Upload folder using huggingface_hub
Browse files- .mdl +0 -0
- .msc +0 -0
- .mv +1 -0
- config.json +33 -0
- configuration.json +1 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +195 -0
- trainer_state.json +2602 -0
.mdl
ADDED
Binary file (78 Bytes). View file
|
|
.msc
ADDED
Binary file (842 Bytes). View file
|
|
.mv
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
Revision:master,CreatedAt:1753939291
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"LlamaForCausalLM"
|
4 |
+
],
|
5 |
+
"attention_bias": false,
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 32013,
|
8 |
+
"eos_token_id": 32021,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5504,
|
14 |
+
"max_position_embeddings": 16384,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 16,
|
18 |
+
"num_hidden_layers": 24,
|
19 |
+
"num_key_value_heads": 16,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-06,
|
22 |
+
"rope_scaling": {
|
23 |
+
"factor": 4.0,
|
24 |
+
"rope_type": "linear",
|
25 |
+
"type": "linear"
|
26 |
+
},
|
27 |
+
"rope_theta": 100000,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "bfloat16",
|
30 |
+
"transformers_version": "4.51.3",
|
31 |
+
"use_cache": false,
|
32 |
+
"vocab_size": 32256
|
33 |
+
}
|
configuration.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 32013,
|
4 |
+
"eos_token_id": 32021,
|
5 |
+
"transformers_version": "4.51.3"
|
6 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75321fcf2645a967dde0a5bc5751fe2a998ad264fa17612124353b64b7e38403
|
3 |
+
size 2692969128
|
special_tokens_map.json
ADDED
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|begin▁of▁sentence|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|EOT|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|end▁of▁sentence|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
}
|
23 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,195 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"32000": {
|
7 |
+
"content": "õ",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": true,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": false
|
13 |
+
},
|
14 |
+
"32001": {
|
15 |
+
"content": "÷",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": false
|
21 |
+
},
|
22 |
+
"32002": {
|
23 |
+
"content": "Á",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": true,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": false
|
29 |
+
},
|
30 |
+
"32003": {
|
31 |
+
"content": "ý",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": true,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": false
|
37 |
+
},
|
38 |
+
"32004": {
|
39 |
+
"content": "À",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": true,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": false
|
45 |
+
},
|
46 |
+
"32005": {
|
47 |
+
"content": "ÿ",
|
48 |
+
"lstrip": false,
|
49 |
+
"normalized": true,
|
50 |
+
"rstrip": false,
|
51 |
+
"single_word": false,
|
52 |
+
"special": false
|
53 |
+
},
|
54 |
+
"32006": {
|
55 |
+
"content": "ø",
|
56 |
+
"lstrip": false,
|
57 |
+
"normalized": true,
|
58 |
+
"rstrip": false,
|
59 |
+
"single_word": false,
|
60 |
+
"special": false
|
61 |
+
},
|
62 |
+
"32007": {
|
63 |
+
"content": "ú",
|
64 |
+
"lstrip": false,
|
65 |
+
"normalized": true,
|
66 |
+
"rstrip": false,
|
67 |
+
"single_word": false,
|
68 |
+
"special": false
|
69 |
+
},
|
70 |
+
"32008": {
|
71 |
+
"content": "þ",
|
72 |
+
"lstrip": false,
|
73 |
+
"normalized": true,
|
74 |
+
"rstrip": false,
|
75 |
+
"single_word": false,
|
76 |
+
"special": false
|
77 |
+
},
|
78 |
+
"32009": {
|
79 |
+
"content": "ü",
|
80 |
+
"lstrip": false,
|
81 |
+
"normalized": true,
|
82 |
+
"rstrip": false,
|
83 |
+
"single_word": false,
|
84 |
+
"special": false
|
85 |
+
},
|
86 |
+
"32010": {
|
87 |
+
"content": "ù",
|
88 |
+
"lstrip": false,
|
89 |
+
"normalized": true,
|
90 |
+
"rstrip": false,
|
91 |
+
"single_word": false,
|
92 |
+
"special": false
|
93 |
+
},
|
94 |
+
"32011": {
|
95 |
+
"content": "ö",
|
96 |
+
"lstrip": false,
|
97 |
+
"normalized": true,
|
98 |
+
"rstrip": false,
|
99 |
+
"single_word": false,
|
100 |
+
"special": false
|
101 |
+
},
|
102 |
+
"32012": {
|
103 |
+
"content": "û",
|
104 |
+
"lstrip": false,
|
105 |
+
"normalized": true,
|
106 |
+
"rstrip": false,
|
107 |
+
"single_word": false,
|
108 |
+
"special": false
|
109 |
+
},
|
110 |
+
"32013": {
|
111 |
+
"content": "<|begin▁of▁sentence|>",
|
112 |
+
"lstrip": false,
|
113 |
+
"normalized": true,
|
114 |
+
"rstrip": false,
|
115 |
+
"single_word": false,
|
116 |
+
"special": true
|
117 |
+
},
|
118 |
+
"32014": {
|
119 |
+
"content": "<|end▁of▁sentence|>",
|
120 |
+
"lstrip": false,
|
121 |
+
"normalized": true,
|
122 |
+
"rstrip": false,
|
123 |
+
"single_word": false,
|
124 |
+
"special": true
|
125 |
+
},
|
126 |
+
"32015": {
|
127 |
+
"content": "<|fim▁hole|>",
|
128 |
+
"lstrip": false,
|
129 |
+
"normalized": true,
|
130 |
+
"rstrip": false,
|
131 |
+
"single_word": false,
|
132 |
+
"special": false
|
133 |
+
},
|
134 |
+
"32016": {
|
135 |
+
"content": "<|fim▁begin|>",
|
136 |
+
"lstrip": false,
|
137 |
+
"normalized": true,
|
138 |
+
"rstrip": false,
|
139 |
+
"single_word": false,
|
140 |
+
"special": false
|
141 |
+
},
|
142 |
+
"32017": {
|
143 |
+
"content": "<|fim▁end|>",
|
144 |
+
"lstrip": false,
|
145 |
+
"normalized": true,
|
146 |
+
"rstrip": false,
|
147 |
+
"single_word": false,
|
148 |
+
"special": false
|
149 |
+
},
|
150 |
+
"32018": {
|
151 |
+
"content": "<pad>",
|
152 |
+
"lstrip": false,
|
153 |
+
"normalized": true,
|
154 |
+
"rstrip": false,
|
155 |
+
"single_word": false,
|
156 |
+
"special": false
|
157 |
+
},
|
158 |
+
"32019": {
|
159 |
+
"content": "<|User|>",
|
160 |
+
"lstrip": false,
|
161 |
+
"normalized": true,
|
162 |
+
"rstrip": false,
|
163 |
+
"single_word": false,
|
164 |
+
"special": false
|
165 |
+
},
|
166 |
+
"32020": {
|
167 |
+
"content": "<|Assistant|>",
|
168 |
+
"lstrip": false,
|
169 |
+
"normalized": true,
|
170 |
+
"rstrip": false,
|
171 |
+
"single_word": false,
|
172 |
+
"special": false
|
173 |
+
},
|
174 |
+
"32021": {
|
175 |
+
"content": "<|EOT|>",
|
176 |
+
"lstrip": false,
|
177 |
+
"normalized": true,
|
178 |
+
"rstrip": false,
|
179 |
+
"single_word": false,
|
180 |
+
"special": true
|
181 |
+
}
|
182 |
+
},
|
183 |
+
"bos_token": "<|begin▁of▁sentence|>",
|
184 |
+
"chat_template": "{% if not add_generation_prompt is defined %}\n{% set add_generation_prompt = false %}\n{% endif %}\n{%- set ns = namespace(found=false) -%}\n{%- for message in messages -%}\n {%- if message['role'] == 'system' -%}\n {%- set ns.found = true -%}\n {%- endif -%}\n{%- endfor -%}\n{{bos_token}}{%- if not ns.found -%}\n{{'You are an AI programming assistant, utilizing the Deepseek Coder model, developed by Deepseek Company, and you only answer questions related to computer science. For politically sensitive questions, security and privacy issues, and other non-computer science questions, you will refuse to answer\\n'}}\n{%- endif %}\n{%- for message in messages %}\n {%- if message['role'] == 'system' %}\n{{ message['content'] }}\n {%- else %}\n {%- if message['role'] == 'user' %}\n{{'### Instruction:\\n' + message['content'] + '\\n'}}\n {%- else %}\n{{'### Response:\\n' + message['content'] + '\\n<|EOT|>\\n'}}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{% if add_generation_prompt %}\n{{'### Response:'}}\n{% endif %}",
|
185 |
+
"clean_up_tokenization_spaces": false,
|
186 |
+
"eos_token": "<|EOT|>",
|
187 |
+
"extra_special_tokens": {},
|
188 |
+
"legacy": true,
|
189 |
+
"model_max_length": 16384,
|
190 |
+
"pad_token": "<|end▁of▁sentence|>",
|
191 |
+
"sp_model_kwargs": {},
|
192 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
193 |
+
"unk_token": null,
|
194 |
+
"use_default_system_prompt": false
|
195 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,2602 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_global_step": null,
|
3 |
+
"best_metric": null,
|
4 |
+
"best_model_checkpoint": null,
|
5 |
+
"epoch": 1.789047219893825,
|
6 |
+
"eval_steps": 500,
|
7 |
+
"global_step": 1600,
|
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": 2.6477396488189697,
|
15 |
+
"learning_rate": 0.0,
|
16 |
+
"loss": 0.9173,
|
17 |
+
"num_tokens": 2283153.0,
|
18 |
+
"step": 1
|
19 |
+
},
|
20 |
+
{
|
21 |
+
"epoch": 0.005588153115395362,
|
22 |
+
"grad_norm": 2.6618285179138184,
|
23 |
+
"learning_rate": 4.46927374301676e-07,
|
24 |
+
"loss": 0.9183,
|
25 |
+
"num_tokens": 11372970.0,
|
26 |
+
"step": 5
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.011176306230790724,
|
30 |
+
"grad_norm": 2.51755690574646,
|
31 |
+
"learning_rate": 1.005586592178771e-06,
|
32 |
+
"loss": 0.9114,
|
33 |
+
"num_tokens": 22783006.0,
|
34 |
+
"step": 10
|
35 |
+
},
|
36 |
+
{
|
37 |
+
"epoch": 0.016764459346186086,
|
38 |
+
"grad_norm": 2.163336992263794,
|
39 |
+
"learning_rate": 1.564245810055866e-06,
|
40 |
+
"loss": 0.8871,
|
41 |
+
"num_tokens": 34178559.0,
|
42 |
+
"step": 15
|
43 |
+
},
|
44 |
+
{
|
45 |
+
"epoch": 0.022352612461581448,
|
46 |
+
"grad_norm": 1.4962947368621826,
|
47 |
+
"learning_rate": 2.1229050279329612e-06,
|
48 |
+
"loss": 0.8116,
|
49 |
+
"num_tokens": 45574554.0,
|
50 |
+
"step": 20
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.02794076557697681,
|
54 |
+
"grad_norm": 1.0881785154342651,
|
55 |
+
"learning_rate": 2.6815642458100562e-06,
|
56 |
+
"loss": 0.7168,
|
57 |
+
"num_tokens": 57052998.0,
|
58 |
+
"step": 25
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.03352891869237217,
|
62 |
+
"grad_norm": 1.133913516998291,
|
63 |
+
"learning_rate": 3.240223463687151e-06,
|
64 |
+
"loss": 0.5776,
|
65 |
+
"num_tokens": 68474831.0,
|
66 |
+
"step": 30
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 0.03911707180776753,
|
70 |
+
"grad_norm": 0.5789642930030823,
|
71 |
+
"learning_rate": 3.798882681564246e-06,
|
72 |
+
"loss": 0.4818,
|
73 |
+
"num_tokens": 79910887.0,
|
74 |
+
"step": 35
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.044705224923162895,
|
78 |
+
"grad_norm": 0.31034183502197266,
|
79 |
+
"learning_rate": 4.357541899441341e-06,
|
80 |
+
"loss": 0.415,
|
81 |
+
"num_tokens": 91319517.0,
|
82 |
+
"step": 40
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.050293378038558254,
|
86 |
+
"grad_norm": 0.2817094027996063,
|
87 |
+
"learning_rate": 4.916201117318436e-06,
|
88 |
+
"loss": 0.4016,
|
89 |
+
"num_tokens": 102702395.0,
|
90 |
+
"step": 45
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.05588153115395362,
|
94 |
+
"grad_norm": 0.2526246905326843,
|
95 |
+
"learning_rate": 5.474860335195531e-06,
|
96 |
+
"loss": 0.3861,
|
97 |
+
"num_tokens": 114127803.0,
|
98 |
+
"step": 50
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.06146968426934898,
|
102 |
+
"grad_norm": 0.2339339554309845,
|
103 |
+
"learning_rate": 6.033519553072626e-06,
|
104 |
+
"loss": 0.3764,
|
105 |
+
"num_tokens": 125524248.0,
|
106 |
+
"step": 55
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 0.06705783738474434,
|
110 |
+
"grad_norm": 0.23666101694107056,
|
111 |
+
"learning_rate": 6.592178770949721e-06,
|
112 |
+
"loss": 0.3671,
|
113 |
+
