BIue-Jay commited on
Commit
2e8f375
·
verified ·
1 Parent(s): 2aca120

Remove training-only files (trainer state / training args / training plan)

Browse files
a18-pour-water/epoch-010/trainer_state.json DELETED
@@ -1,76 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.5034965034965035,
6
- "eval_steps": 500,
7
- "global_step": 72,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.865953266620636,
14
- "learning_rate": 9.998646205897309e-05,
15
- "loss": 1.3321,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 1.0205682516098022,
20
- "learning_rate": 9.837076097314319e-05,
21
- "loss": 1.1383,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.1993144154548645,
26
- "learning_rate": 9.414737964294636e-05,
27
- "loss": 1.0827,
28
- "step": 30
29
- },
30
- {
31
- "grad_norm": 0.12556512653827667,
32
- "learning_rate": 8.754400164907497e-05,
33
- "loss": 1.0568,
34
- "step": 40
35
- },
36
- {
37
- "grad_norm": 0.09524860978126526,
38
- "learning_rate": 7.891661680839932e-05,
39
- "loss": 1.0454,
40
- "step": 50
41
- },
42
- {
43
- "grad_norm": 0.07082647830247879,
44
- "learning_rate": 6.873032967079561e-05,
45
- "loss": 1.0373,
46
- "step": 60
47
- },
48
- {
49
- "grad_norm": 0.07322803884744644,
50
- "learning_rate": 5.753428561247416e-05,
51
- "loss": 1.0327,
52
- "step": 70
53
- }
54
- ],
55
- "logging_steps": 10,
56
- "max_steps": 143,
57
- "num_input_tokens_seen": 0,
58
- "num_train_epochs": 9223372036854775807,
59
- "save_steps": 72,
60
- "stateful_callbacks": {
61
- "TrainerControl": {
62
- "args": {
63
- "should_epoch_stop": false,
64
- "should_evaluate": false,
65
- "should_log": false,
66
- "should_save": true,
67
- "should_training_stop": false
68
- },
69
- "attributes": {}
70
- }
71
- },
72
- "total_flos": 0.0,
73
- "train_batch_size": 320,
74
- "trial_name": null,
75
- "trial_params": null
76
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a18-pour-water/epoch-010/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9b98d3a11150bb3ed45311648a244e62fbbfe4ae80fc128c7cd92c31705ea97
3
- size 8017
 
 
 
 
a18-pour-water/epoch-010/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "a18", "frames": 72752, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 143, "save_steps": 72}
 
 
a18-pour-water/epoch-020/trainer_state.json DELETED
@@ -1,118 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 143,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.865953266620636,
14
- "learning_rate": 9.998646205897309e-05,
15
- "loss": 1.3321,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 1.0205682516098022,
20
- "learning_rate": 9.837076097314319e-05,
21
- "loss": 1.1383,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.1993144154548645,
26
- "learning_rate": 9.414737964294636e-05,
27
- "loss": 1.0827,
28
- "step": 30
29
- },
30
- {
31
- "grad_norm": 0.12556512653827667,
32
- "learning_rate": 8.754400164907497e-05,
33
- "loss": 1.0568,
34
- "step": 40
35
- },
36
- {
37
- "grad_norm": 0.09524860978126526,
38
- "learning_rate": 7.891661680839932e-05,
39
- "loss": 1.0454,
40
- "step": 50
41
- },
42
- {
43
- "grad_norm": 0.07082647830247879,
44
- "learning_rate": 6.873032967079561e-05,
45
- "loss": 1.0373,
46
- "step": 60
47
- },
48
- {
49
- "grad_norm": 0.07322803884744644,
50
- "learning_rate": 5.753428561247416e-05,
51
- "loss": 1.0327,
52
- "step": 70
53
- },
54
- {
55
- "grad_norm": 0.0560687817633152,
56
- "learning_rate": 4.593206626660709e-05,
57
- "loss": 1.0309,
58
- "step": 80
59
- },
60
- {
61
- "grad_norm": 0.05303322523832321,
62
- "learning_rate": 3.4549150281252636e-05,
63
- "loss": 1.0276,
64
- "step": 90
65
- },
66
- {
67
- "grad_norm": 0.05239558592438698,
68
- "learning_rate": 2.399919360353923e-05,
69
- "loss": 1.0247,
70
- "step": 100
71
- },
72
- {
73
- "grad_norm": 0.05378618463873863,
74
- "learning_rate": 1.4850947128716913e-05,
75
- "loss": 1.0242,
76
- "step": 110
77
- },
78
- {
79
- "grad_norm": 0.04511816427111626,
80
- "learning_rate": 7.597595192178702e-06,
81
- "loss": 1.0237,
82
- "step": 120
83
- },
84
- {
85
- "grad_norm": 0.04321844503283501,
86
- "learning_rate": 2.63016787428354e-06,
87
- "loss": 1.0233,
88
- "step": 130
89
- },
90
- {
91
- "grad_norm": 0.046053119003772736,
92
- "learning_rate": 2.1646046750978254e-07,
93
- "loss": 1.0237,
94
- "step": 140
95
- }
96
- ],
97
- "logging_steps": 10,
98
- "max_steps": 143,
99
- "num_input_tokens_seen": 0,
100
- "num_train_epochs": 9223372036854775807,
101
- "save_steps": 72,
102
- "stateful_callbacks": {
103
- "TrainerControl": {
104
- "args": {
105
- "should_epoch_stop": false,
106
- "should_evaluate": false,
107
- "should_log": false,
108
- "should_save": true,
109
- "should_training_stop": true
110
- },
111
- "attributes": {}
112
- }
113
- },
114
- "total_flos": 0.0,
115
- "train_batch_size": 320,
116
- "trial_name": null,
117
- "trial_params": null
118
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a18-pour-water/epoch-020/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9b98d3a11150bb3ed45311648a244e62fbbfe4ae80fc128c7cd92c31705ea97
3
- size 8017
 
