 0.634567141532898,
|
| 560 |
+
"learning_rate": 0.0002,
|
| 561 |
+
"loss": 0.0997,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.0014549455645757128,
|
| 566 |
+
"grad_norm": 0.01041293516755104,
|
| 567 |
+
"learning_rate": 0.0002,
|
| 568 |
+
"loss": 0.0065,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.0014731323841329093,
|
| 573 |
+
"grad_norm": 3.0739810466766357,
|
| 574 |
+
"learning_rate": 0.0002,
|
| 575 |
+
"loss": 0.7739,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.0014913192036901056,
|
| 580 |
+
"grad_norm": 0.4407779276371002,
|
| 581 |
+
"learning_rate": 0.0002,
|
| 582 |
+
"loss": 0.2848,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.0015095060232473022,
|
| 587 |
+
"grad_norm": 0.25743165612220764,
|
| 588 |
+
"learning_rate": 0.0002,
|
| 589 |
+
"loss": 0.1318,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.0015276928428044985,
|
| 594 |
+
"grad_norm": 2.0397753715515137,
|
| 595 |
+
"learning_rate": 0.0002,
|
| 596 |
+
"loss": 0.1385,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.001545879662361695,
|
| 601 |
+
"grad_norm": 0.060638878494501114,
|
| 602 |
+
"learning_rate": 0.0002,
|
| 603 |
+
"loss": 0.047,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.0015640664819188913,
|
| 608 |
+
"grad_norm": 2.5641930103302,
|
| 609 |
+
"learning_rate": 0.0002,
|
| 610 |
+
"loss": 0.5497,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.0015822533014760878,
|
| 615 |
+
"grad_norm": 0.9419782161712646,
|
| 616 |
+
"learning_rate": 0.0002,
|
| 617 |
+
"loss": 0.1626,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.0016004401210332842,
|
| 622 |
+
"grad_norm": 0.1152188628911972,
|
| 623 |
+
"learning_rate": 0.0002,
|
| 624 |
+
"loss": 0.1063,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.0016186269405904805,
|
| 629 |
+
"grad_norm": 0.6502537131309509,
|
| 630 |
+
"learning_rate": 0.0002,
|
| 631 |
+
"loss": 0.0871,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.001636813760147677,
|
| 636 |
+
"grad_norm": 0.023487605154514313,
|
| 637 |
+
"learning_rate": 0.0002,
|
| 638 |
+
"loss": 0.0094,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.0016550005797048733,
|
| 643 |
+
"grad_norm": 1.9080859422683716,
|
| 644 |
+
"learning_rate": 0.0002,
|
| 645 |
+
"loss": 0.5073,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.0016731873992620698,
|
| 650 |
+
"grad_norm": 0.44722509384155273,
|
| 651 |
+
"learning_rate": 0.0002,
|
| 652 |
+
"loss": 0.167,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.0016913742188192661,
|
| 657 |
+
"grad_norm": 0.24151289463043213,
|
| 658 |
+
"learning_rate": 0.0002,
|
| 659 |
+
"loss": 0.1237,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.0017095610383764627,
|
| 664 |
+
"grad_norm": 1.1394294500350952,
|
| 665 |
+
"learning_rate": 0.0002,
|
| 666 |
+
"loss": 0.1014,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.001727747857933659,
|
| 671 |
+
"grad_norm": 0.011057032272219658,
|
| 672 |
+
"learning_rate": 0.0002,
|
| 673 |
+
"loss": 0.0069,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.0017459346774908555,
|
| 678 |
+
"grad_norm": 4.32397985458374,
|
| 679 |
+
"learning_rate": 0.0002,
|
| 680 |
+
"loss": 0.7672,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.0017641214970480518,
|
| 685 |
+
"grad_norm": 0.9529788494110107,
|
| 686 |
+
"learning_rate": 0.0002,
|
| 687 |
+
"loss": 0.3286,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.0017823083166052483,
|
| 692 |
+
"grad_norm": 0.27676528692245483,
|
| 693 |
+
"learning_rate": 0.0002,
|
| 694 |
+
"loss": 0.126,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.0018004951361624446,
|
| 699 |
+
"grad_norm": 0.62413090467453,
|
| 700 |
+
"learning_rate": 0.0002,
|
| 701 |
+
"loss": 0.0844,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.0018186819557196412,
|
| 706 |
+
"grad_norm": 0.010768013074994087,
|
| 707 |
+
"learning_rate": 0.0002,
|
