Upload folder using huggingface_hub
Browse files- checkpoint-82/README.md +3 -0
- checkpoint-82/adapter_config.json +25 -0
- checkpoint-82/adapter_model.bin +3 -0
- checkpoint-82/adapter_model/README.md +3 -0
- checkpoint-82/adapter_model/adapter_config.json +25 -0
- checkpoint-82/adapter_model/adapter_model.bin +3 -0
- checkpoint-82/optimizer.pt +3 -0
- checkpoint-82/rng_state.pth +3 -0
- checkpoint-82/scheduler.pt +3 -0
- checkpoint-82/trainer_state.json +508 -0
- checkpoint-82/training_args.bin +3 -0
checkpoint-82/README.md
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
checkpoint-82/adapter_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"layers_pattern": null,
|
8 |
+
"layers_to_transform": null,
|
9 |
+
"lora_alpha": 32,
|
10 |
+
"lora_dropout": 0.05,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 32,
|
14 |
+
"revision": null,
|
15 |
+
"target_modules": [
|
16 |
+
"gate_proj",
|
17 |
+
"down_proj",
|
18 |
+
"up_proj",
|
19 |
+
"q_proj",
|
20 |
+
"k_proj",
|
21 |
+
"v_proj",
|
22 |
+
"o_proj"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM"
|
25 |
+
}
|
checkpoint-82/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7adc25244b4b04d9d6c139d7fabe4cec27274717891b14dda70d4b5805bb96cc
|
3 |
+
size 319977674
|
checkpoint-82/adapter_model/README.md
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
checkpoint-82/adapter_model/adapter_config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
3 |
+
"bias": "none",
|
4 |
+
"fan_in_fan_out": false,
|
5 |
+
"inference_mode": true,
|
6 |
+
"init_lora_weights": true,
|
7 |
+
"layers_pattern": null,
|
8 |
+
"layers_to_transform": null,
|
9 |
+
"lora_alpha": 32,
|
10 |
+
"lora_dropout": 0.05,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 32,
|
14 |
+
"revision": null,
|
15 |
+
"target_modules": [
|
16 |
+
"gate_proj",
|
17 |
+
"down_proj",
|
18 |
+
"up_proj",
|
19 |
+
"q_proj",
|
20 |
+
"k_proj",
|
21 |
+
"v_proj",
|
22 |
+
"o_proj"
|
23 |
+
],
|
24 |
+
"task_type": "CAUSAL_LM"
|
25 |
+
}
|
checkpoint-82/adapter_model/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7adc25244b4b04d9d6c139d7fabe4cec27274717891b14dda70d4b5805bb96cc
|
3 |
+
size 319977674
|
checkpoint-82/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:859b1e110dc876145212ec16cc5bba13e006efd050580e94bc43c4a871d84347
|
3 |
+
size 160746900
|
checkpoint-82/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:548fd04fdafadc502a0e0ca671ae5dac348646e7d4df711d16ce8a07a0a72e9d
|
3 |
+
size 14244
|
checkpoint-82/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a075607e40fb706be8a51c6ba66ff9d2760a6896810c5223b22b6ab00bd62a0
|
3 |
+
size 1064
|
checkpoint-82/trainer_state.json
ADDED
@@ -0,0 +1,508 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9106796116504854,
|
5 |
+
"global_step": 82,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.02,
|
12 |
+
"learning_rate": 2.631578947368421e-06,
|
13 |
+
"loss": 1.9044,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.05,
|
18 |
+
"learning_rate": 5.263157894736842e-06,
|
19 |
+
"loss": 2.018,
|
20 |
+
"step": 2
|
21 |
+
},
|
