ramdhanfirdaus
commited on
Commit
•
68249f1
1
Parent(s):
9e22210
Training in progress, step 1000, checkpoint
Browse files
last-checkpoint/adapter_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50349441
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f43f1a6738f983616ef9181d252b9c12dd97bc40630e3faed7808619f6f0274
|
3 |
size 50349441
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 100693001
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eba013c6a23ae64f89bf510557c06c2a3eb39e5a9106660abb711cded9be9dda
|
3 |
size 100693001
|
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 sha256:367394aed610ff7068eaf27da3eb89a6cd4769f26c2abeadffb65a7a6d3952cd
|
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 sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
|
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": 0.
|
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,
|
@@ -133,13 +133,27 @@
|
|
133 |
"eval_samples_per_second": 43.55,
|
134 |
"eval_steps_per_second": 5.449,
|
135 |
"step": 900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 100,
|
139 |
"max_steps": 4116,
|
140 |
"num_train_epochs": 3,
|
141 |
"save_steps": 100,
|
142 |
-
"total_flos": 5.
|
143 |
"trial_name": null,
|
144 |
"trial_params": null
|
145 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.6352009773254395,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1000",
|
4 |
+
"epoch": 0.7285974499089253,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"eval_samples_per_second": 43.55,
|
134 |
"eval_steps_per_second": 5.449,
|
135 |
"step": 900
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.73,
|
139 |
+
"learning_rate": 0.0002,
|
140 |
+
"loss": 1.6469,
|
141 |
+
"step": 1000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.73,
|
145 |
+
"eval_loss": 1.6352009773254395,
|
146 |
+
"eval_runtime": 144.0664,
|
147 |
+
"eval_samples_per_second": 43.549,
|
148 |
+
"eval_steps_per_second": 5.449,
|
149 |
+
"step": 1000
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 100,
|
153 |
"max_steps": 4116,
|
154 |
"num_train_epochs": 3,
|
155 |
"save_steps": 100,
|
156 |
+
"total_flos": 5.962359246697267e+16,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
159 |
}
|