| 708 |
+
"loss": 0.0038,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.0018368687752768375,
|
| 713 |
+
"grad_norm": 4.500253200531006,
|
| 714 |
+
"learning_rate": 0.0002,
|
| 715 |
+
"loss": 0.8415,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.001855055594834034,
|
| 720 |
+
"grad_norm": 0.4661908447742462,
|
| 721 |
+
"learning_rate": 0.0002,
|
| 722 |
+
"loss": 0.2552,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.0018732424143912303,
|
| 727 |
+
"grad_norm": 0.17337530851364136,
|
| 728 |
+
"learning_rate": 0.0002,
|
| 729 |
+
"loss": 0.1032,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.0018914292339484266,
|
| 734 |
+
"grad_norm": 0.3994196355342865,
|
| 735 |
+
"learning_rate": 0.0002,
|
| 736 |
+
"loss": 0.0814,
|
| 737 |
+
"step": 1040
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.0019096160535056232,
|
| 741 |
+
"grad_norm": 0.025604812428355217,
|
| 742 |
+
"learning_rate": 0.0002,
|
| 743 |
+
"loss": 0.0077,
|
| 744 |
+
"step": 1050
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.0019278028730628195,
|
| 748 |
+
"grad_norm": 3.7293856143951416,
|
| 749 |
+
"learning_rate": 0.0002,
|
| 750 |
+
"loss": 0.6543,
|
| 751 |
+
"step": 1060
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.001945989692620016,
|
| 755 |
+
"grad_norm": 1.2915587425231934,
|
| 756 |
+
"learning_rate": 0.0002,
|
| 757 |
+
"loss": 0.3782,
|
| 758 |
+
"step": 1070
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.0019641765121772123,
|
| 762 |
+
"grad_norm": 1.0336438417434692,
|
| 763 |
+
"learning_rate": 0.0002,
|
| 764 |
+
"loss": 0.1515,
|
| 765 |
+
"step": 1080
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.0019823633317344086,
|
| 769 |
+
"grad_norm": 1.6816803216934204,
|
| 770 |
+
"learning_rate": 0.0002,
|
| 771 |
+
"loss": 0.1173,
|
| 772 |
+
"step": 1090
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 0.0020005501512916054,
|
| 776 |
+
"grad_norm": 0.015431606210768223,
|
| 777 |
+
"learning_rate": 0.0002,
|
| 778 |
+
"loss": 0.0165,
|
| 779 |
+
"step": 1100
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.0020187369708488017,
|
| 783 |
+
"grad_norm": 3.059936046600342,
|
| 784 |
+
"learning_rate": 0.0002,
|
| 785 |
+
"loss": 0.6981,
|
| 786 |
+
"step": 1110
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.002036923790405998,
|
| 790 |
+
"grad_norm": 0.5564419031143188,
|
| 791 |
+
"learning_rate": 0.0002,
|
| 792 |
+
"loss": 0.2193,
|
| 793 |
+
"step": 1120
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 0.0020551106099631943,
|
| 797 |
+
"grad_norm": 0.11465179920196533,
|
| 798 |
+
"learning_rate": 0.0002,
|
| 799 |
+
"loss": 0.1157,
|
| 800 |
+
"step": 1130
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.002073297429520391,
|
| 804 |
+
"grad_norm": 1.7084763050079346,
|
| 805 |
+
"learning_rate": 0.0002,
|
| 806 |
+
"loss": 0.0997,
|
| 807 |
+
"step": 1140
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.0020914842490775873,
|
| 811 |
+
"grad_norm": 0.00997951254248619,
|
| 812 |
+
"learning_rate": 0.0002,
|
| 813 |
+
"loss": 0.0185,
|
| 814 |
+
"step": 1150
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.0021096710686347836,
|
| 818 |
+
"grad_norm": 4.252767086029053,
|
| 819 |
+
"learning_rate": 0.0002,
|
| 820 |
+
"loss": 0.6719,
|
| 821 |
+
"step": 1160
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"epoch": 0.00212785788819198,
|
| 825 |
+
"grad_norm": 0.7261558175086975,
|
| 826 |
+
"learning_rate": 0.0002,
|
| 827 |
+
"loss": 0.1939,
|
| 828 |
+
"step": 1170
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.0021460447077491763,
|
| 832 |
+
"grad_norm": 0.3190513253211975,
|
| 833 |
+
"learning_rate": 0.0002,
|
| 834 |
+
"loss": 0.0981,
|
| 835 |
+
"step": 1180
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 0.002164231527306373,
|
| 839 |
+
"grad_norm": 0.5305098295211792,
|
| 840 |
+
"learning_rate": 0.0002,
|
| 841 |
+
"loss": 0.0756,
|
