Training in progress, step 2280, 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 389074464
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d130ac47ed7ae141798c2d67da12d00f8f7b9ea7cf027d56de55b3b8590b2850
|
3 |
size 389074464
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 198011700
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c6252331758a1f9b1131927a72d62a3faf0c8dc2d5aab8bd8ebeb638a0536413
|
3 |
size 198011700
|
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 sha256:5b26bb65679d1fbe119ff115522738907e642e45677820751547812f1ce25739
|
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": 1.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -140,6 +140,13 @@
|
|
140 |
"learning_rate": 4.06948109058927e-05,
|
141 |
"loss": 0.7776,
|
142 |
"step": 2166
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 114,
|
@@ -159,7 +166,7 @@
|
|
159 |
"attributes": {}
|
160 |
}
|
161 |
},
|
162 |
-
"total_flos": 1.
|
163 |
"train_batch_size": 1,
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.9964973730297724,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2280,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
140 |
"learning_rate": 4.06948109058927e-05,
|
141 |
"loss": 0.7776,
|
142 |
"step": 2166
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 1.9964973730297724,
|
146 |
+
"grad_norm": 0.636738657951355,
|
147 |
+
"learning_rate": 4.019349164467898e-05,
|
148 |
+
"loss": 0.8015,
|
149 |
+
"step": 2280
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 114,
|
|
|
166 |
"attributes": {}
|
167 |
}
|
168 |
},
|
169 |
+
"total_flos": 1.2959469426231091e+17,
|
170 |
"train_batch_size": 1,
|
171 |
"trial_name": null,
|
172 |
"trial_params": null
|