Training in progress, step 1100, 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:ce4c173b2fb43879819c7d4addd6248e95d776ef36a943009591be0360be702f
|
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:ecc377b37f09f7d68899222e2aac83dfc1ce6417ebedb527f26ad1fd32440950
|
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 sha256:6ccee410b1a78bc7d037fec2e4c83dcffef64092600f52dcd01ce45d1bf4d10a
|
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 sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
|
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": 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,
|
@@ -147,13 +147,27 @@
|
|
147 |
"eval_samples_per_second": 30.466,
|
148 |
"eval_steps_per_second": 3.812,
|
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":
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
159 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.338806390762329,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1100",
|
4 |
+
"epoch": 0.8014571948998178,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
147 |
"eval_samples_per_second": 30.466,
|
148 |
"eval_steps_per_second": 3.812,
|
149 |
"step": 1000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8,
|
153 |
+
"learning_rate": 0.0002,
|
154 |
+
"loss": 2.3599,
|
155 |
+
"step": 1100
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.8,
|
159 |
+
"eval_loss": 2.338806390762329,
|
160 |
+
"eval_runtime": 205.8736,
|
161 |
+
"eval_samples_per_second": 30.475,
|
162 |
+
"eval_steps_per_second": 3.813,
|
163 |
+
"step": 1100
|
164 |
}
|
165 |
],
|
166 |
"logging_steps": 100,
|
167 |
"max_steps": 4116,
|
168 |
"num_train_epochs": 3,
|
169 |
"save_steps": 100,
|
170 |
+
"total_flos": 3.229353773162496e+16,
|
171 |
"trial_name": null,
|
172 |
"trial_params": null
|
173 |
}
|