| 842 |
+
"step": 1190
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.0021824183468635693,
|
| 846 |
+
"grad_norm": 0.03356161713600159,
|
| 847 |
+
"learning_rate": 0.0002,
|
| 848 |
+
"loss": 0.0064,
|
| 849 |
+
"step": 1200
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.0022006051664207656,
|
| 853 |
+
"grad_norm": 3.8724617958068848,
|
| 854 |
+
"learning_rate": 0.0002,
|
| 855 |
+
"loss": 0.6282,
|
| 856 |
+
"step": 1210
|
| 857 |
+
},
|
| 858 |
+
{
|
| 859 |
+
"epoch": 0.002218791985977962,
|
| 860 |
+
"grad_norm": 1.3044495582580566,
|
| 861 |
+
"learning_rate": 0.0002,
|
| 862 |
+
"loss": 0.3827,
|
| 863 |
+
"step": 1220
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 0.0022369788055351587,
|
| 867 |
+
"grad_norm": 0.18937312066555023,
|
| 868 |
+
"learning_rate": 0.0002,
|
| 869 |
+
"loss": 0.1412,
|
| 870 |
+
"step": 1230
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 0.002255165625092355,
|
| 874 |
+
"grad_norm": 2.488002061843872,
|
| 875 |
+
"learning_rate": 0.0002,
|
| 876 |
+
"loss": 0.1299,
|
| 877 |
+
"step": 1240
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 0.0022733524446495513,
|
| 881 |
+
"grad_norm": 0.05979600548744202,
|
| 882 |
+
"learning_rate": 0.0002,
|
| 883 |
+
"loss": 0.0276,
|
| 884 |
+
"step": 1250
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.0022915392642067476,
|
| 888 |
+
"grad_norm": 4.089362144470215,
|
| 889 |
+
"learning_rate": 0.0002,
|
| 890 |
+
"loss": 0.6152,
|
| 891 |
+
"step": 1260
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.0023097260837639444,
|
| 895 |
+
"grad_norm": 0.2717827260494232,
|
| 896 |
+
"learning_rate": 0.0002,
|
| 897 |
+
"loss": 0.277,
|
| 898 |
+
"step": 1270
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.0023279129033211407,
|
| 902 |
+
"grad_norm": 0.40145063400268555,
|
| 903 |
+
"learning_rate": 0.0002,
|
| 904 |
+
"loss": 0.113,
|
| 905 |
+
"step": 1280
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 0.002346099722878337,
|
| 909 |
+
"grad_norm": 0.8193599581718445,
|
| 910 |
+
"learning_rate": 0.0002,
|
| 911 |
+
"loss": 0.0952,
|
| 912 |
+
"step": 1290
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.0023642865424355333,
|
| 916 |
+
"grad_norm": 0.03877554461359978,
|
| 917 |
+
"learning_rate": 0.0002,
|
| 918 |
+
"loss": 0.0187,
|
| 919 |
+
"step": 1300
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.00238247336199273,
|
| 923 |
+
"grad_norm": 3.7022697925567627,
|
| 924 |
+
"learning_rate": 0.0002,
|
| 925 |
+
"loss": 0.6711,
|
| 926 |
+
"step": 1310
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.0024006601815499263,
|
| 930 |
+
"grad_norm": 1.0773606300354004,
|
| 931 |
+
"learning_rate": 0.0002,
|
| 932 |
+
"loss": 0.3495,
|
| 933 |
+
"step": 1320
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.0024188470011071227,
|
| 937 |
+
"grad_norm": 0.46499383449554443,
|
| 938 |
+
"learning_rate": 0.0002,
|
| 939 |
+
"loss": 0.1181,
|
| 940 |
+
"step": 1330
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.002437033820664319,
|
| 944 |
+
"grad_norm": 0.7035688757896423,
|
| 945 |
+
"learning_rate": 0.0002,
|
| 946 |
+
"loss": 0.08,
|
| 947 |
+
"step": 1340
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.0024552206402215153,
|
| 951 |
+
"grad_norm": 0.022035669535398483,
|
| 952 |
+
"learning_rate": 0.0002,
|
| 953 |
+
"loss": 0.0102,
|
| 954 |
+
"step": 1350
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.002473407459778712,
|
| 958 |
+
"grad_norm": 3.3636128902435303,
|
| 959 |
+
"learning_rate": 0.0002,
|
| 960 |
+
"loss": 0.6578,
|
| 961 |
+
"step": 1360
|
| 962 |
+
},
|
| 963 |
+
{
|
| 964 |
+
"epoch": 0.0024915942793359083,
|
| 965 |
+
"grad_norm": 0.21912692487239838,
|
| 966 |
+
"learning_rate": 0.0002,
|
| 967 |
+
"loss": 0.2275,
|
| 968 |
+
"step": 1370
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 0.0025097810988931046,
|
| 972 |
+
"grad_norm": 0.1632055938243866,
