Training in progress, step 12, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 335922386
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ffcbdee743b2f0793b8506b1c1b754122270a1d18367bac3f9e748cb104ea4f
|
3 |
size 335922386
|
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 sha256:3b3fca34acc9f8b5d9d79c93fbd3f0a45dd1602f05b7f4216d37725a12d30450
|
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:a125c681316bfce03f3558f5956b9c0ad33dcb35c93b2ae66a440f25335c8901
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -125,6 +125,28 @@
|
|
125 |
"eval_samples_per_second": 3.932,
|
126 |
"eval_steps_per_second": 3.932,
|
127 |
"step": 10
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
128 |
}
|
129 |
],
|
130 |
"logging_steps": 1,
|
@@ -144,7 +166,7 @@
|
|
144 |
"attributes": {}
|
145 |
}
|
146 |
},
|
147 |
-
"total_flos":
|
148 |
"train_batch_size": 1,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00037570150515415504,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 12,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
125 |
"eval_samples_per_second": 3.932,
|
126 |
"eval_steps_per_second": 3.932,
|
127 |
"step": 10
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 0.0003443930463913088,
|
131 |
+
"grad_norm": NaN,
|
132 |
+
"learning_rate": 0.00019781476007338058,
|
133 |
+
"loss": 0.0,
|
134 |
+
"step": 11
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.00037570150515415504,
|
138 |
+
"grad_norm": NaN,
|
139 |
+
"learning_rate": 0.0001913545457642601,
|
140 |
+
"loss": 0.0,
|
141 |
+
"step": 12
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.00037570150515415504,
|
145 |
+
"eval_loss": NaN,
|
146 |
+
"eval_runtime": 3425.7094,
|
147 |
+
"eval_samples_per_second": 3.926,
|
148 |
+
"eval_steps_per_second": 3.926,
|
149 |
+
"step": 12
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 1,
|
|
|
166 |
"attributes": {}
|
167 |
}
|
168 |
},
|
169 |
+
"total_flos": 8437553984176128.0,
|
170 |
"train_batch_size": 1,
|
171 |
"trial_name": null,
|
172 |
"trial_params": null
|