genejalston
commited on
Commit
•
399b2ff
1
Parent(s):
9e5a240
Training in progress, step 5000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:889de59136aa9261f023a89c62054d3e68a9a6b2f55bf5002d486bd7ef4814d7
|
3 |
size 1625426996
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3250759951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:807fc3d8c6158267d614210b9b2c591ebd96319cde2fb0c23393d90b5abeba53
|
3 |
size 3250759951
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:80819085c6e429ee1ffeeb612e061c3a6138b6de268344587ff6a2fec2bd933c
|
3 |
+
size 14308
|
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:f9a0d3427fb77527a642ebe12f33ef42140be0b7133737795554f25007311e67
|
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": 2.
|
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,
|
@@ -133,13 +133,27 @@
|
|
133 |
"eval_samples_per_second": 1.359,
|
134 |
"eval_steps_per_second": 0.34,
|
135 |
"step": 4500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 500,
|
139 |
"max_steps": 6000,
|
140 |
"num_train_epochs": 3,
|
141 |
"save_steps": 500,
|
142 |
-
"total_flos":
|
143 |
"trial_name": null,
|
144 |
"trial_params": null
|
145 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.5,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"eval_samples_per_second": 1.359,
|
134 |
"eval_steps_per_second": 0.34,
|
135 |
"step": 4500
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 2.5,
|
139 |
+
"learning_rate": 8.333333333333334e-06,
|
140 |
+
"loss": 0.0137,
|
141 |
+
"step": 5000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 2.5,
|
145 |
+
"eval_loss": 3.8697893619537354,
|
146 |
+
"eval_runtime": 365.2291,
|
147 |
+
"eval_samples_per_second": 1.366,
|
148 |
+
"eval_steps_per_second": 0.342,
|
149 |
+
"step": 5000
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 500,
|
153 |
"max_steps": 6000,
|
154 |
"num_train_epochs": 3,
|
155 |
"save_steps": 500,
|
156 |
+
"total_flos": 4231779650764800.0,
|
157 |
"trial_name": null,
|
158 |
"trial_params": null
|
159 |
}
|