MohamedAhmedAE
commited on
Commit
•
84fabf0
1
Parent(s):
ac99d1f
Training in progress, step 2400, 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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:714e6464882a12977f9161b0725f0f293b62727654edea6c7cd1304a993dfac9
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 84581014
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:40a8ffb4f5658e0682ef76e7152bbe595d7237d7f6021f8772ee7e472eef8d29
|
3 |
size 84581014
|
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:f378a879622820d825a4a635bf9928d84f866b9daa73fe1f9fc42587e2508c66
|
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 sha256:41fd41f1ab3b29e88abab4e0f95a7542016a4426d0de6a4edad353ac7f02e3e5
|
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": 2000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -84,6 +84,13 @@
|
|
84 |
"learning_rate": 1.999999475956276e-05,
|
85 |
"loss": 1.6152,
|
86 |
"step": 2200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
}
|
88 |
],
|
89 |
"logging_steps": 200,
|
@@ -91,7 +98,7 @@
|
|
91 |
"num_input_tokens_seen": 0,
|
92 |
"num_train_epochs": 5,
|
93 |
"save_steps": 200,
|
94 |
-
"total_flos":
|
95 |
"train_batch_size": 1,
|
96 |
"trial_name": null,
|
97 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0017847913467366205,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 2400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
84 |
"learning_rate": 1.999999475956276e-05,
|
85 |
"loss": 1.6152,
|
86 |
"step": 2200
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.0,
|
90 |
+
"grad_norm": 4.141517162322998,
|
91 |
+
"learning_rate": 1.9999993759176304e-05,
|
92 |
+
"loss": 1.564,
|
93 |
+
"step": 2400
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 200,
|
|
|
98 |
"num_input_tokens_seen": 0,
|
99 |
"num_train_epochs": 5,
|
100 |
"save_steps": 200,
|
101 |
+
"total_flos": 3.125489981718528e+16,
|
102 |
"train_batch_size": 1,
|
103 |
"trial_name": null,
|
104 |
"trial_params": null
|