|
| 973 |
+
"learning_rate": 0.0002,
|
| 974 |
+
"loss": 0.1015,
|
| 975 |
+
"step": 1380
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.002527967918450301,
|
| 979 |
+
"grad_norm": 0.44282346963882446,
|
| 980 |
+
"learning_rate": 0.0002,
|
| 981 |
+
"loss": 0.103,
|
| 982 |
+
"step": 1390
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 0.0025461547380074977,
|
| 986 |
+
"grad_norm": 0.17366968095302582,
|
| 987 |
+
"learning_rate": 0.0002,
|
| 988 |
+
"loss": 0.0322,
|
| 989 |
+
"step": 1400
|
| 990 |
+
},
|
| 991 |
+
{
|
| 992 |
+
"epoch": 0.002564341557564694,
|
| 993 |
+
"grad_norm": 1.816606879234314,
|
| 994 |
+
"learning_rate": 0.0002,
|
| 995 |
+
"loss": 0.3914,
|
| 996 |
+
"step": 1410
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 0.0025825283771218903,
|
| 1000 |
+
"grad_norm": 0.6741718649864197,
|
| 1001 |
+
"learning_rate": 0.0002,
|
| 1002 |
+
"loss": 0.2593,
|
| 1003 |
+
"step": 1420
|
| 1004 |
+
},
|
| 1005 |
+
{
|
| 1006 |
+
"epoch": 0.0026007151966790866,
|
| 1007 |
+
"grad_norm": 0.580172598361969,
|
| 1008 |
+
"learning_rate": 0.0002,
|
| 1009 |
+
"loss": 0.151,
|
| 1010 |
+
"step": 1430
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.0026189020162362834,
|
| 1014 |
+
"grad_norm": 1.500544548034668,
|
| 1015 |
+
"learning_rate": 0.0002,
|
| 1016 |
+
"loss": 0.1266,
|
| 1017 |
+
"step": 1440
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.0026370888357934797,
|
| 1021 |
+
"grad_norm": 0.03482064977288246,
|
| 1022 |
+
"learning_rate": 0.0002,
|
| 1023 |
+
"loss": 0.0209,
|
| 1024 |
+
"step": 1450
|
| 1025 |
+
},
|
| 1026 |
+
{
|
| 1027 |
+
"epoch": 0.002655275655350676,
|
| 1028 |
+
"grad_norm": 1.9266266822814941,
|
| 1029 |
+
"learning_rate": 0.0002,
|
| 1030 |
+
"loss": 0.5335,
|
| 1031 |
+
"step": 1460
|
| 1032 |
+
},
|
| 1033 |
+
{
|
| 1034 |
+
"epoch": 0.0026734624749078723,
|
| 1035 |
+
"grad_norm": 0.6076328158378601,
|
| 1036 |
+
"learning_rate": 0.0002,
|
| 1037 |
+
"loss": 0.1771,
|
| 1038 |
+
"step": 1470
|
| 1039 |
+
},
|
| 1040 |
+
{
|
| 1041 |
+
"epoch": 0.0026916492944650686,
|
| 1042 |
+
"grad_norm": 0.047803062945604324,
|
| 1043 |
+
"learning_rate": 0.0002,
|
| 1044 |
+
"loss": 0.1312,
|
| 1045 |
+
"step": 1480
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 0.0027098361140222653,
|
| 1049 |
+
"grad_norm": 2.2670884132385254,
|
| 1050 |
+
"learning_rate": 0.0002,
|
| 1051 |
+
"loss": 0.1303,
|
| 1052 |
+
"step": 1490
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 0.0027280229335794617,
|
| 1056 |
+
"grad_norm": 0.4342607259750366,
|
| 1057 |
+
"learning_rate": 0.0002,
|
| 1058 |
+
"loss": 0.0709,
|
| 1059 |
+
"step": 1500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.002746209753136658,
|
| 1063 |
+
"grad_norm": 1.5955005884170532,
|
| 1064 |
+
"learning_rate": 0.0002,
|
| 1065 |
+
"loss": 0.2632,
|
| 1066 |
+
"step": 1510
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.0027643965726938543,
|
| 1070 |
+
"grad_norm": 0.20393006503582,
|
| 1071 |
+
"learning_rate": 0.0002,
|
| 1072 |
+
"loss": 0.1324,
|
| 1073 |
+
"step": 1520
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"epoch": 0.002782583392251051,
|
| 1077 |
+
"grad_norm": 0.2312391996383667,
|
| 1078 |
+
"learning_rate": 0.0002,
|
| 1079 |
+
"loss": 0.1056,
|
| 1080 |
+
"step": 1530
|
| 1081 |
+
},
|
| 1082 |
+
{
|
| 1083 |
+
"epoch": 0.0028007702118082473,
|
| 1084 |
+
"grad_norm": 1.2107295989990234,
|
| 1085 |
+
"learning_rate": 0.0002,
|
| 1086 |
+
"loss": 0.1038,
|
| 1087 |
+
"step": 1540
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 0.0028189570313654436,
|
| 1091 |
+
"grad_norm": 0.07030847668647766,
|
| 1092 |
+
"learning_rate": 0.0002,
|
| 1093 |
+
"loss": 0.032,
|
| 1094 |
+
"step": 1550
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 0.00283714385092264,
|
| 1098 |
+
"grad_norm": 3.563960552215576,
|
| 1099 |
+
"learning_rate": 0.0002,
|
| 1100 |
+
"loss": 0.5389,
|
| 1101 |