"num_tokens": 136911011.0,
|
114 |
+
"step": 60
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.0726459905001397,
|
118 |
+
"grad_norm": 0.2580510973930359,
|
119 |
+
"learning_rate": 7.150837988826816e-06,
|
120 |
+
"loss": 0.3604,
|
121 |
+
"num_tokens": 148350926.0,
|
122 |
+
"step": 65
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.07823414361553506,
|
126 |
+
"grad_norm": 0.31147921085357666,
|
127 |
+
"learning_rate": 7.709497206703911e-06,
|
128 |
+
"loss": 0.3579,
|
129 |
+
"num_tokens": 159702648.0,
|
130 |
+
"step": 70
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.08382229673093043,
|
134 |
+
"grad_norm": 0.19841235876083374,
|
135 |
+
"learning_rate": 8.268156424581007e-06,
|
136 |
+
"loss": 0.348,
|
137 |
+
"num_tokens": 171139841.0,
|
138 |
+
"step": 75
|
139 |
+
},
|
140 |
+
{
|
141 |
+
"epoch": 0.08941044984632579,
|
142 |
+
"grad_norm": 0.0895436629652977,
|
143 |
+
"learning_rate": 8.826815642458101e-06,
|
144 |
+
"loss": 0.3423,
|
145 |
+
"num_tokens": 182567409.0,
|
146 |
+
"step": 80
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.09499860296172115,
|
150 |
+
"grad_norm": 0.09871780127286911,
|
151 |
+
"learning_rate": 9.385474860335197e-06,
|
152 |
+
"loss": 0.3421,
|
153 |
+
"num_tokens": 194004756.0,
|
154 |
+
"step": 85
|
155 |
+
},
|
156 |
+
{
|
157 |
+
"epoch": 0.10058675607711651,
|
158 |
+
"grad_norm": 0.06650134176015854,
|
159 |
+
"learning_rate": 9.944134078212291e-06,
|
160 |
+
"loss": 0.3384,
|
161 |
+
"num_tokens": 205442473.0,
|
162 |
+
"step": 90
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.10617490919251188,
|
166 |
+
"grad_norm": 0.0545571967959404,
|
167 |
+
"learning_rate": 1.0502793296089386e-05,
|
168 |
+
"loss": 0.3352,
|
169 |
+
"num_tokens": 216872981.0,
|
170 |
+
"step": 95
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.11176306230790724,
|
174 |
+
"grad_norm": 0.054781682789325714,
|
175 |
+
"learning_rate": 1.1061452513966481e-05,
|
176 |
+
"loss": 0.3316,
|
177 |
+
"num_tokens": 228325464.0,
|
178 |
+
"step": 100
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.1173512154233026,
|
182 |
+
"grad_norm": 0.05507330223917961,
|
183 |
+
"learning_rate": 1.1620111731843577e-05,
|
184 |
+
"loss": 0.3304,
|
185 |
+
"num_tokens": 239746434.0,
|
186 |
+
"step": 105
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.12293936853869795,
|
190 |
+
"grad_norm": 0.04985460266470909,
|
191 |
+
"learning_rate": 1.2178770949720671e-05,
|
192 |
+
"loss": 0.3286,
|
193 |
+
"num_tokens": 251145034.0,
|
194 |
+
"step": 110
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.1285275216540933,
|
198 |
+
"grad_norm": 0.05047163367271423,
|
199 |
+
"learning_rate": 1.2737430167597766e-05,
|
200 |
+
"loss": 0.3248,
|
201 |
+
"num_tokens": 262525841.0,
|
202 |
+
"step": 115
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 0.13411567476948869,
|
206 |
+
"grad_norm": 0.0513993501663208,
|
207 |
+
"learning_rate": 1.3296089385474861e-05,
|
208 |
+
"loss": 0.3259,
|
209 |
+
"num_tokens": 273895120.0,
|
210 |
+
"step": 120
|
211 |
+
},
|
212 |
+
{
|
213 |
+
"epoch": 0.13970382788488406,
|
214 |
+
"grad_norm": 0.05008988827466965,
|
215 |
+
"learning_rate": 1.3854748603351957e-05,
|
216 |
+
"loss": 0.3216,
|
217 |
+
"num_tokens": 285306751.0,
|
218 |
+
"step": 125
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.1452919810002794,
|
222 |
+
"grad_norm": 0.05217043682932854,
|
223 |
+
"learning_rate": 1.4413407821229052e-05,
|
224 |
+
"loss": 0.3202,
|
225 |
+
"num_tokens": 296700765.0,
|
226 |
+
"step": 130
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 0.15088013411567477,
|
230 |
+
"grad_norm": 0.05048668757081032,
|
231 |
+
"learning_rate": 1.4972067039106146e-05,
|
232 |
+
"loss": 0.3193,
|
233 |
+
"num_tokens": 308137335.0,
|
234 |
+
"step": 135
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.15646828723107012,
|
238 |
+
"grad_norm": 0.0592043362557888,
|
239 |
+
"learning_rate": 1.553072625698324e-05,
|
240 |
+
"loss": 0.3172,
|
241 |
+
"num_tokens": 319571146.0,
|
242 |
+
"step": 140
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.1620564403464655,
|
246 |
+
"grad_norm": 0.06134902313351631,
|
247 |
+
"learning_rate": 1.6089385474860336e-05,
|
248 |
+
"loss": 0.3135,
|
249 |
+
"num_tokens": 330973413.0,
|
250 |
+
"step": 145
|
251 |
+
},
|
252 |
+
{
|
253 |
+
"epoch": 0.16764459346186086,
|
254 |
+
"grad_norm": 0.05340028181672096,
|
255 |
+
"learning_rate": 1.664804469273743e-05,
|
256 |
+
"loss": 0.3124,
|
257 |
+
"num_tokens": 342371116.0,
|
258 |
+
"step": 150
|
259 |
+
},
|
260 |
+
{
|
261 |
+
"epoch": 0.1732327465772562,
|
262 |
+
"grad_norm": 0.05752944201231003,
|
263 |
+
"learning_rate": 1.7206703910614527e-05,
|
264 |
+
"loss": 0.3119,
|
265 |
+
"num_tokens": 353803596.0,
|
266 |
+
"step": 155
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 0.17882089969265158,
|
270 |
+
"grad_norm": 0.06477999687194824,
|
271 |
+
"learning_rate": 1.776536312849162e-05,
|
272 |
+
"loss": 0.3096,
|
273 |
+
"num_tokens": 365240245.0,
|
274 |
+
"step": 160
|
275 |
+
},
|
276 |
+
{
|
277 |
+
"epoch": 0.18440905280804695,
|
278 |
+
"grad_norm": 0.0565628707408905,
|
279 |
+
"learning_rate": 1.8324022346368716e-05,
|
280 |
+
"loss": 0.3111,
|
281 |
+
"num_tokens": 376640271.0,
|
282 |
+
"step": 165
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 0.1899972059234423,
|
286 |
+
"grad_norm": 0.06367555260658264,
|
287 |
+
"learning_rate": 1.888268156424581e-05,
|
288 |
+
"loss": 0.3066,
|
289 |
+
"num_tokens": 388026301.0,
|
290 |
+
"step": 170
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 0.19558535903883767,
|
294 |
+
"grad_norm": 0.06112772226333618,
|
295 |
+
"learning_rate": 1.9441340782122907e-05,
|
296 |
+
"loss": 0.3087,
|
297 |
+
"num_tokens": 399425545.0,
|
298 |
+
"step": 175
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.20117351215423301,
|
302 |
+
"grad_norm": 0.05626397952437401,
|
303 |
+
"learning_rate": 2e-05,
|
304 |
+
"loss": 0.3043,
|
305 |
+
"num_tokens": 410766539.0,
|
306 |
+
"step": 180
|
307 |
+
},
|
308 |
+
{
|
309 |
+
"epoch": 0.2067616652696284,
|
310 |
+
"grad_norm": 0.06474322825670242,
|
311 |
+
"learning_rate": 1.9937849596022375e-05,
|
312 |
+
"loss": 0.3048,
|
313 |
+
"num_tokens": 422199158.0,
|
314 |
+
"step": 185
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.21234981838502376,
|
318 |
+
"grad_norm": 0.05852804705500603,
|
319 |
+
"learning_rate": 1.9875699192044752e-05,
|
320 |
+
"loss": 0.3037,
|
321 |
+
"num_tokens": 433637045.0,
|
322 |
+
"step": 190
|
323 |
+
},
|
324 |
+
{
|
325 |
+
"epoch": 0.2179379715004191,
|
326 |
+
"grad_norm": 0.07262508571147919,
|
327 |
+
"learning_rate": 1.9813548788067125e-05,
|
328 |
+
"loss": 0.3028,
|
329 |
+
"num_tokens": 445060326.0,
|
330 |
+
"step": 195
|
331 |
+
},
|
332 |
+
{
|
333 |
+
"epoch": 0.22352612461581448,
|
334 |
+
"grad_norm": 0.061024755239486694,
|
335 |
+
"learning_rate": 1.97513983840895e-05,
|
336 |
+
"loss": 0.3011,
|
337 |
+
"num_tokens": 456564432.0,
|
338 |
+
"step": 200
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 0.22911427773120985,
|
342 |
+
"grad_norm": 0.05684756860136986,
|
343 |
+
"learning_rate": 1.9689247980111872e-05,
|
344 |
+
"loss": 0.3005,
|
345 |
+
"num_tokens": 467954846.0,
|
346 |
+
"step": 205
|
347 |
+
},
|
348 |
+
{
|
349 |
+
"epoch": 0.2347024308466052,
|
350 |
+
"grad_norm": 0.05736987292766571,
|
351 |
+
"learning_rate": 1.9627097576134246e-05,
|
352 |
+
"loss": 0.2993,
|
353 |
+
"num_tokens": 479322568.0,
|
354 |
+
"step": 210
|
355 |
+
},
|
356 |
+
{
|
357 |
+
"epoch": 0.24029058396200056,
|
358 |
+
"grad_norm": 0.056117478758096695,
|
359 |
+
"learning_rate": 1.9564947172156622e-05,
|
360 |
+
"loss": 0.3015,
|
361 |
+
"num_tokens": 490689992.0,
|
362 |
+
"step": 215
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 0.2458787370773959,
|
366 |
+
"grad_norm": 0.053805723786354065,
|
367 |
+
"learning_rate": 1.9502796768178996e-05,
|
368 |
+
"loss": 0.2969,
|
369 |
+
"num_tokens": 502112760.0,
|
370 |
+
"step": 220
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.2514668901927913,
|
374 |
+
"grad_norm": 0.054624415934085846,
|
375 |
+
"learning_rate": 1.944064636420137e-05,
|
376 |
+
"loss": 0.2962,
|
377 |
+
"num_tokens": 513492046.0,
|
378 |
+
"step": 225
|
379 |
+
},
|
380 |
+
{
|
381 |
+
"epoch": 0.2570550433081866,
|
382 |
+
"grad_norm": 0.05298687517642975,
|
383 |
+
"learning_rate": 1.9378495960223743e-05,
|
384 |
+
"loss": 0.2985,
|
385 |
+
"num_tokens": 524919249.0,
|
386 |
+
"step": 230
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 0.262643196423582,
|
390 |
+
"grad_norm": 0.059946753084659576,
|
391 |
+
"learning_rate": 1.9316345556246116e-05,
|
392 |
+
"loss": 0.2947,
|
393 |
+
"num_tokens": 536324070.0,
|
394 |
+
"step": 235
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 0.26823134953897737,
|
398 |
+
"grad_norm": 0.05546911805868149,
|
399 |
+
"learning_rate": 1.925419515226849e-05,
|
400 |
+
"loss": 0.2947,
|
401 |
+
"num_tokens": 547757412.0,
|
402 |
+
"step": 240
|
403 |
+
},
|
404 |
+
{
|
405 |
+
"epoch": 0.2738195026543727,
|
406 |
+
"grad_norm": 0.05153710022568703,
|
407 |
+
"learning_rate": 1.9192044748290866e-05,
|
408 |
+
"loss": 0.2945,
|
409 |
+
"num_tokens": 559148039.0,
|
410 |
+
"step": 245
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 0.2794076557697681,
|
414 |
+
"grad_norm": 0.05556200444698334,
|
415 |
+
"learning_rate": 1.912989434431324e-05,
|
416 |
+
"loss": 0.2929,
|
417 |
+
"num_tokens": 570614372.0,
|
418 |
+
"step": 250
|
419 |
+
},
|
420 |
+
{
|
421 |
+
"epoch": 0.28499580888516346,
|
422 |
+
"grad_norm": 0.05382775515317917,
|
423 |
+
"learning_rate": 1.9067743940335613e-05,
|
424 |
+
"loss": 0.2943,
|
425 |
+
"num_tokens": 581988955.0,
|
426 |
+
"step": 255
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 0.2905839620005588,
|
430 |
+
"grad_norm": 0.058685433119535446,
|
431 |
+
"learning_rate": 1.9005593536357987e-05,
|
432 |
+
"loss": 0.2936,
|
433 |
+
"num_tokens": 593431393.0,
|
434 |
+
"step": 260
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 0.2961721151159542,
|
438 |
+
"grad_norm": 0.05739787593483925,
|
439 |
+
"learning_rate": 1.894344313238036e-05,
|
440 |
+
"loss": 0.292,
|
441 |
+
"num_tokens": 604833789.0,
|
442 |
+
"step": 265
|
443 |
+
},
|
444 |
+
{
|
445 |
+
"epoch": 0.30176026823134955,
|
446 |
+
"grad_norm": 0.06372752040624619,
|
447 |
+
"learning_rate": 1.8881292728402737e-05,
|
448 |
+
"loss": 0.2904,
|
449 |
+
"num_tokens": 616243936.0,
|
450 |
+
"step": 270
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 0.3073484213467449,
|
454 |
+
"grad_norm": 0.07772672921419144,
|
455 |
+
"learning_rate": 1.881914232442511e-05,
|
456 |
+
"loss": 0.2897,
|
457 |
+
"num_tokens": 627657251.0,
|
458 |
+
"step": 275
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 0.31293657446214024,
|
462 |
+
"grad_norm": 0.05482286587357521,
|
463 |
+
"learning_rate": 1.8756991920447484e-05,
|
464 |
+
"loss": 0.2902,
|
465 |
+
"num_tokens": 639102143.0,
|
466 |
+
"step": 280
|
467 |
+
},
|
468 |
+
{
|
469 |
+
"epoch": 0.31852472757753564,
|
470 |
+
"grad_norm": 0.0831618458032608,
|
471 |
+
