Upload 9 files
Browse files- arena_social_test.json +0 -0
- config.json +28 -0
- generation_config.json +7 -0
- model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- trainer_state.json +508 -0
- training_args.bin +3 -0
arena_social_test.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "eqhylxx/vicuna-160m",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 768,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 3072,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 12,
|
16 |
+
"num_hidden_layers": 12,
|
17 |
+
"num_key_value_heads": 12,
|
18 |
+
"pad_token_id": 1,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-06,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "float32",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 1,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0af302e53e4bcd164891865872c669aae6fcc9152c464d12f27d3ea2357389b2
|
3 |
+
size 649681952
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": true,
|
34 |
+
"model_max_length": 256,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9937694704049844,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 80,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.02,
|
13 |
+
"learning_rate": 6.666666666666667e-06,
|
14 |
+
"loss": 1.6772,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.05,
|
19 |
+
"learning_rate": 1.3333333333333333e-05,
|
20 |
+
"loss": 1.6591,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.07,
|
25 |
+
"learning_rate": 2e-05,
|
26 |
+
"loss": 1.7126,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.1,
|
31 |
+
"learning_rate": 1.9991677993445832e-05,
|
32 |
+
"loss": 1.7077,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.12,
|
37 |
+
"learning_rate": 1.9966725824941933e-05,
|
38 |
+
"loss": 1.6977,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.15,
|
43 |
+
"learning_rate": 1.992518502491028e-05,
|
44 |
+
"loss": 1.6409,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.17,
|
49 |
+
"learning_rate": 1.986712473391289e-05,
|
50 |
+
"loss": 1.6717,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.2,
|
55 |
+
"learning_rate": 1.9792641587574212e-05,
|
56 |
+
"loss": 1.6683,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.22,
|
61 |
+
"learning_rate": 1.9701859555740647e-05,
|
62 |
+
"loss": 1.6339,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.25,
|
67 |
+
"learning_rate": 1.9594929736144978e-05,
|
68 |
+
"loss": 1.5765,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.27,
|
73 |
+
"learning_rate": 1.9472030102919102e-05,
|
74 |
+
"loss": 1.6116,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.3,
|
79 |
+
"learning_rate": 1.9333365210373668e-05,
|
80 |
+
"loss": 1.6752,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.32,
|
85 |
+
"learning_rate": 1.9179165852537596e-05,
|
86 |
+
"loss": 1.5735,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.35,
|
91 |
+
"learning_rate": 1.900968867902419e-05,
|
92 |
+
"loss": 1.6554,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.37,
|
97 |
+
"learning_rate": 1.8825215767863215e-05,
|
98 |
+
"loss": 1.6075,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.4,
|
103 |
+
"learning_rate": 1.8626054156009807e-05,
|
104 |
+
"loss": 1.6091,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.42,
|
109 |
+
"learning_rate": 1.8412535328311813e-05,
|
110 |
+
"loss": 1.599,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.45,
|
115 |
+
"learning_rate": 1.8185014665785936e-05,
|
116 |
+
"loss": 1.5027,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.47,
|
121 |
+
"learning_rate": 1.7943870854121126e-05,
|
122 |
+
"loss": 1.5883,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.5,
|
127 |
+
"learning_rate": 1.768950525339362e-05,
|
128 |
+
"loss": 1.5739,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.52,
|
133 |
+
"learning_rate": 1.74223412300427e-05,
|
134 |
+
"loss": 1.5958,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.55,
|
139 |
+
"learning_rate": 1.7142823452219036e-05,
|
140 |
+
"loss": 1.489,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.57,
|
145 |
+
"learning_rate": 1.6851417149678442e-05,
|
146 |
+
"loss": 1.5861,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.6,
|
151 |
+
"learning_rate": 1.6548607339452853e-05,
|
152 |
+
"loss": 1.5902,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.62,
|
157 |
+
"learning_rate": 1.6234898018587336e-05,
|
158 |
+
