MohamedAhmedAE
commited on
Commit
•
2520d61
1
Parent(s):
57a4e58
Training in progress, step 1200, 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 sha256:15df8bb7b0d650ace01d49121a6ff2801e53098ae1fbd955ed4336f0f8e11ee6
|
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 sha256:44804d51d5f6b390f04a3c04221e0560893966402950edc2362e929c63a832a3
|
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 sha256:42ae668d05ab3aad6ce208eabfc49a053f98a880118709786e12d55282ae6b22
|
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 sha256:9b474e3bac276f26ded4a53adf20938b4253ff5f990814d1b36777f7eb9de45a
|
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,
|
@@ -42,6 +42,13 @@
|
|
42 |
"learning_rate": 1.999999892574807e-05,
|
43 |
"loss": 1.5775,
|
44 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
45 |
}
|
46 |
],
|
47 |
"logging_steps": 200,
|
@@ -49,7 +56,7 @@
|
|
49 |
"num_input_tokens_seen": 0,
|
50 |
"num_train_epochs": 5,
|
51 |
"save_steps": 200,
|
52 |
-
"total_flos": 1.
|
53 |
"train_batch_size": 1,
|
54 |
"trial_name": null,
|
55 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0008923956733683103,
|
5 |
"eval_steps": 2000,
|
6 |
+
"global_step": 1200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
42 |
"learning_rate": 1.999999892574807e-05,
|
43 |
"loss": 1.5775,
|
44 |
"step": 1000
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.0,
|
48 |
+
"grad_norm": 2.1446919441223145,
|
49 |
+
"learning_rate": 1.9999998448916044e-05,
|
50 |
+
"loss": 1.6922,
|
51 |
+
"step": 1200
|
52 |
}
|
53 |
],
|
54 |
"logging_steps": 200,
|
|
|
56 |
"num_input_tokens_seen": 0,
|
57 |
"num_train_epochs": 5,
|
58 |
"save_steps": 200,
|
59 |
+
"total_flos": 1.5519816481284096e+16,
|
60 |
"train_batch_size": 1,
|
61 |
"trial_name": null,
|
62 |
"trial_params": null
|