+
"step": 1560
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.0028553306704798367,
|
| 1105 |
+
"grad_norm": 0.6965789794921875,
|
| 1106 |
+
"learning_rate": 0.0002,
|
| 1107 |
+
"loss": 0.2889,
|
| 1108 |
+
"step": 1570
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 0.002873517490037033,
|
| 1112 |
+
"grad_norm": 0.5975427031517029,
|
| 1113 |
+
"learning_rate": 0.0002,
|
| 1114 |
+
"loss": 0.1235,
|
| 1115 |
+
"step": 1580
|
| 1116 |
+
},
|
| 1117 |
+
{
|
| 1118 |
+
"epoch": 0.0028917043095942293,
|
| 1119 |
+
"grad_norm": 1.371771216392517,
|
| 1120 |
+
"learning_rate": 0.0002,
|
| 1121 |
+
"loss": 0.0971,
|
| 1122 |
+
"step": 1590
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.0029098911291514256,
|
| 1126 |
+
"grad_norm": 0.01906588114798069,
|
| 1127 |
+
"learning_rate": 0.0002,
|
| 1128 |
+
"loss": 0.0172,
|
| 1129 |
+
"step": 1600
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 0.002928077948708622,
|
| 1133 |
+
"grad_norm": 3.8812315464019775,
|
| 1134 |
+
"learning_rate": 0.0002,
|
| 1135 |
+
"loss": 0.621,
|
| 1136 |
+
"step": 1610
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 0.0029462647682658187,
|
| 1140 |
+
"grad_norm": 0.41589802503585815,
|
| 1141 |
+
"learning_rate": 0.0002,
|
| 1142 |
+
"loss": 0.2029,
|
| 1143 |
+
"step": 1620
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.002964451587823015,
|
| 1147 |
+
"grad_norm": 0.24198026955127716,
|
| 1148 |
+
"learning_rate": 0.0002,
|
| 1149 |
+
"loss": 0.1042,
|
| 1150 |
+
"step": 1630
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 0.0029826384073802113,
|
| 1154 |
+
"grad_norm": 0.8711221814155579,
|
| 1155 |
+
"learning_rate": 0.0002,
|
| 1156 |
+
"loss": 0.0904,
|
| 1157 |
+
"step": 1640
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 0.0030008252269374076,
|
| 1161 |
+
"grad_norm": 0.06849978119134903,
|
| 1162 |
+
"learning_rate": 0.0002,
|
| 1163 |
+
"loss": 0.0226,
|
| 1164 |
+
"step": 1650
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 0.0030190120464946043,
|
| 1168 |
+
"grad_norm": 3.912189483642578,
|
| 1169 |
+
"learning_rate": 0.0002,
|
| 1170 |
+
"loss": 0.5554,
|
| 1171 |
+
"step": 1660
|
| 1172 |
+
},
|
| 1173 |
+
{
|
| 1174 |
+
"epoch": 0.0030371988660518007,
|
| 1175 |
+
"grad_norm": 1.076832890510559,
|
| 1176 |
+
"learning_rate": 0.0002,
|
| 1177 |
+
"loss": 0.2968,
|
| 1178 |
+
"step": 1670
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.003055385685608997,
|
| 1182 |
+
"grad_norm": 0.3734837472438812,
|
| 1183 |
+
"learning_rate": 0.0002,
|
| 1184 |
+
"loss": 0.1151,
|
| 1185 |
+
"step": 1680
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.0030735725051661933,
|
| 1189 |
+
"grad_norm": 0.8407588005065918,
|
| 1190 |
+
"learning_rate": 0.0002,
|
| 1191 |
+
"loss": 0.0897,
|
| 1192 |
+
"step": 1690
|
| 1193 |
+
},
|
| 1194 |
+
{
|
| 1195 |
+
"epoch": 0.00309175932472339,
|
| 1196 |
+
"grad_norm": 0.023632407188415527,
|
| 1197 |
+
"learning_rate": 0.0002,
|
| 1198 |
+
"loss": 0.0113,
|
| 1199 |
+
"step": 1700
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 0.0031099461442805863,
|
| 1203 |
+
"grad_norm": 4.268885612487793,
|
| 1204 |
+
"learning_rate": 0.0002,
|
| 1205 |
+
"loss": 0.6717,
|
| 1206 |
+
"step": 1710
|
| 1207 |
+
},
|
| 1208 |
+
{
|
| 1209 |
+
"epoch": 0.0031281329638377826,
|
| 1210 |
+
"grad_norm": 0.3088800013065338,
|
| 1211 |
+
"learning_rate": 0.0002,
|
| 1212 |
+
"loss": 0.2635,
|
| 1213 |
+
"step": 1720
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.003146319783394979,
|
| 1217 |
+
"grad_norm": 0.05659230053424835,
|
| 1218 |
+
"learning_rate": 0.0002,
|
| 1219 |
+
"loss": 0.0987,
|
| 1220 |
+
"step": 1730
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.0031645066029521757,
|
| 1224 |
+
"grad_norm": 0.5756633281707764,
|
| 1225 |
+
"learning_rate": 0.0002,
|
| 1226 |
+
"loss": 0.0949,
|
| 1227 |
+
"step": 1740
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.003182693422509372,