22 |
+
{
|
23 |
+
"epoch": 0.07,
|
24 |
+
"learning_rate": 7.894736842105263e-06,
|
25 |
+
"loss": 2.0221,
|
26 |
+
"step": 3
|
27 |
+
},
|
28 |
+
{
|
29 |
+
"epoch": 0.09,
|
30 |
+
"learning_rate": 1.0526315789473684e-05,
|
31 |
+
"loss": 1.8884,
|
32 |
+
"step": 4
|
33 |
+
},
|
34 |
+
{
|
35 |
+
"epoch": 0.12,
|
36 |
+
"learning_rate": 1.3157894736842106e-05,
|
37 |
+
"loss": 1.9326,
|
38 |
+
"step": 5
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.14,
|
42 |
+
"learning_rate": 1.5789473684210526e-05,
|
43 |
+
"loss": 2.1193,
|
44 |
+
"step": 6
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.16,
|
48 |
+
"learning_rate": 1.8421052631578947e-05,
|
49 |
+
"loss": 2.0827,
|
50 |
+
"step": 7
|
51 |
+
},
|
52 |
+
{
|
53 |
+
"epoch": 0.19,
|
54 |
+
"learning_rate": 2.105263157894737e-05,
|
55 |
+
"loss": 1.8846,
|
56 |
+
"step": 8
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"epoch": 0.21,
|
60 |
+
"learning_rate": 2.368421052631579e-05,
|
61 |
+
"loss": 2.0943,
|
62 |
+
"step": 9
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.23,
|
66 |
+
"learning_rate": 2.6315789473684212e-05,
|
67 |
+
"loss": 2.0881,
|
68 |
+
"step": 10
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.26,
|
72 |
+
"learning_rate": 2.8947368421052634e-05,
|
73 |
+
"loss": 1.9275,
|
74 |
+
"step": 11
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.28,
|
78 |
+
"learning_rate": 3.157894736842105e-05,
|
79 |
+
"loss": 1.6874,
|
80 |
+
"step": 12
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.3,
|
84 |
+
"learning_rate": 3.421052631578947e-05,
|
85 |
+
"loss": 1.9874,
|
86 |
+
"step": 13
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.33,
|
90 |
+
"learning_rate": 3.6842105263157895e-05,
|
91 |
+
"loss": 1.8901,
|
92 |
+
"step": 14
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 0.35,
|
96 |
+
"learning_rate": 3.9473684210526316e-05,
|
97 |
+
"loss": 1.7683,
|
98 |
+
"step": 15
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.37,
|
102 |
+
"learning_rate": 4.210526315789474e-05,
|
103 |
+
"loss": 2.0108,
|
104 |
+
"step": 16
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.4,
|
108 |
+
"learning_rate": 4.473684210526316e-05,
|
109 |
+
"loss": 1.6579,
|
110 |
+
"step": 17
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 0.42,
|
114 |
+
"learning_rate": 4.736842105263158e-05,
|
115 |
+
"loss": 1.9758,
|
116 |
+
"step": 18
|
117 |
+
},
|
118 |
+
{
|
119 |
+
"epoch": 0.44,
|
120 |
+
"learning_rate": 5e-05,
|
121 |
+
"loss": 1.9118,
|
122 |
+
"step": 19
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 0.47,
|
126 |
+
"learning_rate": 5.2631578947368424e-05,
|
127 |
+
"loss": 1.8964,
|
128 |
+
"step": 20
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.49,
|
132 |
+
"learning_rate": 5.526315789473685e-05,
|
133 |
+
"loss": 1.9288,
|
134 |
+
"step": 21
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.51,
|
138 |
+
"learning_rate": 5.789473684210527e-05,
|
139 |
+
"loss": 1.8706,
|
140 |
+
"step": 22
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 0.54,
|
144 |
+
