tuanna08go
commited on
Training in progress, step 26, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
"o_proj",
|
25 |
"v_proj",
|
26 |
"up_proj",
|
27 |
"down_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"gate_proj",
|
24 |
"o_proj",
|
25 |
"v_proj",
|
26 |
"up_proj",
|
27 |
"down_proj",
|
28 |
+
"q_proj",
|
29 |
+
"k_proj"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"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 36981072
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c667f3158c7121051f8f080210a32def773221021715d632a9623fd6c8931b02
|
3 |
size 36981072
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 19859140
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3198af97fd8cfcdad00f14309da038efe5e49694545c548255fddfa9f700511
|
3 |
size 19859140
|
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 sha256:86c1f05421eea4660bc2974d25bb90fb7e89d609ab060bd49ce0ccfb107ace2c
|
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 sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
|
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":
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -11,17 +11,68 @@
|
|
11 |
{
|
12 |
"epoch": 0.002890173410404624,
|
13 |
"eval_loss": NaN,
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second":
|
16 |
-
"eval_steps_per_second": 2.
|
17 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 5,
|
21 |
-
"max_steps":
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 1,
|
24 |
-
"save_steps":
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
27 |
"args": {
|
@@ -29,12 +80,12 @@
|
|
29 |
"should_evaluate": false,
|
30 |
"should_log": false,
|
31 |
"should_save": true,
|
32 |
-
"should_training_stop":
|
33 |
},
|
34 |
"attributes": {}
|
35 |
}
|
36 |
},
|
37 |
-
"total_flos":
|
38 |
"train_batch_size": 2,
|
39 |
"trial_name": null,
|
40 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07514450867052024,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 26,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.002890173410404624,
|
13 |
"eval_loss": NaN,
|
14 |
+
"eval_runtime": 33.0624,
|
15 |
+
"eval_samples_per_second": 4.416,
|
16 |
+
"eval_steps_per_second": 2.208,
|
17 |
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.014450867052023121,
|
21 |
+
"grad_norm": NaN,
|
22 |
+
"learning_rate": 5e-05,
|
23 |
+
"loss": 0.0,
|
24 |
+
"step": 5
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.028901734104046242,
|
28 |
+
"grad_norm": NaN,
|
29 |
+
"learning_rate": 0.0001,
|
30 |
+
"loss": 0.0,
|
31 |
+
"step": 10
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.028901734104046242,
|
35 |
+
"eval_loss": NaN,
|
36 |
+
"eval_runtime": 19.3605,
|
37 |
+
"eval_samples_per_second": 7.541,
|
38 |
+
"eval_steps_per_second": 3.771,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04335260115606936,
|
43 |
+
"grad_norm": NaN,
|
44 |
+
"learning_rate": 9.619397662556435e-05,
|
45 |
+
"loss": 0.0,
|
46 |
+
"step": 15
|
47 |
+
},
|
48 |
+
{
|
49 |
+
"epoch": 0.057803468208092484,
|
50 |
+
"grad_norm": NaN,
|
51 |
+
"learning_rate": 8.535533905932738e-05,
|
52 |
+
"loss": 0.0,
|
53 |
+
"step": 20
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.057803468208092484,
|
57 |
+
"eval_loss": NaN,
|
58 |
+
"eval_runtime": 19.6331,
|
59 |
+
"eval_samples_per_second": 7.436,
|
60 |
+
"eval_steps_per_second": 3.718,
|
61 |
+
"step": 20
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.07225433526011561,
|
65 |
+
"grad_norm": NaN,
|
66 |
+
"learning_rate": 6.91341716182545e-05,
|
67 |
+
"loss": 0.0,
|
68 |
+
"step": 25
|
69 |
}
|
70 |
],
|
71 |
"logging_steps": 5,
|
72 |
+
"max_steps": 50,
|
73 |
"num_input_tokens_seen": 0,
|
74 |
"num_train_epochs": 1,
|
75 |
+
"save_steps": 13,
|
76 |
"stateful_callbacks": {
|
77 |
"TrainerControl": {
|
78 |
"args": {
|
|
|
80 |
"should_evaluate": false,
|
81 |
"should_log": false,
|
82 |
"should_save": true,
|
83 |
+
"should_training_stop": false
|
84 |
},
|
85 |
"attributes": {}
|
86 |
}
|
87 |
},
|
88 |
+
"total_flos": 1678243487809536.0,
|
89 |
"train_batch_size": 2,
|
90 |
"trial_name": null,
|
91 |
"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 6776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c5965fd082c86171b43b37ef2304ff45259d8950c596e22c65b26ea28d27a2c
|
3 |
size 6776
|