Training in progress, step 20, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/rng_state_4.pth +1 -1
- last-checkpoint/rng_state_5.pth +1 -1
- last-checkpoint/rng_state_6.pth +1 -1
- last-checkpoint/rng_state_7.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +47 -4
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50624
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44caaf7ef7e33ddb52bdac5c015394aad33dc90cebb3fd594f8f17485acdc313
|
3 |
size 50624
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 111142
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac022dbb3fc2d99a24d41479434566b8564cc2d853b691e27319d1227d89ee6e
|
3 |
size 111142
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:208c51ec2766c73fe42741b329e4379bc0b0f1175f703ac486a32838bf514b13
|
3 |
size 15984
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e1bff8b595773356fdc187f56d5a0c0121d69fdacf1e76950fba64dacfd5fc3
|
3 |
size 15984
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b8c9e9e3a6b690529f7d95e945c2b416648318213cfc38263c918379e5990e2
|
3 |
size 15984
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eb7fbfe916e55d37e1bd35f58e8ece0a1823cf09f502145e19e13903c1c78ef
|
3 |
size 15984
|
last-checkpoint/rng_state_4.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:829f7d98c51d3dce78cbe15c038b6184a0ffadc9bc4e660d07cdee375d9e34c1
|
3 |
size 15984
|
last-checkpoint/rng_state_5.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7ede1fa0bb4fcf80064a832977f960fd7cf29d0059e918b0611ce520d7d52de
|
3 |
size 15984
|
last-checkpoint/rng_state_6.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbe41f49e8a4d0757f45695e57ded169e0314da0412d34517669df2113c9304c
|
3 |
size 15984
|
last-checkpoint/rng_state_7.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed52cd9a3377c33a6718ff5e7c1e8c573d9b4931bb139825840f14ccdc01ba5b
|
3 |
size 15984
|
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 sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -144,6 +144,49 @@
|
|
144 |
"eval_samples_per_second": 796.022,
|
145 |
"eval_steps_per_second": 99.936,
|
146 |
"step": 15
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
147 |
}
|
148 |
],
|
149 |
"logging_steps": 1,
|
@@ -158,12 +201,12 @@
|
|
158 |
"should_evaluate": false,
|
159 |
"should_log": false,
|
160 |
"should_save": true,
|
161 |
-
"should_training_stop":
|
162 |
},
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
-
"total_flos":
|
167 |
"train_batch_size": 1,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.11747430249632893,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
144 |
"eval_samples_per_second": 796.022,
|
145 |
"eval_steps_per_second": 99.936,
|
146 |
"step": 15
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 0.09397944199706314,
|
150 |
+
"grad_norm": 0.07468053698539734,
|
151 |
+
"learning_rate": 3.4549150281252636e-05,
|
152 |
+
"loss": 10.3794,
|
153 |
+
"step": 16
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.09985315712187959,
|
157 |
+
"grad_norm": 0.07500291615724564,
|
158 |
+
"learning_rate": 2.061073738537635e-05,
|
159 |
+
"loss": 10.3783,
|
160 |
+
"step": 17
|
161 |
+
},
|
162 |
+
{
|
163 |
+
"epoch": 0.10572687224669604,
|
164 |
+
"grad_norm": 0.07731679826974869,
|
165 |
+
"learning_rate": 9.549150281252633e-06,
|
166 |
+
"loss": 10.3793,
|
167 |
+
"step": 18
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.11160058737151249,
|
171 |
+
"grad_norm": 0.07920215278863907,
|
172 |
+
"learning_rate": 2.4471741852423237e-06,
|
173 |
+
"loss": 10.3792,
|
174 |
+
"step": 19
|
175 |
+
},
|
176 |
+
{
|
177 |
+
"epoch": 0.11747430249632893,
|
178 |
+
"grad_norm": 0.07347231358289719,
|
179 |
+
"learning_rate": 0.0,
|
180 |
+
"loss": 10.3791,
|
181 |
+
"step": 20
|
182 |
+
},
|
183 |
+
{
|
184 |
+
"epoch": 0.11747430249632893,
|
185 |
+
"eval_loss": NaN,
|
186 |
+
"eval_runtime": 1.4584,
|
187 |
+
"eval_samples_per_second": 786.475,
|
188 |
+
"eval_steps_per_second": 98.738,
|
189 |
+
"step": 20
|
190 |
}
|
191 |
],
|
192 |
"logging_steps": 1,
|
|
|
201 |
"should_evaluate": false,
|
202 |
"should_log": false,
|
203 |
"should_save": true,
|
204 |
+
"should_training_stop": true
|
205 |
},
|
206 |
"attributes": {}
|
207 |
}
|
208 |
},
|
209 |
+
"total_flos": 33473565818880.0,
|
210 |
"train_batch_size": 1,
|
211 |
"trial_name": null,
|
212 |
"trial_params": null
|