Training in progress, step 15, 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 27024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:54c8253dbc73a123cd4faae88ebbf7d067e3aa28a0d7995cb55b6acc71e62e92
|
3 |
size 27024
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 63974
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd816e918fc943507162e88f5f71a06380b86ee118a6e206eaae60177519754a
|
3 |
size 63974
|
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 sha256:22cdbc90fe5ab190ddc8c8d596470e7106be9ee2374df85af28061b6a32f91c4
|
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 sha256:949bb17004f4d35b0cca7250e720f161498dce460eb9efa361d2fdaf574c9ed5
|
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": 4,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -123,6 +123,27 @@
|
|
123 |
"eval_samples_per_second": 249.237,
|
124 |
"eval_steps_per_second": 124.619,
|
125 |
"step": 12
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
126 |
}
|
127 |
],
|
128 |
"logging_steps": 1,
|
@@ -137,12 +158,12 @@
|
|
137 |
"should_evaluate": false,
|
138 |
"should_log": false,
|
139 |
"should_save": true,
|
140 |
-
"should_training_stop":
|
141 |
},
|
142 |
"attributes": {}
|
143 |
}
|
144 |
},
|
145 |
-
"total_flos":
|
146 |
"train_batch_size": 2,
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.007052186177715092,
|
5 |
"eval_steps": 4,
|
6 |
+
"global_step": 15,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
123 |
"eval_samples_per_second": 249.237,
|
124 |
"eval_steps_per_second": 124.619,
|
125 |
"step": 12
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.0061118946873530795,
|
129 |
+
"grad_norm": 0.02134430967271328,
|
130 |
+
"learning_rate": 6.909830056250527e-05,
|
131 |
+
"loss": 10.3733,
|
132 |
+
"step": 13
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 0.006582040432534086,
|
136 |
+
"grad_norm": 0.025556456297636032,
|
137 |
+
"learning_rate": 1.9098300562505266e-05,
|
138 |
+
"loss": 10.3743,
|
139 |
+
"step": 14
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 0.007052186177715092,
|
143 |
+
"grad_norm": 0.04154999181628227,
|
144 |
+
"learning_rate": 0.0,
|
145 |
+
"loss": 10.3709,
|
146 |
+
"step": 15
|
147 |
}
|
148 |
],
|
149 |
"logging_steps": 1,
|
|
|
158 |
"should_evaluate": false,
|
159 |
"should_log": false,
|
160 |
"should_save": true,
|
161 |
+
"should_training_stop": true
|
162 |
},
|
163 |
"attributes": {}
|
164 |
}
|
165 |
},
|
166 |
+
"total_flos": 219825438720.0,
|
167 |
"train_batch_size": 2,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|