Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .mdl +0 -0
- .msc +0 -0
- .mv +1 -0
- added_tokens.json +28 -0
- config.json +30 -0
- configuration.json +1 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_state.json +2762 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.mdl
ADDED
|
Binary file (60 Bytes). View file
|
|
|
.msc
ADDED
|
Binary file (1.04 kB). View file
|
|
|
.mv
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
Revision:master,CreatedAt:1753937769
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 1024,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"max_position_embeddings": 40960,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen3",
|
| 17 |
+
"num_attention_heads": 16,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 8,
|
| 20 |
+
"rms_norm_eps": 1e-06,
|
| 21 |
+
"rope_scaling": null,
|
| 22 |
+
"rope_theta": 1000000,
|
| 23 |
+
"sliding_window": null,
|
| 24 |
+
"tie_word_embeddings": true,
|
| 25 |
+
"torch_dtype": "bfloat16",
|
| 26 |
+
"transformers_version": "4.51.3",
|
| 27 |
+
"use_cache": false,
|
| 28 |
+
"use_sliding_window": false,
|
| 29 |
+
"vocab_size": 151936
|
| 30 |
+
}
|
configuration.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "4.51.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f12f9246ae57760023e08096ffd8bbd8eddd45b59c95bcf5f41d2cc345e57f2
|
| 3 |
+
size 1503300328
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0].role == 'system' %}\n {{- messages[0].content + '\\n\\n' }}\n {%- endif %}\n {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0].role == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n {%- set index = (messages|length - 1) - loop.index0 %}\n {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n {%- set ns.multi_step_tool = false %}\n {%- set ns.last_query_index = index %}\n {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {%- set content = message.content %}\n {%- set reasoning_content = '' %}\n {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n {%- set reasoning_content = message.reasoning_content %}\n {%- else %}\n {%- if '</think>' in message.content %}\n {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n {%- endif %}\n {%- endif %}\n {%- if loop.index0 > ns.last_query_index %}\n {%- if loop.last or (not loop.last and reasoning_content) %}\n {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- else %}\n {{- '<|im_start|>' + message.role + '\\n' + content }}\n {%- endif %}\n {%- if message.tool_calls %}\n {%- for tool_call in message.tool_calls %}\n {%- if (loop.first and content) or (not loop.first) %}\n {{- '\\n' }}\n {%- endif %}\n {%- if tool_call.function %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {%- if tool_call.arguments is string %}\n {{- tool_call.arguments }}\n {%- else %}\n {{- tool_call.arguments | tojson }}\n {%- endif %}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {%- endif %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if loop.first or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n {%- if enable_thinking is defined and enable_thinking is false %}\n {{- '<think>\\n\\n</think>\\n\\n' }}\n {%- endif %}\n{%- endif %}",
|
| 231 |
+
"clean_up_tokenization_spaces": false,
|
| 232 |
+
"eos_token": "<|im_end|>",
|
| 233 |
+
"errors": "replace",
|
| 234 |
+
"extra_special_tokens": {},
|
| 235 |
+
"model_max_length": 131072,
|
| 236 |
+
"pad_token": "<|endoftext|>",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2762 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.9008102822017323,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 1700,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0011176306230790724,
|
| 14 |
+
"grad_norm": 10.011957168579102,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.2017,
|
| 17 |
+
"num_tokens": 1730426.0,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.005588153115395362,
|
| 22 |
+
"grad_norm": 10.05500602722168,
|
| 23 |
+
"learning_rate": 4.46927374301676e-07,
|
| 24 |
+
"loss": 1.2038,
|
| 25 |
+
"num_tokens": 8603870.0,
|
| 26 |
+
"step": 5
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.011176306230790724,
|
| 30 |
+
"grad_norm": 8.985472679138184,
|
| 31 |
+
"learning_rate": 1.005586592178771e-06,
|
| 32 |
+
"loss": 1.1918,
|
| 33 |
+
"num_tokens": 17231775.0,
|
| 34 |
+
"step": 10
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.016764459346186086,
|
| 38 |
+
"grad_norm": 6.6670756340026855,
|
| 39 |
+
"learning_rate": 1.564245810055866e-06,
|
| 40 |
+
"loss": 1.1476,
|
| 41 |
+
"num_tokens": 25849869.0,
|
| 42 |
+
"step": 15
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.022352612461581448,
|
| 46 |
+
"grad_norm": 3.7649803161621094,
|
| 47 |
+
"learning_rate": 2.1229050279329612e-06,
|
| 48 |
+
"loss": 1.0329,
|
| 49 |
+
"num_tokens": 34465678.0,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.02794076557697681,
|
| 54 |
+
"grad_norm": 2.7102489471435547,
|
| 55 |
+
"learning_rate": 2.6815642458100562e-06,
|
| 56 |
+
"loss": 0.9115,
|
| 57 |
+
"num_tokens": 43150100.0,
|
| 58 |
+
"step": 25
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03352891869237217,
|
| 62 |
+
"grad_norm": 2.4278452396392822,
|
| 63 |
+
"learning_rate": 3.240223463687151e-06,
|
| 64 |
+
"loss": 0.7605,
|
| 65 |
+
"num_tokens": 51786456.0,
|
| 66 |
+
"step": 30
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03911707180776753,
|
| 70 |
+
"grad_norm": 1.5626779794692993,
|
| 71 |
+
"learning_rate": 3.798882681564246e-06,
|
| 72 |
+
"loss": 0.6526,
|
| 73 |
+
"num_tokens": 60435486.0,
|
| 74 |
+
"step": 35
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.044705224923162895,
|
| 78 |
+
"grad_norm": 0.6909887194633484,
|
| 79 |
+
"learning_rate": 4.357541899441341e-06,
|
| 80 |
+
"loss": 0.5659,
|
| 81 |
+
"num_tokens": 69072463.0,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.050293378038558254,
|
| 86 |
+
"grad_norm": 0.5558706521987915,
|
| 87 |
+
"learning_rate": 4.916201117318436e-06,
|
| 88 |
+
"loss": 0.5397,
|
| 89 |
+
"num_tokens": 77692952.0,
|
| 90 |
+
"step": 45
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.05588153115395362,
|
| 94 |
+
"grad_norm": 0.4786052405834198,
|
| 95 |
+
"learning_rate": 5.474860335195531e-06,
|
| 96 |
+
"loss": 0.5163,
|
| 97 |
+
"num_tokens": 86330255.0,
|
| 98 |
+
"step": 50
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.06146968426934898,
|
| 102 |
+
"grad_norm": 0.49514034390449524,
|
| 103 |
+
"learning_rate": 6.033519553072626e-06,
|
| 104 |
+
"loss": 0.5015,
|
| 105 |
+
"num_tokens": 94954407.0,
|
| 106 |
+
"step": 55
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.06705783738474434,
|
| 110 |
+
"grad_norm": 0.8501572012901306,
|
| 111 |
+
"learning_rate": 6.592178770949721e-06,
|
| 112 |
+
"loss": 0.4872,
|
| 113 |
+
"num_tokens": 103559855.0,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.0726459905001397,
|
| 118 |
+
"grad_norm": 0.3786110281944275,
|
| 119 |
+
"learning_rate": 7.150837988826816e-06,
|
| 120 |
+
"loss": 0.4761,
|
| 121 |
+
"num_tokens": 112208289.0,
|
| 122 |
+
"step": 65
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07823414361553506,
|
| 126 |
+
"grad_norm": 0.2072855532169342,
|
| 127 |
+
"learning_rate": 7.709497206703911e-06,
|
| 128 |
+
"loss": 0.4718,
|
| 129 |
+
"num_tokens": 120800497.0,
|
| 130 |
+
"step": 70
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.08382229673093043,
|
| 134 |
+
"grad_norm": 0.2174290269613266,
|
| 135 |
+
"learning_rate": 8.268156424581007e-06,
|
| 136 |
+
"loss": 0.4608,
|
| 137 |
+
"num_tokens": 129451121.0,
|
| 138 |
+
"step": 75
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.08941044984632579,
|
| 142 |
+
"grad_norm": 0.22045612335205078,
|
| 143 |
+
"learning_rate": 8.826815642458101e-06,
|
| 144 |
+
"loss": 0.453,
|
| 145 |
+
"num_tokens": 138103500.0,
|
| 146 |
+
"step": 80
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.09499860296172115,
|
| 150 |
+
"grad_norm": 0.25303542613983154,
|
| 151 |
+
"learning_rate": 9.385474860335197e-06,
|
| 152 |
+
"loss": 0.4518,
|
| 153 |
+
"num_tokens": 146767921.0,
|
| 154 |
+
"step": 85
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.10058675607711651,
|
| 158 |
+
"grad_norm": 0.24008460342884064,
|
| 159 |
+
"learning_rate": 9.944134078212291e-06,
|
| 160 |
+
"loss": 0.4462,
|
| 161 |
+
"num_tokens": 155426403.0,
|
| 162 |
+
"step": 90
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.10617490919251188,
|
| 166 |
+
"grad_norm": 0.2523616850376129,
|
| 167 |
+
"learning_rate": 1.0502793296089386e-05,
|
| 168 |
+
"loss": 0.4419,
|
| 169 |
+
"num_tokens": 164080193.0,
|
| 170 |
+
"step": 95
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.11176306230790724,
|
| 174 |
+
"grad_norm": 0.21842315793037415,
|
| 175 |
+
"learning_rate": 1.1061452513966481e-05,
|
| 176 |
+
"loss": 0.4369,
|
| 177 |
+
"num_tokens": 172737694.0,
|
| 178 |
+
"step": 100
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1173512154233026,
|
| 182 |
+
"grad_norm": 0.3130860924720764,
|
| 183 |
+
"learning_rate": 1.1620111731843577e-05,
|
| 184 |
+
"loss": 0.4347,
|
| 185 |
+
"num_tokens": 181372620.0,
|
| 186 |
+
"step": 105
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.12293936853869795,
|
| 190 |
+
"grad_norm": 0.2151191383600235,
|
| 191 |
+
"learning_rate": 1.2178770949720671e-05,
|
| 192 |
+
"loss": 0.4321,
|
| 193 |
+
"num_tokens": 189993336.0,
|
| 194 |
+
"step": 110
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.1285275216540933,
|
| 198 |
+
"grad_norm": 0.26080241799354553,
|
| 199 |
+
"learning_rate": 1.2737430167597766e-05,
|
| 200 |
+
"loss": 0.4265,
|
| 201 |
+
"num_tokens": 198600121.0,
|
| 202 |
+
"step": 115
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.13411567476948869,
|
| 206 |
+
"grad_norm": 0.21047507226467133,
|
| 207 |
+
"learning_rate": 1.3296089385474861e-05,
|
| 208 |
+
"loss": 0.427,
|
| 209 |
+
"num_tokens": 207208210.0,
|
| 210 |
+
"step": 120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.13970382788488406,
|
| 214 |
+
"grad_norm": 0.49889320135116577,
|
| 215 |
+
"learning_rate": 1.3854748603351957e-05,
|
| 216 |
+
"loss": 0.4213,
|
| 217 |
+
"num_tokens": 215841764.0,
|
| 218 |
+
"step": 125
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.1452919810002794,
|
| 222 |
+
"grad_norm": 0.48499205708503723,
|
| 223 |
+
"learning_rate": 1.4413407821229052e-05,
|
| 224 |
+
"loss": 0.4198,
|
| 225 |
+
"num_tokens": 224461916.0,
|
| 226 |
+
"step": 130
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.15088013411567477,
|
| 230 |
+
"grad_norm": 0.28938624262809753,
|
| 231 |
+
"learning_rate": 1.4972067039106146e-05,
|
| 232 |
+
"loss": 0.4172,
|
| 233 |
+
"num_tokens": 233116996.0,
|
| 234 |
+
"step": 135
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.15646828723107012,
|
| 238 |
+
"grad_norm": 0.41849035024642944,
|
| 239 |
+
"learning_rate": 1.553072625698324e-05,
|
| 240 |
+
"loss": 0.4143,
|
| 241 |
+
"num_tokens": 241767774.0,
|
| 242 |
+
"step": 140
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.1620564403464655,
|
| 246 |
+
"grad_norm": 0.2590814530849457,
|
| 247 |
+
"learning_rate": 1.6089385474860336e-05,
|
| 248 |
+
"loss": 0.4099,
|
| 249 |
+
"num_tokens": 250387551.0,
|
| 250 |
+
"step": 145
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.16764459346186086,
|
| 254 |
+
"grad_norm": 0.3640440106391907,
|
| 255 |
+
"learning_rate": 1.664804469273743e-05,
|
| 256 |
+
"loss": 0.4079,
|
| 257 |
+
"num_tokens": 259008641.0,
|
| 258 |
+
"step": 150
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.1732327465772562,
|
| 262 |
+
"grad_norm": 0.2570585012435913,
|
| 263 |
+
"learning_rate": 1.7206703910614527e-05,
|
| 264 |
+
"loss": 0.4072,
|
| 265 |
+
"num_tokens": 267655165.0,
|
| 266 |
+
"step": 155
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.17882089969265158,
|
| 270 |
+
"grad_norm": 0.31423676013946533,
