Femboyuwu2000
commited on
Commit
•
21a082b
1
Parent(s):
45c3630
Training in progress, step 340, 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 sha256:7a2031f1e6cfe542aa6f89f6acad2e6e61e5eccb774c028eacc849acf7dc731e
|
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:a30a2f52f2a1b0e6af1f396a27551dee57d0a8a9bc75f3983a9f22ff5a3791fb
|
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 sha256:9d6a661ce10cf6ec0952952c89c18c5adfff1f458e16ee8c25253323214e7629
|
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 sha256:958b2ef2ec14693170ade17a6d7d18d3a64014324c4ca5063751e5c7d0563ec3
|
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,
|
@@ -119,6 +119,13 @@
|
|
119 |
"learning_rate": 4.9999526661182696e-05,
|
120 |
"loss": 2.9341,
|
121 |
"step": 320
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
122 |
}
|
123 |
],
|
124 |
"logging_steps": 20,
|
@@ -126,7 +133,7 @@
|
|
126 |
"num_input_tokens_seen": 0,
|
127 |
"num_train_epochs": 1,
|
128 |
"save_steps": 20,
|
129 |
-
"total_flos":
|
130 |
"train_batch_size": 1,
|
131 |
"trial_name": null,
|
132 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00026460585401539384,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 340,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
119 |
"learning_rate": 4.9999526661182696e-05,
|
120 |
"loss": 2.9341,
|
121 |
"step": 320
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.0,
|
125 |
+
"grad_norm": 7.716049671173096,
|
126 |
+
"learning_rate": 4.999800570348766e-05,
|
127 |
+
"loss": 2.5987,
|
128 |
+
"step": 340
|
129 |
}
|
130 |
],
|
131 |
"logging_steps": 20,
|
|
|
133 |
"num_input_tokens_seen": 0,
|
134 |
"num_train_epochs": 1,
|
135 |
"save_steps": 20,
|
136 |
+
"total_flos": 1573291521589248.0,
|
137 |
"train_batch_size": 1,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|