"learning_rate": 1.869484151646986e-05,
|
472 |
+
"loss": 0.2895,
|
473 |
+
"num_tokens": 650526469.0,
|
474 |
+
"step": 285
|
475 |
+
},
|
476 |
+
{
|
477 |
+
"epoch": 0.324112880692931,
|
478 |
+
"grad_norm": 0.08661651611328125,
|
479 |
+
"learning_rate": 1.863269111249223e-05,
|
480 |
+
"loss": 0.2874,
|
481 |
+
"num_tokens": 661978672.0,
|
482 |
+
"step": 290
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 0.3297010338083263,
|
486 |
+
"grad_norm": 0.06093963235616684,
|
487 |
+
"learning_rate": 1.8570540708514607e-05,
|
488 |
+
"loss": 0.2858,
|
489 |
+
"num_tokens": 673371819.0,
|
490 |
+
"step": 295
|
491 |
+
},
|
492 |
+
{
|
493 |
+
"epoch": 0.3352891869237217,
|
494 |
+
"grad_norm": 0.0825875923037529,
|
495 |
+
"learning_rate": 1.850839030453698e-05,
|
496 |
+
"loss": 0.2874,
|
497 |
+
"num_tokens": 684804343.0,
|
498 |
+
"step": 300
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.34087734003911707,
|
502 |
+
"grad_norm": 0.06878200173377991,
|
503 |
+
"learning_rate": 1.8446239900559354e-05,
|
504 |
+
"loss": 0.285,
|
505 |
+
"num_tokens": 696163350.0,
|
506 |
+
"step": 305
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 0.3464654931545124,
|
510 |
+
"grad_norm": 0.054976046085357666,
|
511 |
+
"learning_rate": 1.838408949658173e-05,
|
512 |
+
"loss": 0.2852,
|
513 |
+
"num_tokens": 707554947.0,
|
514 |
+
"step": 310
|
515 |
+
},
|
516 |
+
{
|
517 |
+
"epoch": 0.3520536462699078,
|
518 |
+
"grad_norm": 0.0718793049454689,
|
519 |
+
"learning_rate": 1.8321939092604105e-05,
|
520 |
+
"loss": 0.2854,
|
521 |
+
"num_tokens": 718984412.0,
|
522 |
+
"step": 315
|
523 |
+
},
|
524 |
+
{
|
525 |
+
"epoch": 0.35764179938530316,
|
526 |
+
"grad_norm": 0.06983356922864914,
|
527 |
+
"learning_rate": 1.8259788688626478e-05,
|
528 |
+
"loss": 0.2847,
|
529 |
+
"num_tokens": 730470288.0,
|
530 |
+
"step": 320
|
531 |
+
},
|
532 |
+
{
|
533 |
+
"epoch": 0.3632299525006985,
|
534 |
+
"grad_norm": 0.06837037205696106,
|
535 |
+
"learning_rate": 1.819763828464885e-05,
|
536 |
+
"loss": 0.2845,
|
537 |
+
"num_tokens": 741858439.0,
|
538 |
+
"step": 325
|
539 |
+
},
|
540 |
+
{
|
541 |
+
"epoch": 0.3688181056160939,
|
542 |
+
"grad_norm": 0.0682324767112732,
|
543 |
+
"learning_rate": 1.8135487880671225e-05,
|
544 |
+
"loss": 0.2812,
|
545 |
+
"num_tokens": 753183420.0,
|
546 |
+
"step": 330
|
547 |
+
},
|
548 |
+
{
|
549 |
+
"epoch": 0.37440625873148925,
|
550 |
+
"grad_norm": 0.06449826061725616,
|
551 |
+
"learning_rate": 1.8073337476693598e-05,
|
552 |
+
"loss": 0.2829,
|
553 |
+
"num_tokens": 764629623.0,
|
554 |
+
"step": 335
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.3799944118468846,
|
558 |
+
"grad_norm": 0.061453547328710556,
|
559 |
+
"learning_rate": 1.8011187072715975e-05,
|
560 |
+
"loss": 0.2817,
|
561 |
+
"num_tokens": 776072180.0,
|
562 |
+
"step": 340
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 0.38558256496227994,
|
566 |
+
"grad_norm": 0.06518165022134781,
|
567 |
+
"learning_rate": 1.794903666873835e-05,
|
568 |
+
"loss": 0.2827,
|
569 |
+
"num_tokens": 787454913.0,
|
570 |
+
"step": 345
|
571 |
+
},
|
572 |
+
{
|
573 |
+
"epoch": 0.39117071807767534,
|
574 |
+
"grad_norm": 0.07645566761493683,
|
575 |
+
"learning_rate": 1.7886886264760722e-05,
|
576 |
+
"loss": 0.2798,
|
577 |
+
"num_tokens": 798880783.0,
|
578 |
+
"step": 350
|
579 |
+
},
|
580 |
+
{
|
581 |
+
"epoch": 0.3967588711930707,
|
582 |
+
"grad_norm": 0.06994960457086563,
|
583 |
+
"learning_rate": 1.7824735860783095e-05,
|
584 |
+
"loss": 0.2822,
|
585 |
+
"num_tokens": 810324356.0,
|
586 |
+
"step": 355
|
587 |
+
},
|
588 |
+
{
|
589 |
+
"epoch": 0.40234702430846603,
|
590 |
+
"grad_norm": 0.06685755401849747,
|
591 |
+
"learning_rate": 1.776258545680547e-05,
|
592 |
+
"loss": 0.281,
|
593 |
+
"num_tokens": 821684136.0,
|
594 |
+
"step": 360
|
595 |
+
},
|
596 |
+
{
|
597 |
+
"epoch": 0.40793517742386143,
|
598 |
+
"grad_norm": 0.06723885238170624,
|
599 |
+
"learning_rate": 1.7700435052827846e-05,
|
600 |
+
"loss": 0.2791,
|
601 |
+
"num_tokens": 833138031.0,
|
602 |
+
"step": 365
|
603 |
+
},
|
604 |
+
{
|
605 |
+
"epoch": 0.4135233305392568,
|
606 |
+
"grad_norm": 0.06097578629851341,
|
607 |
+
"learning_rate": 1.763828464885022e-05,
|
608 |
+
"loss": 0.2791,
|
609 |
+
"num_tokens": 844568556.0,
|
610 |
+
"step": 370
|
611 |
+
},
|
612 |
+
{
|
613 |
+
"epoch": 0.4191114836546521,
|
614 |
+
"grad_norm": 0.06696998327970505,
|
615 |
+
"learning_rate": 1.7576134244872592e-05,
|
616 |
+
"loss": 0.2784,
|
617 |
+
"num_tokens": 855958988.0,
|
618 |
+
"step": 375
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 0.4246996367700475,
|
622 |
+
"grad_norm": 0.06988263130187988,
|
623 |
+
"learning_rate": 1.751398384089497e-05,
|
624 |
+
"loss": 0.2785,
|
625 |
+
"num_tokens": 867386144.0,
|
626 |
+
"step": 380
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.43028778988544286,
|
630 |
+
"grad_norm": 0.08155910670757294,
|
631 |
+
"learning_rate": 1.745183343691734e-05,
|
632 |
+
"loss": 0.2783,
|
633 |
+
"num_tokens": 878793737.0,
|
634 |
+
"step": 385
|
635 |
+
},
|
636 |
+
{
|
637 |
+
"epoch": 0.4358759430008382,
|
638 |
+
"grad_norm": 0.06370873749256134,
|
639 |
+
"learning_rate": 1.7389683032939716e-05,
|
640 |
+
"loss": 0.2773,
|
641 |
+
"num_tokens": 890247643.0,
|
642 |
+
"step": 390
|
643 |
+
},
|
644 |
+
{
|
645 |
+
"epoch": 0.4414640961162336,
|
646 |
+
"grad_norm": 0.05926324427127838,
|
647 |
+
"learning_rate": 1.732753262896209e-05,
|
648 |
+
"loss": 0.2785,
|
649 |
+
"num_tokens": 901673170.0,
|
650 |
+
"step": 395
|
651 |
+
},
|
652 |
+
{
|
653 |
+
"epoch": 0.44705224923162895,
|
654 |
+
"grad_norm": 0.06649507582187653,
|
655 |
+
"learning_rate": 1.7265382224984463e-05,
|
656 |
+
"loss": 0.275,
|
657 |
+
"num_tokens": 913137686.0,
|
658 |
+
"step": 400
|
659 |
+
},
|
660 |
+
{
|
661 |
+
"epoch": 0.4526404023470243,
|
662 |
+
"grad_norm": 0.06259816884994507,
|
663 |
+
"learning_rate": 1.720323182100684e-05,
|
664 |
+
"loss": 0.2767,
|
665 |
+
"num_tokens": 924486634.0,
|
666 |
+
"step": 405
|
667 |
+
},
|
668 |
+
{
|
669 |
+
"epoch": 0.4582285554624197,
|
670 |
+
"grad_norm": 0.06120780482888222,
|
671 |
+
"learning_rate": 1.7141081417029213e-05,
|
672 |
+
"loss": 0.2762,
|
673 |
+
"num_tokens": 935847065.0,
|
674 |
+
"step": 410
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 0.46381670857781504,
|
678 |
+
"grad_norm": 0.06271655857563019,
|
679 |
+
"learning_rate": 1.7078931013051587e-05,
|
680 |
+
"loss": 0.2766,
|
681 |
+
"num_tokens": 947288653.0,
|
682 |
+
"step": 415
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.4694048616932104,
|
686 |
+
"grad_norm": 0.06720273941755295,
|
687 |
+
"learning_rate": 1.701678060907396e-05,
|
688 |
+
"loss": 0.2774,
|
689 |
+
"num_tokens": 958753391.0,
|
690 |
+
"step": 420
|
691 |
+
},
|
692 |
+
{
|
693 |
+
"epoch": 0.47499301480860573,
|
694 |
+
"grad_norm": 0.07040219753980637,
|
695 |
+
"learning_rate": 1.6954630205096334e-05,
|
696 |
+
"loss": 0.2745,
|
697 |
+
"num_tokens": 970211625.0,
|
698 |
+
"step": 425
|
699 |
+
},
|
700 |
+
{
|
701 |
+
"epoch": 0.48058116792400113,
|
702 |
+
"grad_norm": 0.06442518532276154,
|
703 |
+
"learning_rate": 1.6892479801118707e-05,
|
704 |
+
"loss": 0.2745,
|
705 |
+
"num_tokens": 981563186.0,
|
706 |
+
"step": 430
|
707 |
+
},
|
708 |
+
{
|
709 |
+
"epoch": 0.4861693210393965,
|
710 |
+
"grad_norm": 0.07135903835296631,
|
711 |
+
"learning_rate": 1.6830329397141084e-05,
|
712 |
+
"loss": 0.2746,
|
713 |
+
"num_tokens": 993028060.0,
|
714 |
+
"step": 435
|
715 |
+
},
|
716 |
+
{
|
717 |
+
"epoch": 0.4917574741547918,
|
718 |
+
"grad_norm": 0.05886778235435486,
|
719 |
+
"learning_rate": 1.6768178993163457e-05,
|
720 |
+
"loss": 0.2742,
|
721 |
+
"num_tokens": 1004435363.0,
|
722 |
+
"step": 440
|
723 |
+
},
|
724 |
+
{
|
725 |
+
"epoch": 0.4973456272701872,
|
726 |
+
"grad_norm": 0.056988589465618134,
|
727 |
+
"learning_rate": 1.670602858918583e-05,
|
728 |
+
"loss": 0.2737,
|
729 |
+
"num_tokens": 1015874037.0,
|
730 |
+
"step": 445
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 0.5029337803855826,
|
734 |
+
"grad_norm": 0.06291932612657547,
|
735 |
+
"learning_rate": 1.6643878185208204e-05,
|
736 |
+
"loss": 0.2725,
|
737 |
+
"num_tokens": 1027283401.0,
|
738 |
+
"step": 450
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.508521933500978,
|
742 |
+
"grad_norm": 0.07145503163337708,
|
743 |
+
"learning_rate": 1.6581727781230577e-05,
|
744 |
+
"loss": 0.2725,
|
745 |
+
"num_tokens": 1038629883.0,
|
746 |
+
"step": 455
|
747 |
+
},
|
748 |
+
{
|
749 |
+
"epoch": 0.5141100866163733,
|
750 |
+
"grad_norm": 0.05856870859861374,
|
751 |
+
"learning_rate": 1.6519577377252954e-05,
|
752 |
+
"loss": 0.2726,
|
753 |
+
"num_tokens": 1050019923.0,
|
754 |
+
"step": 460
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.5196982397317687,
|
758 |
+
"grad_norm": 0.07050315290689468,
|
759 |
+
"learning_rate": 1.6457426973275328e-05,
|
760 |
+
"loss": 0.2706,
|
761 |
+
"num_tokens": 1061416078.0,
|
762 |
+
"step": 465
|
763 |
+
},
|
764 |
+
{
|
765 |
+
"epoch": 0.525286392847164,
|
766 |
+
"grad_norm": 0.06802777945995331,
|
767 |
+
"learning_rate": 1.63952765692977e-05,
|
768 |
+
"loss": 0.2702,
|
769 |
+
"num_tokens": 1072788410.0,
|
770 |
+
"step": 470
|
771 |
+
},
|
772 |
+
{
|
773 |
+
"epoch": 0.5308745459625593,
|
774 |
+
"grad_norm": 0.06870804727077484,
|
775 |
+
"learning_rate": 1.6333126165320078e-05,
|
776 |
+
"loss": 0.2719,
|
777 |
+
"num_tokens": 1084176813.0,
|
778 |
+
"step": 475
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 0.5364626990779547,
|
782 |
+
"grad_norm": 0.05907612666487694,
|
783 |
+
"learning_rate": 1.6270975761342448e-05,
|
784 |
+
"loss": 0.2715,
|
785 |
+
"num_tokens": 1095631809.0,
|
786 |
+
"step": 480
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 0.5420508521933501,
|
790 |
+
"grad_norm": 0.05871352180838585,
|
791 |
+
"learning_rate": 1.6208825357364825e-05,
|
792 |
+
"loss": 0.271,
|
793 |
+
"num_tokens": 1107023659.0,
|
794 |
+
"step": 485
|
795 |
+
},
|
796 |
+
{
|
797 |
+
"epoch": 0.5476390053087454,
|
798 |
+
"grad_norm": 0.07040645182132721,
|
799 |
+
"learning_rate": 1.6146674953387198e-05,
|
800 |
+
"loss": 0.2692,
|
801 |
+
"num_tokens": 1118483440.0,
|
802 |
+
"step": 490
|
803 |
+
},
|
804 |
+
{
|
805 |
+
"epoch": 0.5532271584241408,
|
806 |
+
"grad_norm": 0.09836603701114655,
|
807 |
+
"learning_rate": 1.608452454940957e-05,
|
808 |
+
"loss": 0.2696,
|
809 |
+
"num_tokens": 1129990125.0,
|
810 |
+
"step": 495
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 0.5588153115395362,
|
814 |
+
"grad_norm": 0.060847748070955276,
|
815 |
+
"learning_rate": 1.602237414543195e-05,
|
816 |
+
"loss": 0.2703,
|
817 |
+
"num_tokens": 1141412681.0,
|
818 |
+
"step": 500
|
819 |
+
},
|
820 |
+
{
|
821 |
+
"epoch": 0.5644034646549315,
|
822 |
+
"grad_norm": 0.0608036145567894,
|
823 |
+
"learning_rate": 1.5960223741454322e-05,
|
824 |
+
"loss": 0.269,
|
825 |
+
"num_tokens": 1152853495.0,
|
826 |
+
"step": 505
|
827 |
+
},
|
828 |
+
{
|
829 |
+
"epoch": 0.5699916177703269,
|
830 |
+
"grad_norm": 0.0629318356513977,
|
831 |
+
"learning_rate": 1.5898073337476695e-05,