"learning_rate": 6.052631578947369e-05,
|
145 |
+
"loss": 1.8604,
|
146 |
+
"step": 23
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.56,
|
150 |
+
"learning_rate": 6.31578947368421e-05,
|
151 |
+
"loss": 1.9001,
|
152 |
+
"step": 24
|
153 |
+
},
|
154 |
+
{
|
155 |
+
"epoch": 0.58,
|
156 |
+
"learning_rate": 6.578947368421054e-05,
|
157 |
+
"loss": 1.8254,
|
158 |
+
"step": 25
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.61,
|
162 |
+
"learning_rate": 6.842105263157895e-05,
|
163 |
+
"loss": 1.8111,
|
164 |
+
"step": 26
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.63,
|
168 |
+
"learning_rate": 7.105263157894737e-05,
|
169 |
+
"loss": 1.7496,
|
170 |
+
"step": 27
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 0.65,
|
174 |
+
"learning_rate": 7.368421052631579e-05,
|
175 |
+
"loss": 1.7604,
|
176 |
+
"step": 28
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.68,
|
180 |
+
"learning_rate": 7.631578947368422e-05,
|
181 |
+
"loss": 1.6285,
|
182 |
+
"step": 29
|
183 |
+
},
|
184 |
+
{
|
185 |
+
"epoch": 0.7,
|
186 |
+
"learning_rate": 7.894736842105263e-05,
|
187 |
+
"loss": 1.7226,
|
188 |
+
"step": 30
|
189 |
+
},
|
190 |
+
{
|
191 |
+
"epoch": 0.72,
|
192 |
+
"learning_rate": 8.157894736842105e-05,
|
193 |
+
"loss": 1.9689,
|
194 |
+
"step": 31
|
195 |
+
},
|
196 |
+
{
|
197 |
+
"epoch": 0.75,
|
198 |
+
"learning_rate": 8.421052631578948e-05,
|
199 |
+
"loss": 1.7737,
|
200 |
+
"step": 32
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.77,
|
204 |
+
"learning_rate": 8.68421052631579e-05,
|
205 |
+
"loss": 1.8093,
|
206 |
+
"step": 33
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 0.79,
|
210 |
+
"learning_rate": 8.947368421052632e-05,
|
211 |
+
"loss": 1.6292,
|
212 |
+
"step": 34
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 0.82,
|
216 |
+
"learning_rate": 9.210526315789474e-05,
|
217 |
+
"loss": 1.8351,
|
218 |
+
"step": 35
|
219 |
+
},
|
220 |
+
{
|
221 |
+
"epoch": 0.84,
|
222 |
+
"learning_rate": 9.473684210526316e-05,
|
223 |
+
"loss": 1.918,
|
224 |
+
"step": 36
|
225 |
+
},
|
226 |
+
{
|
227 |
+
"epoch": 0.86,
|
228 |
+
"learning_rate": 9.736842105263158e-05,
|
229 |
+
"loss": 1.8161,
|
230 |
+
"step": 37
|
231 |
+
},
|
232 |
+
{
|
233 |
+
"epoch": 0.89,
|
234 |
+
"learning_rate": 0.0001,
|
235 |
+
"loss": 1.8184,
|
236 |
+
"step": 38
|
237 |
+
},
|
238 |
+
{
|
239 |
+
"epoch": 0.91,
|
240 |
+
"learning_rate": 9.983108108108109e-05,
|
241 |
+
"loss": 1.5839,
|
242 |
+
"step": 39
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.93,
|
246 |
+
"learning_rate": 9.966216216216217e-05,
|
247 |
+
"loss": 1.8736,
|
248 |
+
"step": 40
|
249 |
+
},
|
250 |
+
{
|
251 |
+
"epoch": 0.96,
|
252 |
+
"learning_rate": 9.949324324324325e-05,
|
253 |
+
"loss": 1.77,
|
254 |
+
"step": 41
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 0.98,
|
258 |
+
"learning_rate": 9.932432432432433e-05,
|
259 |
+
"loss": 1.7912,
|
260 |
+
"step": 42
|
261 |
+
},
|
262 |
+
{
|
263 |
+
"epoch": 1.0,
|
264 |
+
"learning_rate": 9.915540540540541e-05,
|
265 |
+
"loss": 1.6989,
|
266 |
+
"step": 43
|
267 |
+