|
| 271 |
+
"learning_rate": 1.776536312849162e-05,
|
| 272 |
+
"loss": 0.4035,
|
| 273 |
+
"num_tokens": 276311055.0,
|
| 274 |
+
"step": 160
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.18440905280804695,
|
| 278 |
+
"grad_norm": 0.3440604507923126,
|
| 279 |
+
"learning_rate": 1.8324022346368716e-05,
|
| 280 |
+
"loss": 0.4049,
|
| 281 |
+
"num_tokens": 284946584.0,
|
| 282 |
+
"step": 165
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.1899972059234423,
|
| 286 |
+
"grad_norm": 0.21540623903274536,
|
| 287 |
+
"learning_rate": 1.888268156424581e-05,
|
| 288 |
+
"loss": 0.4002,
|
| 289 |
+
"num_tokens": 293559223.0,
|
| 290 |
+
"step": 170
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.19558535903883767,
|
| 294 |
+
"grad_norm": 0.23785561323165894,
|
| 295 |
+
"learning_rate": 1.9441340782122907e-05,
|
| 296 |
+
"loss": 0.4022,
|
| 297 |
+
"num_tokens": 302183283.0,
|
| 298 |
+
"step": 175
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.20117351215423301,
|
| 302 |
+
"grad_norm": 0.26867231726646423,
|
| 303 |
+
"learning_rate": 2e-05,
|
| 304 |
+
"loss": 0.3957,
|
| 305 |
+
"num_tokens": 310770434.0,
|
| 306 |
+
"step": 180
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.2067616652696284,
|
| 310 |
+
"grad_norm": 0.300030380487442,
|
| 311 |
+
"learning_rate": 1.9937849596022375e-05,
|
| 312 |
+
"loss": 0.3966,
|
| 313 |
+
"num_tokens": 319421031.0,
|
| 314 |
+
"step": 185
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.21234981838502376,
|
| 318 |
+
"grad_norm": 0.3302135467529297,
|
| 319 |
+
"learning_rate": 1.9875699192044752e-05,
|
| 320 |
+
"loss": 0.3951,
|
| 321 |
+
"num_tokens": 328071145.0,
|
| 322 |
+
"step": 190
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.2179379715004191,
|
| 326 |
+
"grad_norm": 0.29629579186439514,
|
| 327 |
+
"learning_rate": 1.9813548788067125e-05,
|
| 328 |
+
"loss": 0.3937,
|
| 329 |
+
"num_tokens": 336706183.0,
|
| 330 |
+
"step": 195
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.22352612461581448,
|
| 334 |
+
"grad_norm": 0.28898075222969055,
|
| 335 |
+
"learning_rate": 1.97513983840895e-05,
|
| 336 |
+
"loss": 0.3906,
|
| 337 |
+
"num_tokens": 345411712.0,
|
| 338 |
+
"step": 200
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.22911427773120985,
|
| 342 |
+
"grad_norm": 0.3078921139240265,
|
| 343 |
+
"learning_rate": 1.9689247980111872e-05,
|
| 344 |
+
"loss": 0.3898,
|
| 345 |
+
"num_tokens": 354033114.0,
|
| 346 |
+
"step": 205
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2347024308466052,
|
| 350 |
+
"grad_norm": 0.4353577792644501,
|
| 351 |
+
"learning_rate": 1.9627097576134246e-05,
|
| 352 |
+
"loss": 0.388,
|
| 353 |
+
"num_tokens": 362630287.0,
|
| 354 |
+
"step": 210
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.24029058396200056,
|
| 358 |
+
"grad_norm": 0.309552937746048,
|
| 359 |
+
"learning_rate": 1.9564947172156622e-05,
|
| 360 |
+
"loss": 0.3909,
|
| 361 |
+
"num_tokens": 371235488.0,
|
| 362 |
+
"step": 215
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.2458787370773959,
|
| 366 |
+
"grad_norm": 0.2993320822715759,
|
| 367 |
+
"learning_rate": 1.9502796768178996e-05,
|
| 368 |
+
"loss": 0.3849,
|
| 369 |
+
"num_tokens": 379873019.0,
|
| 370 |
+
"step": 220
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.2514668901927913,
|
| 374 |
+
"grad_norm": 0.30897048115730286,
|
| 375 |
+
"learning_rate": 1.944064636420137e-05,
|
| 376 |
+
"loss": 0.3836,
|
| 377 |
+
"num_tokens": 388483293.0,
|
| 378 |
+
"step": 225
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.2570550433081866,
|
| 382 |
+
"grad_norm": 0.319886714220047,
|
| 383 |
+
"learning_rate": 1.9378495960223743e-05,
|
| 384 |
+
"loss": 0.3858,
|
| 385 |
+
"num_tokens": 397132035.0,
|
| 386 |
+
"step": 230
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 0.262643196423582,
|
| 390 |
+
"grad_norm": 0.3353484272956848,
|
| 391 |
+
"learning_rate": 1.9316345556246116e-05,
|
| 392 |
+
"loss": 0.3815,
|
| 393 |
+
"num_tokens": 405760877.0,
|
| 394 |
+
"step": 235
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.26823134953897737,
|
| 398 |
+
"grad_norm": 0.3035387396812439,
|
| 399 |
+
"learning_rate": 1.925419515226849e-05,
|
| 400 |
+
"loss": 0.3811,
|
| 401 |
+
"num_tokens": 414412147.0,
|
| 402 |
+
"step": 240
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.2738195026543727,
|
| 406 |
+
"grad_norm": 0.2977229654788971,
|
| 407 |
+
"learning_rate": 1.9192044748290866e-05,
|
| 408 |
+
"loss": 0.381,
|
| 409 |
+
"num_tokens": 423027670.0,
|
| 410 |
+
"step": 245
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.2794076557697681,
|
| 414 |
+
"grad_norm": 0.23410959541797638,
|
| 415 |
+
"learning_rate": 1.912989434431324e-05,
|
| 416 |
+
"loss": 0.3784,
|
| 417 |
+
"num_tokens": 431706857.0,
|
| 418 |
+
"step": 250
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.28499580888516346,
|
| 422 |
+
"grad_norm": 0.2829587161540985,
|
| 423 |
+
"learning_rate": 1.9067743940335613e-05,
|
| 424 |
+
"loss": 0.3798,
|
| 425 |
+
"num_tokens": 440317430.0,
|
| 426 |
+
"step": 255
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.2905839620005588,
|
| 430 |
+
"grad_norm": 0.26716259121894836,
|
| 431 |
+
"learning_rate": 1.9005593536357987e-05,
|
| 432 |
+
"loss": 0.379,
|
| 433 |
+
"num_tokens": 448976567.0,
|
| 434 |
+
"step": 260
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 0.2961721151159542,
|
| 438 |
+
"grad_norm": 0.2489883005619049,
|
| 439 |
+
"learning_rate": 1.894344313238036e-05,
|
| 440 |
+
"loss": 0.3768,
|
| 441 |
+
"num_tokens": 457608742.0,
|
| 442 |
+
"step": 265
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.30176026823134955,
|
| 446 |
+
"grad_norm": 0.25023195147514343,
|
| 447 |
+
"learning_rate": 1.8881292728402737e-05,
|
| 448 |
+
"loss": 0.3743,
|
| 449 |
+
"num_tokens": 466243999.0,
|
| 450 |
+
"step": 270
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.3073484213467449,
|
| 454 |
+
"grad_norm": 0.23837079107761383,
|
| 455 |
+
"learning_rate": 1.881914232442511e-05,
|
| 456 |
+
"loss": 0.3733,
|
| 457 |
+
"num_tokens": 474886567.0,
|
| 458 |
+
"step": 275
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.31293657446214024,
|
| 462 |
+
"grad_norm": 0.2237701565027237,
|
| 463 |
+
"learning_rate": 1.8756991920447484e-05,
|
| 464 |
+
"loss": 0.3741,
|
| 465 |
+
"num_tokens": 483548448.0,
|
| 466 |
+
"step": 280
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.31852472757753564,
|
| 470 |
+
"grad_norm": 0.2825288474559784,
|
| 471 |
+
"learning_rate": 1.869484151646986e-05,
|
| 472 |
+
"loss": 0.3733,
|
| 473 |
+
"num_tokens": 492194335.0,
|
| 474 |
+
"step": 285
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.324112880692931,
|
| 478 |
+
"grad_norm": 0.4711460769176483,
|
| 479 |
+
"learning_rate": 1.863269111249223e-05,
|
| 480 |
+
"loss": 0.3706,
|
| 481 |
+
"num_tokens": 500857334.0,
|
| 482 |
+
"step": 290
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.3297010338083263,
|
| 486 |
+
"grad_norm": 0.3319377601146698,
|
| 487 |
+
"learning_rate": 1.8570540708514607e-05,
|
| 488 |
+
"loss": 0.3684,
|
| 489 |
+
"num_tokens": 509470803.0,
|
| 490 |
+
"step": 295
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.3352891869237217,
|
| 494 |
+
"grad_norm": 0.25508102774620056,
|
| 495 |
+
"learning_rate": 1.850839030453698e-05,
|
| 496 |
+
"loss": 0.3703,
|
| 497 |
+
"num_tokens": 518116395.0,
|
| 498 |
+
"step": 300
|
| 499 |
+
},
|
| 500 |
+
{
|
| 501 |
+
"epoch": 0.34087734003911707,
|
| 502 |
+
"grad_norm": 0.2849508225917816,
|
| 503 |
+
"learning_rate": 1.8446239900559354e-05,
|
| 504 |
+
"loss": 0.3667,
|
| 505 |
+
"num_tokens": 526715030.0,
|
| 506 |
+
"step": 305
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.3464654931545124,
|
| 510 |
+
"grad_norm": 0.3298902213573456,
|
| 511 |
+
"learning_rate": 1.838408949658173e-05,
|
| 512 |
+
"loss": 0.3674,
|
| 513 |
+
"num_tokens": 535330384.0,
|
| 514 |
+
"step": 310
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.3520536462699078,
|
| 518 |
+
"grad_norm": 0.28954699635505676,
|
| 519 |
+
"learning_rate": 1.8321939092604105e-05,
|
| 520 |
+
"loss": 0.3668,
|
| 521 |
+
"num_tokens": 543982535.0,
|
| 522 |
+
"step": 315
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.35764179938530316,
|
| 526 |
+
"grad_norm": 0.26005271077156067,
|
| 527 |
+
"learning_rate": 1.8259788688626478e-05,
|
| 528 |
+
"loss": 0.3654,
|
| 529 |
+
"num_tokens": 552673445.0,
|
| 530 |
+
"step": 320
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 0.3632299525006985,
|
| 534 |
+
"grad_norm": 0.26138827204704285,
|
| 535 |
+
"learning_rate": 1.819763828464885e-05,
|
| 536 |
+
"loss": 0.3657,
|
| 537 |
+
"num_tokens": 561284033.0,
|
| 538 |
+
"step": 325
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.3688181056160939,
|
| 542 |
+
"grad_norm": 0.2150503545999527,
|
| 543 |
+
"learning_rate": 1.8135487880671225e-05,
|
| 544 |
+
"loss": 0.3617,
|
| 545 |
+
"num_tokens": 569844238.0,
|
| 546 |
+
"step": 330
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.37440625873148925,
|
| 550 |
+
"grad_norm": 0.25445595383644104,
|
| 551 |
+
"learning_rate": 1.8073337476693598e-05,
|
| 552 |
+
"loss": 0.3633,
|
| 553 |
+
"num_tokens": 578513463.0,
|
| 554 |
+
"step": 335
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 0.3799944118468846,
|
| 558 |
+
"grad_norm": 0.25044742226600647,
|
| 559 |
+
"learning_rate": 1.8011187072715975e-05,
|
| 560 |
+
"loss": 0.3623,
|
| 561 |
+
"num_tokens": 587170364.0,
|
| 562 |
+
"step": 340
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.38558256496227994,
|
| 566 |
+
"grad_norm": 0.2201726734638214,
|
| 567 |
+
"learning_rate": 1.794903666873835e-05,
|
| 568 |
+
"loss": 0.363,
|
| 569 |
+
"num_tokens": 595780927.0,
|
| 570 |
+
"step": 345
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.39117071807767534,
|
| 574 |
+
"grad_norm": 0.24220991134643555,
|
| 575 |
+
"learning_rate": 1.7886886264760722e-05,
|
| 576 |
+
"loss": 0.3595,
|
| 577 |
+
"num_tokens": 604423673.0,
|
| 578 |
+
"step": 350
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.3967588711930707,
|
| 582 |
+
"grad_norm": 0.27938011288642883,
|
| 583 |
+
"learning_rate": 1.7824735860783095e-05,
|
| 584 |
+
"loss": 0.3625,
|
| 585 |
+
"num_tokens": 613077425.0,
|
| 586 |
+
"step": 355
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.40234702430846603,
|
| 590 |
+
"grad_norm": 0.3587215542793274,
|
| 591 |
+
"learning_rate": 1.776258545680547e-05,
|
| 592 |
+
"loss": 0.3603,
|
| 593 |
+
"num_tokens": 621679546.0,
|
| 594 |
+
"step": 360
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.40793517742386143,
|
| 598 |
+
"grad_norm": 0.24406756460666656,
|
| 599 |
+
"learning_rate": 1.7700435052827846e-05,
|
| 600 |
+
"loss": 0.358,
|
| 601 |
+
"num_tokens": 630345024.0,
|
| 602 |
+
"step": 365
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.4135233305392568,
|
| 606 |
+
"grad_norm": 0.2351740151643753,
|
| 607 |
+
"learning_rate": 1.763828464885022e-05,
|
| 608 |
+
"loss": 0.357,
|
| 609 |
+
"num_tokens": 638998446.0,
|
| 610 |
+
"step": 370
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.4191114836546521,
|
| 614 |
+
"grad_norm": 0.25008639693260193,
|
| 615 |
+
"learning_rate": 1.7576134244872592e-05,
|
| 616 |
+
"loss": 0.3568,
|
| 617 |
+
"num_tokens": 647620127.0,
|
| 618 |
+
"step": 375
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.4246996367700475,
|
| 622 |
+
"grad_norm": 0.28882575035095215,
|
| 623 |
+
"learning_rate": 1.751398384089497e-05,
|
| 624 |
+
"loss": 0.357,
|
| 625 |
+
"num_tokens": 656263086.0,
|
| 626 |
+
"step": 380
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.43028778988544286,
|
| 630 |
+
"grad_norm": 0.24458937346935272,
|
| 631 |
+
"learning_rate": 1.745183343691734e-05,
|
| 632 |
+
"loss": 0.3565,
|
| 633 |
+
"num_tokens": 664900751.0,
