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 12595704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed11fb73cc04a87e68ded9633b47c1fde2d5bffc0acfb5a17aa3f594a897d0f8
|
3 |
size 12595704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25222341
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5315835fda300944b9c2ae9cb8438dcb2dde6b6885ee28fcdfb592464903f02d
|
3 |
size 25222341
|
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 sha256:28bd09398ec9af0456a9ee14166cd961943ffc74000ebb4c1108e377da2d32df
|
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": 1.
|
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": 10.297,
|
232 |
"eval_steps_per_second": 1.291,
|
233 |
"step": 1600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 100,
|
@@ -238,7 +252,7 @@
|
|
238 |
"num_input_tokens_seen": 0,
|
239 |
"num_train_epochs": 3,
|
240 |
"save_steps": 100,
|
241 |
-
"total_flos": 2.
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
244 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0760257244110107,
|
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": 10.297,
|
232 |
"eval_steps_per_second": 1.291,
|
233 |
"step": 1600
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 2.27,
|
237 |
+
"learning_rate": 0.0002,
|
238 |
+
"loss": 0.9306,
|
239 |
+
"step": 1700
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 2.27,
|
243 |
+
"eval_loss": 1.0760257244110107,
|
244 |
+
"eval_runtime": 186.9978,
|
245 |
+
"eval_samples_per_second": 10.321,
|
246 |
+
"eval_steps_per_second": 1.294,
|
247 |
+
"step": 1700
|
248 |
}
|
249 |
],
|
250 |
"logging_steps": 100,
|
|
|
252 |
"num_input_tokens_seen": 0,
|
253 |
"num_train_epochs": 3,
|
254 |
"save_steps": 100,
|
255 |
+
"total_flos": 2.403652458643538e+17,
|
256 |
"trial_name": null,
|
257 |
"trial_params": null
|
258 |
}
|