Training in progress, step 84, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201892112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:121983274dff80eb5f14c755257724700d2d56e115cc300d0316f914d3cb7dee
|
3 |
size 201892112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 102864548
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d5e2df5660b367f6f036c08934da668f1270a0be7f47fa9b46e2cae168bcf555
|
3 |
size 102864548
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7074cec2061417cedcea0f1edca671f4979b23051157d7011cc5e12489f9fe90
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2df224011d0e75c4a97901f6c1b2930bba4bc3a9aa7c877e6c91e796bec6013f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 42,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -121,6 +121,112 @@
|
|
121 |
"eval_samples_per_second": 48.697,
|
122 |
"eval_steps_per_second": 6.091,
|
123 |
"step": 42
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
124 |
}
|
125 |
],
|
126 |
"logging_steps": 3,
|
@@ -140,7 +246,7 @@
|
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
-
"total_flos":
|
144 |
"train_batch_size": 8,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.01760821716801174,
|
5 |
"eval_steps": 42,
|
6 |
+
"global_step": 84,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
121 |
"eval_samples_per_second": 48.697,
|
122 |
"eval_steps_per_second": 6.091,
|
123 |
"step": 42
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.009432973482863432,
|
127 |
+
"grad_norm": 0.30218949913978577,
|
128 |
+
"learning_rate": 9.874639560909117e-05,
|
129 |
+
"loss": 1.1916,
|
130 |
+
"step": 45
|
131 |
+
},
|
132 |
+
{
|
133 |
+
"epoch": 0.010061838381720993,
|
134 |
+
"grad_norm": 0.3343711197376251,
|
135 |
+
"learning_rate": 9.852339101019574e-05,
|
136 |
+
"loss": 1.1487,
|
137 |
+
"step": 48
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.010690703280578556,
|
141 |
+
"grad_norm": 0.3268805146217346,
|
142 |
+
"learning_rate": 9.828243544427796e-05,
|
143 |
+
"loss": 1.1781,
|
144 |
+
"step": 51
|
145 |
+
},
|
146 |
+
{
|
147 |
+
"epoch": 0.011319568179436117,
|
148 |
+
"grad_norm": 0.34138286113739014,
|
149 |
+
"learning_rate": 9.802361805155097e-05,
|
150 |
+
"loss": 1.1215,
|
151 |
+
"step": 54
|
152 |
+
},
|
153 |
+
{
|
154 |
+
"epoch": 0.01194843307829368,
|
155 |
+
"grad_norm": 0.3412030339241028,
|
156 |
+
"learning_rate": 9.774703458011453e-05,
|
157 |
+
"loss": 1.2044,
|
158 |
+
"step": 57
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.012577297977151241,
|
162 |
+
"grad_norm": 0.3168179392814636,
|
163 |
+
"learning_rate": 9.745278735053343e-05,
|
164 |
+
"loss": 1.1087,
|
165 |
+
"step": 60
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.013206162876008804,
|
169 |
+
"grad_norm": 0.3409186005592346,
|
170 |
+
"learning_rate": 9.714098521798465e-05,
|
171 |
+
"loss": 1.2062,
|
172 |
+
"step": 63
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.013835027774866367,
|
176 |
+
"grad_norm": 0.29721856117248535,
|
177 |
+
"learning_rate": 9.681174353198687e-05,
|
178 |
+
"loss": 1.1158,
|
179 |
+
"step": 66
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.014463892673723928,
|
183 |
+
"grad_norm": 0.3369769752025604,
|
184 |
+
"learning_rate": 9.64651840937276e-05,
|
185 |
+
"loss": 1.1834,
|
186 |
+
"step": 69
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.015092757572581491,
|
190 |
+
"grad_norm": 0.31268638372421265,
|
191 |
+
"learning_rate": 9.610143511100354e-05,
|
192 |
+
"loss": 1.1367,
|
193 |
+
"step": 72
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.015721622471439052,
|
197 |
+
"grad_norm": 0.333360493183136,
|
198 |
+
"learning_rate": 9.572063115079063e-05,
|
199 |
+
"loss": 1.1805,
|
200 |
+
"step": 75
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.016350487370296613,
|
204 |
+
"grad_norm": 0.2951726019382477,
|
205 |
+
"learning_rate": 9.53229130894619e-05,
|
206 |
+
"loss": 1.1459,
|
207 |
+
"step": 78
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.016979352269154178,
|
211 |
+
"grad_norm": 0.36082521080970764,
|
212 |
+
"learning_rate": 9.490842806067095e-05,
|
213 |
+
"loss": 1.17,
|
214 |
+
"step": 81
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.01760821716801174,
|
218 |
+
"grad_norm": 0.33050239086151123,
|
219 |
+
"learning_rate": 9.44773294009206e-05,
|
220 |
+
"loss": 1.1611,
|
221 |
+
"step": 84
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.01760821716801174,
|
225 |
+
"eval_loss": 1.147385835647583,
|
226 |
+
"eval_runtime": 165.0588,
|
227 |
+
"eval_samples_per_second": 48.68,
|
228 |
+
"eval_steps_per_second": 6.089,
|
229 |
+
"step": 84
|
230 |
}
|
231 |
],
|
232 |
"logging_steps": 3,
|
|
|
246 |
"attributes": {}
|
247 |
}
|
248 |
},
|
249 |
+
"total_flos": 1.7918441960767488e+16,
|
250 |
"train_batch_size": 8,
|
251 |
"trial_name": null,
|
252 |
"trial_params": null
|