|
| 634 |
+
"step": 385
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.4358759430008382,
|
| 638 |
+
"grad_norm": 0.2362358570098877,
|
| 639 |
+
"learning_rate": 1.7389683032939716e-05,
|
| 640 |
+
"loss": 0.3553,
|
| 641 |
+
"num_tokens": 673566366.0,
|
| 642 |
+
"step": 390
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 0.4414640961162336,
|
| 646 |
+
"grad_norm": 0.3116516172885895,
|
| 647 |
+
"learning_rate": 1.732753262896209e-05,
|
| 648 |
+
"loss": 0.3562,
|
| 649 |
+
"num_tokens": 682217285.0,
|
| 650 |
+
"step": 395
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 0.44705224923162895,
|
| 654 |
+
"grad_norm": 0.2760963439941406,
|
| 655 |
+
"learning_rate": 1.7265382224984463e-05,
|
| 656 |
+
"loss": 0.3532,
|
| 657 |
+
"num_tokens": 690882999.0,
|
| 658 |
+
"step": 400
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.4526404023470243,
|
| 662 |
+
"grad_norm": 0.2616076171398163,
|
| 663 |
+
"learning_rate": 1.720323182100684e-05,
|
| 664 |
+
"loss": 0.3547,
|
| 665 |
+
"num_tokens": 699464323.0,
|
| 666 |
+
"step": 405
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.4582285554624197,
|
| 670 |
+
"grad_norm": 0.2745835483074188,
|
| 671 |
+
"learning_rate": 1.7141081417029213e-05,
|
| 672 |
+
"loss": 0.3543,
|
| 673 |
+
"num_tokens": 708050644.0,
|
| 674 |
+
"step": 410
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.46381670857781504,
|
| 678 |
+
"grad_norm": 0.22677594423294067,
|
| 679 |
+
"learning_rate": 1.7078931013051587e-05,
|
| 680 |
+
"loss": 0.3545,
|
| 681 |
+
"num_tokens": 716706828.0,
|
| 682 |
+
"step": 415
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.4694048616932104,
|
| 686 |
+
"grad_norm": 0.2808341383934021,
|
| 687 |
+
"learning_rate": 1.701678060907396e-05,
|
| 688 |
+
"loss": 0.3548,
|
| 689 |
+
"num_tokens": 725378942.0,
|
| 690 |
+
"step": 420
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.47499301480860573,
|
| 694 |
+
"grad_norm": 0.23508451879024506,
|
| 695 |
+
"learning_rate": 1.6954630205096334e-05,
|
| 696 |
+
"loss": 0.3509,
|
| 697 |
+
"num_tokens": 734043136.0,
|
| 698 |
+
"step": 425
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.48058116792400113,
|
| 702 |
+
"grad_norm": 0.254522442817688,
|
| 703 |
+
"learning_rate": 1.6892479801118707e-05,
|
| 704 |
+
"loss": 0.3511,
|
| 705 |
+
"num_tokens": 742633173.0,
|
| 706 |
+
"step": 430
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.4861693210393965,
|
| 710 |
+
"grad_norm": 0.31279993057250977,
|
| 711 |
+
"learning_rate": 1.6830329397141084e-05,
|
| 712 |
+
"loss": 0.351,
|
| 713 |
+
"num_tokens": 751312188.0,
|
| 714 |
+
"step": 435
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 0.4917574741547918,
|
| 718 |
+
"grad_norm": 0.25775179266929626,
|
| 719 |
+
"learning_rate": 1.6768178993163457e-05,
|
| 720 |
+
"loss": 0.3501,
|
| 721 |
+
"num_tokens": 759946023.0,
|
| 722 |
+
"step": 440
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 0.4973456272701872,
|
| 726 |
+
"grad_norm": 0.2667147219181061,
|
| 727 |
+
"learning_rate": 1.670602858918583e-05,
|
| 728 |
+
"loss": 0.349,
|
| 729 |
+
"num_tokens": 768604979.0,
|
| 730 |
+
"step": 445
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.5029337803855826,
|
| 734 |
+
"grad_norm": 0.28277674317359924,
|
| 735 |
+
"learning_rate": 1.6643878185208204e-05,
|
| 736 |
+
"loss": 0.348,
|
| 737 |
+
"num_tokens": 777238572.0,
|
| 738 |
+
"step": 450
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.508521933500978,
|
| 742 |
+
"grad_norm": 0.24286143481731415,
|
| 743 |
+
"learning_rate": 1.6581727781230577e-05,
|
| 744 |
+
"loss": 0.3481,
|
| 745 |
+
"num_tokens": 785827036.0,
|
| 746 |
+
"step": 455
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.5141100866163733,
|
| 750 |
+
"grad_norm": 0.23307713866233826,
|
| 751 |
+
"learning_rate": 1.6519577377252954e-05,
|
| 752 |
+
"loss": 0.3478,
|
| 753 |
+
"num_tokens": 794445531.0,
|
| 754 |
+
"step": 460
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.5196982397317687,
|
| 758 |
+
"grad_norm": 0.23410995304584503,
|
| 759 |
+
"learning_rate": 1.6457426973275328e-05,
|
| 760 |
+
"loss": 0.3455,
|
| 761 |
+
"num_tokens": 803071897.0,
|
| 762 |
+
"step": 465
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.525286392847164,
|
| 766 |
+
"grad_norm": 0.2380787432193756,
|
| 767 |
+
"learning_rate": 1.63952765692977e-05,
|
| 768 |
+
"loss": 0.3455,
|
| 769 |
+
"num_tokens": 811671356.0,
|
| 770 |
+
"step": 470
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 0.5308745459625593,
|
| 774 |
+
"grad_norm": 0.23634526133537292,
|
| 775 |
+
"learning_rate": 1.6333126165320078e-05,
|
| 776 |
+
"loss": 0.3466,
|
| 777 |
+
"num_tokens": 820292054.0,
|
| 778 |
+
"step": 475
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 0.5364626990779547,
|
| 782 |
+
"grad_norm": 0.25275230407714844,
|
| 783 |
+
"learning_rate": 1.6270975761342448e-05,
|
| 784 |
+
"loss": 0.3461,
|
| 785 |
+
"num_tokens": 828956490.0,
|
| 786 |
+
"step": 480
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 0.5420508521933501,
|
| 790 |
+
"grad_norm": 0.23368898034095764,
|
| 791 |
+
"learning_rate": 1.6208825357364825e-05,
|
| 792 |
+
"loss": 0.3461,
|
| 793 |
+
"num_tokens": 837575876.0,
|
| 794 |
+
"step": 485
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.5476390053087454,
|
| 798 |
+
"grad_norm": 0.22830277681350708,
|
| 799 |
+
"learning_rate": 1.6146674953387198e-05,
|
| 800 |
+
"loss": 0.3437,
|
| 801 |
+
"num_tokens": 846242404.0,
|
| 802 |
+
"step": 490
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.5532271584241408,
|
| 806 |
+
"grad_norm": 0.24559421837329865,
|
| 807 |
+
"learning_rate": 1.608452454940957e-05,
|
| 808 |
+
"loss": 0.3439,
|
| 809 |
+
"num_tokens": 854952393.0,
|
| 810 |
+
"step": 495
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.5588153115395362,
|
| 814 |
+
"grad_norm": 0.4303223192691803,
|
| 815 |
+
"learning_rate": 1.602237414543195e-05,
|
| 816 |
+
"loss": 0.3455,
|
| 817 |
+
"num_tokens": 863588754.0,
|
| 818 |
+
"step": 500
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.5644034646549315,
|
| 822 |
+
"grad_norm": 0.2650391161441803,
|
| 823 |
+
"learning_rate": 1.5960223741454322e-05,
|
| 824 |
+
"loss": 0.3434,
|
| 825 |
+
"num_tokens": 872242175.0,
|
| 826 |
+
"step": 505
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.5699916177703269,
|
| 830 |
+
"grad_norm": 0.34314268827438354,
|
| 831 |
+
"learning_rate": 1.5898073337476695e-05,
|
| 832 |
+
"loss": 0.3436,
|
| 833 |
+
"num_tokens": 880858359.0,
|
| 834 |
+
"step": 510
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.5755797708857223,
|
| 838 |
+
"grad_norm": 0.2963222861289978,
|
| 839 |
+
"learning_rate": 1.583592293349907e-05,
|
| 840 |
+
"loss": 0.3409,
|
| 841 |
+
"num_tokens": 889452124.0,
|
| 842 |
+
"step": 515
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 0.5811679240011176,
|
| 846 |
+
"grad_norm": 0.2436487376689911,
|
| 847 |
+
"learning_rate": 1.5773772529521442e-05,
|
| 848 |
+
"loss": 0.3405,
|
| 849 |
+
"num_tokens": 898106005.0,
|
| 850 |
+
"step": 520
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.586756077116513,
|
| 854 |
+
"grad_norm": 0.26480334997177124,
|
| 855 |
+
"learning_rate": 1.5711622125543816e-05,
|
| 856 |
+
"loss": 0.342,
|
| 857 |
+
"num_tokens": 906759880.0,
|
| 858 |
+
"step": 525
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.5923442302319084,
|
| 862 |
+
"grad_norm": 0.24269545078277588,
|
| 863 |
+
"learning_rate": 1.5649471721566192e-05,
|
| 864 |
+
"loss": 0.3404,
|
| 865 |
+
"num_tokens": 915407081.0,
|
| 866 |
+
"step": 530
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5979323833473037,
|
| 870 |
+
"grad_norm": 0.25484395027160645,
|
| 871 |
+
"learning_rate": 1.5587321317588566e-05,
|
| 872 |
+
"loss": 0.3414,
|
| 873 |
+
"num_tokens": 924034724.0,
|
| 874 |
+
"step": 535
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 0.6035205364626991,
|
| 878 |
+
"grad_norm": 0.26847922801971436,
|
| 879 |
+
"learning_rate": 1.552517091361094e-05,
|
| 880 |
+
"loss": 0.3396,
|
| 881 |
+
"num_tokens": 932639422.0,
|
| 882 |
+
"step": 540
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 0.6091086895780944,
|
| 886 |
+
"grad_norm": 0.3018784821033478,
|
| 887 |
+
"learning_rate": 1.5463020509633313e-05,
|
| 888 |
+
"loss": 0.3388,
|
| 889 |
+
"num_tokens": 941252618.0,
|
| 890 |
+
"step": 545
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.6146968426934898,
|
| 894 |
+
"grad_norm": 0.2776123583316803,
|
| 895 |
+
"learning_rate": 1.5400870105655686e-05,
|
| 896 |
+
"loss": 0.3378,
|
| 897 |
+
"num_tokens": 949916767.0,
|
| 898 |
+
"step": 550
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 0.6202849958088852,
|
| 902 |
+
"grad_norm": 0.26316747069358826,
|
| 903 |
+
"learning_rate": 1.5338719701678063e-05,
|
| 904 |
+
"loss": 0.3377,
|
| 905 |
+
"num_tokens": 958556988.0,
|
| 906 |
+
"step": 555
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.6258731489242805,
|
| 910 |
+
"grad_norm": 0.35456159710884094,
|
| 911 |
+
"learning_rate": 1.5276569297700436e-05,
|
| 912 |
+
"loss": 0.336,
|
| 913 |
+
"num_tokens": 967198821.0,
|
| 914 |
+
"step": 560
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.6314613020396759,
|
| 918 |
+
"grad_norm": 0.2805976867675781,
|
| 919 |
+
"learning_rate": 1.5214418893722812e-05,
|
| 920 |
+
"loss": 0.3371,
|
| 921 |
+
"num_tokens": 975836394.0,
|
| 922 |
+
"step": 565
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.6370494551550713,
|
| 926 |
+
"grad_norm": 0.3051447868347168,
|
| 927 |
+
"learning_rate": 1.5152268489745185e-05,
|
| 928 |
+
"loss": 0.3355,
|
| 929 |
+
"num_tokens": 984478918.0,
|
| 930 |
+
"step": 570
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.6426376082704666,
|
| 934 |
+
"grad_norm": 0.29085445404052734,
|
| 935 |
+
"learning_rate": 1.5090118085767558e-05,
|
| 936 |
+
"loss": 0.3349,
|
| 937 |
+
"num_tokens": 993082498.0,
|
| 938 |
+
"step": 575
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 0.648225761385862,
|
| 942 |
+
"grad_norm": 0.21163810789585114,
|
| 943 |
+
"learning_rate": 1.5027967681789932e-05,
|
| 944 |
+
"loss": 0.3363,
|
| 945 |
+
"num_tokens": 1001741153.0,
|
| 946 |
+
"step": 580
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 0.6538139145012574,
|
| 950 |
+
"grad_norm": 0.221357524394989,
|
| 951 |
+
"learning_rate": 1.4965817277812307e-05,
|
| 952 |
+
"loss": 0.3358,
|
| 953 |
+
"num_tokens": 1010394285.0,
|
| 954 |
+
"step": 585
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.6594020676166527,
|
| 958 |
+
"grad_norm": 0.2421073317527771,
|
| 959 |
+
"learning_rate": 1.4903666873834682e-05,
|
| 960 |
+
"loss": 0.3345,
|
| 961 |
+
"num_tokens": 1019057041.0,
|
| 962 |
+
"step": 590
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.664990220732048,
|
| 966 |
+
"grad_norm": 0.32805293798446655,
|
| 967 |
+
"learning_rate": 1.4841516469857056e-05,
|
| 968 |
+
"loss": 0.3335,
|
| 969 |
+
"num_tokens": 1027673717.0,
|
| 970 |
+
"step": 595
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.6705783738474435,
|
| 974 |
+
"grad_norm": 0.25039365887641907,
|
| 975 |
+
"learning_rate": 1.477936606587943e-05,
|
| 976 |
+
"loss": 0.3346,
|
| 977 |
+
"num_tokens": 1036289387.0,
|
| 978 |
+
"step": 600
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.6761665269628387,
|
| 982 |
+
"grad_norm": 0.2505406141281128,
|
| 983 |
+
"learning_rate": 1.4717215661901802e-05,
|
| 984 |
+
"loss": 0.3344,
|
| 985 |
+
"num_tokens": 1044956336.0,
|
| 986 |
+
"step": 605
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 0.6817546800782341,
|
| 990 |
+
"grad_norm": 0.21238237619400024,
|
| 991 |
+
"learning_rate": 1.4655065257924177e-05,
|
| 992 |
+
"loss": 0.3313,
|
| 993 |
+
"num_tokens": 1053596820.0,
|
| 994 |
+
"step": 610
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 0.6873428331936295,