|
832 |
+
"loss": 0.2696,
|
833 |
+
"num_tokens": 1164243394.0,
|
834 |
+
"step": 510
|
835 |
+
},
|
836 |
+
{
|
837 |
+
"epoch": 0.5755797708857223,
|
838 |
+
"grad_norm": 0.0749465599656105,
|
839 |
+
"learning_rate": 1.583592293349907e-05,
|
840 |
+
"loss": 0.2671,
|
841 |
+
"num_tokens": 1175612357.0,
|
842 |
+
"step": 515
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 0.5811679240011176,
|
846 |
+
"grad_norm": 0.09776467829942703,
|
847 |
+
"learning_rate": 1.5773772529521442e-05,
|
848 |
+
"loss": 0.2669,
|
849 |
+
"num_tokens": 1187046869.0,
|
850 |
+
"step": 520
|
851 |
+
},
|
852 |
+
{
|
853 |
+
"epoch": 0.586756077116513,
|
854 |
+
"grad_norm": 0.12097107619047165,
|
855 |
+
"learning_rate": 1.5711622125543816e-05,
|
856 |
+
"loss": 0.2681,
|
857 |
+
"num_tokens": 1198478715.0,
|
858 |
+
"step": 525
|
859 |
+
},
|
860 |
+
{
|
861 |
+
"epoch": 0.5923442302319084,
|
862 |
+
"grad_norm": 0.08982737362384796,
|
863 |
+
"learning_rate": 1.5649471721566192e-05,
|
864 |
+
"loss": 0.2676,
|
865 |
+
"num_tokens": 1209894292.0,
|
866 |
+
"step": 530
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 0.5979323833473037,
|
870 |
+
"grad_norm": 0.05943426489830017,
|
871 |
+
"learning_rate": 1.5587321317588566e-05,
|
872 |
+
"loss": 0.2681,
|
873 |
+
"num_tokens": 1221288210.0,
|
874 |
+
"step": 535
|
875 |
+
},
|
876 |
+
{
|
877 |
+
"epoch": 0.6035205364626991,
|
878 |
+
"grad_norm": 0.05909049138426781,
|
879 |
+
"learning_rate": 1.552517091361094e-05,
|
880 |
+
"loss": 0.2666,
|
881 |
+
"num_tokens": 1232662337.0,
|
882 |
+
"step": 540
|
883 |
+
},
|
884 |
+
{
|
885 |
+
"epoch": 0.6091086895780944,
|
886 |
+
"grad_norm": 0.06840803474187851,
|
887 |
+
"learning_rate": 1.5463020509633313e-05,
|
888 |
+
"loss": 0.2656,
|
889 |
+
"num_tokens": 1244049474.0,
|
890 |
+
"step": 545
|
891 |
+
},
|
892 |
+
{
|
893 |
+
"epoch": 0.6146968426934898,
|
894 |
+
"grad_norm": 0.0623379684984684,
|
895 |
+
"learning_rate": 1.5400870105655686e-05,
|
896 |
+
"loss": 0.2648,
|
897 |
+
"num_tokens": 1255501882.0,
|
898 |
+
"step": 550
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 0.6202849958088852,
|
902 |
+
"grad_norm": 0.05863022804260254,
|
903 |
+
"learning_rate": 1.5338719701678063e-05,
|
904 |
+
"loss": 0.2645,
|
905 |
+
"num_tokens": 1266929882.0,
|
906 |
+
"step": 555
|
907 |
+
},
|
908 |
+
{
|
909 |
+
"epoch": 0.6258731489242805,
|
910 |
+
"grad_norm": 0.0742977187037468,
|
911 |
+
"learning_rate": 1.5276569297700436e-05,
|
912 |
+
"loss": 0.2637,
|
913 |
+
"num_tokens": 1278348389.0,
|
914 |
+
"step": 560
|
915 |
+
},
|
916 |
+
{
|
917 |
+
"epoch": 0.6314613020396759,
|
918 |
+
"grad_norm": 0.06603442877531052,
|
919 |
+
"learning_rate": 1.5214418893722812e-05,
|
920 |
+
"loss": 0.2642,
|
921 |
+
"num_tokens": 1289764706.0,
|
922 |
+
"step": 565
|
923 |
+
},
|
924 |
+
{
|
925 |
+
"epoch": 0.6370494551550713,
|
926 |
+
"grad_norm": 0.06260518729686737,
|
927 |
+
"learning_rate": 1.5152268489745185e-05,
|
928 |
+
"loss": 0.2635,
|
929 |
+
"num_tokens": 1301188033.0,
|
930 |
+
"step": 570
|
931 |
+
},
|
932 |
+
{
|
933 |
+
"epoch": 0.6426376082704666,
|
934 |
+
"grad_norm": 0.06276093423366547,
|
935 |
+
"learning_rate": 1.5090118085767558e-05,
|
936 |
+
"loss": 0.2626,
|
937 |
+
"num_tokens": 1312563993.0,
|
938 |
+
"step": 575
|
939 |
+
},
|
940 |
+
{
|
941 |
+
"epoch": 0.648225761385862,
|
942 |
+
"grad_norm": 0.05987481400370598,
|
943 |
+
"learning_rate": 1.5027967681789932e-05,
|
944 |
+
"loss": 0.2642,
|
945 |
+
"num_tokens": 1323998912.0,
|
946 |
+
"step": 580
|
947 |
+
},
|
948 |
+
{
|
949 |
+
"epoch": 0.6538139145012574,
|
950 |
+
"grad_norm": 0.07826969027519226,
|
951 |
+
"learning_rate": 1.4965817277812307e-05,
|
952 |
+
"loss": 0.2637,
|
953 |
+
"num_tokens": 1335437946.0,
|
954 |
+
"step": 585
|
955 |
+
},
|
956 |
+
{
|
957 |
+
"epoch": 0.6594020676166527,
|
958 |
+
"grad_norm": 0.07437111437320709,
|
959 |
+
"learning_rate": 1.4903666873834682e-05,
|
960 |
+
"loss": 0.2625,
|
961 |
+
"num_tokens": 1346881745.0,
|
962 |
+
"step": 590
|
963 |
+
},
|
964 |
+
{
|
965 |
+
"epoch": 0.664990220732048,
|
966 |
+
"grad_norm": 0.09087026864290237,
|
967 |
+
"learning_rate": 1.4841516469857056e-05,
|
968 |
+
"loss": 0.2617,
|
969 |
+
"num_tokens": 1358272528.0,
|
970 |
+
"step": 595
|
971 |
+
},
|
972 |
+
{
|
973 |
+
"epoch": 0.6705783738474435,
|
974 |
+
"grad_norm": 0.09543482959270477,
|
975 |
+
"learning_rate": 1.477936606587943e-05,
|
976 |
+
"loss": 0.2628,
|
977 |
+
"num_tokens": 1369658784.0,
|
978 |
+
"step": 600
|
979 |
+
},
|
980 |
+
{
|
981 |
+
"epoch": 0.6761665269628387,
|
982 |
+
"grad_norm": 0.07354892790317535,
|
983 |
+
"learning_rate": 1.4717215661901802e-05,
|
984 |
+
"loss": 0.263,
|
985 |
+
"num_tokens": 1381096596.0,
|
986 |
+
"step": 605
|
987 |
+
},
|
988 |
+
{
|
989 |
+
"epoch": 0.6817546800782341,
|
990 |
+
"grad_norm": 0.08725232630968094,
|
991 |
+
"learning_rate": 1.4655065257924177e-05,
|
992 |
+
"loss": 0.2601,
|
993 |
+
"num_tokens": 1392519601.0,
|
994 |
+
"step": 610
|
995 |
+
},
|
996 |
+
{
|
997 |
+
"epoch": 0.6873428331936295,
|
998 |
+
"grad_norm": 0.06985431909561157,
|
999 |
+
"learning_rate": 1.4592914853946551e-05,
|
1000 |
+
"loss": 0.2608,
|
1001 |
+
"num_tokens": 1403941561.0,
|
1002 |
+
"step": 615
|
1003 |
+
},
|
1004 |
+
{
|
1005 |
+
"epoch": 0.6929309863090248,
|
1006 |
+
"grad_norm": 0.0729910135269165,
|
1007 |
+
"learning_rate": 1.4530764449968926e-05,
|
1008 |
+
"loss": 0.2595,
|
1009 |
+
"num_tokens": 1415354409.0,
|
1010 |
+
"step": 620
|
1011 |
+
},
|
1012 |
+
{
|
1013 |
+
"epoch": 0.6985191394244202,
|
1014 |
+
"grad_norm": 0.07240404933691025,
|
1015 |
+
"learning_rate": 1.4468614045991301e-05,
|
1016 |
+
"loss": 0.2605,
|
1017 |
+
"num_tokens": 1426725558.0,
|
1018 |
+
"step": 625
|
1019 |
+
},
|
1020 |
+
{
|
1021 |
+
"epoch": 0.7041072925398156,
|
1022 |
+
"grad_norm": 0.06184804067015648,
|
1023 |
+
"learning_rate": 1.4406463642013675e-05,
|
1024 |
+
"loss": 0.2611,
|
1025 |
+
"num_tokens": 1438189513.0,
|
1026 |
+
"step": 630
|
1027 |
+
},
|
1028 |
+
{
|
1029 |
+
"epoch": 0.7096954456552109,
|
1030 |
+
"grad_norm": 0.08360790461301804,
|
1031 |
+
"learning_rate": 1.434431323803605e-05,
|
1032 |
+
"loss": 0.2607,
|
1033 |
+
"num_tokens": 1449608422.0,
|
1034 |
+
"step": 635
|
1035 |
+
},
|
1036 |
+
{
|
1037 |
+
"epoch": 0.7152835987706063,
|
1038 |
+
"grad_norm": 0.13933835923671722,
|
1039 |
+
"learning_rate": 1.4282162834058421e-05,
|
1040 |
+
"loss": 0.2585,
|
1041 |
+
"num_tokens": 1461023964.0,
|
1042 |
+
"step": 640
|
1043 |
+
},
|
1044 |
+
{
|
1045 |
+
"epoch": 0.7208717518860017,
|
1046 |
+
"grad_norm": 0.07683195173740387,
|
1047 |
+
"learning_rate": 1.4220012430080797e-05,
|
1048 |
+
"loss": 0.2591,
|
1049 |
+
"num_tokens": 1472442326.0,
|
1050 |
+
"step": 645
|
1051 |
+
},
|
1052 |
+
{
|
1053 |
+
"epoch": 0.726459905001397,
|
1054 |
+
"grad_norm": 0.08932902663946152,
|
1055 |
+
"learning_rate": 1.415786202610317e-05,
|
1056 |
+
"loss": 0.2584,
|
1057 |
+
"num_tokens": 1483853206.0,
|
1058 |
+
"step": 650
|
1059 |
+
},
|
1060 |
+
{
|
1061 |
+
"epoch": 0.7320480581167924,
|
1062 |
+
"grad_norm": 0.07598485797643661,
|
1063 |
+
"learning_rate": 1.4095711622125545e-05,
|
1064 |
+
"loss": 0.2586,
|
1065 |
+
"num_tokens": 1495295410.0,
|
1066 |
+
"step": 655
|
1067 |
+
},
|
1068 |
+
{
|
1069 |
+
"epoch": 0.7376362112321878,
|
1070 |
+
"grad_norm": 0.0836004987359047,
|
1071 |
+
"learning_rate": 1.403356121814792e-05,
|
1072 |
+
"loss": 0.2589,
|
1073 |
+
"num_tokens": 1506682604.0,
|
1074 |
+
"step": 660
|
1075 |
+
},
|
1076 |
+
{
|
1077 |
+
"epoch": 0.7432243643475831,
|
1078 |
+
"grad_norm": 0.10632190108299255,
|
1079 |
+
"learning_rate": 1.3971410814170294e-05,
|
1080 |
+
"loss": 0.2591,
|
1081 |
+
"num_tokens": 1518151316.0,
|
1082 |
+
"step": 665
|
1083 |
+
},
|
1084 |
+
{
|
1085 |
+
"epoch": 0.7488125174629785,
|
1086 |
+
"grad_norm": 0.07187483459711075,
|
1087 |
+
"learning_rate": 1.3909260410192667e-05,
|
1088 |
+
"loss": 0.2586,
|
1089 |
+
"num_tokens": 1529536050.0,
|
1090 |
+
"step": 670
|
1091 |
+
},
|
1092 |
+
{
|
1093 |
+
"epoch": 0.7544006705783739,
|
1094 |
+
"grad_norm": 0.06604966521263123,
|
1095 |
+
"learning_rate": 1.384711000621504e-05,
|
1096 |
+
"loss": 0.2572,
|
1097 |
+
"num_tokens": 1540906374.0,
|
1098 |
+
"step": 675
|
1099 |
+
},
|
1100 |
+
{
|
1101 |
+
"epoch": 0.7599888236937692,
|
1102 |
+
"grad_norm": 0.059948720037937164,
|
1103 |
+
"learning_rate": 1.3784959602237416e-05,
|
1104 |
+
"loss": 0.2564,
|
1105 |
+
"num_tokens": 1552367588.0,
|
1106 |
+
"step": 680
|
1107 |
+
},
|
1108 |
+
{
|
1109 |
+
"epoch": 0.7655769768091646,
|
1110 |
+
"grad_norm": 0.10807392001152039,
|
1111 |
+
"learning_rate": 1.372280919825979e-05,
|
1112 |
+
"loss": 0.2572,
|
1113 |
+
"num_tokens": 1563798845.0,
|
1114 |
+
"step": 685
|
1115 |
+
},
|
1116 |
+
{
|
1117 |
+
"epoch": 0.7711651299245599,
|
1118 |
+
"grad_norm": 0.07425787299871445,
|
1119 |
+
"learning_rate": 1.3660658794282164e-05,
|
1120 |
+
"loss": 0.256,
|
1121 |
+
"num_tokens": 1575159561.0,
|
1122 |
+
"step": 690
|
1123 |
+
},
|
1124 |
+
{
|
1125 |
+
"epoch": 0.7767532830399553,
|
1126 |
+
"grad_norm": 0.10806109756231308,
|
1127 |
+
"learning_rate": 1.359850839030454e-05,
|
1128 |
+
"loss": 0.2544,
|
1129 |
+
"num_tokens": 1586595617.0,
|
1130 |
+
"step": 695
|
1131 |
+
},
|
1132 |
+
{
|
1133 |
+
"epoch": 0.7823414361553507,
|
1134 |
+
"grad_norm": 0.08122843503952026,
|
1135 |
+
"learning_rate": 1.3536357986326911e-05,
|
1136 |
+
"loss": 0.2558,
|
1137 |
+
"num_tokens": 1598019511.0,
|
1138 |
+
"step": 700
|
1139 |
+
},
|
1140 |
+
{
|
1141 |
+
"epoch": 0.787929589270746,
|
1142 |
+
"grad_norm": 0.08998622000217438,
|
1143 |
+
"learning_rate": 1.3474207582349286e-05,
|
1144 |
+
"loss": 0.2551,
|
1145 |
+
"num_tokens": 1609449516.0,
|
1146 |
+
"step": 705
|
1147 |
+
},
|
1148 |
+
{
|
1149 |
+
"epoch": 0.7935177423861414,
|
1150 |
+
"grad_norm": 0.06237884238362312,
|
1151 |
+
"learning_rate": 1.341205717837166e-05,
|
1152 |
+
"loss": 0.2558,
|
1153 |
+
"num_tokens": 1620942485.0,
|
1154 |
+
"step": 710
|
1155 |
+
},
|
1156 |
+
{
|
1157 |
+
"epoch": 0.7991058955015368,
|
1158 |
+
"grad_norm": 0.08027390390634537,
|
1159 |
+
"learning_rate": 1.3349906774394035e-05,
|
1160 |
+
"loss": 0.2551,
|
1161 |
+
"num_tokens": 1632316514.0,
|
1162 |
+
"step": 715
|
1163 |
+
},
|
1164 |
+
{
|
1165 |
+
"epoch": 0.8046940486169321,
|
1166 |
+
"grad_norm": 0.06748659908771515,
|
1167 |
+
"learning_rate": 1.328775637041641e-05,
|
1168 |
+
"loss": 0.2551,
|
1169 |
+
"num_tokens": 1643728845.0,
|
1170 |
+
"step": 720
|
1171 |
+
},
|
1172 |
+
{
|
1173 |
+
"epoch": 0.8102822017323275,
|
1174 |
+
"grad_norm": 0.06500785052776337,
|
1175 |
+
"learning_rate": 1.3225605966438783e-05,
|
1176 |
+
"loss": 0.2552,
|
1177 |
+
"num_tokens": 1655109711.0,
|
1178 |
+
"step": 725
|
1179 |
+
},
|
1180 |
+
{
|
1181 |
+
"epoch": 0.8158703548477229,
|
1182 |
+
"grad_norm": 0.07137981057167053,
|
1183 |
+
"learning_rate": 1.3163455562461157e-05,
|
1184 |
+
"loss": 0.2527,
|
1185 |
+
"num_tokens": 1666511424.0,
|
1186 |
+
"step": 730
|
1187 |
+
},
|
1188 |
+
{
|
1189 |
+
"epoch": 0.8214585079631181,
