Hugging Face's logo

player1537
/
Bloom-560m-LoRA-trained-on-Dolphin

PEFT
TensorBoard
English
Model card Files Metrics Community
1
player1537 commited on
Commit
0486018
·
1 Parent(s): 422f1d4

Training in progress, step 262

Browse files
Files changed (11) hide show
  1. adapter_model.bin +1 -1
  2. last-checkpoint/README.md +1 -0
  3. last-checkpoint/adapter_model.bin +1 -1
  4. last-checkpoint/optimizer.pt +1 -1
  5. last-checkpoint/rng_state.pth +1 -1
  6. last-checkpoint/scheduler.pt +1 -1
  7. last-checkpoint/trainer_state.json +36 -96
  8. last-checkpoint/training_args.bin +1 -1
  9. runs/Jul30_21-45-15_04d48b04b124/events.out.tfevents.1690753519.04d48b04b124.12710.0 +2 -2
  10. runs/Jul30_21-54-04_04d48b04b124/events.out.tfevents.1690754048.04d48b04b124.15811.0 +3 -0
  11. training_args.bin +1 -1
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb3e39c69cf87ac8f88f27ce6f33ebc40816ea621b5669a014b039c0efc7f541
3
  size 3163457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb17bc2fe82d416a3cc83553c026993315e8226c358bb4e5c2daecd7a305cae9
3
  size 3163457
last-checkpoint/README.md CHANGED
@@ -5,5 +5,6 @@ library_name: peft
5
 