|
| 998 |
+
"grad_norm": 0.2559036910533905,
|
| 999 |
+
"learning_rate": 1.4592914853946551e-05,
|
| 1000 |
+
"loss": 0.3318,
|
| 1001 |
+
"num_tokens": 1062244415.0,
|
| 1002 |
+
"step": 615
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 0.6929309863090248,
|
| 1006 |
+
"grad_norm": 0.23106950521469116,
|
| 1007 |
+
"learning_rate": 1.4530764449968926e-05,
|
| 1008 |
+
"loss": 0.3309,
|
| 1009 |
+
"num_tokens": 1070875234.0,
|
| 1010 |
+
"step": 620
|
| 1011 |
+
},
|
| 1012 |
+
{
|
| 1013 |
+
"epoch": 0.6985191394244202,
|
| 1014 |
+
"grad_norm": 0.24224470555782318,
|
| 1015 |
+
"learning_rate": 1.4468614045991301e-05,
|
| 1016 |
+
"loss": 0.3317,
|
| 1017 |
+
"num_tokens": 1079478349.0,
|
| 1018 |
+
"step": 625
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.7041072925398156,
|
| 1022 |
+
"grad_norm": 0.2289455533027649,
|
| 1023 |
+
"learning_rate": 1.4406463642013675e-05,
|
| 1024 |
+
"loss": 0.3325,
|
| 1025 |
+
"num_tokens": 1088152645.0,
|
| 1026 |
+
"step": 630
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.7096954456552109,
|
| 1030 |
+
"grad_norm": 0.23123560845851898,
|
| 1031 |
+
"learning_rate": 1.434431323803605e-05,
|
| 1032 |
+
"loss": 0.3315,
|
| 1033 |
+
"num_tokens": 1096793450.0,
|
| 1034 |
+
"step": 635
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.7152835987706063,
|
| 1038 |
+
"grad_norm": 0.2753809988498688,
|
| 1039 |
+
"learning_rate": 1.4282162834058421e-05,
|
| 1040 |
+
"loss": 0.3295,
|
| 1041 |
+
"num_tokens": 1105421755.0,
|
| 1042 |
+
"step": 640
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 0.7208717518860017,
|
| 1046 |
+
"grad_norm": 0.19695010781288147,
|
| 1047 |
+
"learning_rate": 1.4220012430080797e-05,
|
| 1048 |
+
"loss": 0.3297,
|
| 1049 |
+
"num_tokens": 1114063613.0,
|
| 1050 |
+
"step": 645
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 0.726459905001397,
|
| 1054 |
+
"grad_norm": 0.23159605264663696,
|
| 1055 |
+
"learning_rate": 1.415786202610317e-05,
|
| 1056 |
+
"loss": 0.3287,
|
| 1057 |
+
"num_tokens": 1122701970.0,
|
| 1058 |
+
"step": 650
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 0.7320480581167924,
|
| 1062 |
+
"grad_norm": 0.2736544609069824,
|
| 1063 |
+
"learning_rate": 1.4095711622125545e-05,
|
| 1064 |
+
"loss": 0.3292,
|
| 1065 |
+
"num_tokens": 1131362655.0,
|
| 1066 |
+
"step": 655
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 0.7376362112321878,
|
| 1070 |
+
"grad_norm": 0.21057793498039246,
|
| 1071 |
+
"learning_rate": 1.403356121814792e-05,
|
| 1072 |
+
"loss": 0.3301,
|
| 1073 |
+
"num_tokens": 1139970963.0,
|
| 1074 |
+
"step": 660
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.7432243643475831,
|
| 1078 |
+
"grad_norm": 0.24804027378559113,
|
| 1079 |
+
"learning_rate": 1.3971410814170294e-05,
|
| 1080 |
+
"loss": 0.3292,
|
| 1081 |
+
"num_tokens": 1148655402.0,
|
| 1082 |
+
"step": 665
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 0.7488125174629785,
|
| 1086 |
+
"grad_norm": 0.26707762479782104,
|
| 1087 |
+
"learning_rate": 1.3909260410192667e-05,
|
| 1088 |
+
"loss": 0.3288,
|
| 1089 |
+
"num_tokens": 1157277819.0,
|
| 1090 |
+
"step": 670
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.7544006705783739,
|
| 1094 |
+
"grad_norm": 0.22491665184497833,
|
| 1095 |
+
"learning_rate": 1.384711000621504e-05,
|
| 1096 |
+
"loss": 0.3275,
|
| 1097 |
+
"num_tokens": 1165874070.0,
|
| 1098 |
+
"step": 675
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.7599888236937692,
|
| 1102 |
+
"grad_norm": 0.35867735743522644,
|
| 1103 |
+
"learning_rate": 1.3784959602237416e-05,
|
| 1104 |
+
"loss": 0.3259,
|
| 1105 |
+
"num_tokens": 1174553674.0,
|
| 1106 |
+
"step": 680
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 0.7655769768091646,
|
| 1110 |
+
"grad_norm": 0.2906293272972107,
|
| 1111 |
+
"learning_rate": 1.372280919825979e-05,
|
| 1112 |
+
"loss": 0.3275,
|
| 1113 |
+
"num_tokens": 1183203660.0,
|
| 1114 |
+
"step": 685
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 0.7711651299245599,
|
| 1118 |
+
"grad_norm": 0.2248237431049347,
|
| 1119 |
+
"learning_rate": 1.3660658794282164e-05,
|
| 1120 |
+
"loss": 0.3257,
|
| 1121 |
+
"num_tokens": 1191792299.0,
|
| 1122 |
+
"step": 690
|
| 1123 |
+
},
|
| 1124 |
+
{
|
| 1125 |
+
"epoch": 0.7767532830399553,
|
| 1126 |
+
"grad_norm": 0.22850936651229858,
|
| 1127 |
+
"learning_rate": 1.359850839030454e-05,
|
| 1128 |
+
"loss": 0.3241,
|
| 1129 |
+
"num_tokens": 1200443497.0,
|
| 1130 |
+
"step": 695
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.7823414361553507,
|
| 1134 |
+
"grad_norm": 0.2620466649532318,
|
| 1135 |
+
"learning_rate": 1.3536357986326911e-05,
|
| 1136 |
+
"loss": 0.3255,
|
| 1137 |
+
"num_tokens": 1209088496.0,
|
| 1138 |
+
"step": 700
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 0.787929589270746,
|
| 1142 |
+
"grad_norm": 0.2618216574192047,
|
| 1143 |
+
"learning_rate": 1.3474207582349286e-05,
|
| 1144 |
+
"loss": 0.3248,
|
| 1145 |
+
"num_tokens": 1217733862.0,
|
| 1146 |
+
"step": 705
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.7935177423861414,
|
| 1150 |
+
"grad_norm": 0.22120532393455505,
|
| 1151 |
+
"learning_rate": 1.341205717837166e-05,
|
| 1152 |
+
"loss": 0.3253,
|
| 1153 |
+
"num_tokens": 1226435221.0,
|
| 1154 |
+
"step": 710
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.7991058955015368,
|
| 1158 |
+
"grad_norm": 0.23882830142974854,
|
| 1159 |
+
"learning_rate": 1.3349906774394035e-05,
|
| 1160 |
+
"loss": 0.3247,
|
| 1161 |
+
"num_tokens": 1235039345.0,
|
| 1162 |
+
"step": 715
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.8046940486169321,
|
| 1166 |
+
"grad_norm": 0.2220090627670288,
|
| 1167 |
+
"learning_rate": 1.328775637041641e-05,
|
| 1168 |
+
"loss": 0.3242,
|
| 1169 |
+
"num_tokens": 1243676965.0,
|
| 1170 |
+
"step": 720
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.8102822017323275,
|
| 1174 |
+
"grad_norm": 0.2509444057941437,
|
| 1175 |
+
"learning_rate": 1.3225605966438783e-05,
|
| 1176 |
+
"loss": 0.3246,
|
| 1177 |
+
"num_tokens": 1252287521.0,
|
| 1178 |
+
"step": 725
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 0.8158703548477229,
|
| 1182 |
+
"grad_norm": 0.2144639939069748,
|
| 1183 |
+
"learning_rate": 1.3163455562461157e-05,
|
| 1184 |
+
"loss": 0.3219,
|
| 1185 |
+
"num_tokens": 1260906284.0,
|
| 1186 |
+
"step": 730
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.8214585079631181,
|
| 1190 |
+
"grad_norm": 0.24812334775924683,
|
| 1191 |
+
"learning_rate": 1.310130515848353e-05,
|
| 1192 |
+
"loss": 0.3216,
|
| 1193 |
+
"num_tokens": 1269550220.0,
|
| 1194 |
+
"step": 735
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 0.8270466610785135,
|
| 1198 |
+
"grad_norm": 0.25637102127075195,
|
| 1199 |
+
"learning_rate": 1.3039154754505905e-05,
|
| 1200 |
+
"loss": 0.3223,
|
| 1201 |
+
"num_tokens": 1278166875.0,
|
| 1202 |
+
"step": 740
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.832634814193909,
|
| 1206 |
+
"grad_norm": 0.2210138738155365,
|
| 1207 |
+
"learning_rate": 1.2977004350528279e-05,
|
| 1208 |
+
"loss": 0.3215,
|
| 1209 |
+
"num_tokens": 1286779173.0,
|
| 1210 |
+
"step": 745
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.8382229673093042,
|
| 1214 |
+
"grad_norm": 0.24274571239948273,
|
| 1215 |
+
"learning_rate": 1.2914853946550654e-05,
|
| 1216 |
+
"loss": 0.322,
|
| 1217 |
+
"num_tokens": 1295400109.0,
|
| 1218 |
+
"step": 750
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 0.8438111204246996,
|
| 1222 |
+
"grad_norm": 0.22785916924476624,
|
| 1223 |
+
"learning_rate": 1.2852703542573029e-05,
|
| 1224 |
+
"loss": 0.3212,
|
| 1225 |
+
"num_tokens": 1304038572.0,
|
| 1226 |
+
"step": 755
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 0.849399273540095,
|
| 1230 |
+
"grad_norm": 0.24811935424804688,
|
| 1231 |
+
"learning_rate": 1.2790553138595402e-05,
|
| 1232 |
+
"loss": 0.3208,
|
| 1233 |
+
"num_tokens": 1312695953.0,
|
| 1234 |
+
"step": 760
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.8549874266554903,
|
| 1238 |
+
"grad_norm": 0.2515169084072113,
|
| 1239 |
+
"learning_rate": 1.2728402734617776e-05,
|
| 1240 |
+
"loss": 0.3219,
|
| 1241 |
+
"num_tokens": 1321320330.0,
|
| 1242 |
+
"step": 765
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.8605755797708857,
|
| 1246 |
+
"grad_norm": 0.23009227216243744,
|
| 1247 |
+
"learning_rate": 1.266625233064015e-05,
|
| 1248 |
+
"loss": 0.32,
|
| 1249 |
+
"num_tokens": 1329933663.0,
|
| 1250 |
+
"step": 770
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 0.8661637328862811,
|
| 1254 |
+
"grad_norm": 0.286752313375473,
|
| 1255 |
+
"learning_rate": 1.2604101926662524e-05,
|
| 1256 |
+
"loss": 0.3191,
|
| 1257 |
+
"num_tokens": 1338601890.0,
|
| 1258 |
+
"step": 775
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.8717518860016764,
|
| 1262 |
+
"grad_norm": 0.25049400329589844,
|
| 1263 |
+
"learning_rate": 1.25419515226849e-05,
|
| 1264 |
+
"loss": 0.3193,
|
| 1265 |
+
"num_tokens": 1347191005.0,
|
| 1266 |
+
"step": 780
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.8773400391170718,
|
| 1270 |
+
"grad_norm": 0.3110709488391876,
|
| 1271 |
+
"learning_rate": 1.2479801118707273e-05,
|
| 1272 |
+
"loss": 0.3199,
|
| 1273 |
+
"num_tokens": 1355865305.0,
|
| 1274 |
+
"step": 785
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 0.8829281922324672,
|
| 1278 |
+
"grad_norm": 0.27292343974113464,
|
| 1279 |
+
"learning_rate": 1.2417650714729648e-05,
|
| 1280 |
+
"loss": 0.3186,
|
| 1281 |
+
"num_tokens": 1364495144.0,
|
| 1282 |
+
"step": 790
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 0.8885163453478625,
|
| 1286 |
+
"grad_norm": 0.24087272584438324,
|
| 1287 |
+
"learning_rate": 1.235550031075202e-05,
|
| 1288 |
+
"loss": 0.3179,
|
| 1289 |
+
"num_tokens": 1373161011.0,
|
| 1290 |
+
"step": 795
|
| 1291 |
+
},
|
| 1292 |
+
{
|
| 1293 |
+
"epoch": 0.8941044984632579,
|
| 1294 |
+
"grad_norm": 0.22793588042259216,
|
| 1295 |
+
"learning_rate": 1.2293349906774395e-05,
|
| 1296 |
+
"loss": 0.3175,
|
| 1297 |
+
"num_tokens": 1381821262.0,
|
| 1298 |
+
"step": 800
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.8996926515786533,
|
| 1302 |
+
"grad_norm": 0.26788079738616943,
|
| 1303 |
+
"learning_rate": 1.2231199502796768e-05,
|
| 1304 |
+
"loss": 0.3173,
|
| 1305 |
+
"num_tokens": 1390460262.0,
|
| 1306 |
+
"step": 805
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.9052808046940486,
|
| 1310 |
+
"grad_norm": 0.24791817367076874,
|
| 1311 |
+
"learning_rate": 1.2169049098819143e-05,
|
| 1312 |
+
"loss": 0.3198,
|
| 1313 |
+
"num_tokens": 1399107355.0,
|
| 1314 |
+
"step": 810
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.910868957809444,
|
| 1318 |
+
"grad_norm": 0.23244717717170715,
|
| 1319 |
+
"learning_rate": 1.2106898694841519e-05,
|
| 1320 |
+
"loss": 0.3178,
|
| 1321 |
+
"num_tokens": 1407743698.0,
|
| 1322 |
+
"step": 815
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.9164571109248394,
|
| 1326 |
+
"grad_norm": 0.22195950150489807,
|
| 1327 |
+
"learning_rate": 1.2044748290863892e-05,
|
| 1328 |
+
"loss": 0.3174,
|
| 1329 |
+
"num_tokens": 1416397325.0,
|
| 1330 |
+
"step": 820
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 0.9220452640402347,
|
| 1334 |
+
"grad_norm": 0.23812797665596008,
|
| 1335 |
+
"learning_rate": 1.1982597886886265e-05,
|
| 1336 |
+
"loss": 0.3172,
|
| 1337 |
+
"num_tokens": 1425035981.0,
|
| 1338 |
+
"step": 825
|
| 1339 |
+
},
|
| 1340 |
+
{
|
| 1341 |
+
"epoch": 0.9276334171556301,
|
| 1342 |
+
"grad_norm": 0.26328200101852417,
|
| 1343 |
+
"learning_rate": 1.1920447482908639e-05,
|
| 1344 |
+
"loss": 0.3165,
|
| 1345 |
+
"num_tokens": 1433658159.0,
|
| 1346 |
+
"step": 830
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.9332215702710255,
|
| 1350 |
+
"grad_norm": 0.29811593890190125,
