Femboyuwu2000
commited on
Commit
•
a6cab9b
1
Parent(s):
f7f01bd
Training in progress, step 280, 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 sha256:3b69e1ece531ae04226ab8e666c97b14f0d7a11afc5625e4c77a464e4ce29496
|
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:dbd9ad863a348d05efe28bd6743c02865fa3ef1f49db9e787ff7a2fb7012c27d
|
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:b08248ed26b28c1a0bd4b42e309ef4427a1e5fb6da926b6c61e6c6e7cc3b09fb
|
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:c08479d3d6dabb601d418ce802b775aad13d7bf7b26fde0b24c32b2a8f36ef6e
|
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,
|
@@ -98,6 +98,13 @@
|
|
98 |
"learning_rate": 4.316666666666667e-05,
|
99 |
"loss": 3.0079,
|
100 |
"step": 260
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 20,
|
@@ -105,7 +112,7 @@
|
|
105 |
"num_input_tokens_seen": 0,
|
106 |
"num_train_epochs": 1,
|
107 |
"save_steps": 20,
|
108 |
-
"total_flos":
|
109 |
"train_batch_size": 1,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00021791070330679492,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 280,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"learning_rate": 4.316666666666667e-05,
|
99 |
"loss": 3.0079,
|
100 |
"step": 260
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.0,
|
104 |
+
"grad_norm": 4.502331256866455,
|
105 |
+
"learning_rate": 4.6500000000000005e-05,
|
106 |
+
"loss": 2.6839,
|
107 |
+
"step": 280
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 20,
|
|
|
112 |
"num_input_tokens_seen": 0,
|
113 |
"num_train_epochs": 1,
|
114 |
"save_steps": 20,
|
115 |
+
"total_flos": 1322195234439168.0,
|
116 |
"train_batch_size": 1,
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|