|
1190 |
+
"grad_norm": 0.07075709849596024,
|
1191 |
+
"learning_rate": 1.310130515848353e-05,
|
1192 |
+
"loss": 0.2524,
|
1193 |
+
"num_tokens": 1677945037.0,
|
1194 |
+
"step": 735
|
1195 |
+
},
|
1196 |
+
{
|
1197 |
+
"epoch": 0.8270466610785135,
|
1198 |
+
"grad_norm": 0.07283911108970642,
|
1199 |
+
"learning_rate": 1.3039154754505905e-05,
|
1200 |
+
"loss": 0.2531,
|
1201 |
+
"num_tokens": 1689328065.0,
|
1202 |
+
"step": 740
|
1203 |
+
},
|
1204 |
+
{
|
1205 |
+
"epoch": 0.832634814193909,
|
1206 |
+
"grad_norm": 0.07047147303819656,
|
1207 |
+
"learning_rate": 1.2977004350528279e-05,
|
1208 |
+
"loss": 0.2526,
|
1209 |
+
"num_tokens": 1700701797.0,
|
1210 |
+
"step": 745
|
1211 |
+
},
|
1212 |
+
{
|
1213 |
+
"epoch": 0.8382229673093042,
|
1214 |
+
"grad_norm": 0.0700286328792572,
|
1215 |
+
"learning_rate": 1.2914853946550654e-05,
|
1216 |
+
"loss": 0.2529,
|
1217 |
+
"num_tokens": 1712094439.0,
|
1218 |
+
"step": 750
|
1219 |
+
},
|
1220 |
+
{
|
1221 |
+
"epoch": 0.8438111204246996,
|
1222 |
+
"grad_norm": 0.07566844671964645,
|
1223 |
+
"learning_rate": 1.2852703542573029e-05,
|
1224 |
+
"loss": 0.2525,
|
1225 |
+
"num_tokens": 1723506482.0,
|
1226 |
+
"step": 755
|
1227 |
+
},
|
1228 |
+
{
|
1229 |
+
"epoch": 0.849399273540095,
|
1230 |
+
"grad_norm": 0.0756835788488388,
|
1231 |
+
"learning_rate": 1.2790553138595402e-05,
|
1232 |
+
"loss": 0.2515,
|
1233 |
+
"num_tokens": 1734948173.0,
|
1234 |
+
"step": 760
|
1235 |
+
},
|
1236 |
+
{
|
1237 |
+
"epoch": 0.8549874266554903,
|
1238 |
+
"grad_norm": 0.10192592442035675,
|
1239 |
+
"learning_rate": 1.2728402734617776e-05,
|
1240 |
+
"loss": 0.2527,
|
1241 |
+
"num_tokens": 1746339575.0,
|
1242 |
+
"step": 765
|
1243 |
+
},
|
1244 |
+
{
|
1245 |
+
"epoch": 0.8605755797708857,
|
1246 |
+
"grad_norm": 0.06903030723333359,
|
1247 |
+
"learning_rate": 1.266625233064015e-05,
|
1248 |
+
"loss": 0.2511,
|
1249 |
+
"num_tokens": 1757726090.0,
|
1250 |
+
"step": 770
|
1251 |
+
},
|
1252 |
+
{
|
1253 |
+
"epoch": 0.8661637328862811,
|
1254 |
+
"grad_norm": 0.07352637499570847,
|
1255 |
+
"learning_rate": 1.2604101926662524e-05,
|
1256 |
+
"loss": 0.2505,
|
1257 |
+
"num_tokens": 1769185846.0,
|
1258 |
+
"step": 775
|
1259 |
+
},
|
1260 |
+
{
|
1261 |
+
"epoch": 0.8717518860016764,
|
1262 |
+
"grad_norm": 0.0697358250617981,
|
1263 |
+
"learning_rate": 1.25419515226849e-05,
|
1264 |
+
"loss": 0.251,
|
1265 |
+
"num_tokens": 1780540282.0,
|
1266 |
+
"step": 780
|
1267 |
+
},
|
1268 |
+
{
|
1269 |
+
"epoch": 0.8773400391170718,
|
1270 |
+
"grad_norm": 0.07313339412212372,
|
1271 |
+
"learning_rate": 1.2479801118707273e-05,
|
1272 |
+
"loss": 0.251,
|
1273 |
+
"num_tokens": 1792000179.0,
|
1274 |
+
"step": 785
|
1275 |
+
},
|
1276 |
+
{
|
1277 |
+
"epoch": 0.8829281922324672,
|
1278 |
+
"grad_norm": 0.07740647345781326,
|
1279 |
+
"learning_rate": 1.2417650714729648e-05,
|
1280 |
+
"loss": 0.2498,
|
1281 |
+
"num_tokens": 1803413179.0,
|
1282 |
+
"step": 790
|
1283 |
+
},
|
1284 |
+
{
|
1285 |
+
"epoch": 0.8885163453478625,
|
1286 |
+
"grad_norm": 0.06439563632011414,
|
1287 |
+
"learning_rate": 1.235550031075202e-05,
|
1288 |
+
"loss": 0.2495,
|
1289 |
+
"num_tokens": 1814874417.0,
|
1290 |
+
"step": 795
|
1291 |
+
},
|
1292 |
+
{
|
1293 |
+
"epoch": 0.8941044984632579,
|
1294 |
+
"grad_norm": 0.07976026087999344,
|
1295 |
+
"learning_rate": 1.2293349906774395e-05,
|
1296 |
+
"loss": 0.2492,
|
1297 |
+
"num_tokens": 1826321606.0,
|
1298 |
+
"step": 800
|
1299 |
+
},
|
1300 |
+
{
|
1301 |
+
"epoch": 0.8996926515786533,
|
1302 |
+
"grad_norm": 0.07340570539236069,
|
1303 |
+
"learning_rate": 1.2231199502796768e-05,
|
1304 |
+
"loss": 0.2491,
|
1305 |
+
"num_tokens": 1837738496.0,
|
1306 |
+
"step": 805
|
1307 |
+
},
|
1308 |
+
{
|
1309 |
+
"epoch": 0.9052808046940486,
|
1310 |
+
"grad_norm": 0.074010469019413,
|
1311 |
+
"learning_rate": 1.2169049098819143e-05,
|
1312 |
+
"loss": 0.2509,
|
1313 |
+
"num_tokens": 1849163294.0,
|
1314 |
+
"step": 810
|
1315 |
+
},
|
1316 |
+
{
|
1317 |
+
"epoch": 0.910868957809444,
|
1318 |
+
"grad_norm": 0.06877516210079193,
|
1319 |
+
"learning_rate": 1.2106898694841519e-05,
|
1320 |
+
"loss": 0.2491,
|
1321 |
+
"num_tokens": 1860581937.0,
|
1322 |
+
"step": 815
|
1323 |
+
},
|
1324 |
+
{
|
1325 |
+
"epoch": 0.9164571109248394,
|
1326 |
+
"grad_norm": 0.11264199018478394,
|
1327 |
+
"learning_rate": 1.2044748290863892e-05,
|
1328 |
+
"loss": 0.249,
|
1329 |
+
"num_tokens": 1872023057.0,
|
1330 |
+
"step": 820
|
1331 |
+
},
|
1332 |
+
{
|
1333 |
+
"epoch": 0.9220452640402347,
|
1334 |
+
"grad_norm": 0.07071848213672638,
|
1335 |
+
"learning_rate": 1.1982597886886265e-05,
|
1336 |
+
"loss": 0.2491,
|
1337 |
+
"num_tokens": 1883430495.0,
|
1338 |
+
"step": 825
|
1339 |
+
},
|
1340 |
+
{
|
1341 |
+
"epoch": 0.9276334171556301,
|
1342 |
+
"grad_norm": 0.06249503418803215,
|
1343 |
+
"learning_rate": 1.1920447482908639e-05,
|
1344 |
+
"loss": 0.2479,
|
1345 |
+
"num_tokens": 1894830982.0,
|
1346 |
+
"step": 830
|
1347 |
+
},
|
1348 |
+
{
|
1349 |
+
"epoch": 0.9332215702710255,
|
1350 |
+
"grad_norm": 0.09320665150880814,
|
1351 |
+
"learning_rate": 1.1858297078931014e-05,
|
1352 |
+
"loss": 0.249,
|
1353 |
+
"num_tokens": 1906265064.0,
|
1354 |
+
"step": 835
|
1355 |
+
},
|
1356 |
+
{
|
1357 |
+
"epoch": 0.9388097233864208,
|
1358 |
+
"grad_norm": 0.07534969598054886,
|
1359 |
+
"learning_rate": 1.1796146674953387e-05,
|
1360 |
+
"loss": 0.2457,
|
1361 |
+
"num_tokens": 1917622370.0,
|
1362 |
+
"step": 840
|
1363 |
+
},
|
1364 |
+
{
|
1365 |
+
"epoch": 0.9443978765018162,
|
1366 |
+
"grad_norm": 0.06999360024929047,
|
1367 |
+
"learning_rate": 1.1733996270975763e-05,
|
1368 |
+
"loss": 0.2472,
|
1369 |
+
"num_tokens": 1929083402.0,
|
1370 |
+
"step": 845
|
1371 |
+
},
|
1372 |
+
{
|
1373 |
+
"epoch": 0.9499860296172115,
|
1374 |
+
"grad_norm": 0.0674748569726944,
|
1375 |
+
"learning_rate": 1.1671845866998138e-05,
|
1376 |
+
"loss": 0.247,
|
1377 |
+
"num_tokens": 1940493455.0,
|
1378 |
+
"step": 850
|
1379 |
+
},
|
1380 |
+
{
|
1381 |
+
"epoch": 0.9555741827326069,
|
1382 |
+
"grad_norm": 0.07490040361881256,
|
1383 |
+
"learning_rate": 1.1609695463020511e-05,
|
1384 |
+
"loss": 0.2472,
|
1385 |
+
"num_tokens": 1951881506.0,
|
1386 |
+
"step": 855
|
1387 |
+
},
|
1388 |
+
{
|
1389 |
+
"epoch": 0.9611623358480023,
|
1390 |
+
"grad_norm": 0.06616108119487762,
|
1391 |
+
"learning_rate": 1.1547545059042884e-05,
|
1392 |
+
"loss": 0.246,
|
1393 |
+
"num_tokens": 1963273217.0,
|
1394 |
+
"step": 860
|
1395 |
+
},
|
1396 |
+
{
|
1397 |
+
"epoch": 0.9667504889633975,
|
1398 |
+
"grad_norm": 0.06972012668848038,
|
1399 |
+
"learning_rate": 1.1485394655065258e-05,
|
1400 |
+
"loss": 0.2465,
|
1401 |
+
"num_tokens": 1974706747.0,
|
1402 |
+
"step": 865
|
1403 |
+
},
|
1404 |
+
{
|
1405 |
+
"epoch": 0.972338642078793,
|
1406 |
+
"grad_norm": 0.07631607353687286,
|
1407 |
+
"learning_rate": 1.1423244251087633e-05,
|
1408 |
+
"loss": 0.2449,
|
1409 |
+
"num_tokens": 1986149340.0,
|
1410 |
+
"step": 870
|
1411 |
+
},
|
1412 |
+
{
|
1413 |
+
"epoch": 0.9779267951941883,
|
1414 |
+
"grad_norm": 0.06611183285713196,
|
1415 |
+
"learning_rate": 1.1361093847110008e-05,
|
1416 |
+
"loss": 0.2454,
|
1417 |
+
"num_tokens": 1997579388.0,
|
1418 |
+
"step": 875
|
1419 |
+
},
|
1420 |
+
{
|
1421 |
+
"epoch": 0.9835149483095836,
|
1422 |
+
"grad_norm": 0.06674376130104065,
|
1423 |
+
"learning_rate": 1.1298943443132382e-05,
|
1424 |
+
"loss": 0.2455,
|
1425 |
+
"num_tokens": 2008982302.0,
|
1426 |
+
"step": 880
|
1427 |
+
},
|
1428 |
+
{
|
1429 |
+
"epoch": 0.989103101424979,
|
1430 |
+
"grad_norm": 0.06652665883302689,
|
1431 |
+
"learning_rate": 1.1236793039154757e-05,
|
1432 |
+
"loss": 0.2431,
|
1433 |
+
"num_tokens": 2020472578.0,
|
1434 |
+
"step": 885
|
1435 |
+
},
|
1436 |
+
{
|
1437 |
+
"epoch": 0.9946912545403744,
|
1438 |
+
"grad_norm": 0.06591866910457611,
|
1439 |
+
"learning_rate": 1.1174642635177128e-05,
|
1440 |
+
"loss": 0.2449,
|
1441 |
+
"num_tokens": 2031841635.0,
|
1442 |
+
"step": 890
|
1443 |
+
},
|
1444 |
+
{
|
1445 |
+
"epoch": 1.0011176306230791,
|
1446 |
+
"grad_norm": 0.23118355870246887,
|
1447 |
+
"learning_rate": 1.1112492231199504e-05,
|
1448 |
+
"loss": 0.2933,
|
1449 |
+
"num_tokens": 2044427047.0,
|
1450 |
+
"step": 895
|
1451 |
+
},
|
1452 |
+
{
|
1453 |
+
"epoch": 1.0067057837384745,
|
1454 |
+
"grad_norm": 0.10587958991527557,
|
1455 |
+
"learning_rate": 1.1050341827221877e-05,
|
1456 |
+
"loss": 0.2414,
|
1457 |
+
"num_tokens": 2055793025.0,
|
1458 |
+
"step": 900
|
1459 |
+
},
|
1460 |
+
{
|
1461 |
+
"epoch": 1.0122939368538697,
|
1462 |
+
"grad_norm": 0.0685587227344513,
|
1463 |
+
"learning_rate": 1.0988191423244252e-05,
|
1464 |
+
"loss": 0.2432,
|
1465 |
+
"num_tokens": 2067243827.0,
|
1466 |
+
"step": 905
|
1467 |
+
},
|
1468 |
+
{
|
1469 |
+
"epoch": 1.017882089969265,
|
1470 |
+
"grad_norm": 0.08346986025571823,
|
1471 |
+
"learning_rate": 1.0926041019266627e-05,
|
1472 |
+
"loss": 0.2409,
|
1473 |
+
"num_tokens": 2078620577.0,
|
1474 |
+
"step": 910
|
1475 |
+
},
|
1476 |
+
{
|
1477 |
+
"epoch": 1.0234702430846605,
|
1478 |
+
"grad_norm": 0.08620323985815048,
|
1479 |
+
"learning_rate": 1.0863890615289e-05,
|
1480 |
+
"loss": 0.2415,
|
1481 |
+
"num_tokens": 2089971736.0,
|
1482 |
+
"step": 915
|
1483 |
+
},
|
1484 |
+
{
|
1485 |
+
"epoch": 1.029058396200056,
|
1486 |
+
"grad_norm": 0.0674772635102272,
|
1487 |
+
"learning_rate": 1.0801740211311374e-05,
|
1488 |
+
"loss": 0.2421,
|
1489 |
+
"num_tokens": 2101379103.0,
|
1490 |
+
"step": 920
|
1491 |
+
},
|
1492 |
+
{
|
1493 |
+
"epoch": 1.0346465493154513,
|
1494 |
+
"grad_norm": 0.07416342943906784,
|
1495 |
+
"learning_rate": 1.0739589807333748e-05,
|
1496 |
+
"loss": 0.2407,
|
1497 |
+
"num_tokens": 2112776077.0,
|
1498 |
+
"step": 925
|
1499 |
+
},
|
1500 |
+
{
|
1501 |
+
"epoch": 1.0402347024308467,
|
1502 |
+
"grad_norm": 0.07598921656608582,
|
1503 |
+
"learning_rate": 1.0677439403356123e-05,
|
1504 |
+
"loss": 0.2409,
|
1505 |
+
"num_tokens": 2124236482.0,
|
1506 |
+
"step": 930
|
1507 |
+
},
|
1508 |
+
{
|
1509 |
+
"epoch": 1.0458228555462419,
|
1510 |
+
"grad_norm": 0.0737273246049881,
|
1511 |
+
"learning_rate": 1.0615288999378496e-05,
|
1512 |
+
"loss": 0.2413,
|
1513 |
+
"num_tokens": 2135688525.0,
|
1514 |
+
"step": 935
|
1515 |
+
},
|
1516 |
+
{
|
1517 |
+
"epoch": 1.0514110086616373,
|
1518 |
+
"grad_norm": 0.06743738800287247,
|
1519 |
+
"learning_rate": 1.0553138595400871e-05,
|
1520 |
+
"loss": 0.2386,
|
1521 |
+
"num_tokens": 2147122071.0,
|
1522 |
+
"step": 940
|
1523 |
+
},
|
1524 |
+
{
|
1525 |
+
"epoch": 1.0569991617770327,
|
1526 |
+
"grad_norm": 0.06557197123765945,
|
1527 |
+
"learning_rate": 1.0490988191423246e-05,
|
1528 |
+
"loss": 0.2403,
|
1529 |
+
"num_tokens": 2158530375.0,
|
1530 |
+
"step": 945
|
1531 |
+
},
|
1532 |
+
{
|
1533 |
+
"epoch": 1.062587314892428,
|
1534 |
+
"grad_norm": 0.06542874127626419,
|
1535 |
+
"learning_rate": 1.0428837787445618e-05,
|
1536 |
+
"loss": 0.2402,
|
1537 |
+
"num_tokens": 2169932710.0,
|
1538 |
+
"step": 950
|
1539 |
+
},
|
1540 |
+
{
|
1541 |
+
"epoch": 1.0681754680078235,
|
1542 |
+
"grad_norm": 0.06733342260122299,
