Training in progress, step 20, 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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be0baf9cda41e263fd80618baa5e2f59a5a168e2ac3b3d3b81d360a4aafb9332
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37430836
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:20b7145b9cc8702a5055b11432bdca180b9b55b81b469911481c77865131f9f9
|
3 |
size 37430836
|
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 sha256:1b1ece0846e2afe71b4b44981fd9a82ee7e8be48b72c44e6ff1c690617d2b724
|
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": 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": 3.8e-05,
|
141 |
"loss": 1.8081,
|
142 |
"step": 19
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 1,
|
@@ -159,7 +166,7 @@
|
|
159 |
"attributes": {}
|
160 |
}
|
161 |
},
|
162 |
-
"total_flos": 2.
|
163 |
"train_batch_size": 4,
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.05486968449931413,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 20,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
140 |
"learning_rate": 3.8e-05,
|
141 |
"loss": 1.8081,
|
142 |
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.05486968449931413,
|
146 |
+
"grad_norm": 0.3805089592933655,
|
147 |
+
"learning_rate": 4e-05,
|
148 |
+
"loss": 1.7553,
|
149 |
+
"step": 20
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 1,
|
|
|
166 |
"attributes": {}
|
167 |
}
|
168 |
},
|
169 |
+
"total_flos": 2.508763359401165e+16,
|
170 |
"train_batch_size": 4,
|
171 |
"trial_name": null,
|
172 |
"trial_params": null
|