MohamedAhmedAE
commited on
Commit
•
c0f27e7
1
Parent(s):
247481d
Training in progress, step 2000, 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:ab0d2cef0a520f95d1b3a5e19c4faf1f2fdd4b669b292c657819c3293f9777df
|
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 sha256:6e19bb13e6ddd38b55d269b81836df099f52d521292cc3147c8069c577d0d7f7
|
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 sha256:473e97fa4a79ae2cdbec269f5dd726507565e4476964fba62228ef7aefe54818
|
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 sha256:0a564ad02175d1fc4a411742de225c89f8307036c81f34a693a28057e5f5ff71
|
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,
|
@@ -70,6 +70,13 @@
|
|
70 |
"learning_rate": 1.9999996494428805e-05,
|
71 |
"loss": 1.5682,
|
72 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 200,
|
@@ -77,7 +84,7 @@
|
|
77 |
"num_input_tokens_seen": 0,
|
78 |
"num_train_epochs": 5,
|
79 |
"save_steps": 200,
|
80 |
-
"total_flos": 2.
|
81 |
"train_batch_size": 1,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.001487326122280517,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
70 |
"learning_rate": 1.9999996494428805e-05,
|
71 |
"loss": 1.5682,
|
72 |
"step": 1800
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.0,
|
76 |
+
"grad_norm": 4.574249267578125,
|
77 |
+
"learning_rate": 1.9999995668269356e-05,
|
78 |
+
"loss": 1.5658,
|
79 |
+
"step": 2000
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 200,
|
|
|
84 |
"num_input_tokens_seen": 0,
|
85 |
"num_train_epochs": 5,
|
86 |
"save_steps": 200,
|
87 |
+
"total_flos": 2.6047198846255104e+16,
|
88 |
"train_batch_size": 1,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|