Femboyuwu2000
commited on
Commit
•
ec7b2c2
1
Parent(s):
116b078
Training in progress, step 260, 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 sha256:4c74abcbc22a956d2c4927f3cd90c498db1401577c1a95edd5aa2828ae826f3e
|
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 sha256:0405dd9af2f32c8a1a022354904e4a96c6491985948aa4e13d81d2e6b0537b10
|
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 sha256:1257d052b4a8dc172dc42140b2ee6a8793b59746e8cf14885edb0b6f2889582d
|
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 sha256:1b9b1b69a7ab8ccbf3078c429a8961ade0793a75661dbafee0da970c8ab67482
|
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,
|
@@ -91,6 +91,13 @@
|
|
91 |
"learning_rate": 3.983333333333333e-05,
|
92 |
"loss": 2.8566,
|
93 |
"step": 240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 20,
|
@@ -98,7 +105,7 @@
|
|
98 |
"num_input_tokens_seen": 0,
|
99 |
"num_train_epochs": 1,
|
100 |
"save_steps": 20,
|
101 |
-
"total_flos":
|
102 |
"train_batch_size": 1,
|
103 |
"trial_name": null,
|
104 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.00020234565307059528,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 260,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
91 |
"learning_rate": 3.983333333333333e-05,
|
92 |
"loss": 2.8566,
|
93 |
"step": 240
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.0,
|
97 |
+
"grad_norm": 4.688353538513184,
|
98 |
+
"learning_rate": 4.316666666666667e-05,
|
99 |
+
"loss": 3.0079,
|
100 |
+
"step": 260
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 20,
|
|
|
105 |
"num_input_tokens_seen": 0,
|
106 |
"num_train_epochs": 1,
|
107 |
"save_steps": 20,
|
108 |
+
"total_flos": 1238496472055808.0,
|
109 |
"train_batch_size": 1,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|