|
| 1231 |
+
"grad_norm": 0.23241274058818817,
|
| 1232 |
+
"learning_rate": 0.0002,
|
| 1233 |
+
"loss": 0.044,
|
| 1234 |
+
"step": 1750
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.0032008802420665683,
|
| 1238 |
+
"grad_norm": 2.2380006313323975,
|
| 1239 |
+
"learning_rate": 0.0002,
|
| 1240 |
+
"loss": 0.3458,
|
| 1241 |
+
"step": 1760
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.0032190670616237646,
|
| 1245 |
+
"grad_norm": 0.4196106493473053,
|
| 1246 |
+
"learning_rate": 0.0002,
|
| 1247 |
+
"loss": 0.2116,
|
| 1248 |
+
"step": 1770
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.003237253881180961,
|
| 1252 |
+
"grad_norm": 0.3544403612613678,
|
| 1253 |
+
"learning_rate": 0.0002,
|
| 1254 |
+
"loss": 0.1011,
|
| 1255 |
+
"step": 1780
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"epoch": 0.0032554407007381577,
|
| 1259 |
+
"grad_norm": 0.6422521471977234,
|
| 1260 |
+
"learning_rate": 0.0002,
|
| 1261 |
+
"loss": 0.084,
|
| 1262 |
+
"step": 1790
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 0.003273627520295354,
|
| 1266 |
+
"grad_norm": 0.03676289692521095,
|
| 1267 |
+
"learning_rate": 0.0002,
|
| 1268 |
+
"loss": 0.0115,
|
| 1269 |
+
"step": 1800
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.0032918143398525503,
|
| 1273 |
+
"grad_norm": 3.173424243927002,
|
| 1274 |
+
"learning_rate": 0.0002,
|
| 1275 |
+
"loss": 0.5644,
|
| 1276 |
+
"step": 1810
|
| 1277 |
+
},
|
| 1278 |
+
{
|
| 1279 |
+
"epoch": 0.0033100011594097466,
|
| 1280 |
+
"grad_norm": 0.14629468321800232,
|
| 1281 |
+
"learning_rate": 0.0002,
|
| 1282 |
+
"loss": 0.2249,
|
| 1283 |
+
"step": 1820
|
| 1284 |
+
},
|
| 1285 |
+
{
|
| 1286 |
+
"epoch": 0.0033281879789669433,
|
| 1287 |
+
"grad_norm": 0.27524232864379883,
|
| 1288 |
+
"learning_rate": 0.0002,
|
| 1289 |
+
"loss": 0.0965,
|
| 1290 |
+
"step": 1830
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.0033463747985241397,
|
| 1294 |
+
"grad_norm": 0.5685613751411438,
|
| 1295 |
+
"learning_rate": 0.0002,
|
| 1296 |
+
"loss": 0.0949,
|
| 1297 |
+
"step": 1840
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 0.003364561618081336,
|
| 1301 |
+
"grad_norm": 0.19684627652168274,
|
| 1302 |
+
"learning_rate": 0.0002,
|
| 1303 |
+
"loss": 0.0423,
|
| 1304 |
+
"step": 1850
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 0.0033827484376385323,
|
| 1308 |
+
"grad_norm": 2.0270469188690186,
|
| 1309 |
+
"learning_rate": 0.0002,
|
| 1310 |
+
"loss": 0.3322,
|
| 1311 |
+
"step": 1860
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.003400935257195729,
|
| 1315 |
+
"grad_norm": 0.3960348963737488,
|
| 1316 |
+
"learning_rate": 0.0002,
|
| 1317 |
+
"loss": 0.1933,
|
| 1318 |
+
"step": 1870
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 0.0034191220767529253,
|
| 1322 |
+
"grad_norm": 0.8636507391929626,
|
| 1323 |
+
"learning_rate": 0.0002,
|
| 1324 |
+
"loss": 0.1056,
|
| 1325 |
+
"step": 1880
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 0.0034373088963101216,
|
| 1329 |
+
"grad_norm": 0.7978588342666626,
|
| 1330 |
+
"learning_rate": 0.0002,
|
| 1331 |
+
"loss": 0.0812,
|
| 1332 |
+
"step": 1890
|
| 1333 |
+
},
|
| 1334 |
+
{
|
| 1335 |
+
"epoch": 0.003455495715867318,
|
| 1336 |
+
"grad_norm": 0.020584411919116974,
|
| 1337 |
+
"learning_rate": 0.0002,
|
| 1338 |
+
"loss": 0.0098,
|
| 1339 |
+
"step": 1900
|
| 1340 |
+
},
|
| 1341 |
+
{
|
| 1342 |
+
"epoch": 0.0034736825354245143,
|
| 1343 |
+
"grad_norm": 2.648928165435791,
|
| 1344 |
+
"learning_rate": 0.0002,
|
| 1345 |
+
"loss": 0.5485,
|
| 1346 |
+
"step": 1910
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.003491869354981711,
|
| 1350 |
+
"grad_norm": 0.5433089137077332,
|
| 1351 |
+
"learning_rate": 0.0002,
|
| 1352 |
+
"loss": 0.1546,
|
| 1353 |
+
"step": 1920
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.0035100561745389073,
|
| 1357 |
+
