Training in progress, step 1700, 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 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07fcc2c83afa8aef617c8c7a76e8a2d64563403585682fe54b2153efef4a4ce0
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deb1bcef585fc0d939a9e2979fe46f64f13377b8c9efad0e3e75a0a33398544e
|
3 |
size 39356997
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8041837488fe9482526415d7b12f19e2710ce8aad1458a5a111ab5868da9e865
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 2.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -231,6 +231,20 @@
|
|
231 |
"eval_samples_per_second": 2.467,
|
232 |
"eval_steps_per_second": 0.309,
|
233 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 100,
|
@@ -238,7 +252,7 @@
|
|
238 |
"num_input_tokens_seen": 0,
|
239 |
"num_train_epochs": 5,
|
240 |
"save_steps": 100,
|
241 |
-
"total_flos": 4.
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9513885378837585,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1700",
|
4 |
+
"epoch": 2.2666666666666666,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
231 |
"eval_samples_per_second": 2.467,
|
232 |
"eval_steps_per_second": 0.309,
|
233 |
"step": 1600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.27,
|
237 |
+
"learning_rate": 0.0002,
|
238 |
+
"loss": 0.7676,
|
239 |
+
"step": 1700
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 2.27,
|
243 |
+
"eval_loss": 0.9513885378837585,
|
244 |
+
"eval_runtime": 768.2363,
|
245 |
+
"eval_samples_per_second": 2.512,
|
246 |
+
"eval_steps_per_second": 0.315,
|
247 |
+
"step": 1700
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 100,
|
|
|
252 |
"num_input_tokens_seen": 0,
|
253 |
"num_train_epochs": 5,
|
254 |
"save_steps": 100,
|
255 |
+
"total_flos": 4.402578582306816e+17,
|
256 |
"trial_name": null,
|
257 |
"trial_params": null
|
258 |
}
|