|
| 1351 |
+
"learning_rate": 1.1858297078931014e-05,
|
| 1352 |
+
"loss": 0.3174,
|
| 1353 |
+
"num_tokens": 1442308046.0,
|
| 1354 |
+
"step": 835
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.9388097233864208,
|
| 1358 |
+
"grad_norm": 0.3524268567562103,
|
| 1359 |
+
"learning_rate": 1.1796146674953387e-05,
|
| 1360 |
+
"loss": 0.3134,
|
| 1361 |
+
"num_tokens": 1450897134.0,
|
| 1362 |
+
"step": 840
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 0.9443978765018162,
|
| 1366 |
+
"grad_norm": 0.29091647267341614,
|
| 1367 |
+
"learning_rate": 1.1733996270975763e-05,
|
| 1368 |
+
"loss": 0.3153,
|
| 1369 |
+
"num_tokens": 1459562818.0,
|
| 1370 |
+
"step": 845
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.9499860296172115,
|
| 1374 |
+
"grad_norm": 0.24113890528678894,
|
| 1375 |
+
"learning_rate": 1.1671845866998138e-05,
|
| 1376 |
+
"loss": 0.315,
|
| 1377 |
+
"num_tokens": 1468199788.0,
|
| 1378 |
+
"step": 850
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.9555741827326069,
|
| 1382 |
+
"grad_norm": 0.24603360891342163,
|
| 1383 |
+
"learning_rate": 1.1609695463020511e-05,
|
| 1384 |
+
"loss": 0.3146,
|
| 1385 |
+
"num_tokens": 1476828577.0,
|
| 1386 |
+
"step": 855
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 0.9611623358480023,
|
| 1390 |
+
"grad_norm": 0.2403990924358368,
|
| 1391 |
+
"learning_rate": 1.1547545059042884e-05,
|
| 1392 |
+
"loss": 0.3136,
|
| 1393 |
+
"num_tokens": 1485446216.0,
|
| 1394 |
+
"step": 860
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 0.9667504889633975,
|
| 1398 |
+
"grad_norm": 0.23709586262702942,
|
| 1399 |
+
"learning_rate": 1.1485394655065258e-05,
|
| 1400 |
+
"loss": 0.314,
|
| 1401 |
+
"num_tokens": 1494105354.0,
|
| 1402 |
+
"step": 865
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 0.972338642078793,
|
| 1406 |
+
"grad_norm": 0.22443188726902008,
|
| 1407 |
+
"learning_rate": 1.1423244251087633e-05,
|
| 1408 |
+
"loss": 0.3128,
|
| 1409 |
+
"num_tokens": 1502756944.0,
|
| 1410 |
+
"step": 870
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.9779267951941883,
|
| 1414 |
+
"grad_norm": 0.22289405763149261,
|
| 1415 |
+
"learning_rate": 1.1361093847110008e-05,
|
| 1416 |
+
"loss": 0.3128,
|
| 1417 |
+
"num_tokens": 1511405759.0,
|
| 1418 |
+
"step": 875
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 0.9835149483095836,
|
| 1422 |
+
"grad_norm": 0.21792230010032654,
|
| 1423 |
+
"learning_rate": 1.1298943443132382e-05,
|
| 1424 |
+
"loss": 0.3128,
|
| 1425 |
+
"num_tokens": 1520041593.0,
|
| 1426 |
+
"step": 880
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.989103101424979,
|
| 1430 |
+
"grad_norm": 0.23965007066726685,
|
| 1431 |
+
"learning_rate": 1.1236793039154757e-05,
|
| 1432 |
+
"loss": 0.3105,
|
| 1433 |
+
"num_tokens": 1528731440.0,
|
| 1434 |
+
"step": 885
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.9946912545403744,
|
| 1438 |
+
"grad_norm": 0.21196743845939636,
|
| 1439 |
+
"learning_rate": 1.1174642635177128e-05,
|
| 1440 |
+
"loss": 0.313,
|
| 1441 |
+
"num_tokens": 1537329601.0,
|
| 1442 |
+
"step": 890
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 1.0011176306230791,
|
| 1446 |
+
"grad_norm": 0.4137466251850128,
|
| 1447 |
+
"learning_rate": 1.1112492231199504e-05,
|
| 1448 |
+
"loss": 0.3744,
|
| 1449 |
+
"num_tokens": 1546855399.0,
|
| 1450 |
+
"step": 895
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.0067057837384745,
|
| 1454 |
+
"grad_norm": 0.3543248772621155,
|
| 1455 |
+
"learning_rate": 1.1050341827221877e-05,
|
| 1456 |
+
"loss": 0.3073,
|
| 1457 |
+
"num_tokens": 1555449486.0,
|
| 1458 |
+
"step": 900
|
| 1459 |
+
},
|
| 1460 |
+
{
|
| 1461 |
+
"epoch": 1.0122939368538697,
|
| 1462 |
+
"grad_norm": 0.2658456563949585,
|
| 1463 |
+
"learning_rate": 1.0988191423244252e-05,
|
| 1464 |
+
"loss": 0.3094,
|
| 1465 |
+
"num_tokens": 1564115495.0,
|
| 1466 |
+
"step": 905
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.017882089969265,
|
| 1470 |
+
"grad_norm": 0.23490653932094574,
|
| 1471 |
+
"learning_rate": 1.0926041019266627e-05,
|
| 1472 |
+
"loss": 0.3073,
|
| 1473 |
+
"num_tokens": 1572713661.0,
|
| 1474 |
+
"step": 910
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.0234702430846605,
|
| 1478 |
+
"grad_norm": 0.2108413279056549,
|
| 1479 |
+
"learning_rate": 1.0863890615289e-05,
|
| 1480 |
+
"loss": 0.3078,
|
| 1481 |
+
"num_tokens": 1581295552.0,
|
| 1482 |
+
"step": 915
|
| 1483 |
+
},
|
| 1484 |
+
{
|
| 1485 |
+
"epoch": 1.029058396200056,
|
| 1486 |
+
"grad_norm": 0.21604564785957336,
|
| 1487 |
+
"learning_rate": 1.0801740211311374e-05,
|
| 1488 |
+
"loss": 0.308,
|
| 1489 |
+
"num_tokens": 1589925350.0,
|
| 1490 |
+
"step": 920
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 1.0346465493154513,
|
| 1494 |
+
"grad_norm": 0.24258844554424286,
|
| 1495 |
+
"learning_rate": 1.0739589807333748e-05,
|
| 1496 |
+
"loss": 0.3071,
|
| 1497 |
+
"num_tokens": 1598552250.0,
|
| 1498 |
+
"step": 925
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.0402347024308467,
|
| 1502 |
+
"grad_norm": 0.2516770362854004,
|
| 1503 |
+
"learning_rate": 1.0677439403356123e-05,
|
| 1504 |
+
"loss": 0.3074,
|
| 1505 |
+
"num_tokens": 1607226139.0,
|
| 1506 |
+
"step": 930
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 1.0458228555462419,
|
| 1510 |
+
"grad_norm": 0.267008900642395,
|
| 1511 |
+
"learning_rate": 1.0615288999378496e-05,
|
| 1512 |
+
"loss": 0.3075,
|
| 1513 |
+
"num_tokens": 1615893500.0,
|
| 1514 |
+
"step": 935
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 1.0514110086616373,
|
| 1518 |
+
"grad_norm": 0.22778408229351044,
|
| 1519 |
+
"learning_rate": 1.0553138595400871e-05,
|
| 1520 |
+
"loss": 0.305,
|
| 1521 |
+
"num_tokens": 1624544526.0,
|
| 1522 |
+
"step": 940
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.0569991617770327,
|
| 1526 |
+
"grad_norm": 0.24864831566810608,
|
| 1527 |
+
"learning_rate": 1.0490988191423246e-05,
|
| 1528 |
+
"loss": 0.3071,
|
| 1529 |
+
"num_tokens": 1633169926.0,
|
| 1530 |
+
"step": 945
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 1.062587314892428,
|
| 1534 |
+
"grad_norm": 0.24507726728916168,
|
| 1535 |
+
"learning_rate": 1.0428837787445618e-05,
|
| 1536 |
+
"loss": 0.3067,
|
| 1537 |
+
"num_tokens": 1641807825.0,
|
| 1538 |
+
"step": 950
|
| 1539 |
+
},
|
| 1540 |
+
{
|
| 1541 |
+
"epoch": 1.0681754680078235,
|
| 1542 |
+
"grad_norm": 0.24927540123462677,
|
| 1543 |
+
"learning_rate": 1.0366687383467993e-05,
|
| 1544 |
+
"loss": 0.305,
|
| 1545 |
+
"num_tokens": 1650440605.0,
|
| 1546 |
+
"step": 955
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 1.0737636211232187,
|
| 1550 |
+
"grad_norm": 0.23993715643882751,
|
| 1551 |
+
"learning_rate": 1.0304536979490367e-05,
|
| 1552 |
+
"loss": 0.3062,
|
| 1553 |
+
"num_tokens": 1659114119.0,
|
| 1554 |
+
"step": 960
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.079351774238614,
|
| 1558 |
+
"grad_norm": 0.23860405385494232,
|
| 1559 |
+
"learning_rate": 1.0242386575512742e-05,
|
| 1560 |
+
"loss": 0.3051,
|
| 1561 |
+
"num_tokens": 1667790637.0,
|
| 1562 |
+
"step": 965
|
| 1563 |
+
},
|
| 1564 |
+
{
|
| 1565 |
+
"epoch": 1.0849399273540095,
|
| 1566 |
+
"grad_norm": 0.22328642010688782,
|
| 1567 |
+
"learning_rate": 1.0180236171535117e-05,
|
| 1568 |
+
"loss": 0.3036,
|
| 1569 |
+
"num_tokens": 1676410799.0,
|
| 1570 |
+
"step": 970
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 1.0905280804694049,
|
| 1574 |
+
"grad_norm": 0.22773276269435883,
|
| 1575 |
+
"learning_rate": 1.011808576755749e-05,
|
| 1576 |
+
"loss": 0.3045,
|
| 1577 |
+
"num_tokens": 1685038550.0,
|
| 1578 |
+
"step": 975
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.0961162335848003,
|
| 1582 |
+
"grad_norm": 0.24300263822078705,
|
| 1583 |
+
"learning_rate": 1.0055935363579865e-05,
|
| 1584 |
+
"loss": 0.3036,
|
| 1585 |
+
"num_tokens": 1693653167.0,
|
| 1586 |
+
"step": 980
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 1.1017043867001957,
|
| 1590 |
+
"grad_norm": 0.2338700294494629,
|
| 1591 |
+
"learning_rate": 9.993784959602239e-06,
|
| 1592 |
+
"loss": 0.3035,
|
| 1593 |
+
"num_tokens": 1702298742.0,
|
| 1594 |
+
"step": 985
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 1.107292539815591,
|
| 1598 |
+
"grad_norm": 0.26763731241226196,
|
| 1599 |
+
"learning_rate": 9.931634555624612e-06,
|
| 1600 |
+
"loss": 0.3031,
|
| 1601 |
+
"num_tokens": 1710896315.0,
|
| 1602 |
+
"step": 990
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 1.1128806929309862,
|
| 1606 |
+
"grad_norm": 0.2267494946718216,
|
| 1607 |
+
"learning_rate": 9.869484151646986e-06,
|
| 1608 |
+
"loss": 0.3025,
|
| 1609 |
+
"num_tokens": 1719508004.0,
|
| 1610 |
+
"step": 995
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 1.1184688460463816,
|
| 1614 |
+
"grad_norm": 0.2253628671169281,
|
| 1615 |
+
"learning_rate": 9.80733374766936e-06,
|
| 1616 |
+
"loss": 0.302,
|
| 1617 |
+
"num_tokens": 1728072354.0,
|
| 1618 |
+
"step": 1000
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 1.124056999161777,
|
| 1622 |
+
"grad_norm": 0.3325177729129791,
|
| 1623 |
+
"learning_rate": 9.745183343691734e-06,
|
| 1624 |
+
"loss": 0.3023,
|
| 1625 |
+
"num_tokens": 1736731519.0,
|
| 1626 |
+
"step": 1005
|
| 1627 |
+
},
|
| 1628 |
+
{
|
| 1629 |
+
"epoch": 1.1296451522771724,
|
| 1630 |
+
"grad_norm": 0.25409770011901855,
|
| 1631 |
+
"learning_rate": 9.68303293971411e-06,
|
| 1632 |
+
"loss": 0.3025,
|
| 1633 |
+
"num_tokens": 1745381878.0,
|
| 1634 |
+
"step": 1010
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.1352333053925678,
|
| 1638 |
+
"grad_norm": 0.2311965525150299,
|
| 1639 |
+
"learning_rate": 9.620882535736483e-06,
|
| 1640 |
+
"loss": 0.3035,
|
| 1641 |
+
"num_tokens": 1753981361.0,
|
| 1642 |
+
"step": 1015
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 1.140821458507963,
|
| 1646 |
+
"grad_norm": 0.215187668800354,
|
| 1647 |
+
"learning_rate": 9.558732131758858e-06,
|
| 1648 |
+
"loss": 0.3008,
|
| 1649 |
+
"num_tokens": 1762589098.0,
|
| 1650 |
+
"step": 1020
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 1.1464096116233584,
|
| 1654 |
+
"grad_norm": 0.26533347368240356,
|
| 1655 |
+
"learning_rate": 9.496581727781231e-06,
|
| 1656 |
+
"loss": 0.3,
|
| 1657 |
+
"num_tokens": 1771273179.0,
|
| 1658 |
+
"step": 1025
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 1.1519977647387538,
|
| 1662 |
+
"grad_norm": 0.25665122270584106,
|
| 1663 |
+
"learning_rate": 9.434431323803605e-06,
|
| 1664 |
+
"loss": 0.3021,
|
| 1665 |
+
"num_tokens": 1779963496.0,
|
| 1666 |
+
"step": 1030
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 1.1575859178541492,
|
| 1670 |
+
"grad_norm": 0.25517359375953674,
|
| 1671 |
+
"learning_rate": 9.37228091982598e-06,
|
| 1672 |
+
"loss": 0.3016,
|
| 1673 |
+
"num_tokens": 1788626566.0,
|
| 1674 |
+
"step": 1035
|
| 1675 |
+
},
|
| 1676 |
+
{
|
| 1677 |
+
"epoch": 1.1631740709695446,
|
| 1678 |
+
"grad_norm": 0.24597561359405518,
|
| 1679 |
+
"learning_rate": 9.310130515848353e-06,
|
| 1680 |
+
"loss": 0.2999,
|
| 1681 |
+
"num_tokens": 1797251848.0,
|
| 1682 |
+
"step": 1040
|
| 1683 |
+
},
|
| 1684 |
+
{
|
| 1685 |
+
"epoch": 1.16876222408494,
|
| 1686 |
+
"grad_norm": 0.234393909573555,
|
| 1687 |
+
"learning_rate": 9.247980111870728e-06,
|
| 1688 |
+
"loss": 0.3003,
|
| 1689 |
+
"num_tokens": 1805885491.0,
|
| 1690 |
+
"step": 1045
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 1.1743503772003352,
|
| 1694 |
+
"grad_norm": 0.23870638012886047,
|
| 1695 |
+
"learning_rate": 9.185829707893102e-06,
|
| 1696 |
+
"loss": 0.299,
|
| 1697 |
+
"num_tokens": 1814510483.0,
|
| 1698 |
+
"step": 1050
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 1.1799385303157306,
|
| 1702 |
+
"grad_norm": 0.23010727763175964,
|
| 1703 |
+
"learning_rate": 9.123679303915475e-06,
|
