Training in progress, step 1000, 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 31466288
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:34e5b714b9ad018579c0395bd88c1f526737a3a7591470f0bdcf9a363e6f9f9e
|
3 |
size 31466288
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 62950917
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:27f65bc053b2ff572651b0fae1a50460b90cdac3d97fcdc7808a0375409aa015
|
3 |
size 62950917
|
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:a0f78b2562bc8727c20689e149baf87f12d40909810dc10b46acf10485d1b41a
|
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": 11.316,
|
134 |
"eval_steps_per_second": 1.416,
|
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": 2.
|
143 |
"trial_name": null,
|
144 |
"trial_params": null
|
145 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.8282623291015625,
|
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": 11.316,
|
134 |
"eval_steps_per_second": 1.416,
|
135 |
"step": 900
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.73,
|
139 |
+
"learning_rate": 0.0002,
|
140 |
+
"loss": 1.8397,
|
141 |
+
"step": 1000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.73,
|
145 |
+
"eval_loss": 1.8282623291015625,
|
146 |
+
"eval_runtime": 554.0635,
|
147 |
+
"eval_samples_per_second": 11.324,
|
148 |
+
"eval_steps_per_second": 1.417,
|
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": 2.6035701176578867e+17,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
159 |
}
|