},
|
268 |
+
{
|
269 |
+
"epoch": 1.03,
|
270 |
+
"learning_rate": 9.89864864864865e-05,
|
271 |
+
"loss": 1.7327,
|
272 |
+
"step": 44
|
273 |
+
},
|
274 |
+
{
|
275 |
+
"epoch": 1.05,
|
276 |
+
"learning_rate": 9.881756756756757e-05,
|
277 |
+
"loss": 1.7799,
|
278 |
+
"step": 45
|
279 |
+
},
|
280 |
+
{
|
281 |
+
"epoch": 1.07,
|
282 |
+
"learning_rate": 9.864864864864865e-05,
|
283 |
+
"loss": 1.8298,
|
284 |
+
"step": 46
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 1.1,
|
288 |
+
"learning_rate": 9.847972972972973e-05,
|
289 |
+
"loss": 1.8616,
|
290 |
+
"step": 47
|
291 |
+
},
|
292 |
+
{
|
293 |
+
"epoch": 1.12,
|
294 |
+
"learning_rate": 9.831081081081081e-05,
|
295 |
+
"loss": 1.7984,
|
296 |
+
"step": 48
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 1.14,
|
300 |
+
"learning_rate": 9.81418918918919e-05,
|
301 |
+
"loss": 1.7626,
|
302 |
+
"step": 49
|
303 |
+
},
|
304 |
+
{
|
305 |
+
"epoch": 1.17,
|
306 |
+
"learning_rate": 9.797297297297297e-05,
|
307 |
+
"loss": 1.8424,
|
308 |
+
"step": 50
|
309 |
+
},
|
310 |
+
{
|
311 |
+
"epoch": 1.19,
|
312 |
+
"learning_rate": 9.780405405405407e-05,
|
313 |
+
"loss": 1.6436,
|
314 |
+
"step": 51
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 1.21,
|
318 |
+
"learning_rate": 9.763513513513513e-05,
|
319 |
+
"loss": 1.6303,
|
320 |
+
"step": 52
|
321 |
+
},
|
322 |
+
{
|
323 |
+
"epoch": 1.23,
|
324 |
+
"learning_rate": 9.746621621621623e-05,
|
325 |
+
"loss": 1.7199,
|
326 |
+
"step": 53
|
327 |
+
},
|
328 |
+
{
|
329 |
+
"epoch": 1.26,
|
330 |
+
"learning_rate": 9.729729729729731e-05,
|
331 |
+
"loss": 1.6789,
|
332 |
+
"step": 54
|
333 |
+
},
|
334 |
+
{
|
335 |
+
"epoch": 1.28,
|
336 |
+
"learning_rate": 9.712837837837838e-05,
|
337 |
+
"loss": 1.8519,
|
338 |
+
"step": 55
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 1.3,
|
342 |
+
"learning_rate": 9.695945945945947e-05,
|
343 |
+
"loss": 1.7961,
|
344 |
+
"step": 56
|
345 |
+
},
|
346 |
+
{
|
347 |
+
"epoch": 1.33,
|
348 |
+
"learning_rate": 9.679054054054054e-05,
|
349 |
+
"loss": 1.6725,
|
350 |
+
"step": 57
|
351 |
+
},
|
352 |
+
{
|
353 |
+
"epoch": 1.35,
|
354 |
+
"learning_rate": 9.662162162162163e-05,
|
355 |
+
"loss": 1.7249,
|
356 |
+
"step": 58
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 1.37,
|
360 |
+
"learning_rate": 9.64527027027027e-05,
|
361 |
+
"loss": 1.5996,
|
362 |
+
"step": 59
|
363 |
+
},
|
364 |
+
{
|
365 |
+
"epoch": 1.4,
|
366 |
+
"learning_rate": 9.628378378378379e-05,
|
367 |
+
"loss": 1.7033,
|
368 |
+
"step": 60
|
369 |
+
},
|
370 |
+
{
|
371 |
+
"epoch": 1.42,
|
372 |
+
"learning_rate": 9.611486486486487e-05,
|
373 |
+
"loss": 1.7387,
|
374 |
+
"step": 61
|
375 |
+
},
|
376 |
+
{
|
377 |
+
"epoch": 1.44,
|
378 |
+
"learning_rate": 9.594594594594595e-05,
|
379 |
+
"loss": 1.7804,
|
380 |
+
"step": 62
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 1.47,
|
384 |
+
"learning_rate": 9.577702702702703e-05,
|
385 |
+
"loss": 1.7484,
|
386 |
+
"step": 63
|
387 |
+
},
|
388 |
+
{
|
389 |
+
"epoch": 1.49,
|
390 |
+
"learning_rate": 9.56081081081081e-05,