|
1543 |
+
"learning_rate": 1.0366687383467993e-05,
|
1544 |
+
"loss": 0.2388,
|
1545 |
+
"num_tokens": 2181338844.0,
|
1546 |
+
"step": 955
|
1547 |
+
},
|
1548 |
+
{
|
1549 |
+
"epoch": 1.0737636211232187,
|
1550 |
+
"grad_norm": 0.0743744820356369,
|
1551 |
+
"learning_rate": 1.0304536979490367e-05,
|
1552 |
+
"loss": 0.2398,
|
1553 |
+
"num_tokens": 2192802959.0,
|
1554 |
+
"step": 960
|
1555 |
+
},
|
1556 |
+
{
|
1557 |
+
"epoch": 1.079351774238614,
|
1558 |
+
"grad_norm": 0.06693757325410843,
|
1559 |
+
"learning_rate": 1.0242386575512742e-05,
|
1560 |
+
"loss": 0.2388,
|
1561 |
+
"num_tokens": 2204275699.0,
|
1562 |
+
"step": 965
|
1563 |
+
},
|
1564 |
+
{
|
1565 |
+
"epoch": 1.0849399273540095,
|
1566 |
+
"grad_norm": 0.06969534605741501,
|
1567 |
+
"learning_rate": 1.0180236171535117e-05,
|
1568 |
+
"loss": 0.2374,
|
1569 |
+
"num_tokens": 2215670693.0,
|
1570 |
+
"step": 970
|
1571 |
+
},
|
1572 |
+
{
|
1573 |
+
"epoch": 1.0905280804694049,
|
1574 |
+
"grad_norm": 0.06961479038000107,
|
1575 |
+
"learning_rate": 1.011808576755749e-05,
|
1576 |
+
"loss": 0.2388,
|
1577 |
+
"num_tokens": 2227056672.0,
|
1578 |
+
"step": 975
|
1579 |
+
},
|
1580 |
+
{
|
1581 |
+
"epoch": 1.0961162335848003,
|
1582 |
+
"grad_norm": 0.07095306366682053,
|
1583 |
+
"learning_rate": 1.0055935363579865e-05,
|
1584 |
+
"loss": 0.2378,
|
1585 |
+
"num_tokens": 2238434978.0,
|
1586 |
+
"step": 980
|
1587 |
+
},
|
1588 |
+
{
|
1589 |
+
"epoch": 1.1017043867001957,
|
1590 |
+
"grad_norm": 0.06813249737024307,
|
1591 |
+
"learning_rate": 9.993784959602239e-06,
|
1592 |
+
"loss": 0.2375,
|
1593 |
+
"num_tokens": 2249850683.0,
|
1594 |
+
"step": 985
|
1595 |
+
},
|
1596 |
+
{
|
1597 |
+
"epoch": 1.107292539815591,
|
1598 |
+
"grad_norm": 0.0719991996884346,
|
1599 |
+
"learning_rate": 9.931634555624612e-06,
|
1600 |
+
"loss": 0.2373,
|
1601 |
+
"num_tokens": 2261212383.0,
|
1602 |
+
"step": 990
|
1603 |
+
},
|
1604 |
+
{
|
1605 |
+
"epoch": 1.1128806929309862,
|
1606 |
+
"grad_norm": 0.06997533142566681,
|
1607 |
+
"learning_rate": 9.869484151646986e-06,
|
1608 |
+
"loss": 0.237,
|
1609 |
+
"num_tokens": 2272587162.0,
|
1610 |
+
"step": 995
|
1611 |
+
},
|
1612 |
+
{
|
1613 |
+
"epoch": 1.1184688460463816,
|
1614 |
+
"grad_norm": 0.07270677387714386,
|
1615 |
+
"learning_rate": 9.80733374766936e-06,
|
1616 |
+
"loss": 0.2359,
|
1617 |
+
"num_tokens": 2283912018.0,
|
1618 |
+
"step": 1000
|
1619 |
+
},
|
1620 |
+
{
|
1621 |
+
"epoch": 1.124056999161777,
|
1622 |
+
"grad_norm": 0.07579246163368225,
|
1623 |
+
"learning_rate": 9.745183343691734e-06,
|
1624 |
+
"loss": 0.2366,
|
1625 |
+
"num_tokens": 2295347080.0,
|
1626 |
+
"step": 1005
|
1627 |
+
},
|
1628 |
+
{
|
1629 |
+
"epoch": 1.1296451522771724,
|
1630 |
+
"grad_norm": 0.07113311439752579,
|
1631 |
+
"learning_rate": 9.68303293971411e-06,
|
1632 |
+
"loss": 0.2365,
|
1633 |
+
"num_tokens": 2306773064.0,
|
1634 |
+
"step": 1010
|
1635 |
+
},
|
1636 |
+
{
|
1637 |
+
"epoch": 1.1352333053925678,
|
1638 |
+
"grad_norm": 0.07556473463773727,
|
1639 |
+
"learning_rate": 9.620882535736483e-06,
|
1640 |
+
"loss": 0.2372,
|
1641 |
+
"num_tokens": 2318150911.0,
|
1642 |
+
"step": 1015
|
1643 |
+
},
|
1644 |
+
{
|
1645 |
+
"epoch": 1.140821458507963,
|
1646 |
+
"grad_norm": 0.06698355823755264,
|
1647 |
+
"learning_rate": 9.558732131758858e-06,
|
1648 |
+
"loss": 0.235,
|
1649 |
+
"num_tokens": 2329523719.0,
|
1650 |
+
"step": 1020
|
1651 |
+
},
|
1652 |
+
{
|
1653 |
+
"epoch": 1.1464096116233584,
|
1654 |
+
"grad_norm": 0.08231225609779358,
|
1655 |
+
"learning_rate": 9.496581727781231e-06,
|
1656 |
+
"loss": 0.2344,
|
1657 |
+
"num_tokens": 2340997447.0,
|
1658 |
+
"step": 1025
|
1659 |
+
},
|
1660 |
+
{
|
1661 |
+
"epoch": 1.1519977647387538,
|
1662 |
+
"grad_norm": 0.06964124739170074,
|
1663 |
+
"learning_rate": 9.434431323803605e-06,
|
1664 |
+
"loss": 0.2361,
|
1665 |
+
"num_tokens": 2352475029.0,
|
1666 |
+
"step": 1030
|
1667 |
+
},
|
1668 |
+
{
|
1669 |
+
"epoch": 1.1575859178541492,
|
1670 |
+
"grad_norm": 0.0700337216258049,
|
1671 |
+
"learning_rate": 9.37228091982598e-06,
|
1672 |
+
"loss": 0.2355,
|
1673 |
+
"num_tokens": 2363920017.0,
|
1674 |
+
"step": 1035
|
1675 |
+
},
|
1676 |
+
{
|
1677 |
+
"epoch": 1.1631740709695446,
|
1678 |
+
"grad_norm": 0.0741286426782608,
|
1679 |
+
"learning_rate": 9.310130515848353e-06,
|
1680 |
+
"loss": 0.2341,
|
1681 |
+
"num_tokens": 2375322119.0,
|
1682 |
+
"step": 1040
|
1683 |
+
},
|
1684 |
+
{
|
1685 |
+
"epoch": 1.16876222408494,
|
1686 |
+
"grad_norm": 0.06947010010480881,
|
1687 |
+
"learning_rate": 9.247980111870728e-06,
|
1688 |
+
"loss": 0.2342,
|
1689 |
+
"num_tokens": 2386741113.0,
|
1690 |
+
"step": 1045
|
1691 |
+
},
|
1692 |
+
{
|
1693 |
+
"epoch": 1.1743503772003352,
|
1694 |
+
"grad_norm": 0.07005992531776428,
|
1695 |
+
"learning_rate": 9.185829707893102e-06,
|
1696 |
+
"loss": 0.2332,
|
1697 |
+
"num_tokens": 2398129082.0,
|
1698 |
+
"step": 1050
|
1699 |
+
},
|
1700 |
+
{
|
1701 |
+
"epoch": 1.1799385303157306,
|
1702 |
+
"grad_norm": 0.08020587265491486,
|
1703 |
+
"learning_rate": 9.123679303915475e-06,
|
1704 |
+
"loss": 0.2339,
|
1705 |
+
"num_tokens": 2409586941.0,
|
1706 |
+
"step": 1055
|
1707 |
+
},
|
1708 |
+
{
|
1709 |
+
"epoch": 1.185526683431126,
|
1710 |
+
"grad_norm": 0.06929939240217209,
|
1711 |
+
"learning_rate": 9.06152889993785e-06,
|
1712 |
+
"loss": 0.2327,
|
1713 |
+
"num_tokens": 2421044006.0,
|
1714 |
+
"step": 1060
|
1715 |
+
},
|
1716 |
+
{
|
1717 |
+
"epoch": 1.1911148365465214,
|
1718 |
+
"grad_norm": 0.06981244683265686,
|
1719 |
+
"learning_rate": 8.999378495960226e-06,
|
1720 |
+
"loss": 0.2341,
|
1721 |
+
"num_tokens": 2432441590.0,
|
1722 |
+
"step": 1065
|
1723 |
+
},
|
1724 |
+
{
|
1725 |
+
"epoch": 1.1967029896619168,
|
1726 |
+
"grad_norm": 0.06755483150482178,
|
1727 |
+
"learning_rate": 8.937228091982599e-06,
|
1728 |
+
"loss": 0.235,
|
1729 |
+
"num_tokens": 2443840149.0,
|
1730 |
+
"step": 1070
|
1731 |
+
},
|
1732 |
+
{
|
1733 |
+
"epoch": 1.2022911427773122,
|
1734 |
+
"grad_norm": 0.0726640447974205,
|
1735 |
+
"learning_rate": 8.875077688004972e-06,
|
1736 |
+
"loss": 0.2323,
|
1737 |
+
"num_tokens": 2455313893.0,
|
1738 |
+
"step": 1075
|
1739 |
+
},
|
1740 |
+
{
|
1741 |
+
"epoch": 1.2078792958927074,
|
1742 |
+
"grad_norm": 0.08011981844902039,
|
1743 |
+
"learning_rate": 8.812927284027348e-06,
|
1744 |
+
"loss": 0.2326,
|
1745 |
+
"num_tokens": 2466720769.0,
|
1746 |
+
"step": 1080
|
1747 |
+
},
|
1748 |
+
{
|
1749 |
+
"epoch": 1.2134674490081028,
|
1750 |
+
"grad_norm": 0.07221303135156631,
|
1751 |
+
"learning_rate": 8.750776880049721e-06,
|
1752 |
+
"loss": 0.2334,
|
1753 |
+
"num_tokens": 2478131913.0,
|
1754 |
+
"step": 1085
|
1755 |
+
},
|
1756 |
+
{
|
1757 |
+
"epoch": 1.2190556021234982,
|
1758 |
+
"grad_norm": 0.0708707943558693,
|
1759 |
+
"learning_rate": 8.688626476072094e-06,
|
1760 |
+
"loss": 0.2322,
|
1761 |
+
"num_tokens": 2489518624.0,
|
1762 |
+
"step": 1090
|
1763 |
+
},
|
1764 |
+
{
|
1765 |
+
"epoch": 1.2246437552388936,
|
1766 |
+
"grad_norm": 0.08248551189899445,
|
1767 |
+
"learning_rate": 8.62647607209447e-06,
|
1768 |
+
"loss": 0.232,
|
1769 |
+
"num_tokens": 2500909560.0,
|
1770 |
+
"step": 1095
|
1771 |
+
},
|
1772 |
+
{
|
1773 |
+
"epoch": 1.230231908354289,
|
1774 |
+
"grad_norm": 0.0947834923863411,
|
1775 |
+
"learning_rate": 8.564325668116843e-06,
|
1776 |
+
"loss": 0.2329,
|
1777 |
+
"num_tokens": 2512309464.0,
|
1778 |
+
"step": 1100
|
1779 |
+
},
|
1780 |
+
{
|
1781 |
+
"epoch": 1.2358200614696844,
|
1782 |
+
"grad_norm": 0.07485756278038025,
|
1783 |
+
"learning_rate": 8.502175264139218e-06,
|
1784 |
+
"loss": 0.2327,
|
1785 |
+
"num_tokens": 2523712493.0,
|
1786 |
+
"step": 1105
|
1787 |
+
},
|
1788 |
+
{
|
1789 |
+
"epoch": 1.2414082145850796,
|
1790 |
+
"grad_norm": 0.07397732138633728,
|
1791 |
+
"learning_rate": 8.440024860161591e-06,
|
1792 |
+
"loss": 0.2323,
|
1793 |
+
"num_tokens": 2535086363.0,
|
1794 |
+
"step": 1110
|
1795 |
+
},
|
1796 |
+
{
|
1797 |
+
"epoch": 1.246996367700475,
|
1798 |
+
"grad_norm": 0.07793208956718445,
|
1799 |
+
"learning_rate": 8.377874456183965e-06,
|
1800 |
+
"loss": 0.2314,
|
1801 |
+
"num_tokens": 2546530108.0,
|
1802 |
+
"step": 1115
|
1803 |
+
},
|
1804 |
+
{
|
1805 |
+
"epoch": 1.2525845208158704,
|
1806 |
+
"grad_norm": 0.07121593505144119,
|
1807 |
+
"learning_rate": 8.31572405220634e-06,
|
1808 |
+
"loss": 0.2323,
|
1809 |
+
"num_tokens": 2557949004.0,
|
1810 |
+
"step": 1120
|
1811 |
+
},
|
1812 |
+
{
|
1813 |
+
"epoch": 1.2581726739312658,
|
1814 |
+
"grad_norm": 0.0731595903635025,
|
1815 |
+
"learning_rate": 8.253573648228713e-06,
|
1816 |
+
"loss": 0.2296,
|
1817 |
+
"num_tokens": 2569329945.0,
|
1818 |
+
"step": 1125
|
1819 |
+
},
|
1820 |
+
{
|
1821 |
+
"epoch": 1.2637608270466612,
|
1822 |
+
"grad_norm": 0.07631632685661316,
|
1823 |
+
"learning_rate": 8.191423244251089e-06,
|
1824 |
+
"loss": 0.2302,
|
1825 |
+
"num_tokens": 2580772666.0,
|
1826 |
+
"step": 1130
|
1827 |
+
},
|
1828 |
+
{
|
1829 |
+
"epoch": 1.2693489801620563,
|
1830 |
+
"grad_norm": 0.07604105025529861,
|
1831 |
+
"learning_rate": 8.129272840273462e-06,
|
1832 |
+
"loss": 0.2301,
|
1833 |
+
"num_tokens": 2592188030.0,
|
1834 |
+
"step": 1135
|
1835 |
+
},
|
1836 |
+
{
|
1837 |
+
"epoch": 1.2749371332774517,
|
1838 |
+
"grad_norm": 0.08908157795667648,
|
1839 |
+
"learning_rate": 8.067122436295837e-06,
|
1840 |
+
"loss": 0.2302,
|
1841 |
+
"num_tokens": 2603596771.0,
|
1842 |
+
"step": 1140
|
1843 |
+
},
|
1844 |
+
{
|
1845 |
+
"epoch": 1.2805252863928471,
|
1846 |
+
"grad_norm": 0.07644952088594437,
|
1847 |
+
"learning_rate": 8.00497203231821e-06,
|
1848 |
+
"loss": 0.2299,
|
1849 |
+
"num_tokens": 2615012662.0,
|
1850 |
+
"step": 1145
|
1851 |
+
},
|
1852 |
+
{
|
1853 |
+
"epoch": 1.2861134395082425,
|
1854 |
+
"grad_norm": 0.07276136428117752,
|
1855 |
+
"learning_rate": 7.942821628340584e-06,
|
1856 |
+
"loss": 0.2302,
|
1857 |
+
"num_tokens": 2626465997.0,
|
1858 |
+
"step": 1150
|
1859 |
+
},
|
1860 |
+
{
|
1861 |
+
"epoch": 1.291701592623638,
|
1862 |
+
"grad_norm": 0.06722812354564667,
|
1863 |
+
"learning_rate": 7.880671224362959e-06,
|
1864 |
+
"loss": 0.2297,
|
1865 |
+
"num_tokens": 2637906310.0,
|
1866 |
+
"step": 1155
|
1867 |
+
},
|
1868 |
+
{
|
1869 |
+
"epoch": 1.2972897457390333,
|
1870 |
+
"grad_norm": 0.06997846812009811,
|
1871 |
+
"learning_rate": 7.818520820385334e-06,
|
1872 |
+
"loss": 0.2299,
|
1873 |
+
"num_tokens": 2649317945.0,
|
1874 |
+
"step": 1160
|
1875 |
+
},
|
1876 |
+
{
|
1877 |
+
"epoch": 1.3028778988544287,
|
1878 |
+
"grad_norm": 0.06939522922039032,
|
1879 |
+
"learning_rate": 7.756370416407708e-06,
|
1880 |
+
"loss": 0.2297,
|
1881 |
+
"num_tokens": 2660728809.0,
|
1882 |
+
"step": 1165
|
1883 |
+
},
|
1884 |
+
{
|
1885 |
+
"epoch": 1.308466051969824,
|
1886 |
+
"grad_norm": 0.07478871941566467,
|
1887 |
+
"learning_rate": 7.694220012430081e-06,
|
1888 |
+
"loss": 0.2289,
|
1889 |
+
"num_tokens": 2672175476.0,
|
1890 |
+
"step": 1170
|
1891 |
+
},
|
1892 |
+
{
|
1893 |
+
"epoch": 1.3140542050852193,
|
1894 |
+
"grad_norm": 0.07200620323419571,
|
1895 |
+
"learning_rate": 7.632069608452456e-06,
