Femboyuwu2000
commited on
Commit
•
33ccafb
1
Parent(s):
c74a8fd
Training in progress, step 360, 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 4725640
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be1c47e7c45521d38d74b6126649ceb2df1743106d5e52fc59729f4ddcf09e52
|
3 |
size 4725640
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2423802
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:31e10b2453d5453cceff4fb57f534a9b54fdfe1be7ed87e2e4b9beeda333818a
|
3 |
size 2423802
|
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 sha256:02f5b5a227715c8a325f29bcdaf22cb2fe8c97e7e518c73e6e4c68f1401babb7
|
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 sha256:01d446e79fdfc140702e79e052d05618372a6b4805597d3945b4257938e49f2a
|
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,
|
@@ -126,6 +126,13 @@
|
|
126 |
"learning_rate": 4.999800570348766e-05,
|
127 |
"loss": 2.5987,
|
128 |
"step": 340
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
129 |
}
|
130 |
],
|
131 |
"logging_steps": 20,
|
@@ -133,7 +140,7 @@
|
|
133 |
"num_input_tokens_seen": 0,
|
134 |
"num_train_epochs": 1,
|
135 |
"save_steps": 20,
|
136 |
-
"total_flos":
|
137 |
"train_batch_size": 1,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00028017090425159347,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 360,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
126 |
"learning_rate": 4.999800570348766e-05,
|
127 |
"loss": 2.5987,
|
128 |
"step": 340
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.0,
|
132 |
+
"grad_norm": 4.9223952293396,
|
133 |
+
"learning_rate": 4.9995435879539254e-05,
|
134 |
+
"loss": 2.7863,
|
135 |
+
"step": 360
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 20,
|
|
|
140 |
"num_input_tokens_seen": 0,
|
141 |
"num_train_epochs": 1,
|
142 |
"save_steps": 20,
|
143 |
+
"total_flos": 1656990283972608.0,
|
144 |
"train_batch_size": 1,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|