| 1704 |
+
"loss": 0.2997,
|
| 1705 |
+
"num_tokens": 1823182283.0,
|
| 1706 |
+
"step": 1055
|
| 1707 |
+
},
|
| 1708 |
+
{
|
| 1709 |
+
"epoch": 1.185526683431126,
|
| 1710 |
+
"grad_norm": 0.22427524626255035,
|
| 1711 |
+
"learning_rate": 9.06152889993785e-06,
|
| 1712 |
+
"loss": 0.2986,
|
| 1713 |
+
"num_tokens": 1831855032.0,
|
| 1714 |
+
"step": 1060
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 1.1911148365465214,
|
| 1718 |
+
"grad_norm": 0.24159206449985504,
|
| 1719 |
+
"learning_rate": 8.999378495960226e-06,
|
| 1720 |
+
"loss": 0.3003,
|
| 1721 |
+
"num_tokens": 1840477078.0,
|
| 1722 |
+
"step": 1065
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 1.1967029896619168,
|
| 1726 |
+
"grad_norm": 0.25824683904647827,
|
| 1727 |
+
"learning_rate": 8.937228091982599e-06,
|
| 1728 |
+
"loss": 0.3012,
|
| 1729 |
+
"num_tokens": 1849104626.0,
|
| 1730 |
+
"step": 1070
|
| 1731 |
+
},
|
| 1732 |
+
{
|
| 1733 |
+
"epoch": 1.2022911427773122,
|
| 1734 |
+
"grad_norm": 0.23380401730537415,
|
| 1735 |
+
"learning_rate": 8.875077688004972e-06,
|
| 1736 |
+
"loss": 0.2982,
|
| 1737 |
+
"num_tokens": 1857782320.0,
|
| 1738 |
+
"step": 1075
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 1.2078792958927074,
|
| 1742 |
+
"grad_norm": 0.2337757796049118,
|
| 1743 |
+
"learning_rate": 8.812927284027348e-06,
|
| 1744 |
+
"loss": 0.2988,
|
| 1745 |
+
"num_tokens": 1866411525.0,
|
| 1746 |
+
"step": 1080
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 1.2134674490081028,
|
| 1750 |
+
"grad_norm": 0.23148195445537567,
|
| 1751 |
+
"learning_rate": 8.750776880049721e-06,
|
| 1752 |
+
"loss": 0.2994,
|
| 1753 |
+
"num_tokens": 1875046108.0,
|
| 1754 |
+
"step": 1085
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 1.2190556021234982,
|
| 1758 |
+
"grad_norm": 0.2387813925743103,
|
| 1759 |
+
"learning_rate": 8.688626476072094e-06,
|
| 1760 |
+
"loss": 0.298,
|
| 1761 |
+
"num_tokens": 1883663395.0,
|
| 1762 |
+
"step": 1090
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 1.2246437552388936,
|
| 1766 |
+
"grad_norm": 0.23834937810897827,
|
| 1767 |
+
"learning_rate": 8.62647607209447e-06,
|
| 1768 |
+
"loss": 0.2976,
|
| 1769 |
+
"num_tokens": 1892282345.0,
|
| 1770 |
+
"step": 1095
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 1.230231908354289,
|
| 1774 |
+
"grad_norm": 0.22994597256183624,
|
| 1775 |
+
"learning_rate": 8.564325668116843e-06,
|
| 1776 |
+
"loss": 0.2994,
|
| 1777 |
+
"num_tokens": 1900904719.0,
|
| 1778 |
+
"step": 1100
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 1.2358200614696844,
|
| 1782 |
+
"grad_norm": 0.2896011769771576,
|
| 1783 |
+
"learning_rate": 8.502175264139218e-06,
|
| 1784 |
+
"loss": 0.2986,
|
| 1785 |
+
"num_tokens": 1909539207.0,
|
| 1786 |
+
"step": 1105
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 1.2414082145850796,
|
| 1790 |
+
"grad_norm": 0.2331543117761612,
|
| 1791 |
+
"learning_rate": 8.440024860161591e-06,
|
| 1792 |
+
"loss": 0.2987,
|
| 1793 |
+
"num_tokens": 1918146801.0,
|
| 1794 |
+
"step": 1110
|
| 1795 |
+
},
|
| 1796 |
+
{
|
| 1797 |
+
"epoch": 1.246996367700475,
|
| 1798 |
+
"grad_norm": 0.27627456188201904,
|
| 1799 |
+
"learning_rate": 8.377874456183965e-06,
|
| 1800 |
+
"loss": 0.2973,
|
| 1801 |
+
"num_tokens": 1926809633.0,
|
| 1802 |
+
"step": 1115
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 1.2525845208158704,
|
| 1806 |
+
"grad_norm": 0.22385410964488983,
|
| 1807 |
+
"learning_rate": 8.31572405220634e-06,
|
| 1808 |
+
"loss": 0.2989,
|
| 1809 |
+
"num_tokens": 1935446815.0,
|
| 1810 |
+
"step": 1120
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 1.2581726739312658,
|
| 1814 |
+
"grad_norm": 0.2674117982387543,
|
| 1815 |
+
"learning_rate": 8.253573648228713e-06,
|
| 1816 |
+
"loss": 0.2959,
|
| 1817 |
+
"num_tokens": 1944051171.0,
|
| 1818 |
+
"step": 1125
|
| 1819 |
+
},
|
| 1820 |
+
{
|
| 1821 |
+
"epoch": 1.2637608270466612,
|
| 1822 |
+
"grad_norm": 0.23551645874977112,
|
| 1823 |
+
"learning_rate": 8.191423244251089e-06,
|
| 1824 |
+
"loss": 0.2966,
|
| 1825 |
+
"num_tokens": 1952699890.0,
|
| 1826 |
+
"step": 1130
|
| 1827 |
+
},
|
| 1828 |
+
{
|
| 1829 |
+
"epoch": 1.2693489801620563,
|
| 1830 |
+
"grad_norm": 0.2742044925689697,
|
| 1831 |
+
"learning_rate": 8.129272840273462e-06,
|
| 1832 |
+
"loss": 0.2959,
|
| 1833 |
+
"num_tokens": 1961336294.0,
|
| 1834 |
+
"step": 1135
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 1.2749371332774517,
|
| 1838 |
+
"grad_norm": 0.300987184047699,
|
| 1839 |
+
"learning_rate": 8.067122436295837e-06,
|
| 1840 |
+
"loss": 0.297,
|
| 1841 |
+
"num_tokens": 1969959503.0,
|
| 1842 |
+
"step": 1140
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 1.2805252863928471,
|
| 1846 |
+
"grad_norm": 0.26457130908966064,
|
| 1847 |
+
"learning_rate": 8.00497203231821e-06,
|
| 1848 |
+
"loss": 0.2958,
|
| 1849 |
+
"num_tokens": 1978592174.0,
|
| 1850 |
+
"step": 1145
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 1.2861134395082425,
|
| 1854 |
+
"grad_norm": 0.25730499625205994,
|
| 1855 |
+
"learning_rate": 7.942821628340584e-06,
|
| 1856 |
+
"loss": 0.2957,
|
| 1857 |
+
"num_tokens": 1987264337.0,
|
| 1858 |
+
"step": 1150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 1.291701592623638,
|
| 1862 |
+
"grad_norm": 0.23706525564193726,
|
| 1863 |
+
"learning_rate": 7.880671224362959e-06,
|
| 1864 |
+
"loss": 0.296,
|
| 1865 |
+
"num_tokens": 1995921874.0,
|
| 1866 |
+
"step": 1155
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 1.2972897457390333,
|
| 1870 |
+
"grad_norm": 0.2367008924484253,
|
| 1871 |
+
"learning_rate": 7.818520820385334e-06,
|
| 1872 |
+
"loss": 0.2961,
|
| 1873 |
+
"num_tokens": 2004554306.0,
|
| 1874 |
+
"step": 1160
|
| 1875 |
+
},
|
| 1876 |
+
{
|
| 1877 |
+
"epoch": 1.3028778988544287,
|
| 1878 |
+
"grad_norm": 0.24648545682430267,
|
| 1879 |
+
"learning_rate": 7.756370416407708e-06,
|
| 1880 |
+
"loss": 0.296,
|
| 1881 |
+
"num_tokens": 2013186850.0,
|
| 1882 |
+
"step": 1165
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 1.308466051969824,
|
| 1886 |
+
"grad_norm": 0.23670046031475067,
|
| 1887 |
+
"learning_rate": 7.694220012430081e-06,
|
| 1888 |
+
"loss": 0.2955,
|
| 1889 |
+
"num_tokens": 2021845658.0,
|
| 1890 |
+
"step": 1170
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"epoch": 1.3140542050852193,
|
| 1894 |
+
"grad_norm": 0.25605788826942444,
|
| 1895 |
+
"learning_rate": 7.632069608452456e-06,
|
| 1896 |
+
"loss": 0.2954,
|
| 1897 |
+
"num_tokens": 2030475717.0,
|
| 1898 |
+
"step": 1175
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 1.3196423582006147,
|
| 1902 |
+
"grad_norm": 0.231962651014328,
|
| 1903 |
+
"learning_rate": 7.56991920447483e-06,
|
| 1904 |
+
"loss": 0.2933,
|
| 1905 |
+
"num_tokens": 2039123741.0,
|
| 1906 |
+
"step": 1180
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 1.32523051131601,
|
| 1910 |
+
"grad_norm": 0.27191412448883057,
|
| 1911 |
+
"learning_rate": 7.507768800497204e-06,
|
| 1912 |
+
"loss": 0.2956,
|
| 1913 |
+
"num_tokens": 2047780009.0,
|
| 1914 |
+
"step": 1185
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 1.3308186644314053,
|
| 1918 |
+
"grad_norm": 0.25106704235076904,
|
| 1919 |
+
"learning_rate": 7.445618396519578e-06,
|
| 1920 |
+
"loss": 0.2943,
|
| 1921 |
+
"num_tokens": 2056375982.0,
|
| 1922 |
+
"step": 1190
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 1.3364068175468007,
|
| 1926 |
+
"grad_norm": 0.24563732743263245,
|
| 1927 |
+
"learning_rate": 7.383467992541952e-06,
|
| 1928 |
+
"loss": 0.2941,
|
| 1929 |
+
"num_tokens": 2064961201.0,
|
| 1930 |
+
"step": 1195
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 1.341994970662196,
|
| 1934 |
+
"grad_norm": 0.22767555713653564,
|
| 1935 |
+
"learning_rate": 7.321317588564326e-06,
|
| 1936 |
+
"loss": 0.292,
|
| 1937 |
+
"num_tokens": 2073631036.0,
|
| 1938 |
+
"step": 1200
|
| 1939 |
+
},
|
| 1940 |
+
{
|
| 1941 |
+
"epoch": 1.3475831237775915,
|
| 1942 |
+
"grad_norm": 0.2571980655193329,
|
| 1943 |
+
"learning_rate": 7.259167184586701e-06,
|
| 1944 |
+
"loss": 0.2927,
|
| 1945 |
+
"num_tokens": 2082296071.0,
|
| 1946 |
+
"step": 1205
|
| 1947 |
+
},
|
| 1948 |
+
{
|
| 1949 |
+
"epoch": 1.3531712768929869,
|
| 1950 |
+
"grad_norm": 0.3146756887435913,
|
| 1951 |
+
"learning_rate": 7.1970167806090745e-06,
|
| 1952 |
+
"loss": 0.2941,
|
| 1953 |
+
"num_tokens": 2090940329.0,
|
| 1954 |
+
"step": 1210
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 1.3587594300083823,
|
| 1958 |
+
"grad_norm": 0.26144880056381226,
|
| 1959 |
+
"learning_rate": 7.134866376631449e-06,
|
| 1960 |
+
"loss": 0.2931,
|
| 1961 |
+
"num_tokens": 2099611466.0,
|
| 1962 |
+
"step": 1215
|
| 1963 |
+
},
|
| 1964 |
+
{
|
| 1965 |
+
"epoch": 1.3643475831237777,
|
| 1966 |
+
"grad_norm": 0.22552551329135895,
|
| 1967 |
+
"learning_rate": 7.072715972653823e-06,
|
| 1968 |
+
"loss": 0.2936,
|
| 1969 |
+
"num_tokens": 2108254412.0,
|
| 1970 |
+
"step": 1220
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 1.369935736239173,
|
| 1974 |
+
"grad_norm": 0.23567764461040497,
|
| 1975 |
+
"learning_rate": 7.0105655686761964e-06,
|
| 1976 |
+
"loss": 0.2941,
|
| 1977 |
+
"num_tokens": 2116883454.0,
|
| 1978 |
+
"step": 1225
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 1.3755238893545683,
|
| 1982 |
+
"grad_norm": 0.26882192492485046,
|
| 1983 |
+
"learning_rate": 6.948415164698571e-06,
|
| 1984 |
+
"loss": 0.292,
|
| 1985 |
+
"num_tokens": 2125531177.0,
|
| 1986 |
+
"step": 1230
|
| 1987 |
+
},
|
| 1988 |
+
{
|
| 1989 |
+
"epoch": 1.3811120424699637,
|
| 1990 |
+
"grad_norm": 0.24953489005565643,
|
| 1991 |
+
"learning_rate": 6.886264760720945e-06,
|
| 1992 |
+
"loss": 0.2926,
|
| 1993 |
+
"num_tokens": 2134240135.0,
|
| 1994 |
+
"step": 1235
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 1.386700195585359,
|
| 1998 |
+
"grad_norm": 0.21380962431430817,
|
| 1999 |
+
"learning_rate": 6.82411435674332e-06,
|
| 2000 |
+
"loss": 0.2918,
|
| 2001 |
+
"num_tokens": 2142853666.0,
|
| 2002 |
+
"step": 1240
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 1.3922883487007545,
|
| 2006 |
+
"grad_norm": 0.2518530786037445,
|
| 2007 |
+
"learning_rate": 6.7619639527656935e-06,
|
| 2008 |
+
"loss": 0.2923,
|
| 2009 |
+
"num_tokens": 2151466944.0,
|
| 2010 |
+
"step": 1245
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 1.3978765018161496,
|
| 2014 |
+
"grad_norm": 0.2241937220096588,
|
| 2015 |
+
"learning_rate": 6.699813548788068e-06,
|
| 2016 |
+
"loss": 0.2912,
|
| 2017 |
+
"num_tokens": 2160077640.0,
|
| 2018 |
+
"step": 1250
|
| 2019 |
+
},
|
| 2020 |
+
{
|
| 2021 |
+
"epoch": 1.403464654931545,
|
| 2022 |
+
"grad_norm": 0.21372365951538086,
|
| 2023 |
+
"learning_rate": 6.637663144810442e-06,
|
| 2024 |
+
"loss": 0.2891,
|
| 2025 |
+
"num_tokens": 2168745642.0,
|
| 2026 |
+
"step": 1255
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 1.4090528080469404,
|
| 2030 |
+
"grad_norm": 0.2071543037891388,
|
| 2031 |
+
"learning_rate": 6.5755127408328155e-06,
|
| 2032 |
+
"loss": 0.2917,
|
| 2033 |
+
"num_tokens": 2177378583.0,
|
| 2034 |
+
"step": 1260
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 1.4146409611623358,
|
| 2038 |
+
"grad_norm": 0.21559269726276398,
|
| 2039 |
+
"learning_rate": 6.51336233685519e-06,
|
| 2040 |
+
"loss": 0.291,
|
| 2041 |
+
"num_tokens": 2186021687.0,
|
| 2042 |
+
"step": 1265
|
| 2043 |
+
},
|
| 2044 |
+
{
|
| 2045 |
+
"epoch": 1.4202291142777312,
|
| 2046 |
+
"grad_norm": 0.2227635681629181,
|
| 2047 |
+
"learning_rate": 6.451211932877565e-06,
|
| 2048 |
+
"loss": 0.2918,
|
| 2049 |
+
"num_tokens": 2194630054.0,
|
| 2050 |
+
"step": 1270
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 1.4258172673931266,
|
| 2054 |
+
"grad_norm": 0.21467848122119904,
|
| 2055 |
+
"learning_rate": 6.389061528899938e-06,
|
| 2056 |
+
"loss": 0.2905,
|
