phungkhaccuong
commited on
Training in progress, step 13, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -22,11 +22,11 @@
|
|
22 |
"target_modules": [
|
23 |
"down_proj",
|
24 |
"v_proj",
|
|
|
25 |
"up_proj",
|
26 |
-
"o_proj",
|
27 |
"k_proj",
|
28 |
-
"
|
29 |
-
"
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
22 |
"target_modules": [
|
23 |
"down_proj",
|
24 |
"v_proj",
|
25 |
+
"gate_proj",
|
26 |
"up_proj",
|
|
|
27 |
"k_proj",
|
28 |
+
"o_proj",
|
29 |
+
"q_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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1875a1e1a0231a5d66224e761b7b5512717d15617f1545eac2af583852f74bdd
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8298ee01f6509009e8436e1c83527fe8cd81469ba8f6a80488cd8ebfd83a53f0
|
3 |
size 41119636
|
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 sha256:5e4f58d5f408c6018d9f8191cde9d7af64c8ada1d418fb9f6236d2673d276140
|
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 sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
|
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 +11,39 @@
|
|
11 |
{
|
12 |
"epoch": 0.00034057045551298427,
|
13 |
"eval_loss": 1.7009656429290771,
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second": 12.
|
16 |
-
"eval_steps_per_second": 6.
|
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 +51,12 @@
|
|
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": 0.004427415921668796,
|
5 |
+
"eval_steps": 10,
|
6 |
+
"global_step": 13,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.00034057045551298427,
|
13 |
"eval_loss": 1.7009656429290771,
|
14 |
+
"eval_runtime": 99.2017,
|
15 |
+
"eval_samples_per_second": 12.47,
|
16 |
+
"eval_steps_per_second": 6.24,
|
17 |
"step": 1
|
18 |
+
},
|
19 |
+
{
|
20 |
+
"epoch": 0.0017028522775649213,
|
21 |
+
"grad_norm": 0.27365946769714355,
|
22 |
+
"learning_rate": 5e-05,
|
23 |
+
"loss": 1.1698,
|
24 |
+
"step": 5
|
25 |
+
},
|
26 |
+
{
|
27 |
+
"epoch": 0.0034057045551298426,
|
28 |
+
"grad_norm": 0.5234311819076538,
|
29 |
+
"learning_rate": 0.0001,
|
30 |
+
"loss": 1.0425,
|
31 |
+
"step": 10
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"epoch": 0.0034057045551298426,
|
35 |
+
"eval_loss": 1.6530998945236206,
|
36 |
+
"eval_runtime": 99.8257,
|
37 |
+
"eval_samples_per_second": 12.392,
|
38 |
+
"eval_steps_per_second": 6.201,
|
39 |
+
"step": 10
|
40 |
}
|
41 |
],
|
42 |
"logging_steps": 5,
|
43 |
+
"max_steps": 50,
|
44 |
"num_input_tokens_seen": 0,
|
45 |
"num_train_epochs": 1,
|
46 |
+
"save_steps": 13,
|
47 |
"stateful_callbacks": {
|
48 |
"TrainerControl": {
|
49 |
"args": {
|
|
|
51 |
"should_evaluate": false,
|
52 |
"should_log": false,
|
53 |
"should_save": true,
|
54 |
+
"should_training_stop": false
|
55 |
},
|
56 |
"attributes": {}
|
57 |
}
|
58 |
},
|
59 |
+
"total_flos": 2966081262059520.0,
|
60 |
"train_batch_size": 2,
|
61 |
"trial_name": null,
|
62 |
"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 sha256:0c35e43f45e3f7456349937b21aee1bd037faa52505eb39ad789f180f6595d61
|
3 |
size 6776
|