Training in progress, step 25, 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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5992a86747cef14f63762668b2ac2fbf9e23ce5e8bb74133abf9d11c202cc4f4
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c1e8f5f88992d2a779e848ba59169c2a7ac5ded2dac15a4d2e66d46ef348edf
|
3 |
size 43122580
|
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:cc695d50fa9c7a7b39e7508c0827b13b4400b02508b8aa483545d12dba8b4308
|
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 sha256:7cbe95d5ecd33771846042e20aabf210775f4e6a78ced16f0764898d40abeba5
|
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": 34,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -155,6 +155,41 @@
|
|
155 |
"learning_rate": 0.00013333333333333334,
|
156 |
"loss": 1.1023,
|
157 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
158 |
}
|
159 |
],
|
160 |
"logging_steps": 1,
|
@@ -174,7 +209,7 @@
|
|
174 |
"attributes": {}
|
175 |
}
|
176 |
},
|
177 |
-
"total_flos":
|
178 |
"train_batch_size": 3,
|
179 |
"trial_name": null,
|
180 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.012225686166636102,
|
5 |
"eval_steps": 34,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
155 |
"learning_rate": 0.00013333333333333334,
|
156 |
"loss": 1.1023,
|
157 |
"step": 20
|
158 |
+
},
|
159 |
+
{
|
160 |
+
"epoch": 0.010269576379974325,
|
161 |
+
"grad_norm": 0.4289817214012146,
|
162 |
+
"learning_rate": 0.00014,
|
163 |
+
"loss": 1.0195,
|
164 |
+
"step": 21
|
165 |
+
},
|
166 |
+
{
|
167 |
+
"epoch": 0.01075860382663977,
|
168 |
+
"grad_norm": 1.290226936340332,
|
169 |
+
"learning_rate": 0.00014666666666666666,
|
170 |
+
"loss": 0.9534,
|
171 |
+
"step": 22
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.011247631273305215,
|
175 |
+
"grad_norm": 0.5022335648536682,
|
176 |
+
"learning_rate": 0.00015333333333333334,
|
177 |
+
"loss": 0.8952,
|
178 |
+
"step": 23
|
179 |
+
},
|
180 |
+
{
|
181 |
+
"epoch": 0.011736658719970658,
|
182 |
+
"grad_norm": 0.5421992540359497,
|
183 |
+
"learning_rate": 0.00016,
|
184 |
+
"loss": 0.8553,
|
185 |
+
"step": 24
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.012225686166636102,
|
189 |
+
"grad_norm": 1.568458080291748,
|
190 |
+
"learning_rate": 0.0001666666666666667,
|
191 |
+
"loss": 0.9764,
|
192 |
+
"step": 25
|
193 |
}
|
194 |
],
|
195 |
"logging_steps": 1,
|
|
|
209 |
"attributes": {}
|
210 |
}
|
211 |
},
|
212 |
+
"total_flos": 1.109738548887552e+17,
|
213 |
"train_batch_size": 3,
|
214 |
"trial_name": null,
|
215 |
"trial_params": null
|