Training in progress, step 500, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,8 +20,8 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM",
|
27 |
"use_dora": false,
|
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3208536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad3b3ec88853861a6dcb1ae878fa729ec778b4cfe38e09504f0fa9bdfa9613ec
|
3 |
size 3208536
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6477306
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff1811973a5cdb3fb20278d973911f2e63c2db0365377817f8d0d5046972f294
|
3 |
size 6477306
|
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:efc8ab690e8a394c395a6f80836609b81bd0ceeab33b87e812b5f24f277e7e1d
|
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 sha256:8cc70b99f783009e9bc521a702be6ffc66450585d22580bd0270abac6affb5ea
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,26 +1,19 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
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,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.3850415512465375,
|
13 |
-
"grad_norm":
|
14 |
"learning_rate": 2.6915974145891044e-05,
|
15 |
-
"loss":
|
16 |
"step": 500
|
17 |
-
},
|
18 |
-
{
|
19 |
-
"epoch": 2.770083102493075,
|
20 |
-
"grad_norm": 27.87322235107422,
|
21 |
-
"learning_rate": 3.831948291782087e-06,
|
22 |
-
"loss": 0.5339,
|
23 |
-
"step": 1000
|
24 |
}
|
25 |
],
|
26 |
"logging_steps": 500,
|
@@ -35,12 +28,12 @@
|
|
35 |
"should_evaluate": false,
|
36 |
"should_log": false,
|
37 |
"should_save": true,
|
38 |
-
"should_training_stop":
|
39 |
},
|
40 |
"attributes": {}
|
41 |
}
|
42 |
},
|
43 |
-
"total_flos":
|
44 |
"train_batch_size": 1,
|
45 |
"trial_name": null,
|
46 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.3850415512465375,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
10 |
"log_history": [
|
11 |
{
|
12 |
"epoch": 1.3850415512465375,
|
13 |
+
"grad_norm": 6.100043773651123,
|
14 |
"learning_rate": 2.6915974145891044e-05,
|
15 |
+
"loss": 1.5549,
|
16 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
17 |
}
|
18 |
],
|
19 |
"logging_steps": 500,
|
|
|
28 |
"should_evaluate": false,
|
29 |
"should_log": false,
|
30 |
"should_save": true,
|
31 |
+
"should_training_stop": false
|
32 |
},
|
33 |
"attributes": {}
|
34 |
}
|
35 |
},
|
36 |
+
"total_flos": 536579280857088.0,
|
37 |
"train_batch_size": 1,
|
38 |
"trial_name": null,
|
39 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5432
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0b5fc168c667c783502daeffd67275f4cea90a21f0e342c03248122527bf4b04
|
3 |
size 5432
|