 
 
 
a18-pour-water/epoch-020/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "a18", "frames": 72752, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 143, "save_steps": 72}
 
 
a3-fridge-open/epoch-010/trainer_state.json DELETED
@@ -1,46 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.5,
6
- "eval_steps": 500,
7
- "global_step": 28,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.4957716166973114,
14
- "learning_rate": 9.687098305670605e-05,
15
- "loss": 1.2306,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 0.14771342277526855,
20
- "learning_rate": 7.91489739557236e-05,
21
- "loss": 1.1263,
22
- "step": 20
23
- }
24
- ],
25
- "logging_steps": 10,
26
- "max_steps": 56,
27
- "num_input_tokens_seen": 0,
28
- "num_train_epochs": 9223372036854775807,
29
- "save_steps": 28,
30
- "stateful_callbacks": {
31
- "TrainerControl": {
32
- "args": {
33
- "should_epoch_stop": false,
34
- "should_evaluate": false,
35
- "should_log": false,
36
- "should_save": true,
37
- "should_training_stop": false
38
- },
39
- "attributes": {}
40
- }
41
- },
42
- "total_flos": 0.0,
43
- "train_batch_size": 320,
44
- "trial_name": null,
45
- "trial_params": null
46
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3-fridge-open/epoch-010/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:70a6b1a0e4d95256ab19401789ec0781600e6949da7facc2610a837b70b9ddb3
3
- size 8017
 
 
 
 
a3-fridge-open/epoch-010/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "a3", "frames": 28180, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 56, "save_steps": 28}
 
 
a3-fridge-open/epoch-020/trainer_state.json DELETED
@@ -1,64 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 56,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.4957716166973114,
14
- "learning_rate": 9.687098305670605e-05,
15
- "loss": 1.2306,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 0.14771342277526855,
20
- "learning_rate": 7.91489739557236e-05,
21
- "loss": 1.1263,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.11152204871177673,
26
- "learning_rate": 5.148166639112799e-05,
27
- "loss": 1.095,
28
- "step": 30
29
- },
30
- {
31
- "grad_norm": 0.09289290755987167,
32
- "learning_rate": 2.3308831101760486e-05,
33
- "loss": 1.0864,
34
- "step": 40
35
- },
36
- {
37
- "grad_norm": 0.07126279175281525,
38
- "learning_rate": 4.242719137849077e-06,
39
- "loss": 1.0813,
40
- "step": 50
41
- }
42
- ],
43
- "logging_steps": 10,
44
- "max_steps": 56,
45
- "num_input_tokens_seen": 0,
46
- "num_train_epochs": 9223372036854775807,
47
- "save_steps": 28,
48
- "stateful_callbacks": {
49
- "TrainerControl": {
50
- "args": {
51
- "should_epoch_stop": false,
52
- "should_evaluate": false,
53
- "should_log": false,
54
- "should_save": true,
55
- "should_training_stop": true
56
- },
57
- "attributes": {}
58
- }
59
- },
60
- "total_flos": 0.0,
61
- "train_batch_size": 320,
62
- "trial_name": null,
63
- "trial_params": null
64
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a3-fridge-open/epoch-020/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:70a6b1a0e4d95256ab19401789ec0781600e6949da7facc2610a837b70b9ddb3
3
- size 8017
 