| 2057 |
+
"num_tokens": 2203290213.0,
|
| 2058 |
+
"step": 1275
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 1.431405420508522,
|
| 2062 |
+
"grad_norm": 0.2505319118499756,
|
| 2063 |
+
"learning_rate": 6.326911124922313e-06,
|
| 2064 |
+
"loss": 0.2896,
|
| 2065 |
+
"num_tokens": 2211929982.0,
|
| 2066 |
+
"step": 1280
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 1.4369935736239172,
|
| 2070 |
+
"grad_norm": 0.23950278759002686,
|
| 2071 |
+
"learning_rate": 6.264760720944687e-06,
|
| 2072 |
+
"loss": 0.2922,
|
| 2073 |
+
"num_tokens": 2220561765.0,
|
| 2074 |
+
"step": 1285
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 1.4425817267393126,
|
| 2078 |
+
"grad_norm": 0.2342691272497177,
|
| 2079 |
+
"learning_rate": 6.20261031696706e-06,
|
| 2080 |
+
"loss": 0.2897,
|
| 2081 |
+
"num_tokens": 2229218119.0,
|
| 2082 |
+
"step": 1290
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 1.448169879854708,
|
| 2086 |
+
"grad_norm": 0.2966405749320984,
|
| 2087 |
+
"learning_rate": 6.140459912989435e-06,
|
| 2088 |
+
"loss": 0.2908,
|
| 2089 |
+
"num_tokens": 2237855571.0,
|
| 2090 |
+
"step": 1295
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 1.4537580329701034,
|
| 2094 |
+
"grad_norm": 0.24424313008785248,
|
| 2095 |
+
"learning_rate": 6.07830950901181e-06,
|
| 2096 |
+
"loss": 0.2907,
|
| 2097 |
+
"num_tokens": 2246501573.0,
|
| 2098 |
+
"step": 1300
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 1.4593461860854988,
|
| 2102 |
+
"grad_norm": 0.23377157747745514,
|
| 2103 |
+
"learning_rate": 6.016159105034183e-06,
|
| 2104 |
+
"loss": 0.2909,
|
| 2105 |
+
"num_tokens": 2255130456.0,
|
| 2106 |
+
"step": 1305
|
| 2107 |
+
},
|
| 2108 |
+
{
|
| 2109 |
+
"epoch": 1.464934339200894,
|
| 2110 |
+
"grad_norm": 0.21223483979701996,
|
| 2111 |
+
"learning_rate": 5.9540087010565574e-06,
|
| 2112 |
+
"loss": 0.29,
|
| 2113 |
+
"num_tokens": 2263746485.0,
|
| 2114 |
+
"step": 1310
|
| 2115 |
+
},
|
| 2116 |
+
{
|
| 2117 |
+
"epoch": 1.4705224923162894,
|
| 2118 |
+
"grad_norm": 0.23736342787742615,
|
| 2119 |
+
"learning_rate": 5.891858297078932e-06,
|
| 2120 |
+
"loss": 0.2901,
|
| 2121 |
+
"num_tokens": 2272362242.0,
|
| 2122 |
+
"step": 1315
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 1.4761106454316848,
|
| 2126 |
+
"grad_norm": 0.2492651641368866,
|
| 2127 |
+
"learning_rate": 5.829707893101305e-06,
|
| 2128 |
+
"loss": 0.2895,
|
| 2129 |
+
"num_tokens": 2280978917.0,
|
| 2130 |
+
"step": 1320
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 1.4816987985470802,
|
| 2134 |
+
"grad_norm": 0.23298749327659607,
|
| 2135 |
+
"learning_rate": 5.767557489123679e-06,
|
| 2136 |
+
"loss": 0.2883,
|
| 2137 |
+
"num_tokens": 2289618555.0,
|
| 2138 |
+
"step": 1325
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 1.4872869516624756,
|
| 2142 |
+
"grad_norm": 0.23725226521492004,
|
| 2143 |
+
"learning_rate": 5.7054070851460545e-06,
|
| 2144 |
+
"loss": 0.2875,
|
| 2145 |
+
"num_tokens": 2298320508.0,
|
| 2146 |
+
"step": 1330
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 1.492875104777871,
|
| 2150 |
+
"grad_norm": 0.22084194421768188,
|
| 2151 |
+
"learning_rate": 5.643256681168427e-06,
|
| 2152 |
+
"loss": 0.2892,
|
| 2153 |
+
"num_tokens": 2306960721.0,
|
| 2154 |
+
"step": 1335
|
| 2155 |
+
},
|
| 2156 |
+
{
|
| 2157 |
+
"epoch": 1.4984632578932664,
|
| 2158 |
+
"grad_norm": 0.24300003051757812,
|
| 2159 |
+
"learning_rate": 5.581106277190802e-06,
|
| 2160 |
+
"loss": 0.289,
|
| 2161 |
+
"num_tokens": 2315621645.0,
|
| 2162 |
+
"step": 1340
|
| 2163 |
+
},
|
| 2164 |
+
{
|
| 2165 |
+
"epoch": 1.5040514110086618,
|
| 2166 |
+
"grad_norm": 0.24459832906723022,
|
| 2167 |
+
"learning_rate": 5.5189558732131765e-06,
|
| 2168 |
+
"loss": 0.2896,
|
| 2169 |
+
"num_tokens": 2324231293.0,
|
| 2170 |
+
"step": 1345
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 1.509639564124057,
|
| 2174 |
+
"grad_norm": 0.20767633616924286,
|
| 2175 |
+
"learning_rate": 5.456805469235551e-06,
|
| 2176 |
+
"loss": 0.288,
|
| 2177 |
+
"num_tokens": 2332877527.0,
|
| 2178 |
+
"step": 1350
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 1.5152277172394524,
|
| 2182 |
+
"grad_norm": 0.2096388041973114,
|
| 2183 |
+
"learning_rate": 5.394655065257924e-06,
|
| 2184 |
+
"loss": 0.2892,
|
| 2185 |
+
"num_tokens": 2341473674.0,
|
| 2186 |
+
"step": 1355
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 1.5208158703548478,
|
| 2190 |
+
"grad_norm": 0.21928216516971588,
|
| 2191 |
+
"learning_rate": 5.3325046612802985e-06,
|
| 2192 |
+
"loss": 0.288,
|
| 2193 |
+
"num_tokens": 2350114516.0,
|
| 2194 |
+
"step": 1360
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 1.526404023470243,
|
| 2198 |
+
"grad_norm": 0.22901827096939087,
|
| 2199 |
+
"learning_rate": 5.270354257302674e-06,
|
| 2200 |
+
"loss": 0.2878,
|
| 2201 |
+
"num_tokens": 2358726348.0,
|
| 2202 |
+
"step": 1365
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 1.5319921765856384,
|
| 2206 |
+
"grad_norm": 0.23737923800945282,
|
| 2207 |
+
"learning_rate": 5.208203853325047e-06,
|
| 2208 |
+
"loss": 0.2873,
|
| 2209 |
+
"num_tokens": 2367370170.0,
|
| 2210 |
+
"step": 1370
|
| 2211 |
+
},
|
| 2212 |
+
{
|
| 2213 |
+
"epoch": 1.5375803297010338,
|
| 2214 |
+
"grad_norm": 0.2369966357946396,
|
| 2215 |
+
"learning_rate": 5.146053449347421e-06,
|
| 2216 |
+
"loss": 0.287,
|
| 2217 |
+
"num_tokens": 2375996366.0,
|
| 2218 |
+
"step": 1375
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 1.5431684828164292,
|
| 2222 |
+
"grad_norm": 0.23443567752838135,
|
| 2223 |
+
"learning_rate": 5.083903045369796e-06,
|
| 2224 |
+
"loss": 0.2874,
|
| 2225 |
+
"num_tokens": 2384613549.0,
|
| 2226 |
+
"step": 1380
|
| 2227 |
+
},
|
| 2228 |
+
{
|
| 2229 |
+
"epoch": 1.5487566359318246,
|
| 2230 |
+
"grad_norm": 0.23766714334487915,
|
| 2231 |
+
"learning_rate": 5.021752641392169e-06,
|
| 2232 |
+
"loss": 0.2878,
|
| 2233 |
+
"num_tokens": 2393259198.0,
|
| 2234 |
+
"step": 1385
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 1.55434478904722,
|
| 2238 |
+
"grad_norm": 0.25128668546676636,
|
| 2239 |
+
"learning_rate": 4.959602237414543e-06,
|
| 2240 |
+
"loss": 0.288,
|
| 2241 |
+
"num_tokens": 2401875320.0,
|
| 2242 |
+
"step": 1390
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 1.5599329421626154,
|
| 2246 |
+
"grad_norm": 0.25003600120544434,
|
| 2247 |
+
"learning_rate": 4.897451833436918e-06,
|
| 2248 |
+
"loss": 0.2872,
|
| 2249 |
+
"num_tokens": 2410464461.0,
|
| 2250 |
+
"step": 1395
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 1.5655210952780108,
|
| 2254 |
+
"grad_norm": 0.23323696851730347,
|
| 2255 |
+
"learning_rate": 4.835301429459292e-06,
|
| 2256 |
+
"loss": 0.2877,
|
| 2257 |
+
"num_tokens": 2419104733.0,
|
| 2258 |
+
"step": 1400
|
| 2259 |
+
},
|
| 2260 |
+
{
|
| 2261 |
+
"epoch": 1.571109248393406,
|
| 2262 |
+
"grad_norm": 0.22660532593727112,
|
| 2263 |
+
"learning_rate": 4.773151025481666e-06,
|
| 2264 |
+
"loss": 0.2868,
|
| 2265 |
+
"num_tokens": 2427723495.0,
|
| 2266 |
+
"step": 1405
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 1.5766974015088013,
|
| 2270 |
+
"grad_norm": 0.23528066277503967,
|
| 2271 |
+
"learning_rate": 4.7110006215040396e-06,
|
| 2272 |
+
"loss": 0.2858,
|
| 2273 |
+
"num_tokens": 2436394221.0,
|
| 2274 |
+
"step": 1410
|
| 2275 |
+
},
|
| 2276 |
+
{
|
| 2277 |
+
"epoch": 1.5822855546241967,
|
| 2278 |
+
"grad_norm": 0.20659767091274261,
|
| 2279 |
+
"learning_rate": 4.648850217526415e-06,
|
| 2280 |
+
"loss": 0.2867,
|
| 2281 |
+
"num_tokens": 2444987195.0,
|
| 2282 |
+
"step": 1415
|
| 2283 |
+
},
|
| 2284 |
+
{
|
| 2285 |
+
"epoch": 1.587873707739592,
|
| 2286 |
+
"grad_norm": 0.202503964304924,
|
| 2287 |
+
"learning_rate": 4.586699813548788e-06,
|
| 2288 |
+
"loss": 0.287,
|
| 2289 |
+
"num_tokens": 2453647252.0,
|
| 2290 |
+
"step": 1420
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 1.5934618608549873,
|
| 2294 |
+
"grad_norm": 0.20872440934181213,
|
| 2295 |
+
"learning_rate": 4.524549409571163e-06,
|
| 2296 |
+
"loss": 0.2858,
|
| 2297 |
+
"num_tokens": 2462329940.0,
|
| 2298 |
+
"step": 1425
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 1.5990500139703827,
|
| 2302 |
+
"grad_norm": 0.2105245143175125,
|
| 2303 |
+
"learning_rate": 4.462399005593537e-06,
|
| 2304 |
+
"loss": 0.2873,
|
| 2305 |
+
"num_tokens": 2471002799.0,
|
| 2306 |
+
"step": 1430
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 1.604638167085778,
|
| 2310 |
+
"grad_norm": 0.26558104157447815,
|
| 2311 |
+
"learning_rate": 4.400248601615911e-06,
|
| 2312 |
+
"loss": 0.2861,
|
| 2313 |
+
"num_tokens": 2479692110.0,
|
| 2314 |
+
"step": 1435
|
| 2315 |
+
},
|
| 2316 |
+
{
|
| 2317 |
+
"epoch": 1.6102263202011735,
|
| 2318 |
+
"grad_norm": 0.21139390766620636,
|
| 2319 |
+
"learning_rate": 4.338098197638285e-06,
|
| 2320 |
+
"loss": 0.2852,
|
| 2321 |
+
"num_tokens": 2488300993.0,
|
| 2322 |
+
"step": 1440
|
| 2323 |
+
},
|
| 2324 |
+
{
|
| 2325 |
+
"epoch": 1.615814473316569,
|
| 2326 |
+
"grad_norm": 0.215835839509964,
|
| 2327 |
+
"learning_rate": 4.2759477936606595e-06,
|
| 2328 |
+
"loss": 0.2844,
|
| 2329 |
+
"num_tokens": 2496941072.0,
|
| 2330 |
+
"step": 1445
|
| 2331 |
+
},
|
| 2332 |
+
{
|
| 2333 |
+
"epoch": 1.6214026264319643,
|
| 2334 |
+
"grad_norm": 0.2279125303030014,
|
| 2335 |
+
"learning_rate": 4.213797389683033e-06,
|
| 2336 |
+
"loss": 0.2857,
|
| 2337 |
+
"num_tokens": 2505590520.0,
|
| 2338 |
+
"step": 1450
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 1.6269907795473597,
|
| 2342 |
+
"grad_norm": 0.2454751431941986,
|
| 2343 |
+
"learning_rate": 4.151646985705407e-06,
|
| 2344 |
+
"loss": 0.284,
|
| 2345 |
+
"num_tokens": 2514264211.0,
|
| 2346 |
+
"step": 1455
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 1.6325789326627551,
|
| 2350 |
+
"grad_norm": 0.22797976434230804,
|
| 2351 |
+
"learning_rate": 4.0894965817277815e-06,
|
| 2352 |
+
"loss": 0.2853,
|
| 2353 |
+
"num_tokens": 2522903645.0,
|
| 2354 |
+
"step": 1460
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 1.6381670857781503,
|
| 2358 |
+
"grad_norm": 0.2286279946565628,
|
| 2359 |
+
"learning_rate": 4.027346177750156e-06,
|
| 2360 |
+
"loss": 0.2841,
|
| 2361 |
+
"num_tokens": 2531516266.0,
|
| 2362 |
+
"step": 1465
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 1.6437552388935457,
|
| 2366 |
+
"grad_norm": 0.19183382391929626,
|
| 2367 |
+
"learning_rate": 3.96519577377253e-06,
|
| 2368 |
+
"loss": 0.2834,
|
| 2369 |
+
"num_tokens": 2540132651.0,
|
| 2370 |
+
"step": 1470
|
| 2371 |
+
},
|
| 2372 |
+
{
|
| 2373 |
+
"epoch": 1.649343392008941,
|
| 2374 |
+
"grad_norm": 0.20147649943828583,
|
| 2375 |
+
"learning_rate": 3.903045369794904e-06,
|
| 2376 |
+
"loss": 0.2844,
|
| 2377 |
+
"num_tokens": 2548789057.0,
|
| 2378 |
+
"step": 1475
|
| 2379 |
+
},
|
| 2380 |
+
{
|
| 2381 |
+
"epoch": 1.6549315451243363,
|
| 2382 |
+
"grad_norm": 0.21062539517879486,
|
| 2383 |
+
"learning_rate": 3.8408949658172786e-06,
|
| 2384 |
+
"loss": 0.286,
|
| 2385 |
+
"num_tokens": 2557438457.0,
|
| 2386 |
+
"step": 1480
|
| 2387 |
+
},
|
| 2388 |
+
{
|
| 2389 |
+
"epoch": 1.6605196982397317,
|
| 2390 |
+
"grad_norm": 0.20658695697784424,
|
| 2391 |
+
"learning_rate": 3.7787445618396524e-06,
|
| 2392 |
+
"loss": 0.2844,
|
| 2393 |
+
"num_tokens": 2566104615.0,
|
| 2394 |
+
"step": 1485
|
| 2395 |
+
},
|
| 2396 |
+
{
|
| 2397 |
+
"epoch": 1.666107851355127,
|
| 2398 |
+
"grad_norm": 0.21198123693466187,
|
| 2399 |
+
"learning_rate": 3.7165941578620263e-06,
|
| 2400 |
+
"loss": 0.2845,
|
| 2401 |
+
"num_tokens": 2574730671.0,
|
| 2402 |
+
"step": 1490
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 1.6716960044705225,
|
| 2406 |
+
"grad_norm": 0.22207552194595337,
|
| 2407 |
+
"learning_rate": 3.6544437538844006e-06,
|
| 2408 |
+
"loss": 0.2841,
|
| 2409 |
+
"num_tokens": 2583386151.0,
