tuanna08go
commited on
Training in progress, step 1, checkpoint
Browse files
last-checkpoint/adapter_config.json
CHANGED
@@ -20,13 +20,13 @@
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
-
"
|
24 |
-
"gate_proj",
|
25 |
"v_proj",
|
26 |
-
"up_proj",
|
27 |
"down_proj",
|
28 |
-
"
|
29 |
-
"k_proj"
|
|
|
|
|
30 |
],
|
31 |
"task_type": "CAUSAL_LM",
|
32 |
"use_dora": false,
|
|
|
20 |
"rank_pattern": {},
|
21 |
"revision": null,
|
22 |
"target_modules": [
|
23 |
+
"q_proj",
|
|
|
24 |
"v_proj",
|
|
|
25 |
"down_proj",
|
26 |
+
"o_proj",
|
27 |
+
"k_proj",
|
28 |
+
"up_proj",
|
29 |
+
"gate_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 sha256:20fcebe4e922b0ffc6322a21ceb2e248db7b5c62e7c79589466e3da72ced6a3f
|
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:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
|
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:da80317735abd5d7a29a7220f00b3b233d1e998e1437bb05f3ba2da5a84eb5d2
|
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:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
|
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,
|
@@ -11,92 +11,17 @@
|
|
11 |
{
|
12 |
"epoch": 0.0004970178926441351,
|
13 |
"eval_loss": NaN,
|
14 |
-
"eval_runtime":
|
15 |
-
"eval_samples_per_second": 26.
|
16 |
-
"eval_steps_per_second": 3.
|
17 |
"step": 1
|
18 |
-
},
|
19 |
-
{
|
20 |
-
"epoch": 0.004970178926441352,
|
21 |
-
"grad_norm": NaN,
|
22 |
-
"learning_rate": 9.330127018922194e-05,
|
23 |
-
"loss": 0.0,
|
24 |
-
"step": 10
|
25 |
-
},
|
26 |
-
{
|
27 |
-
"epoch": 0.004970178926441352,
|
28 |
-
"eval_loss": NaN,
|
29 |
-
"eval_runtime": 507.9575,
|
30 |
-
"eval_samples_per_second": 26.685,
|
31 |
-
"eval_steps_per_second": 3.337,
|
32 |
-
"step": 10
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.009940357852882704,
|
36 |
-
"grad_norm": NaN,
|
37 |
-
"learning_rate": 6.91341716182545e-05,
|
38 |
-
"loss": 0.0,
|
39 |
-
"step": 20
|
40 |
-
},
|
41 |
-
{
|
42 |
-
"epoch": 0.009940357852882704,
|
43 |
-
"eval_loss": NaN,
|
44 |
-
"eval_runtime": 507.5099,
|
45 |
-
"eval_samples_per_second": 26.709,
|
46 |
-
"eval_steps_per_second": 3.34,
|
47 |
-
"step": 20
|
48 |
-
},
|
49 |
-
{
|
50 |
-
"epoch": 0.014910536779324055,
|
51 |
-
"grad_norm": NaN,
|
52 |
-
"learning_rate": 3.705904774487396e-05,
|
53 |
-
"loss": 0.0,
|
54 |
-
"step": 30
|
55 |
-
},
|
56 |
-
{
|
57 |
-
"epoch": 0.014910536779324055,
|
58 |
-
"eval_loss": NaN,
|
59 |
-
"eval_runtime": 505.8777,
|
60 |
-
"eval_samples_per_second": 26.795,
|
61 |
-
"eval_steps_per_second": 3.351,
|
62 |
-
"step": 30
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 0.019880715705765408,
|
66 |
-
"grad_norm": NaN,
|
67 |
-
"learning_rate": 1.0332332985438248e-05,
|
68 |
-
"loss": 0.0,
|
69 |
-
"step": 40
|
70 |
-
},
|
71 |
-
{
|
72 |
-
"epoch": 0.019880715705765408,
|
73 |
-
"eval_loss": NaN,
|
74 |
-
"eval_runtime": 507.6116,
|
75 |
-
"eval_samples_per_second": 26.703,
|
76 |
-
"eval_steps_per_second": 3.339,
|
77 |
-
"step": 40
|
78 |
-
},
|
79 |
-
{
|
80 |
-
"epoch": 0.02485089463220676,
|
81 |
-
"grad_norm": NaN,
|
82 |
-
"learning_rate": 0.0,
|
83 |
-
"loss": 0.0,
|
84 |
-
"step": 50
|
85 |
-
},
|
86 |
-
{
|
87 |
-
"epoch": 0.02485089463220676,
|
88 |
-
"eval_loss": NaN,
|
89 |
-
"eval_runtime": 506.8758,
|
90 |
-
"eval_samples_per_second": 26.742,
|
91 |
-
"eval_steps_per_second": 3.344,
|
92 |
-
"step": 50
|
93 |
}
|
94 |
],
|
95 |
"logging_steps": 10,
|
96 |
-
"max_steps":
|
97 |
"num_input_tokens_seen": 0,
|
98 |
"num_train_epochs": 1,
|
99 |
-
"save_steps":
|
100 |
"stateful_callbacks": {
|
101 |
"TrainerControl": {
|
102 |
"args": {
|
@@ -109,7 +34,7 @@
|
|
109 |
"attributes": {}
|
110 |
}
|
111 |
},
|
112 |
-
"total_flos":
|
113 |
"train_batch_size": 8,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0004970178926441351,
|
5 |
+
"eval_steps": 1,
|
6 |
+
"global_step": 1,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
11 |
{
|
12 |
"epoch": 0.0004970178926441351,
|
13 |
"eval_loss": NaN,
|
14 |
+
"eval_runtime": 506.5724,
|
15 |
+
"eval_samples_per_second": 26.758,
|
16 |
+
"eval_steps_per_second": 3.346,
|
17 |
"step": 1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
"logging_steps": 10,
|
21 |
+
"max_steps": 1,
|
22 |
"num_input_tokens_seen": 0,
|
23 |
"num_train_epochs": 1,
|
24 |
+
"save_steps": 1,
|
25 |
"stateful_callbacks": {
|
26 |
"TrainerControl": {
|
27 |
"args": {
|
|
|
34 |
"attributes": {}
|
35 |
}
|
36 |
},
|
37 |
+
"total_flos": 1037754427244544.0,
|
38 |
"train_batch_size": 8,
|
39 |
"trial_name": null,
|
40 |
"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 sha256:873662a17914ea13833be8de5d6c637c4504bec742c7417b17a6bd79c01be49d
|
3 |
size 6776
|