"grad_norm": 0.2638677656650543,
|
| 1358 |
+
"learning_rate": 0.0002,
|
| 1359 |
+
"loss": 0.0935,
|
| 1360 |
+
"step": 1930
|
| 1361 |
+
},
|
| 1362 |
+
{
|
| 1363 |
+
"epoch": 0.0035282429940961036,
|
| 1364 |
+
"grad_norm": 0.4292812943458557,
|
| 1365 |
+
"learning_rate": 0.0002,
|
| 1366 |
+
"loss": 0.0879,
|
| 1367 |
+
"step": 1940
|
| 1368 |
+
},
|
| 1369 |
+
{
|
| 1370 |
+
"epoch": 0.0035464298136533,
|
| 1371 |
+
"grad_norm": 0.09974557906389236,
|
| 1372 |
+
"learning_rate": 0.0002,
|
| 1373 |
+
"loss": 0.0234,
|
| 1374 |
+
"step": 1950
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 0.0035646166332104967,
|
| 1378 |
+
"grad_norm": 1.626259446144104,
|
| 1379 |
+
"learning_rate": 0.0002,
|
| 1380 |
+
"loss": 0.4046,
|
| 1381 |
+
"step": 1960
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 0.003582803452767693,
|
| 1385 |
+
"grad_norm": 0.7747110724449158,
|
| 1386 |
+
"learning_rate": 0.0002,
|
| 1387 |
+
"loss": 0.2436,
|
| 1388 |
+
"step": 1970
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 0.0036009902723248893,
|
| 1392 |
+
"grad_norm": 1.130542516708374,
|
| 1393 |
+
"learning_rate": 0.0002,
|
| 1394 |
+
"loss": 0.1371,
|
| 1395 |
+
"step": 1980
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.0036191770918820856,
|
| 1399 |
+
"grad_norm": 2.542160987854004,
|
| 1400 |
+
"learning_rate": 0.0002,
|
| 1401 |
+
"loss": 0.1204,
|
| 1402 |
+
"step": 1990
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.0036373639114392823,
|
| 1406 |
+
"grad_norm": 0.1563112586736679,
|
| 1407 |
+
"learning_rate": 0.0002,
|
| 1408 |
+
"loss": 0.0343,
|
| 1409 |
+
"step": 2000
|
| 1410 |
+
},
|
| 1411 |
+
{
|
| 1412 |
+
"epoch": 0.0036555507309964787,
|
| 1413 |
+
"grad_norm": 3.1544902324676514,
|
| 1414 |
+
"learning_rate": 0.0002,
|
| 1415 |
+
"loss": 0.4769,
|
| 1416 |
+
"step": 2010
|
| 1417 |
+
},
|
| 1418 |
+
{
|
| 1419 |
+
"epoch": 0.003673737550553675,
|
| 1420 |
+
"grad_norm": 1.0212864875793457,
|
| 1421 |
+
"learning_rate": 0.0002,
|
| 1422 |
+
"loss": 0.2462,
|
| 1423 |
+
"step": 2020
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 0.0036919243701108713,
|
| 1427 |
+
"grad_norm": 0.3565104305744171,
|
| 1428 |
+
"learning_rate": 0.0002,
|
| 1429 |
+
"loss": 0.1209,
|
| 1430 |
+
"step": 2030
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 0.003710111189668068,
|
| 1434 |
+
"grad_norm": 1.3275020122528076,
|
| 1435 |
+
"learning_rate": 0.0002,
|
| 1436 |
+
"loss": 0.1064,
|
| 1437 |
+
"step": 2040
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.0037282980092252643,
|
| 1441 |
+
"grad_norm": 0.11180760711431503,
|
| 1442 |
+
"learning_rate": 0.0002,
|
| 1443 |
+
"loss": 0.0326,
|
| 1444 |
+
"step": 2050
|
| 1445 |
+
},
|
| 1446 |
+
{
|
| 1447 |
+
"epoch": 0.0037464848287824606,
|
| 1448 |
+
"grad_norm": 1.9683802127838135,
|
| 1449 |
+
"learning_rate": 0.0002,
|
| 1450 |
+
"loss": 0.3878,
|
| 1451 |
+
"step": 2060
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 0.003764671648339657,
|
| 1455 |
+
"grad_norm": 0.7875238060951233,
|
| 1456 |
+
"learning_rate": 0.0002,
|
| 1457 |
+
"loss": 0.1145,
|
| 1458 |
+
"step": 2070
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 0.0037828584678968533,
|
| 1462 |
+
"grad_norm": 0.4307851195335388,
|
| 1463 |
+
"learning_rate": 0.0002,
|
| 1464 |
+
"loss": 0.0891,
|
| 1465 |
+
"step": 2080
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 0.00380104528745405,
|
| 1469 |
+
"grad_norm": 0.6907076239585876,
|
| 1470 |
+
"learning_rate": 0.0002,
|
| 1471 |
+
"loss": 0.0801,
|
| 1472 |
+
"step": 2090
|
| 1473 |
+
},
|
| 1474 |
+
{
|
| 1475 |
+
"epoch": 0.0038192321070112463,
|
| 1476 |
+
"grad_norm": 0.04466943070292473,
|
| 1477 |
+
"learning_rate": 0.0002,
|
| 1478 |
+
"loss": 0.0148,
|
| 1479 |
+
"step": 2100
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.0038374189265684426,
|
| 1483 |
+
"grad_norm": 2.8212766647338867,
|
| 1484 |
+
"learning_rate": 0.0002,