|
1896 |
+
"loss": 0.2292,
|
1897 |
+
"num_tokens": 2683583065.0,
|
1898 |
+
"step": 1175
|
1899 |
+
},
|
1900 |
+
{
|
1901 |
+
"epoch": 1.3196423582006147,
|
1902 |
+
"grad_norm": 0.085682712495327,
|
1903 |
+
"learning_rate": 7.56991920447483e-06,
|
1904 |
+
"loss": 0.2277,
|
1905 |
+
"num_tokens": 2695002849.0,
|
1906 |
+
"step": 1180
|
1907 |
+
},
|
1908 |
+
{
|
1909 |
+
"epoch": 1.32523051131601,
|
1910 |
+
"grad_norm": 0.07334276288747787,
|
1911 |
+
"learning_rate": 7.507768800497204e-06,
|
1912 |
+
"loss": 0.2291,
|
1913 |
+
"num_tokens": 2706445460.0,
|
1914 |
+
"step": 1185
|
1915 |
+
},
|
1916 |
+
{
|
1917 |
+
"epoch": 1.3308186644314053,
|
1918 |
+
"grad_norm": 0.07264410704374313,
|
1919 |
+
"learning_rate": 7.445618396519578e-06,
|
1920 |
+
"loss": 0.2279,
|
1921 |
+
"num_tokens": 2717815944.0,
|
1922 |
+
"step": 1190
|
1923 |
+
},
|
1924 |
+
{
|
1925 |
+
"epoch": 1.3364068175468007,
|
1926 |
+
"grad_norm": 0.06988160312175751,
|
1927 |
+
"learning_rate": 7.383467992541952e-06,
|
1928 |
+
"loss": 0.2279,
|
1929 |
+
"num_tokens": 2729163930.0,
|
1930 |
+
"step": 1195
|
1931 |
+
},
|
1932 |
+
{
|
1933 |
+
"epoch": 1.341994970662196,
|
1934 |
+
"grad_norm": 0.06736642867326736,
|
1935 |
+
"learning_rate": 7.321317588564326e-06,
|
1936 |
+
"loss": 0.2264,
|
1937 |
+
"num_tokens": 2740621790.0,
|
1938 |
+
"step": 1200
|
1939 |
+
},
|
1940 |
+
{
|
1941 |
+
"epoch": 1.3475831237775915,
|
1942 |
+
"grad_norm": 0.07245367765426636,
|
1943 |
+
"learning_rate": 7.259167184586701e-06,
|
1944 |
+
"loss": 0.2267,
|
1945 |
+
"num_tokens": 2752072684.0,
|
1946 |
+
"step": 1205
|
1947 |
+
},
|
1948 |
+
{
|
1949 |
+
"epoch": 1.3531712768929869,
|
1950 |
+
"grad_norm": 0.08028583973646164,
|
1951 |
+
"learning_rate": 7.1970167806090745e-06,
|
1952 |
+
"loss": 0.2278,
|
1953 |
+
"num_tokens": 2763500501.0,
|
1954 |
+
"step": 1210
|
1955 |
+
},
|
1956 |
+
{
|
1957 |
+
"epoch": 1.3587594300083823,
|
1958 |
+
"grad_norm": 0.07318496704101562,
|
1959 |
+
"learning_rate": 7.134866376631449e-06,
|
1960 |
+
"loss": 0.2273,
|
1961 |
+
"num_tokens": 2774964965.0,
|
1962 |
+
"step": 1215
|
1963 |
+
},
|
1964 |
+
{
|
1965 |
+
"epoch": 1.3643475831237777,
|
1966 |
+
"grad_norm": 0.07295212149620056,
|
1967 |
+
"learning_rate": 7.072715972653823e-06,
|
1968 |
+
"loss": 0.2274,
|
1969 |
+
"num_tokens": 2786383778.0,
|
1970 |
+
"step": 1220
|
1971 |
+
},
|
1972 |
+
{
|
1973 |
+
"epoch": 1.369935736239173,
|
1974 |
+
"grad_norm": 0.09171269088983536,
|
1975 |
+
"learning_rate": 7.0105655686761964e-06,
|
1976 |
+
"loss": 0.2277,
|
1977 |
+
"num_tokens": 2797785341.0,
|
1978 |
+
"step": 1225
|
1979 |
+
},
|
1980 |
+
{
|
1981 |
+
"epoch": 1.3755238893545683,
|
1982 |
+
"grad_norm": 0.07763542234897614,
|
1983 |
+
"learning_rate": 6.948415164698571e-06,
|
1984 |
+
"loss": 0.2259,
|
1985 |
+
"num_tokens": 2809216451.0,
|
1986 |
+
"step": 1230
|
1987 |
+
},
|
1988 |
+
{
|
1989 |
+
"epoch": 1.3811120424699637,
|
1990 |
+
"grad_norm": 0.0825599804520607,
|
1991 |
+
"learning_rate": 6.886264760720945e-06,
|
1992 |
+
"loss": 0.2262,
|
1993 |
+
"num_tokens": 2820729443.0,
|
1994 |
+
"step": 1235
|
1995 |
+
},
|
1996 |
+
{
|
1997 |
+
"epoch": 1.386700195585359,
|
1998 |
+
"grad_norm": 0.08326242119073868,
|
1999 |
+
"learning_rate": 6.82411435674332e-06,
|
2000 |
+
"loss": 0.2255,
|
2001 |
+
"num_tokens": 2832131712.0,
|
2002 |
+
"step": 1240
|
2003 |
+
},
|
2004 |
+
{
|
2005 |
+
"epoch": 1.3922883487007545,
|
2006 |
+
"grad_norm": 0.077967569231987,
|
2007 |
+
"learning_rate": 6.7619639527656935e-06,
|
2008 |
+
"loss": 0.2261,
|
2009 |
+
"num_tokens": 2843515554.0,
|
2010 |
+
"step": 1245
|
2011 |
+
},
|
2012 |
+
{
|
2013 |
+
"epoch": 1.3978765018161496,
|
2014 |
+
"grad_norm": 0.06851288676261902,
|
2015 |
+
"learning_rate": 6.699813548788068e-06,
|
2016 |
+
"loss": 0.2249,
|
2017 |
+
"num_tokens": 2854912230.0,
|
2018 |
+
"step": 1250
|
2019 |
+
},
|
2020 |
+
{
|
2021 |
+
"epoch": 1.403464654931545,
|
2022 |
+
"grad_norm": 0.07257357984781265,
|
2023 |
+
"learning_rate": 6.637663144810442e-06,
|
2024 |
+
"loss": 0.2238,
|
2025 |
+
"num_tokens": 2866364126.0,
|
2026 |
+
"step": 1255
|
2027 |
+
},
|
2028 |
+
{
|
2029 |
+
"epoch": 1.4090528080469404,
|
2030 |
+
"grad_norm": 0.07548319548368454,
|
2031 |
+
"learning_rate": 6.5755127408328155e-06,
|
2032 |
+
"loss": 0.2258,
|
2033 |
+
"num_tokens": 2877776317.0,
|
2034 |
+
"step": 1260
|
2035 |
+
},
|
2036 |
+
{
|
2037 |
+
"epoch": 1.4146409611623358,
|
2038 |
+
"grad_norm": 0.06983385235071182,
|
2039 |
+
"learning_rate": 6.51336233685519e-06,
|
2040 |
+
"loss": 0.2247,
|
2041 |
+
"num_tokens": 2889208578.0,
|
2042 |
+
"step": 1265
|
2043 |
+
},
|
2044 |
+
{
|
2045 |
+
"epoch": 1.4202291142777312,
|
2046 |
+
"grad_norm": 0.06997440755367279,
|
2047 |
+
"learning_rate": 6.451211932877565e-06,
|
2048 |
+
"loss": 0.2253,
|
2049 |
+
"num_tokens": 2900590760.0,
|
2050 |
+
"step": 1270
|
2051 |
+
},
|
2052 |
+
{
|
2053 |
+
"epoch": 1.4258172673931266,
|
2054 |
+
"grad_norm": 0.070710189640522,
|
2055 |
+
"learning_rate": 6.389061528899938e-06,
|
2056 |
+
"loss": 0.2248,
|
2057 |
+
"num_tokens": 2912023196.0,
|
2058 |
+
"step": 1275
|
2059 |
+
},
|
2060 |
+
{
|
2061 |
+
"epoch": 1.431405420508522,
|
2062 |
+
"grad_norm": 0.07270118594169617,
|
2063 |
+
"learning_rate": 6.326911124922313e-06,
|
2064 |
+
"loss": 0.2238,
|
2065 |
+
"num_tokens": 2923429499.0,
|
2066 |
+
"step": 1280
|
2067 |
+
},
|
2068 |
+
{
|
2069 |
+
"epoch": 1.4369935736239172,
|
2070 |
+
"grad_norm": 0.08694124966859818,
|
2071 |
+
"learning_rate": 6.264760720944687e-06,
|
2072 |
+
"loss": 0.2259,
|
2073 |
+
"num_tokens": 2934837080.0,
|
2074 |
+
"step": 1285
|
2075 |
+
},
|
2076 |
+
{
|
2077 |
+
"epoch": 1.4425817267393126,
|
2078 |
+
"grad_norm": 0.07063344120979309,
|
2079 |
+
"learning_rate": 6.20261031696706e-06,
|
2080 |
+
"loss": 0.2239,
|
2081 |
+
"num_tokens": 2946269327.0,
|
2082 |
+
"step": 1290
|
2083 |
+
},
|
2084 |
+
{
|
2085 |
+
"epoch": 1.448169879854708,
|
2086 |
+
"grad_norm": 0.07271133363246918,
|
2087 |
+
"learning_rate": 6.140459912989435e-06,
|
2088 |
+
"loss": 0.2245,
|
2089 |
+
"num_tokens": 2957677718.0,
|
2090 |
+
"step": 1295
|
2091 |
+
},
|
2092 |
+
{
|
2093 |
+
"epoch": 1.4537580329701034,
|
2094 |
+
"grad_norm": 0.07457529008388519,
|
2095 |
+
"learning_rate": 6.07830950901181e-06,
|
2096 |
+
"loss": 0.2243,
|
2097 |
+
"num_tokens": 2969106309.0,
|
2098 |
+
"step": 1300
|
2099 |
+
},
|
2100 |
+
{
|
2101 |
+
"epoch": 1.4593461860854988,
|
2102 |
+
"grad_norm": 0.08053404092788696,
|
2103 |
+
"learning_rate": 6.016159105034183e-06,
|
2104 |
+
"loss": 0.2246,
|
2105 |
+
"num_tokens": 2980514913.0,
|
2106 |
+
"step": 1305
|
2107 |
+
},
|
2108 |
+
{
|
2109 |
+
"epoch": 1.464934339200894,
|
2110 |
+
"grad_norm": 0.08139532804489136,
|
2111 |
+
"learning_rate": 5.9540087010565574e-06,
|
2112 |
+
"loss": 0.2235,
|
2113 |
+
"num_tokens": 2991911920.0,
|
2114 |
+
"step": 1310
|
2115 |
+
},
|
2116 |
+
{
|
2117 |
+
"epoch": 1.4705224923162894,
|
2118 |
+
"grad_norm": 0.07161208987236023,
|
2119 |
+
"learning_rate": 5.891858297078932e-06,
|
2120 |
+
"loss": 0.2238,
|
2121 |
+
"num_tokens": 3003300184.0,
|
2122 |
+
"step": 1315
|
2123 |
+
},
|
2124 |
+
{
|
2125 |
+
"epoch": 1.4761106454316848,
|
2126 |
+
"grad_norm": 0.07118191570043564,
|
2127 |
+
"learning_rate": 5.829707893101305e-06,
|
2128 |
+
"loss": 0.2234,
|
2129 |
+
"num_tokens": 3014691103.0,
|
2130 |
+
"step": 1320
|
2131 |
+
},
|
2132 |
+
{
|
2133 |
+
"epoch": 1.4816987985470802,
|
2134 |
+
"grad_norm": 0.07934009283781052,
|
2135 |
+
"learning_rate": 5.767557489123679e-06,
|
2136 |
+
"loss": 0.2224,
|
2137 |
+
"num_tokens": 3026103118.0,
|
2138 |
+
"step": 1325
|
2139 |
+
},
|
2140 |
+
{
|
2141 |
+
"epoch": 1.4872869516624756,
|
2142 |
+
"grad_norm": 0.07582356035709381,
|
2143 |
+
"learning_rate": 5.7054070851460545e-06,
|
2144 |
+
"loss": 0.2221,
|
2145 |
+
"num_tokens": 3037596869.0,
|
2146 |
+
"step": 1330
|
2147 |
+
},
|
2148 |
+
{
|
2149 |
+
"epoch": 1.492875104777871,
|
2150 |
+
"grad_norm": 0.07446973025798798,
|
2151 |
+
"learning_rate": 5.643256681168427e-06,
|
2152 |
+
"loss": 0.2229,
|
2153 |
+
"num_tokens": 3049028284.0,
|
2154 |
+
"step": 1335
|
2155 |
+
},
|
2156 |
+
{
|
2157 |
+
"epoch": 1.4984632578932664,
|
2158 |
+
"grad_norm": 0.0742158517241478,
|
2159 |
+
"learning_rate": 5.581106277190802e-06,
|
2160 |
+
"loss": 0.2227,
|
2161 |
+
"num_tokens": 3060480880.0,
|
2162 |
+
"step": 1340
|
2163 |
+
},
|
2164 |
+
{
|
2165 |
+
"epoch": 1.5040514110086618,
|
2166 |
+
"grad_norm": 0.07621730864048004,
|
2167 |
+
"learning_rate": 5.5189558732131765e-06,
|
2168 |
+
"loss": 0.2233,
|
2169 |
+
"num_tokens": 3071863505.0,
|
2170 |
+
"step": 1345
|
2171 |
+
},
|
2172 |
+
{
|
2173 |
+
"epoch": 1.509639564124057,
|
2174 |
+
"grad_norm": 0.07590433955192566,
|
2175 |
+
"learning_rate": 5.456805469235551e-06,
|
2176 |
+
"loss": 0.2218,
|
2177 |
+
"num_tokens": 3083299766.0,
|
2178 |
+
"step": 1350
|
2179 |
+
},
|
2180 |
+
{
|
2181 |
+
"epoch": 1.5152277172394524,
|
2182 |
+
"grad_norm": 0.07606492191553116,
|
2183 |
+
"learning_rate": 5.394655065257924e-06,
|
2184 |
+
"loss": 0.2229,
|
2185 |
+
"num_tokens": 3094669059.0,
|
2186 |
+
"step": 1355
|
2187 |
+
},
|
2188 |
+
{
|
2189 |
+
"epoch": 1.5208158703548478,
|
2190 |
+
"grad_norm": 0.07033602148294449,
|
2191 |
+
"learning_rate": 5.3325046612802985e-06,
|
2192 |
+
"loss": 0.2217,
|
2193 |
+
"num_tokens": 3106096591.0,
|
2194 |
+
"step": 1360
|
2195 |
+
},
|
2196 |
+
{
|
2197 |
+
"epoch": 1.526404023470243,
|
2198 |
+
"grad_norm": 0.07336968928575516,
|
2199 |
+
"learning_rate": 5.270354257302674e-06,
|
2200 |
+
"loss": 0.2216,
|
2201 |
+
"num_tokens": 3117475057.0,
|
2202 |
+
"step": 1365
|
2203 |
+
},
|
2204 |
+
{
|
2205 |
+
"epoch": 1.5319921765856384,
|
2206 |
+
"grad_norm": 0.07641858607530594,
|
2207 |
+
"learning_rate": 5.208203853325047e-06,
|
2208 |
+
"loss": 0.221,
|
2209 |
+
"num_tokens": 3128902661.0,
|
2210 |
+
"step": 1370
|
2211 |
+
},
|
2212 |
+
{
|
2213 |
+
"epoch": 1.5375803297010338,
|
2214 |
+
"grad_norm": 0.07360400259494781,
|
2215 |
+
"learning_rate": 5.146053449347421e-06,
|
2216 |
+
"loss": 0.2211,
|
2217 |
+
"num_tokens": 3140300853.0,
|
2218 |
+
"step": 1375
|
2219 |
+
},
|
2220 |
+
{
|
2221 |
+
"epoch": 1.5431684828164292,
|
2222 |
+
"grad_norm": 0.07237103581428528,
|
2223 |
+
"learning_rate": 5.083903045369796e-06,
|
2224 |
+
"loss": 0.2212,
|
2225 |
+
"num_tokens": 3151699200.0,
|
2226 |
+
"step": 1380
|
2227 |
+
},
|
2228 |
+
{
|
2229 |
+
"epoch": 1.5487566359318246,
|
2230 |
+
"grad_norm": 0.07762517035007477,
|
2231 |
+
"learning_rate": 5.021752641392169e-06,
|
2232 |
+
"loss": 0.2217,
|
2233 |
+
"num_tokens": 3163130506.0,
|
2234 |
+
"step": 1385
|
2235 |
+
},
|
2236 |
+
{
|
2237 |
+
"epoch": 1.55434478904722,
|
2238 |
+
"grad_norm": 0.08191149681806564,
|
2239 |
+
"learning_rate": 4.959602237414543e-06,
|
2240 |
+
"loss": 0.2217,
|
2241 |
+
"num_tokens": 3174508734.0,
|
2242 |
+
"step": 1390
|
2243 |
+
},
|
2244 |
+
{
|
2245 |
+
"epoch": 1.5599329421626154,
|
2246 |
+
"grad_norm": 0.07370056957006454,
|
2247 |
+
"learning_rate": 4.897451833436918e-06,
|
2248 |
