Commit
•
5516b2a
1
Parent(s):
b255830
Training in progress, step 4400, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:78b3e09c4e01a30ef881735499660d4412e95b93c75556d23b1ed6810bcf64b8
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ede9351d0e560e402f48b63d9ef5f99a54f6f3c33467860dc582674848a7dd81
|
3 |
size 84581014
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c980230c9b331cf755c313cb53fe86e70becec911cf990f83cc255f22cc4cb3d
|
3 |
size 14244
|
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:c019041ef3f15ade90caa60ec00bd9729de47047048dfbd8b528e52704018ac7
|
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": 0.
|
5 |
"eval_steps": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -154,6 +154,13 @@
|
|
154 |
"learning_rate": 1.9999980825767474e-05,
|
155 |
"loss": 1.5963,
|
156 |
"step": 4200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
157 |
}
|
158 |
],
|
159 |
"logging_steps": 200,
|
@@ -161,7 +168,7 @@
|
|
161 |
"num_input_tokens_seen": 0,
|
162 |
"num_train_epochs": 5,
|
163 |
"save_steps": 200,
|
164 |
-
"total_flos": 5.
|
165 |
"train_batch_size": 1,
|
166 |
"trial_name": null,
|
167 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.003272117469017138,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 4400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
154 |
"learning_rate": 1.9999980825767474e-05,
|
155 |
"loss": 1.5963,
|
156 |
"step": 4200
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 0.0,
|
160 |
+
"grad_norm": 3.360860824584961,
|
161 |
+
"learning_rate": 1.999997896164907e-05,
|
162 |
+
"loss": 1.5837,
|
163 |
+
"step": 4400
|
164 |
}
|
165 |
],
|
166 |
"logging_steps": 200,
|
|
|
168 |
"num_input_tokens_seen": 0,
|
169 |
"num_train_epochs": 5,
|
170 |
"save_steps": 200,
|
171 |
+
"total_flos": 5.776057087694438e+16,
|
172 |
"train_batch_size": 1,
|
173 |
"trial_name": null,
|
174 |
"trial_params": null
|