|
| 1485 |
+
"loss": 0.501,
|
| 1486 |
+
"step": 2110
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 0.003855605746125639,
|
| 1490 |
+
"grad_norm": 0.4052332639694214,
|
| 1491 |
+
"learning_rate": 0.0002,
|
| 1492 |
+
"loss": 0.2379,
|
| 1493 |
+
"step": 2120
|
| 1494 |
+
},
|
| 1495 |
+
{
|
| 1496 |
+
"epoch": 0.0038737925656828357,
|
| 1497 |
+
"grad_norm": 0.5726248621940613,
|
| 1498 |
+
"learning_rate": 0.0002,
|
| 1499 |
+
"loss": 0.0925,
|
| 1500 |
+
"step": 2130
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 0.003891979385240032,
|
| 1504 |
+
"grad_norm": 0.7385726571083069,
|
| 1505 |
+
"learning_rate": 0.0002,
|
| 1506 |
+
"loss": 0.0744,
|
| 1507 |
+
"step": 2140
|
| 1508 |
+
},
|
| 1509 |
+
{
|
| 1510 |
+
"epoch": 0.003910166204797228,
|
| 1511 |
+
"grad_norm": 0.01478211022913456,
|
| 1512 |
+
"learning_rate": 0.0002,
|
| 1513 |
+
"loss": 0.0094,
|
| 1514 |
+
"step": 2150
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.003928353024354425,
|
| 1518 |
+
"grad_norm": 4.001941204071045,
|
| 1519 |
+
"learning_rate": 0.0002,
|
| 1520 |
+
"loss": 0.5398,
|
| 1521 |
+
"step": 2160
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.003946539843911621,
|
| 1525 |
+
"grad_norm": 0.5501906275749207,
|
| 1526 |
+
"learning_rate": 0.0002,
|
| 1527 |
+
"loss": 0.1502,
|
| 1528 |
+
"step": 2170
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.003964726663468817,
|
| 1532 |
+
"grad_norm": 0.05887573957443237,
|
| 1533 |
+
"learning_rate": 0.0002,
|
| 1534 |
+
"loss": 0.1137,
|
| 1535 |
+
"step": 2180
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.003982913483026014,
|
| 1539 |
+
"grad_norm": 0.6087843179702759,
|
| 1540 |
+
"learning_rate": 0.0002,
|
| 1541 |
+
"loss": 0.0738,
|
| 1542 |
+
"step": 2190
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.004001100302583211,
|
| 1546 |
+
"grad_norm": 0.027440447360277176,
|
| 1547 |
+
"learning_rate": 0.0002,
|
| 1548 |
+
"loss": 0.0122,
|
| 1549 |
+
"step": 2200
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.004019287122140407,
|
| 1553 |
+
"grad_norm": 3.8189752101898193,
|
| 1554 |
+
"learning_rate": 0.0002,
|
| 1555 |
+
"loss": 0.5507,
|
| 1556 |
+
"step": 2210
|
| 1557 |
+
},
|
| 1558 |
+
{
|
| 1559 |
+
"epoch": 0.004037473941697603,
|
| 1560 |
+
"grad_norm": 0.7837066054344177,
|
| 1561 |
+
"learning_rate": 0.0002,
|
| 1562 |
+
"loss": 0.2931,
|
| 1563 |
+
"step": 2220
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.0040556607612548,
|
| 1567 |
+
"grad_norm": 0.4113297462463379,
|
| 1568 |
+
"learning_rate": 0.0002,
|
| 1569 |
+
"loss": 0.1169,
|
| 1570 |
+
"step": 2230
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 0.004073847580811996,
|
| 1574 |
+
"grad_norm": 0.9759702086448669,
|
| 1575 |
+
"learning_rate": 0.0002,
|
| 1576 |
+
"loss": 0.0902,
|
| 1577 |
+
"step": 2240
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 0.004092034400369192,
|
| 1581 |
+
"grad_norm": 0.03002658113837242,
|
| 1582 |
+
"learning_rate": 0.0002,
|
| 1583 |
+
"loss": 0.0165,
|
| 1584 |
+
"step": 2250
|
| 1585 |
+
}
|
| 1586 |
+
],
|
| 1587 |
+
"logging_steps": 10,
|
| 1588 |
+
"max_steps": 100000,
|
| 1589 |
+
"num_input_tokens_seen": 0,
|
| 1590 |
+
"num_train_epochs": 1,
|
| 1591 |
+
"save_steps": 250,
|
| 1592 |
+
"stateful_callbacks": {
|
| 1593 |
+
"TrainerControl": {
|
| 1594 |
+
"args": {
|
| 1595 |
+
"should_epoch_stop": false,
|
| 1596 |
+
"should_evaluate": false,
|
| 1597 |
+
"should_log": false,
|
| 1598 |
+
"should_save": true,
|
| 1599 |
+
"should_training_stop": false
|
| 1600 |
+
},
|
| 1601 |
+
"attributes": {}
|
| 1602 |
+
}
|
| 1603 |
+
},
|
| 1604 |
+
"total_flos": 2.3899519044675994e+17,
|
| 1605 |
+
"train_batch_size": 24,
|
| 1606 |
+
"trial_name": null,
|
| 1607 |
+
"trial_params": null
|
| 1608 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835d980c1831d95ebfa035e21e3a4faf330f4c45eb8ffe7d87d2d7582396387a
|
| 3 |
+
size 7224
|