+
"loss": 0.2207,
|
2249 |
+
"num_tokens": 3185863770.0,
|
2250 |
+
"step": 1395
|
2251 |
+
},
|
2252 |
+
{
|
2253 |
+
"epoch": 1.5655210952780108,
|
2254 |
+
"grad_norm": 0.08156365156173706,
|
2255 |
+
"learning_rate": 4.835301429459292e-06,
|
2256 |
+
"loss": 0.2211,
|
2257 |
+
"num_tokens": 3197279089.0,
|
2258 |
+
"step": 1400
|
2259 |
+
},
|
2260 |
+
{
|
2261 |
+
"epoch": 1.571109248393406,
|
2262 |
+
"grad_norm": 0.0858791321516037,
|
2263 |
+
"learning_rate": 4.773151025481666e-06,
|
2264 |
+
"loss": 0.2205,
|
2265 |
+
"num_tokens": 3208673959.0,
|
2266 |
+
"step": 1405
|
2267 |
+
},
|
2268 |
+
{
|
2269 |
+
"epoch": 1.5766974015088013,
|
2270 |
+
"grad_norm": 0.07985149323940277,
|
2271 |
+
"learning_rate": 4.7110006215040396e-06,
|
2272 |
+
"loss": 0.2198,
|
2273 |
+
"num_tokens": 3220133881.0,
|
2274 |
+
"step": 1410
|
2275 |
+
},
|
2276 |
+
{
|
2277 |
+
"epoch": 1.5822855546241967,
|
2278 |
+
"grad_norm": 0.07632007449865341,
|
2279 |
+
"learning_rate": 4.648850217526415e-06,
|
2280 |
+
"loss": 0.2206,
|
2281 |
+
"num_tokens": 3231491155.0,
|
2282 |
+
"step": 1415
|
2283 |
+
},
|
2284 |
+
{
|
2285 |
+
"epoch": 1.587873707739592,
|
2286 |
+
"grad_norm": 0.07036534696817398,
|
2287 |
+
"learning_rate": 4.586699813548788e-06,
|
2288 |
+
"loss": 0.2207,
|
2289 |
+
"num_tokens": 3242935540.0,
|
2290 |
+
"step": 1420
|
2291 |
+
},
|
2292 |
+
{
|
2293 |
+
"epoch": 1.5934618608549873,
|
2294 |
+
"grad_norm": 0.06916205585002899,
|
2295 |
+
"learning_rate": 4.524549409571163e-06,
|
2296 |
+
"loss": 0.2197,
|
2297 |
+
"num_tokens": 3254402835.0,
|
2298 |
+
"step": 1425
|
2299 |
+
},
|
2300 |
+
{
|
2301 |
+
"epoch": 1.5990500139703827,
|
2302 |
+
"grad_norm": 0.07398437708616257,
|
2303 |
+
"learning_rate": 4.462399005593537e-06,
|
2304 |
+
"loss": 0.2207,
|
2305 |
+
"num_tokens": 3265876131.0,
|
2306 |
+
"step": 1430
|
2307 |
+
},
|
2308 |
+
{
|
2309 |
+
"epoch": 1.604638167085778,
|
2310 |
+
"grad_norm": 0.07751976698637009,
|
2311 |
+
"learning_rate": 4.400248601615911e-06,
|
2312 |
+
"loss": 0.22,
|
2313 |
+
"num_tokens": 3277349860.0,
|
2314 |
+
"step": 1435
|
2315 |
+
},
|
2316 |
+
{
|
2317 |
+
"epoch": 1.6102263202011735,
|
2318 |
+
"grad_norm": 0.07772251963615417,
|
2319 |
+
"learning_rate": 4.338098197638285e-06,
|
2320 |
+
"loss": 0.2191,
|
2321 |
+
"num_tokens": 3288733768.0,
|
2322 |
+
"step": 1440
|
2323 |
+
},
|
2324 |
+
{
|
2325 |
+
"epoch": 1.615814473316569,
|
2326 |
+
"grad_norm": 0.08139509707689285,
|
2327 |
+
"learning_rate": 4.2759477936606595e-06,
|
2328 |
+
"loss": 0.2185,
|
2329 |
+
"num_tokens": 3300158714.0,
|
2330 |
+
"step": 1445
|
2331 |
+
},
|
2332 |
+
{
|
2333 |
+
"epoch": 1.6214026264319643,
|
2334 |
+
"grad_norm": 0.06895268708467484,
|
2335 |
+
"learning_rate": 4.213797389683033e-06,
|
2336 |
+
"loss": 0.2196,
|
2337 |
+
"num_tokens": 3311588436.0,
|
2338 |
+
"step": 1450
|
2339 |
+
},
|
2340 |
+
{
|
2341 |
+
"epoch": 1.6269907795473597,
|
2342 |
+
"grad_norm": 0.07353264838457108,
|
2343 |
+
"learning_rate": 4.151646985705407e-06,
|
2344 |
+
"loss": 0.2181,
|
2345 |
+
"num_tokens": 3323053103.0,
|
2346 |
+
"step": 1455
|
2347 |
+
},
|
2348 |
+
{
|
2349 |
+
"epoch": 1.6325789326627551,
|
2350 |
+
"grad_norm": 0.07424376159906387,
|
2351 |
+
"learning_rate": 4.0894965817277815e-06,
|
2352 |
+
"loss": 0.2191,
|
2353 |
+
"num_tokens": 3334470782.0,
|
2354 |
+
"step": 1460
|
2355 |
+
},
|
2356 |
+
{
|
2357 |
+
"epoch": 1.6381670857781503,
|
2358 |
+
"grad_norm": 0.07496050000190735,
|
2359 |
+
"learning_rate": 4.027346177750156e-06,
|
2360 |
+
"loss": 0.2177,
|
2361 |
+
"num_tokens": 3345862999.0,
|
2362 |
+
"step": 1465
|
2363 |
+
},
|
2364 |
+
{
|
2365 |
+
"epoch": 1.6437552388935457,
|
2366 |
+
"grad_norm": 0.0735882893204689,
|
2367 |
+
"learning_rate": 3.96519577377253e-06,
|
2368 |
+
"loss": 0.2173,
|
2369 |
+
"num_tokens": 3357254289.0,
|
2370 |
+
"step": 1470
|
2371 |
+
},
|
2372 |
+
{
|
2373 |
+
"epoch": 1.649343392008941,
|
2374 |
+
"grad_norm": 0.06661386042833328,
|
2375 |
+
"learning_rate": 3.903045369794904e-06,
|
2376 |
+
"loss": 0.2183,
|
2377 |
+
"num_tokens": 3368694368.0,
|
2378 |
+
"step": 1475
|
2379 |
+
},
|
2380 |
+
{
|
2381 |
+
"epoch": 1.6549315451243363,
|
2382 |
+
"grad_norm": 0.07148396968841553,
|
2383 |
+
"learning_rate": 3.8408949658172786e-06,
|
2384 |
+
"loss": 0.2193,
|
2385 |
+
"num_tokens": 3380126124.0,
|
2386 |
+
"step": 1480
|
2387 |
+
},
|
2388 |
+
{
|
2389 |
+
"epoch": 1.6605196982397317,
|
2390 |
+
"grad_norm": 0.0710797905921936,
|
2391 |
+
"learning_rate": 3.7787445618396524e-06,
|
2392 |
+
"loss": 0.2184,
|
2393 |
+
"num_tokens": 3391574072.0,
|
2394 |
+
"step": 1485
|
2395 |
+
},
|
2396 |
+
{
|
2397 |
+
"epoch": 1.666107851355127,
|
2398 |
+
"grad_norm": 0.07196183502674103,
|
2399 |
+
"learning_rate": 3.7165941578620263e-06,
|
2400 |
+
"loss": 0.2182,
|
2401 |
+
"num_tokens": 3402977723.0,
|
2402 |
+
"step": 1490
|
2403 |
+
},
|
2404 |
+
{
|
2405 |
+
"epoch": 1.6716960044705225,
|
2406 |
+
"grad_norm": 0.07636953890323639,
|
2407 |
+
"learning_rate": 3.6544437538844006e-06,
|
2408 |
+
"loss": 0.2182,
|
2409 |
+
"num_tokens": 3414408734.0,
|
2410 |
+
"step": 1495
|
2411 |
+
},
|
2412 |
+
{
|
2413 |
+
"epoch": 1.6772841575859179,
|
2414 |
+
"grad_norm": 0.08158502727746964,
|
2415 |
+
"learning_rate": 3.592293349906775e-06,
|
2416 |
+
"loss": 0.2185,
|
2417 |
+
"num_tokens": 3425813751.0,
|
2418 |
+
"step": 1500
|
2419 |
+
},
|
2420 |
+
{
|
2421 |
+
"epoch": 1.6828723107013133,
|
2422 |
+
"grad_norm": 0.07502773404121399,
|
2423 |
+
"learning_rate": 3.5301429459291487e-06,
|
2424 |
+
"loss": 0.2179,
|
2425 |
+
"num_tokens": 3437193392.0,
|
2426 |
+
"step": 1505
|
2427 |
+
},
|
2428 |
+
{
|
2429 |
+
"epoch": 1.6884604638167087,
|
2430 |
+
"grad_norm": 0.07863924652338028,
|
2431 |
+
"learning_rate": 3.467992541951523e-06,
|
2432 |
+
"loss": 0.2172,
|
2433 |
+
"num_tokens": 3448632773.0,
|
2434 |
+
"step": 1510
|
2435 |
+
},
|
2436 |
+
{
|
2437 |
+
"epoch": 1.694048616932104,
|
2438 |
+
"grad_norm": 0.07169536501169205,
|
2439 |
+
"learning_rate": 3.4058421379738972e-06,
|
2440 |
+
"loss": 0.2187,
|
2441 |
+
"num_tokens": 3460067160.0,
|
2442 |
+
"step": 1515
|
2443 |
+
},
|
2444 |
+
{
|
2445 |
+
"epoch": 1.6996367700474995,
|
2446 |
+
"grad_norm": 0.0705784261226654,
|
2447 |
+
"learning_rate": 3.343691733996271e-06,
|
2448 |
+
"loss": 0.2179,
|
2449 |
+
"num_tokens": 3471516712.0,
|
2450 |
+
"step": 1520
|
2451 |
+
},
|
2452 |
+
{
|
2453 |
+
"epoch": 1.7052249231628946,
|
2454 |
+
"grad_norm": 0.07223106175661087,
|
2455 |
+
"learning_rate": 3.2815413300186454e-06,
|
2456 |
+
"loss": 0.2175,
|
2457 |
+
"num_tokens": 3482932353.0,
|
2458 |
+
"step": 1525
|
2459 |
+
},
|
2460 |
+
{
|
2461 |
+
"epoch": 1.71081307627829,
|
2462 |
+
"grad_norm": 0.07556425780057907,
|
2463 |
+
"learning_rate": 3.2193909260410196e-06,
|
2464 |
+
"loss": 0.2165,
|
2465 |
+
"num_tokens": 3494314753.0,
|
2466 |
+
"step": 1530
|
2467 |
+
},
|
2468 |
+
{
|
2469 |
+
"epoch": 1.7164012293936852,
|
2470 |
+
"grad_norm": 0.06876374036073685,
|
2471 |
+
"learning_rate": 3.157240522063394e-06,
|
2472 |
+
"loss": 0.2173,
|
2473 |
+
"num_tokens": 3505725660.0,
|
2474 |
+
"step": 1535
|
2475 |
+
},
|
2476 |
+
{
|
2477 |
+
"epoch": 1.7219893825090806,
|
2478 |
+
"grad_norm": 0.0745040625333786,
|
2479 |
+
"learning_rate": 3.0950901180857678e-06,
|
2480 |
+
"loss": 0.2167,
|
2481 |
+
"num_tokens": 3517142975.0,
|
2482 |
+
"step": 1540
|
2483 |
+
},
|
2484 |
+
{
|
2485 |
+
"epoch": 1.727577535624476,
|
2486 |
+
"grad_norm": 0.07012300193309784,
|
2487 |
+
"learning_rate": 3.0329397141081416e-06,
|
2488 |
+
"loss": 0.2182,
|
2489 |
+
"num_tokens": 3528528432.0,
|
2490 |
+
"step": 1545
|
2491 |
+
},
|
2492 |
+
{
|
2493 |
+
"epoch": 1.7331656887398714,
|
2494 |
+
"grad_norm": 0.07678242027759552,
|
2495 |
+
"learning_rate": 2.9707893101305163e-06,
|
2496 |
+
"loss": 0.2163,
|
2497 |
+
"num_tokens": 3539941340.0,
|
2498 |
+
"step": 1550
|
2499 |
+
},
|
2500 |
+
{
|
2501 |
+
"epoch": 1.7387538418552668,
|
2502 |
+
"grad_norm": 0.07423070818185806,
|
2503 |
+
"learning_rate": 2.90863890615289e-06,
|
2504 |
+
"loss": 0.2173,
|
2505 |
+
"num_tokens": 3551323443.0,
|
2506 |
+
"step": 1555
|
2507 |
+
},
|
2508 |
+
{
|
2509 |
+
"epoch": 1.7443419949706622,
|
2510 |
+
"grad_norm": 0.06830978393554688,
|
2511 |
+
"learning_rate": 2.846488502175264e-06,
|
2512 |
+
"loss": 0.2163,
|
2513 |
+
"num_tokens": 3562717030.0,
|
2514 |
+
"step": 1560
|
2515 |
+
},
|
2516 |
+
{
|
2517 |
+
"epoch": 1.7499301480860576,
|
2518 |
+
"grad_norm": 0.06994173675775528,
|
2519 |
+
"learning_rate": 2.7843380981976387e-06,
|
2520 |
+
"loss": 0.2165,
|
2521 |
+
"num_tokens": 3574144181.0,
|
2522 |
+
"step": 1565
|
2523 |
+
},
|
2524 |
+
{
|
2525 |
+
"epoch": 1.755518301201453,
|
2526 |
+
"grad_norm": 0.07089458405971527,
|
2527 |
+
"learning_rate": 2.7221876942200126e-06,
|
2528 |
+
"loss": 0.2157,
|
2529 |
+
"num_tokens": 3585556833.0,
|
2530 |
+
"step": 1570
|
2531 |
+
},
|
2532 |
+
{
|
2533 |
+
"epoch": 1.7611064543168484,
|
2534 |
+
"grad_norm": 0.07160953432321548,
|
2535 |
+
"learning_rate": 2.6600372902423864e-06,
|
2536 |
+
"loss": 0.2162,
|
2537 |
+
"num_tokens": 3596978608.0,
|
2538 |
+
"step": 1575
|
2539 |
+
},
|
2540 |
+
{
|
2541 |
+
"epoch": 1.7666946074322436,
|
2542 |
+
"grad_norm": 0.07307710498571396,
|
2543 |
+
"learning_rate": 2.597886886264761e-06,
|
2544 |
+
"loss": 0.2174,
|
2545 |
+
"num_tokens": 3608380361.0,
|
2546 |
+
"step": 1580
|
2547 |
+
},
|
2548 |
+
{
|
2549 |
+
"epoch": 1.772282760547639,
|
2550 |
+
"grad_norm": 0.07015839219093323,
|
2551 |
+
"learning_rate": 2.535736482287135e-06,
|
2552 |
+
"loss": 0.2158,
|
2553 |
+
"num_tokens": 3619811825.0,
|
2554 |
+
"step": 1585
|
2555 |
+
},
|
2556 |
+
{
|
2557 |
+
"epoch": 1.7778709136630344,
|
2558 |
+
"grad_norm": 0.07099422812461853,
|
2559 |
+
"learning_rate": 2.4735860783095093e-06,
|
2560 |
+
"loss": 0.2165,
|
2561 |
+
"num_tokens": 3631237698.0,
|
2562 |
+
"step": 1590
|
2563 |
+
},
|
2564 |
+
{
|
2565 |
+
"epoch": 1.7834590667784296,
|
2566 |
+
"grad_norm": 0.06655248254537582,
|
2567 |
+
"learning_rate": 2.4114356743318835e-06,
|
2568 |
+
"loss": 0.2173,
|
2569 |
+
"num_tokens": 3642666802.0,
|
2570 |
+
"step": 1595
|
2571 |
+
},
|
2572 |
+
{
|
2573 |
+
"epoch": 1.789047219893825,
|
2574 |
+
"grad_norm": 0.06884568929672241,
|
2575 |
+
"learning_rate": 2.349285270354258e-06,
|
2576 |
+
"loss": 0.2146,
|
2577 |
+
"num_tokens": 3654090172.0,
|
2578 |
+
"step": 1600
|
2579 |
+
}
|
2580 |
+
],
|
2581 |
+
"logging_steps": 5,
|
2582 |
+
"max_steps": 1788,
|
2583 |
+
"num_input_tokens_seen": 0,
|
2584 |
+
"num_train_epochs": 2,
|
2585 |
+
"save_steps": 200,
|
2586 |
+
"stateful_callbacks": {
|
2587 |
+
"TrainerControl": {
|
2588 |
+
"args": {
|
2589 |
+
"should_epoch_stop": false,
|
2590 |
+
"should_evaluate": false,
|
2591 |
+
"should_log": false,
|
2592 |
+
"should_save": true,
|
2593 |
+
"should_training_stop": false
|
2594 |
+
},
|
2595 |
+
"attributes": {}
|
2596 |
+
}
|
2597 |
+
},
|
2598 |
+
"total_flos": 3.823986412087568e+19,
|
2599 |
+
"train_batch_size": 32,
|
2600 |
+
"trial_name": null,
|
2601 |
+
"trial_params": null
|
2602 |
+
}
|