"loss": 1.514,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.65,
|
163 |
+
"learning_rate": 1.5910811325286768e-05,
|
164 |
+
"loss": 1.5592,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.67,
|
169 |
+
"learning_rate": 1.5576886669868297e-05,
|
170 |
+
"loss": 1.5757,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.7,
|
175 |
+
"learning_rate": 1.5233679836966122e-05,
|
176 |
+
"loss": 1.5668,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.72,
|
181 |
+
"learning_rate": 1.4881762060482814e-05,
|
182 |
+
"loss": 1.5971,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.75,
|
187 |
+
"learning_rate": 1.4521719072826858e-05,
|
188 |
+
"loss": 1.5389,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.77,
|
193 |
+
"learning_rate": 1.4154150130018867e-05,
|
194 |
+
"loss": 1.5161,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.8,
|
199 |
+
"learning_rate": 1.3779667014289067e-05,
|
200 |
+
"loss": 1.6,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.82,
|
205 |
+
"learning_rate": 1.3398893015826166e-05,
|
206 |
+
"loss": 1.5598,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.85,
|
211 |
+
"learning_rate": 1.3012461895372343e-05,
|
212 |
+
"loss": 1.5645,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 0.87,
|
217 |
+
"learning_rate": 1.2621016829391022e-05,
|
218 |
+
"loss": 1.8278,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 0.9,
|
223 |
+
"learning_rate": 1.2225209339563144e-05,
|
224 |
+
"loss": 1.5166,
|
225 |
+
"step": 36
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 0.92,
|
229 |
+
"learning_rate": 1.182569820839362e-05,
|
230 |
+
"loss": 1.7329,
|
231 |
+
"step": 37
|
232 |
+
},
|
233 |
+
{
|
234 |
+
"epoch": 0.95,
|
235 |
+
"learning_rate": 1.1423148382732854e-05,
|
236 |
+
"loss": 1.5313,
|
237 |
+
"step": 38
|
238 |
+
},
|
239 |
+
{
|
240 |
+
"epoch": 0.97,
|
241 |
+
"learning_rate": 1.1018229867038358e-05,
|
242 |
+
"loss": 1.5852,
|
243 |
+
"step": 39
|
244 |
+
},
|
245 |
+
{
|
246 |
+
"epoch": 1.0,
|
247 |
+
"learning_rate": 1.0611616608218429e-05,
|
248 |
+
"loss": 1.5125,
|
249 |
+
"step": 40
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 1.02,
|
253 |
+
"learning_rate": 1.0203985373914056e-05,
|
254 |
+
"loss": 1.4622,
|
255 |
+
"step": 41
|
256 |
+
},
|
257 |
+
{
|
258 |
+
"epoch": 1.05,
|
259 |
+
"learning_rate": 9.79601462608595e-06,
|
260 |
+
"loss": 1.4274,
|
261 |
+
"step": 42
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 1.07,
|
265 |
+
"learning_rate": 9.388383391781576e-06,
|
266 |
+
"loss": 1.4272,
|
267 |
+
"step": 43
|
268 |
+
},
|
269 |
+
{
|
270 |
+
"epoch": 1.1,
|
271 |
+
"learning_rate": 8.981770132961649e-06,
|
272 |
+
"loss": 1.4694,
|
273 |
+
"step": 44
|
274 |
+
},
|
275 |
+
{
|
276 |
+
"epoch": 1.12,
|
277 |
+
"learning_rate": 8.576851617267151e-06,
|
278 |
+
"loss": 1.4136,
|
279 |
+
"step": 45
|
280 |
+
},
|
281 |
+
{
|
282 |
+
"epoch": 1.15,
|
283 |
+
"learning_rate": 8.174301791606384e-06,
|
284 |
+
"loss": 1.39,
|
285 |
+
"step": 46
|
286 |
+
},
|
287 |
+
{
|
288 |
+
"epoch": 1.17,
|
289 |
+
"learning_rate": 7.774790660436857e-06,
|
290 |
+
"loss": 1.3597,
|
291 |
+
"step": 47
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 1.2,
|
295 |
+
"learning_rate": 7.378983170608982e-06,
|
296 |
+
"loss": 1.3729,
|
297 |
+
"step": 48
|
298 |
+
},
|
299 |
+
{
|
300 |
+
"epoch": 1.22,
|
301 |
+
"learning_rate": 6.9875381046276605e-06,
|
302 |
+
"loss": 1.4594,
|
303 |
+
"step": 49
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 1.25,
|
307 |
+
"learning_rate": 6.601106984173835e-06,
|
308 |
+
"loss": 1.3709,
|
309 |
+
"step": 50
|
310 |
+
},
|
311 |
+
{
|
312 |
+
"epoch": 1.27,
|
313 |
+
"learning_rate": 6.220332985710936e-06,
|
314 |
+
"loss": 1.3582,
|
315 |
+
"step": 51
|
316 |
+
},
|
317 |
+
{
|
318 |
+
"epoch": 1.3,
|
319 |
+
"learning_rate": 5.845849869981137e-06,
|
320 |
+
"loss": 1.3942,
|
321 |
+
"step": 52
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 1.32,
|
325 |
+
"learning_rate": 5.478280927173145e-06,
|
326 |
+
"loss": 1.4468,
|
327 |
+
"step": 53
|
328 |
+
},
|
329 |
+
{
|
330 |
+
"epoch": 1.35,
|
331 |
+
"learning_rate": 5.11823793951719e-06,
|
332 |
+
"loss": 1.3877,
|
333 |
+
"step": 54
|
334 |
+
},
|
335 |
+
{
|
336 |
+
"epoch": 1.37,
|
337 |
+
"learning_rate": 4.766320163033882e-06,
|
338 |
+
"loss": 1.4887,
|
339 |
+
"step": 55
|
340 |
+
},
|
341 |
+
{
|
342 |
+
"epoch": 1.4,
|
343 |
+
"learning_rate": 4.423113330131708e-06,
|
344 |
+