|
391 |
+
"loss": 1.7526,
|
392 |
+
"step": 64
|
393 |
+
},
|
394 |
+
{
|
395 |
+
"epoch": 1.51,
|
396 |
+
"learning_rate": 9.54391891891892e-05,
|
397 |
+
"loss": 1.7247,
|
398 |
+
"step": 65
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 1.54,
|
402 |
+
"learning_rate": 9.527027027027028e-05,
|
403 |
+
"loss": 1.6276,
|
404 |
+
"step": 66
|
405 |
+
},
|
406 |
+
{
|
407 |
+
"epoch": 1.56,
|
408 |
+
"learning_rate": 9.510135135135136e-05,
|
409 |
+
"loss": 1.8279,
|
410 |
+
"step": 67
|
411 |
+
},
|
412 |
+
{
|
413 |
+
"epoch": 1.58,
|
414 |
+
"learning_rate": 9.493243243243244e-05,
|
415 |
+
"loss": 1.7067,
|
416 |
+
"step": 68
|
417 |
+
},
|
418 |
+
{
|
419 |
+
"epoch": 1.61,
|
420 |
+
"learning_rate": 9.476351351351352e-05,
|
421 |
+
"loss": 1.7865,
|
422 |
+
"step": 69
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 1.63,
|
426 |
+
"learning_rate": 9.45945945945946e-05,
|
427 |
+
"loss": 1.6693,
|
428 |
+
"step": 70
|
429 |
+
},
|
430 |
+
{
|
431 |
+
"epoch": 1.65,
|
432 |
+
"learning_rate": 9.442567567567568e-05,
|
433 |
+
"loss": 1.6939,
|
434 |
+
"step": 71
|
435 |
+
},
|
436 |
+
{
|
437 |
+
"epoch": 1.68,
|
438 |
+
"learning_rate": 9.425675675675676e-05,
|
439 |
+
"loss": 1.8667,
|
440 |
+
"step": 72
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 1.7,
|
444 |
+
"learning_rate": 9.408783783783784e-05,
|
445 |
+
"loss": 1.746,
|
446 |
+
"step": 73
|
447 |
+
},
|
448 |
+
{
|
449 |
+
"epoch": 1.72,
|
450 |
+
"learning_rate": 9.391891891891892e-05,
|
451 |
+
"loss": 1.6951,
|
452 |
+
"step": 74
|
453 |
+
},
|
454 |
+
{
|
455 |
+
"epoch": 1.75,
|
456 |
+
"learning_rate": 9.375e-05,
|
457 |
+
"loss": 1.6749,
|
458 |
+
"step": 75
|
459 |
+
},
|
460 |
+
{
|
461 |
+
"epoch": 1.77,
|
462 |
+
"learning_rate": 9.35810810810811e-05,
|
463 |
+
"loss": 1.8773,
|
464 |
+
"step": 76
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 1.79,
|
468 |
+
"learning_rate": 9.341216216216216e-05,
|
469 |
+
"loss": 1.8064,
|
470 |
+
"step": 77
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 1.82,
|
474 |
+
"learning_rate": 9.324324324324324e-05,
|
475 |
+
"loss": 1.6596,
|
476 |
+
"step": 78
|
477 |
+
},
|
478 |
+
{
|
479 |
+
"epoch": 1.84,
|
480 |
+
"learning_rate": 9.307432432432432e-05,
|
481 |
+
"loss": 1.7321,
|
482 |
+
"step": 79
|
483 |
+
},
|
484 |
+
{
|
485 |
+
"epoch": 1.86,
|
486 |
+
"learning_rate": 9.29054054054054e-05,
|
487 |
+
"loss": 1.7029,
|
488 |
+
"step": 80
|
489 |
+
},
|
490 |
+
{
|
491 |
+
"epoch": 1.89,
|
492 |
+
"learning_rate": 9.27364864864865e-05,
|
493 |
+
"loss": 1.7392,
|
494 |
+
"step": 81
|
495 |
+
},
|
496 |
+
{
|
497 |
+
"epoch": 1.91,
|
498 |
+
"learning_rate": 9.256756756756757e-05,
|
499 |
+
"loss": 1.7904,
|
500 |
+
"step": 82
|
501 |
+
}
|
502 |
+
],
|
503 |
+
"max_steps": 630,
|
504 |
+
"num_train_epochs": 15,
|
505 |
+
"total_flos": 2.959859225119949e+16,
|
506 |
+
"trial_name": null,
|
507 |
+
"trial_params": null
|
508 |
+
}
|
checkpoint-82/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba2fe107dab361c51487de4fc8c9ce45e8134a0096f693cda683706e603b37d9
|
3 |
+
size 4344
|