 
 
 
a3-fridge-open/epoch-020/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "a3", "frames": 28180, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 56, "save_steps": 28}
 
 
a7-cabinet-close/epoch-010/trainer_state.json DELETED
@@ -1,52 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.5,
6
- "eval_steps": 500,
7
- "global_step": 30,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.6150157451629639,
14
- "learning_rate": 9.729086208503174e-05,
15
- "loss": 1.2466,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 0.12818367779254913,
20
- "learning_rate": 8.178618741049842e-05,
21
- "loss": 1.133,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.09001472592353821,
26
- "learning_rate": 5.686767789092041e-05,
27
- "loss": 1.1132,
28
- "step": 30
29
- }
30
- ],
31
- "logging_steps": 10,
32
- "max_steps": 60,
33
- "num_input_tokens_seen": 0,
34
- "num_train_epochs": 9223372036854775807,
35
- "save_steps": 30,
36
- "stateful_callbacks": {
37
- "TrainerControl": {
38
- "args": {
39
- "should_epoch_stop": false,
40
- "should_evaluate": false,
41
- "should_log": false,
42
- "should_save": true,
43
- "should_training_stop": false
44
- },
45
- "attributes": {}
46
- }
47
- },
48
- "total_flos": 0.0,
49
- "train_batch_size": 320,
50
- "trial_name": null,
51
- "trial_params": null
52
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a7-cabinet-close/epoch-010/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e1a5bbd8c71cf280208385c4a1c24d8a9f74fb48e9dd88d1476d05572781e3
3
- size 8017
 
 
 
 
a7-cabinet-close/epoch-010/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "a7", "frames": 30664, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 60, "save_steps": 30}
 
 
a7-cabinet-close/epoch-020/trainer_state.json DELETED
@@ -1,70 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 60,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.6150157451629639,
14
- "learning_rate": 9.729086208503174e-05,
15
- "loss": 1.2466,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 0.12818367779254913,
20
- "learning_rate": 8.178618741049842e-05,
21
- "loss": 1.133,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.09001472592353821,
26
- "learning_rate": 5.686767789092041e-05,
27
- "loss": 1.1132,
28
- "step": 30
29
- },
30
- {
31
- "grad_norm": 0.08212777227163315,
32
- "learning_rate": 2.991522876735154e-05,
33
- "loss": 1.1047,
34
- "step": 40
35
- },
36
- {
37
- "grad_norm": 0.06334591656923294,
38
- "learning_rate": 8.911109238737747e-06,
39
- "loss": 1.1015,
40
- "step": 50
41
- },
42
- {
43
- "grad_norm": 0.05820993706583977,
44
- "learning_rate": 7.59241783341913e-08,
45
- "loss": 1.0989,
46
- "step": 60
47
- }
48
- ],
49
- "logging_steps": 10,
50
- "max_steps": 60,
51
- "num_input_tokens_seen": 0,
52
- "num_train_epochs": 9223372036854775807,
53
- "save_steps": 30,
54
- "stateful_callbacks": {
55
- "TrainerControl": {
56
- "args": {
57
- "should_epoch_stop": false,
58
- "should_evaluate": false,
59
- "should_log": false,
60
- "should_save": true,
61
- "should_training_stop": true
62
- },
63
- "attributes": {}
64
- }
65
- },
66
- "total_flos": 0.0,
67
- "train_batch_size": 320,
68
- "trial_name": null,
69
- "trial_params": null
70
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a7-cabinet-close/epoch-020/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e1a5bbd8c71cf280208385c4a1c24d8a9f74fb48e9dd88d1476d05572781e3
3
- size 8017
 
 
 
 
a7-cabinet-close/epoch-020/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "a7", "frames": 30664, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 60, "save_steps": 30}
 
 
b6-pedal-bin/epoch-010/trainer_state.json DELETED
@@ -1,70 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 0.5,
6
- "eval_steps": 500,
7
- "global_step": 64,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.25197651982307434,
14
- "learning_rate": 9.993260441994116e-05,
15
- "loss": 1.2426,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 0.20836573839187622,
20
- "learning_rate": 9.759278142180348e-05,
21
- "loss": 1.1191,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.1473357230424881,
26
- "learning_rate": 9.206267664155907e-05,
27
- "loss": 1.0777,
28
- "step": 30
29
- },
30
- {
31
- "grad_norm": 0.11595264822244644,
32
- "learning_rate": 8.371298899628091e-05,
33
- "loss": 1.0637,
34
- "step": 40
35
- },
36
- {
37
- "grad_norm": 0.21844695508480072,
38
- "learning_rate": 7.310342219701981e-05,
39
- "loss": 1.0536,
40
- "step": 50
41
- },
42
- {
43
- "grad_norm": 0.5528692603111267,
44
- "learning_rate": 6.094516619032975e-05,
45
- "loss": 1.0276,
46
- "step": 60
47
- }
48
- ],
49
- "logging_steps": 10,
50
- "max_steps": 128,
51
- "num_input_tokens_seen": 0,
52
- "num_train_epochs": 9223372036854775807,
53
- "save_steps": 64,
54
- "stateful_callbacks": {
55
- "TrainerControl": {
56
- "args": {
57
- "should_epoch_stop": false,
58
- "should_evaluate": false,
59
- "should_log": false,
60
- "should_save": true,
61
- "should_training_stop": false
62
- },
63
- "attributes": {}
64
- }
65
- },
66
- "total_flos": 0.0,
67
- "train_batch_size": 320,
68
- "trial_name": null,
69
- "trial_params": null
70
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b6-pedal-bin/epoch-010/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8417ba3e031b007cb6ec6f405128686cc6a52eb749b37aa02bed5795f98ca08
3
- size 8017
 