6
  ### Framework versions
7
 
 
8
 
9
  - PEFT 0.4.0
 
5
 
6
  ### Framework versions
7
 
8
+ - PEFT 0.4.0
9
 
10
  - PEFT 0.4.0
last-checkpoint/adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb3e39c69cf87ac8f88f27ce6f33ebc40816ea621b5669a014b039c0efc7f541
3
  size 3163457
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb17bc2fe82d416a3cc83553c026993315e8226c358bb4e5c2daecd7a305cae9
3
  size 3163457
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d687ffed6510ec1c76cffe4448a4eb5c5312677e63e6ba40479737f7ad1b8a7f
3
  size 6319689
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c165638982fb21744f847d94ac6044ad06995225c9d8fc3e3de8e9b5c7cb95
3
  size 6319689
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6227a8020263fdf5f88e2d88cee5778418bbde4b0cf3767c692dc92f26c6f75d
3
  size 14639
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5063f67e2c88884cab54e05296e5e83ac9a3c954c9e23cfb2d9a21a6c8d8e10
3
  size 14639
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0efecc10e44e390de6dc6bd5194bdbd19c81b879ba1d4cdb7a5e0d951d3f168
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9935b5a06054c8c90ed974465d8053eb5fdd3df979620133d59a0646585b7e
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,142 +1,82 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.3002865329512894,
5
- "global_step": 524,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.0,
12
- "learning_rate": 1.9988538681948425e-05,
13
- "loss": 3.3001,
14
  "step": 1
15
  },
16
  {
17
- "epoch": 0.01,
18
- "learning_rate": 1.970200573065903e-05,
19
- "loss": 2.9734,
20
  "step": 26
21
  },
22
  {
23
- "epoch": 0.03,
24
- "learning_rate": 1.9404011461318052e-05,
25
- "loss": 2.9919,
26
  "step": 52
27
  },
28
  {
29
- "epoch": 0.04,
30
- "learning_rate": 1.910601719197708e-05,
31
- "loss": 2.9257,
32
  "step": 78
33
  },
34
  {
35
- "epoch": 0.06,
36
- "learning_rate": 1.8808022922636103e-05,
37
- "loss": 2.9255,
38
  "step": 104
39
  },
40
  {
41
- "epoch": 0.07,
42
- "learning_rate": 1.851002865329513e-05,
43
- "loss": 2.9036,
44
  "step": 130
45
  },
46
  {
47
- "epoch": 0.09,
48
- "learning_rate": 1.8212034383954157e-05,
49
- "loss": 2.9194,
50
  "step": 156
51
  },
52
  {
53
- "epoch": 0.1,
54
- "learning_rate": 1.791404011461318e-05,
55
- "loss": 2.726,
56
  "step": 182
57
  },
58
  {
59
- "epoch": 0.12,
60
- "learning_rate": 1.7616045845272208e-05,
61
- "loss": 2.909,
62
  "step": 208
63
  },
64
  {
65
- "epoch": 0.13,
66
- "learning_rate": 1.7318051575931235e-05,
67
- "loss": 2.6554,
68
  "step": 234
69
  },
70
  {
71
- "epoch": 0.15,
72
- "learning_rate": 1.702005730659026e-05,
73
- "loss": 2.7529,
74
  "step": 260
75
- },
76
- {
77
- "epoch": 0.16,
78
- "learning_rate": 1.6722063037249286e-05,
79
- "loss": 2.7147,
80
- "step": 286
81
- },
82
- {
83
- "epoch": 0.18,
84
- "learning_rate": 1.642406876790831e-05,
85
- "loss": 2.695,
86
- "step": 312
87
- },
88
- {
89
- "epoch": 0.19,
90
- "learning_rate": 1.6137535816618913e-05,
91
- "loss": 2.7071,
92
- "step": 338
93
- },
94
- {
95
- "epoch": 0.21,
96
- "learning_rate": 1.583954154727794e-05,
97
- "loss": 2.7039,
98
- "step": 364
99
- },
100
- {
101
- "epoch": 0.22,
102
- "learning_rate": 1.5541547277936964e-05,
103
- "loss": 2.7586,
104
- "step": 390
105
- },
106
- {
107
- "epoch": 0.24,
108
- "learning_rate": 1.5243553008595991e-05,
109
- "loss": 2.8132,
110
- "step": 416
111
- },
112
- {
113
- "epoch": 0.25,
114
- "learning_rate": 1.495702005730659e-05,
115
- "loss": 2.7552,
116
- "step": 442
117
- },
118
- {
119
- "epoch": 0.27,
120
- "learning_rate": 1.4659025787965618e-05,
121
- "loss": 2.7388,
122
- "step": 468
123
- },
124
- {
125
- "epoch": 0.28,
126
- "learning_rate": 1.4361031518624645e-05,
127
- "loss": 2.6576,
128
- "step": 494
129
- },
130
- {
131
- "epoch": 0.3,
132
- "learning_rate": 1.4063037249283669e-05,
133
- "loss": 2.6962,
134
- "step": 520
135
  }
136
  ],
137
- "max_steps": 1745,
138
  "num_train_epochs": 1,
139
- "total_flos": 975816804532224.0,
140
  "trial_name": null,
141
  "trial_params": null
142
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03031705623698218,
5
+ "global_step": 262,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
9
  "log_history": [
10
  {
11
  "epoch": 0.0,
12
+ "learning_rate": 1.9997685720897943e-05,
13
+ "loss": 2.316,
14
  "step": 1
15
  },
16
  {
17
+ "epoch": 0.0,
18
+ "learning_rate": 1.993982874334645e-05,
19
+ "loss": 3.0145,
20
  "step": 26
21
  },
22
  {
23
+ "epoch": 0.01,
24
+ "learning_rate": 1.9881971765794957e-05,
25
+ "loss": 2.9775,
26
  "step": 52
27
  },
28
  {
29
+ "epoch": 0.01,
30
+ "learning_rate": 1.9821800509141405e-05,
31
+ "loss": 2.9141,
32
  "step": 78
33
  },
34
  {
35
+ "epoch": 0.01,
36
+ "learning_rate": 1.976162925248785e-05,
37
+ "loss": 2.8213,
38
  "step": 104
39
  },
40
  {
41
+ "epoch": 0.02,
42
+ "learning_rate": 1.9701457995834298e-05,
43
+ "loss": 2.8003,
44
  "step": 130
45
  },
46
  {
47
+ "epoch": 0.02,
48
+ "learning_rate": 1.9641286739180746e-05,
49
+ "loss": 2.8823,
50
  "step": 156
51
  },
52
  {
53
+ "epoch": 0.02,
54
+ "learning_rate": 1.9581115482527195e-05,
55
+ "loss": 2.8253,
56
  "step": 182
57
  },
58
  {
59
+ "epoch": 0.02,
60
+ "learning_rate": 1.9520944225873643e-05,
61
+ "loss": 2.7823,
62
  "step": 208
63
  },
64
  {
65
+ "epoch": 0.03,
66
+ "learning_rate": 1.946077296922009e-05,
67
+ "loss": 2.7374,
68
  "step": 234
69
  },
70
  {
71
+ "epoch": 0.03,
72
+ "learning_rate": 1.9402915991668595e-05,
73
+ "loss": 2.8325,
74
  "step": 260
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  }
76
  ],
77
+ "max_steps": 8642,
78
  "num_train_epochs": 1,
79
+ "total_flos": 487908402266112.0,
80
  "trial_name": null,
81
  "trial_params": null
82
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdb95308720d4497fd5245399d223487b98a1eda7b2b9a7b69e1bde4f1d73925
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df21442a83629064d51dbf553c12fcf058ba3dd0e15292ad62178e5a432f012
3
  size 4027
runs/Jul30_21-45-15_04d48b04b124/events.out.tfevents.1690753519.04d48b04b124.12710.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08b8b3fba46577efad57cda38fc4207645b4446372c05c26f20f746cc1d5014e
3
- size 7485
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db92c9eb0b2003c64afa3c67bd18498972a6e01e54fa23531a5b93824dcdbe7c
3
+ size 7642
runs/Jul30_21-54-04_04d48b04b124/events.out.tfevents.1690754048.04d48b04b124.15811.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f8e253ff0a0dc0d228774fbeb2adc26677b503720137c05eaa52f7264a13df
3
+ size 5915
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdb95308720d4497fd5245399d223487b98a1eda7b2b9a7b69e1bde4f1d73925
3
  size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4df21442a83629064d51dbf553c12fcf058ba3dd0e15292ad62178e5a432f012
3
  size 4027