Training in progress, step 54, 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 338298
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2f2971439d88f6db0bc8827138b0e15bf7514b74aa28fdbbe00e3b10f7a2248
|
3 |
size 338298
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 418030
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88254e9b0975f5d59302c648d167fdb1882638b5516bfcd2a47b8961fa05da7b
|
3 |
size 418030
|
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 sha256:4dbb97c11c6f1318074260e982b59a91d8a5584bd279926c1beca30dfe95c3f0
|
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 sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -160,6 +160,35 @@
|
|
160 |
"eval_samples_per_second": 604.065,
|
161 |
"eval_steps_per_second": 153.762,
|
162 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
@@ -179,7 +208,7 @@
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
-
"total_flos":
|
183 |
"train_batch_size": 4,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.2755102040816326,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 54,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
160 |
"eval_samples_per_second": 604.065,
|
161 |
"eval_steps_per_second": 153.762,
|
162 |
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.24489795918367346,
|
166 |
+
"grad_norm": 0.25101956725120544,
|
167 |
+
"learning_rate": 6.209609477998338e-05,
|
168 |
+
"loss": 6.8369,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.2602040816326531,
|
173 |
+
"grad_norm": 0.21246355772018433,
|
174 |
+
"learning_rate": 5.695865504800327e-05,
|
175 |
+
"loss": 6.8376,
|
176 |
+
"step": 51
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.2755102040816326,
|
180 |
+
"grad_norm": 0.20616650581359863,
|
181 |
+
"learning_rate": 5.174497483512506e-05,
|
182 |
+
"loss": 6.8328,
|
183 |
+
"step": 54
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.2755102040816326,
|
187 |
+
"eval_loss": 6.832831859588623,
|
188 |
+
"eval_runtime": 0.2703,
|
189 |
+
"eval_samples_per_second": 610.543,
|
190 |
+
"eval_steps_per_second": 155.411,
|
191 |
+
"step": 54
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
+
"total_flos": 519009140736.0,
|
212 |
"train_batch_size": 4,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|