|
| 2410 |
+
"step": 1495
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 1.6772841575859179,
|
| 2414 |
+
"grad_norm": 0.21470749378204346,
|
| 2415 |
+
"learning_rate": 3.592293349906775e-06,
|
| 2416 |
+
"loss": 0.2854,
|
| 2417 |
+
"num_tokens": 2592007075.0,
|
| 2418 |
+
"step": 1500
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 1.6828723107013133,
|
| 2422 |
+
"grad_norm": 0.22267666459083557,
|
| 2423 |
+
"learning_rate": 3.5301429459291487e-06,
|
| 2424 |
+
"loss": 0.2843,
|
| 2425 |
+
"num_tokens": 2600618307.0,
|
| 2426 |
+
"step": 1505
|
| 2427 |
+
},
|
| 2428 |
+
{
|
| 2429 |
+
"epoch": 1.6884604638167087,
|
| 2430 |
+
"grad_norm": 0.25010621547698975,
|
| 2431 |
+
"learning_rate": 3.467992541951523e-06,
|
| 2432 |
+
"loss": 0.2834,
|
| 2433 |
+
"num_tokens": 2609275015.0,
|
| 2434 |
+
"step": 1510
|
| 2435 |
+
},
|
| 2436 |
+
{
|
| 2437 |
+
"epoch": 1.694048616932104,
|
| 2438 |
+
"grad_norm": 0.21234430372714996,
|
| 2439 |
+
"learning_rate": 3.4058421379738972e-06,
|
| 2440 |
+
"loss": 0.2852,
|
| 2441 |
+
"num_tokens": 2617927159.0,
|
| 2442 |
+
"step": 1515
|
| 2443 |
+
},
|
| 2444 |
+
{
|
| 2445 |
+
"epoch": 1.6996367700474995,
|
| 2446 |
+
"grad_norm": 0.212777242064476,
|
| 2447 |
+
"learning_rate": 3.343691733996271e-06,
|
| 2448 |
+
"loss": 0.2835,
|
| 2449 |
+
"num_tokens": 2626598520.0,
|
| 2450 |
+
"step": 1520
|
| 2451 |
+
},
|
| 2452 |
+
{
|
| 2453 |
+
"epoch": 1.7052249231628946,
|
| 2454 |
+
"grad_norm": 0.2279113233089447,
|
| 2455 |
+
"learning_rate": 3.2815413300186454e-06,
|
| 2456 |
+
"loss": 0.2836,
|
| 2457 |
+
"num_tokens": 2635241607.0,
|
| 2458 |
+
"step": 1525
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 1.71081307627829,
|
| 2462 |
+
"grad_norm": 0.2212340086698532,
|
| 2463 |
+
"learning_rate": 3.2193909260410196e-06,
|
| 2464 |
+
"loss": 0.2828,
|
| 2465 |
+
"num_tokens": 2643858312.0,
|
| 2466 |
+
"step": 1530
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 1.7164012293936852,
|
| 2470 |
+
"grad_norm": 0.20195508003234863,
|
| 2471 |
+
"learning_rate": 3.157240522063394e-06,
|
| 2472 |
+
"loss": 0.2835,
|
| 2473 |
+
"num_tokens": 2652491273.0,
|
| 2474 |
+
"step": 1535
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 1.7219893825090806,
|
| 2478 |
+
"grad_norm": 0.21651341021060944,
|
| 2479 |
+
"learning_rate": 3.0950901180857678e-06,
|
| 2480 |
+
"loss": 0.2826,
|
| 2481 |
+
"num_tokens": 2661125711.0,
|
| 2482 |
+
"step": 1540
|
| 2483 |
+
},
|
| 2484 |
+
{
|
| 2485 |
+
"epoch": 1.727577535624476,
|
| 2486 |
+
"grad_norm": 0.20481155812740326,
|
| 2487 |
+
"learning_rate": 3.0329397141081416e-06,
|
| 2488 |
+
"loss": 0.2849,
|
| 2489 |
+
"num_tokens": 2669737453.0,
|
| 2490 |
+
"step": 1545
|
| 2491 |
+
},
|
| 2492 |
+
{
|
| 2493 |
+
"epoch": 1.7331656887398714,
|
| 2494 |
+
"grad_norm": 0.20491968095302582,
|
| 2495 |
+
"learning_rate": 2.9707893101305163e-06,
|
| 2496 |
+
"loss": 0.2826,
|
| 2497 |
+
"num_tokens": 2678374413.0,
|
| 2498 |
+
"step": 1550
|
| 2499 |
+
},
|
| 2500 |
+
{
|
| 2501 |
+
"epoch": 1.7387538418552668,
|
| 2502 |
+
"grad_norm": 0.2029823362827301,
|
| 2503 |
+
"learning_rate": 2.90863890615289e-06,
|
| 2504 |
+
"loss": 0.2838,
|
| 2505 |
+
"num_tokens": 2686987442.0,
|
| 2506 |
+
"step": 1555
|
| 2507 |
+
},
|
| 2508 |
+
{
|
| 2509 |
+
"epoch": 1.7443419949706622,
|
| 2510 |
+
"grad_norm": 0.2510753571987152,
|
| 2511 |
+
"learning_rate": 2.846488502175264e-06,
|
| 2512 |
+
"loss": 0.2824,
|
| 2513 |
+
"num_tokens": 2695607973.0,
|
| 2514 |
+
"step": 1560
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 1.7499301480860576,
|
| 2518 |
+
"grad_norm": 0.23176781833171844,
|
| 2519 |
+
"learning_rate": 2.7843380981976387e-06,
|
| 2520 |
+
"loss": 0.2829,
|
| 2521 |
+
"num_tokens": 2704257689.0,
|
| 2522 |
+
"step": 1565
|
| 2523 |
+
},
|
| 2524 |
+
{
|
| 2525 |
+
"epoch": 1.755518301201453,
|
| 2526 |
+
"grad_norm": 0.22666539251804352,
|
| 2527 |
+
"learning_rate": 2.7221876942200126e-06,
|
| 2528 |
+
"loss": 0.282,
|
| 2529 |
+
"num_tokens": 2712898044.0,
|
| 2530 |
+
"step": 1570
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 1.7611064543168484,
|
| 2534 |
+
"grad_norm": 0.22624371945858002,
|
| 2535 |
+
"learning_rate": 2.6600372902423864e-06,
|
| 2536 |
+
"loss": 0.2833,
|
| 2537 |
+
"num_tokens": 2721529682.0,
|
| 2538 |
+
"step": 1575
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 1.7666946074322436,
|
| 2542 |
+
"grad_norm": 0.24672020971775055,
|
| 2543 |
+
"learning_rate": 2.597886886264761e-06,
|
| 2544 |
+
"loss": 0.2837,
|
| 2545 |
+
"num_tokens": 2730153928.0,
|
| 2546 |
+
"step": 1580
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 1.772282760547639,
|
| 2550 |
+
"grad_norm": 0.22057084739208221,
|
| 2551 |
+
"learning_rate": 2.535736482287135e-06,
|
| 2552 |
+
"loss": 0.2825,
|
| 2553 |
+
"num_tokens": 2738797091.0,
|
| 2554 |
+
"step": 1585
|
| 2555 |
+
},
|
| 2556 |
+
{
|
| 2557 |
+
"epoch": 1.7778709136630344,
|
| 2558 |
+
"grad_norm": 0.1964276283979416,
|
| 2559 |
+
"learning_rate": 2.4735860783095093e-06,
|
| 2560 |
+
"loss": 0.2831,
|
| 2561 |
+
"num_tokens": 2747438652.0,
|
| 2562 |
+
"step": 1590
|
| 2563 |
+
},
|
| 2564 |
+
{
|
| 2565 |
+
"epoch": 1.7834590667784296,
|
| 2566 |
+
"grad_norm": 0.18753261864185333,
|
| 2567 |
+
"learning_rate": 2.4114356743318835e-06,
|
| 2568 |
+
"loss": 0.2836,
|
| 2569 |
+
"num_tokens": 2756092674.0,
|
| 2570 |
+
"step": 1595
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 1.789047219893825,
|
| 2574 |
+
"grad_norm": 0.19848628342151642,
|
| 2575 |
+
"learning_rate": 2.349285270354258e-06,
|
| 2576 |
+
"loss": 0.2813,
|
| 2577 |
+
"num_tokens": 2764728890.0,
|
| 2578 |
+
"step": 1600
|
| 2579 |
+
},
|
| 2580 |
+
{
|
| 2581 |
+
"epoch": 1.7946353730092204,
|
| 2582 |
+
"grad_norm": 0.19272516667842865,
|
| 2583 |
+
"learning_rate": 2.2871348663766317e-06,
|
| 2584 |
+
"loss": 0.2829,
|
| 2585 |
+
"num_tokens": 2773303612.0,
|
| 2586 |
+
"step": 1605
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 1.8002235261246158,
|
| 2590 |
+
"grad_norm": 0.20509815216064453,
|
| 2591 |
+
"learning_rate": 2.224984462399006e-06,
|
| 2592 |
+
"loss": 0.2822,
|
| 2593 |
+
"num_tokens": 2781943420.0,
|
| 2594 |
+
"step": 1610
|
| 2595 |
+
},
|
| 2596 |
+
{
|
| 2597 |
+
"epoch": 1.8058116792400112,
|
| 2598 |
+
"grad_norm": 0.19751939177513123,
|
| 2599 |
+
"learning_rate": 2.16283405842138e-06,
|
| 2600 |
+
"loss": 0.2813,
|
| 2601 |
+
"num_tokens": 2790544836.0,
|
| 2602 |
+
"step": 1615
|
| 2603 |
+
},
|
| 2604 |
+
{
|
| 2605 |
+
"epoch": 1.8113998323554066,
|
| 2606 |
+
"grad_norm": 0.2047342211008072,
|
| 2607 |
+
"learning_rate": 2.100683654443754e-06,
|
| 2608 |
+
"loss": 0.2814,
|
| 2609 |
+
"num_tokens": 2799179051.0,
|
| 2610 |
+
"step": 1620
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 1.816987985470802,
|
| 2614 |
+
"grad_norm": 0.21204353868961334,
|
| 2615 |
+
"learning_rate": 2.0385332504661283e-06,
|
| 2616 |
+
"loss": 0.2819,
|
| 2617 |
+
"num_tokens": 2807859657.0,
|
| 2618 |
+
"step": 1625
|
| 2619 |
+
},
|
| 2620 |
+
{
|
| 2621 |
+
"epoch": 1.8225761385861974,
|
| 2622 |
+
"grad_norm": 0.20583118498325348,
|
| 2623 |
+
"learning_rate": 1.976382846488502e-06,
|
| 2624 |
+
"loss": 0.2815,
|
| 2625 |
+
"num_tokens": 2816535171.0,
|
| 2626 |
+
"step": 1630
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 1.8281642917015928,
|
| 2630 |
+
"grad_norm": 0.21081192791461945,
|
| 2631 |
+
"learning_rate": 1.9142324425108765e-06,
|
| 2632 |
+
"loss": 0.2826,
|
| 2633 |
+
"num_tokens": 2825189719.0,
|
| 2634 |
+
"step": 1635
|
| 2635 |
+
},
|
| 2636 |
+
{
|
| 2637 |
+
"epoch": 1.833752444816988,
|
| 2638 |
+
"grad_norm": 0.18788641691207886,
|
| 2639 |
+
"learning_rate": 1.8520820385332505e-06,
|
| 2640 |
+
"loss": 0.2804,
|
| 2641 |
+
"num_tokens": 2833874847.0,
|
| 2642 |
+
"step": 1640
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 1.8393405979323834,
|
| 2646 |
+
"grad_norm": 0.20237120985984802,
|
| 2647 |
+
"learning_rate": 1.7899316345556248e-06,
|
| 2648 |
+
"loss": 0.2824,
|
| 2649 |
+
"num_tokens": 2842459461.0,
|
| 2650 |
+
"step": 1645
|
| 2651 |
+
},
|
| 2652 |
+
{
|
| 2653 |
+
"epoch": 1.8449287510477788,
|
| 2654 |
+
"grad_norm": 0.1973085254430771,
|
| 2655 |
+
"learning_rate": 1.7277812305779989e-06,
|
| 2656 |
+
"loss": 0.2815,
|
| 2657 |
+
"num_tokens": 2851115535.0,
|
| 2658 |
+
"step": 1650
|
| 2659 |
+
},
|
| 2660 |
+
{
|
| 2661 |
+
"epoch": 1.850516904163174,
|
| 2662 |
+
"grad_norm": 0.1954537183046341,
|
| 2663 |
+
"learning_rate": 1.6656308266003731e-06,
|
| 2664 |
+
"loss": 0.2811,
|
| 2665 |
+
"num_tokens": 2859739184.0,
|
| 2666 |
+
"step": 1655
|
| 2667 |
+
},
|
| 2668 |
+
{
|
| 2669 |
+
"epoch": 1.8561050572785693,
|
| 2670 |
+
"grad_norm": 0.1938507854938507,
|
| 2671 |
+
"learning_rate": 1.6034804226227472e-06,
|
| 2672 |
+
"loss": 0.281,
|
| 2673 |
+
"num_tokens": 2868403974.0,
|
| 2674 |
+
"step": 1660
|
| 2675 |
+
},
|
| 2676 |
+
{
|
| 2677 |
+
"epoch": 1.8616932103939647,
|
| 2678 |
+
"grad_norm": 0.20135918259620667,
|
| 2679 |
+
"learning_rate": 1.5413300186451213e-06,
|
| 2680 |
+
"loss": 0.2821,
|
| 2681 |
+
"num_tokens": 2877010029.0,
|
| 2682 |
+
"step": 1665
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 1.8672813635093601,
|
| 2686 |
+
"grad_norm": 0.19300834834575653,
|
| 2687 |
+
"learning_rate": 1.4791796146674955e-06,
|
| 2688 |
+
"loss": 0.2818,
|
| 2689 |
+
"num_tokens": 2885631493.0,
|
| 2690 |
+
"step": 1670
|
| 2691 |
+
},
|
| 2692 |
+
{
|
| 2693 |
+
"epoch": 1.8728695166247555,
|
| 2694 |
+
"grad_norm": 0.19174011051654816,
|
| 2695 |
+
"learning_rate": 1.4170292106898694e-06,
|
| 2696 |
+
"loss": 0.282,
|
| 2697 |
+
"num_tokens": 2894271003.0,
|
| 2698 |
+
"step": 1675
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 1.878457669740151,
|
| 2702 |
+
"grad_norm": 0.19045238196849823,
|
| 2703 |
+
"learning_rate": 1.3548788067122437e-06,
|
| 2704 |
+
"loss": 0.2812,
|
| 2705 |
+
"num_tokens": 2902878445.0,
|
| 2706 |
+
"step": 1680
|
| 2707 |
+
},
|
| 2708 |
+
{
|
| 2709 |
+
"epoch": 1.8840458228555463,
|
| 2710 |
+
"grad_norm": 0.18684354424476624,
|
| 2711 |
+
"learning_rate": 1.292728402734618e-06,
|
| 2712 |
+
"loss": 0.2824,
|
| 2713 |
+
"num_tokens": 2911477156.0,
|
| 2714 |
+
"step": 1685
|
| 2715 |
+
},
|
| 2716 |
+
{
|
| 2717 |
+
"epoch": 1.8896339759709417,
|
| 2718 |
+
"grad_norm": 0.1858016550540924,
|
| 2719 |
+
"learning_rate": 1.230577998756992e-06,
|
| 2720 |
+
"loss": 0.2804,
|
| 2721 |
+
"num_tokens": 2920099568.0,
|
| 2722 |
+
"step": 1690
|
| 2723 |
+
},
|
| 2724 |
+
{
|
| 2725 |
+
"epoch": 1.895222129086337,
|
| 2726 |
+
"grad_norm": 0.18339896202087402,
|
| 2727 |
+
"learning_rate": 1.1684275947793663e-06,
|
| 2728 |
+
"loss": 0.2827,
|
| 2729 |
+
"num_tokens": 2928733423.0,
|
| 2730 |
+
"step": 1695
|
| 2731 |
+
},
|
| 2732 |
+
{
|
| 2733 |
+
"epoch": 1.9008102822017323,
|
| 2734 |
+
"grad_norm": 0.1879528909921646,
|
| 2735 |
+
"learning_rate": 1.1062771908017403e-06,
|
| 2736 |
+
"loss": 0.2812,
|
| 2737 |
+
"num_tokens": 2937387124.0,
|
| 2738 |
+
"step": 1700
|
| 2739 |
+
}
|
| 2740 |
+
],
|
| 2741 |
+
"logging_steps": 5,
|
| 2742 |
+
"max_steps": 1788,
|
| 2743 |
+
"num_input_tokens_seen": 0,
|
| 2744 |
+
"num_train_epochs": 2,
|
| 2745 |
+
"save_steps": 100,
|
| 2746 |
+
"stateful_callbacks": {
|
| 2747 |
+
"TrainerControl": {
|
| 2748 |
+
"args": {
|
| 2749 |
+
"should_epoch_stop": false,
|
| 2750 |
+
"should_evaluate": false,
|
| 2751 |
+
"should_log": false,
|
| 2752 |
+
"should_save": true,
|
| 2753 |
+
"should_training_stop": false
|
| 2754 |
+
},
|
| 2755 |
+
"attributes": {}
|
| 2756 |
+
}
|
| 2757 |
+
},
|
| 2758 |
+
"total_flos": 1.0851623166841717e+19,
|
| 2759 |
+
"train_batch_size": 32,
|
| 2760 |
+
"trial_name": null,
|
| 2761 |
+
"trial_params": null
|
| 2762 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|