 
 
 
b6-pedal-bin/epoch-010/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "b6", "frames": 65127, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 128, "save_steps": 64}
 
 
b6-pedal-bin/epoch-020/trainer_state.json DELETED
@@ -1,106 +0,0 @@
1
- {
2
- "best_global_step": null,
3
- "best_metric": null,
4
- "best_model_checkpoint": null,
5
- "epoch": 1.0,
6
- "eval_steps": 500,
7
- "global_step": 128,
8
- "is_hyper_param_search": false,
9
- "is_local_process_zero": true,
10
- "is_world_process_zero": true,
11
- "log_history": [
12
- {
13
- "grad_norm": 0.25197651982307434,
14
- "learning_rate": 9.993260441994116e-05,
15
- "loss": 1.2426,
16
- "step": 10
17
- },
18
- {
19
- "grad_norm": 0.20836573839187622,
20
- "learning_rate": 9.759278142180348e-05,
21
- "loss": 1.1191,
22
- "step": 20
23
- },
24
- {
25
- "grad_norm": 0.1473357230424881,
26
- "learning_rate": 9.206267664155907e-05,
27
- "loss": 1.0777,
28
- "step": 30
29
- },
30
- {
31
- "grad_norm": 0.11595264822244644,
32
- "learning_rate": 8.371298899628091e-05,
33
- "loss": 1.0637,
34
- "step": 40
35
- },
36
- {
37
- "grad_norm": 0.21844695508480072,
38
- "learning_rate": 7.310342219701981e-05,
39
- "loss": 1.0536,
40
- "step": 50
41
- },
42
- {
43
- "grad_norm": 0.5528692603111267,
44
- "learning_rate": 6.094516619032975e-05,
45
- "loss": 1.0276,
46
- "step": 60
47
- },
48
- {
49
- "grad_norm": 0.2670411169528961,
50
- "learning_rate": 4.8053224039313125e-05,
51
- "loss": 0.9812,
52
- "step": 70
53
- },
54
- {
55
- "grad_norm": 0.2912217974662781,
56
- "learning_rate": 3.5291779911225186e-05,
57
- "loss": 0.9128,
58
- "step": 80
59
- },
60
- {
61
- "grad_norm": 0.2936597466468811,
62
- "learning_rate": 2.3516270313430083e-05,
63
- "loss": 0.8594,
64
- "step": 90
65
- },
66
- {
67
- "grad_norm": 0.23985952138900757,
68
- "learning_rate": 1.35160417102985e-05,
69
- "loss": 0.8175,
70
- "step": 100
71
- },
72
- {
73
- "grad_norm": 0.20528154075145721,
74
- "learning_rate": 5.9614383468267924e-06,
75
- "loss": 0.796,
76
- "step": 110
77
- },
78
- {
79
- "grad_norm": 0.1692812293767929,
80
- "learning_rate": 1.358867135187636e-06,
81
- "loss": 0.7881,
82
- "step": 120
83
- }
84
- ],
85
- "logging_steps": 10,
86
- "max_steps": 128,
87
- "num_input_tokens_seen": 0,
88
- "num_train_epochs": 9223372036854775807,
89
- "save_steps": 64,
90
- "stateful_callbacks": {
91
- "TrainerControl": {
92
- "args": {
93
- "should_epoch_stop": false,
94
- "should_evaluate": false,
95
- "should_log": false,
96
- "should_save": true,
97
- "should_training_stop": true
98
- },
99
- "attributes": {}
100
- }
101
- },
102
- "total_flos": 0.0,
103
- "train_batch_size": 320,
104
- "trial_name": null,
105
- "trial_params": null
106
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b6-pedal-bin/epoch-020/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8417ba3e031b007cb6ec6f405128686cc6a52eb749b37aa02bed5795f98ca08
3
- size 8017
 
 
 
 
b6-pedal-bin/epoch-020/training_plan.json DELETED
@@ -1 +0,0 @@
1
- {"task": "b6", "frames": 65127, "epochs": 20, "per_gpu_batch": 320, "global_batch": 10240, "max_steps": 128, "save_steps": 64}