"loss": 1.3755,
|
345 |
+
"step": 56
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 1.42,
|
349 |
+
"learning_rate": 4.0891886747132356e-06,
|
350 |
+
"loss": 1.3375,
|
351 |
+
"step": 57
|
352 |
+
},
|
353 |
+
{
|
354 |
+
"epoch": 1.45,
|
355 |
+
"learning_rate": 3.7651019814126656e-06,
|
356 |
+
"loss": 1.3972,
|
357 |
+
"step": 58
|
358 |
+
},
|
359 |
+
{
|
360 |
+
"epoch": 1.47,
|
361 |
+
"learning_rate": 3.4513926605471504e-06,
|
362 |
+
"loss": 1.4204,
|
363 |
+
"step": 59
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 1.5,
|
367 |
+
"learning_rate": 3.1485828503215588e-06,
|
368 |
+
"loss": 1.4541,
|
369 |
+
"step": 60
|
370 |
+
},
|
371 |
+
{
|
372 |
+
"epoch": 1.52,
|
373 |
+
"learning_rate": 2.8571765477809645e-06,
|
374 |
+
"loss": 1.4123,
|
375 |
+
"step": 61
|
376 |
+
},
|
377 |
+
{
|
378 |
+
"epoch": 1.55,
|
379 |
+
"learning_rate": 2.5776587699573007e-06,
|
380 |
+
"loss": 1.3873,
|
381 |
+
"step": 62
|
382 |
+
},
|
383 |
+
{
|
384 |
+
"epoch": 1.57,
|
385 |
+
"learning_rate": 2.3104947466063785e-06,
|
386 |
+
"loss": 1.4418,
|
387 |
+
"step": 63
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 1.6,
|
391 |
+
"learning_rate": 2.0561291458788736e-06,
|
392 |
+
"loss": 1.4231,
|
393 |
+
"step": 64
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 1.62,
|
397 |
+
"learning_rate": 1.8149853342140644e-06,
|
398 |
+
"loss": 1.3752,
|
399 |
+
"step": 65
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 1.64,
|
403 |
+
"learning_rate": 1.587464671688187e-06,
|
404 |
+
"loss": 1.4395,
|
405 |
+
"step": 66
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 1.67,
|
409 |
+
"learning_rate": 1.373945843990192e-06,
|
410 |
+
"loss": 1.3792,
|
411 |
+
"step": 67
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 1.69,
|
415 |
+
"learning_rate": 1.1747842321367886e-06,
|
416 |
+
"loss": 1.4226,
|
417 |
+
"step": 68
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 1.72,
|
421 |
+
"learning_rate": 9.903113209758098e-07,
|
422 |
+
"loss": 1.4125,
|
423 |
+
"step": 69
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 1.74,
|
427 |
+
"learning_rate": 8.208341474624071e-07,
|
428 |
+
"loss": 1.4429,
|
429 |
+
"step": 70
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 1.77,
|
433 |
+
"learning_rate": 6.666347896263326e-07,
|
434 |
+
"loss": 1.3913,
|
435 |
+
"step": 71
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 1.79,
|
439 |
+
"learning_rate": 5.279698970809011e-07,
|
440 |
+
"loss": 1.4418,
|
441 |
+
"step": 72
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 1.82,
|
445 |
+
"learning_rate": 4.0507026385502747e-07,
|
446 |
+
"loss": 1.3814,
|
447 |
+
"step": 73
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 1.84,
|
451 |
+
"learning_rate": 2.9814044425935605e-07,
|
452 |
+
"loss": 1.4249,
|
453 |
+
"step": 74
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 1.87,
|
457 |
+
"learning_rate": 2.0735841242578992e-07,
|
458 |
+
"loss": 1.4325,
|
459 |
+
"step": 75
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 1.89,
|
463 |
+
"learning_rate": 1.3287526608711132e-07,
|
464 |
+
"loss": 1.4635,
|
465 |
+
"step": 76
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 1.92,
|
469 |
+
"learning_rate": 7.481497508972313e-08,
|
470 |
+
"loss": 1.4079,
|
471 |
+
"step": 77
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 1.94,
|
475 |
+
"learning_rate": 3.327417505806785e-08,
|
476 |
+
"loss": 1.3911,
|
477 |
+
"step": 78
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 1.97,
|
481 |
+
"learning_rate": 8.322006554171147e-09,
|
482 |
+
"loss": 1.4636,
|
483 |
+
"step": 79
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 1.99,
|
487 |
+
"learning_rate": 0.0,
|
488 |
+
"loss": 1.318,
|
489 |
+
"step": 80
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 1.99,
|
493 |
+
"step": 80,
|
494 |
+
"total_flos": 2166787537108992.0,
|
495 |
+
"train_loss": 1.5083298146724702,
|
496 |
+
"train_runtime": 64.7879,
|
497 |
+
"train_samples_per_second": 158.363,
|
498 |
+
"train_steps_per_second": 1.235
|
499 |
+
}
|
500 |
+
],
|
501 |
+
"logging_steps": 1.0,
|
502 |
+
"max_steps": 80,
|
503 |
+
"num_train_epochs": 2,
|
504 |
+
"save_steps": 500,
|
505 |
+
"total_flos": 2166787537108992.0,
|
506 |
+
"trial_name": null,
|
507 |
+
"trial_params": null
|
508 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:082e873c248b34927ced198ecd6675020270ce444f6603b2587bdb406f2e4ee3
|
3 |
+
size 4600
|