Training in progress, step 1600, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dcc963b9974429fbf17295871d0585952e3d747883cf04ea7c1dba83c12409d
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:253d535f3400ed76c0ab226fbcb367b601a0c99d61a8257b5061b804144b6a23
|
3 |
size 18902665
|
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:c3f14f26e1c82af1569197c946ee60a682af9d056666c7fed1d76396f3ef87dc
|
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:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 1.
|
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,
|
@@ -217,13 +217,27 @@
|
|
217 |
"eval_samples_per_second": 30.542,
|
218 |
"eval_steps_per_second": 3.821,
|
219 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
}
|
221 |
],
|
222 |
"logging_steps": 100,
|
223 |
"max_steps": 4116,
|
224 |
"num_train_epochs": 3,
|
225 |
"save_steps": 100,
|
226 |
-
"total_flos": 4.
|
227 |
"trial_name": null,
|
228 |
"trial_params": null
|
229 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.2731645107269287,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1600",
|
4 |
+
"epoch": 1.1657559198542806,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
217 |
"eval_samples_per_second": 30.542,
|
218 |
"eval_steps_per_second": 3.821,
|
219 |
"step": 1500
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 1.17,
|
223 |
+
"learning_rate": 0.0002,
|
224 |
+
"loss": 2.2532,
|
225 |
+
"step": 1600
|
226 |
+
},
|
227 |
+
{
|
228 |
+
"epoch": 1.17,
|
229 |
+
"eval_loss": 2.2731645107269287,
|
230 |
+
"eval_runtime": 205.0407,
|
231 |
+
"eval_samples_per_second": 30.599,
|
232 |
+
"eval_steps_per_second": 3.829,
|
233 |
+
"step": 1600
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 100,
|
237 |
"max_steps": 4116,
|
238 |
"num_train_epochs": 3,
|
239 |
"save_steps": 100,
|
240 |
+
"total_flos": 4.676360009803776e+16,
|
241 |
"trial_name": null,
|
242 |
"trial_params": null
|
243 |
}
|