Hugging Face's logo

lfhe
/
task-2-microsoft-Phi-3.5-mini-instruct

PEFT
Safetensors
Model card Files
xet
 Community
lfhe commited on
Commit
842d896
·
1 Parent(s): 6dc4597

update

Browse files
Files changed (4) hide show
  1. adapter_config.json +2 -2
  2. adapter_model.safetensors +1 -1
  3. trainer_state.json +162 -0
  4. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "qkv_proj",
24
- "o_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
+ "o_proj",
24
+ "qkv_proj"
25
  ],
26
  "task_type": "CAUSAL_LM",
27
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ec8449dfadc4ff49a10b07a83ec8c7855982cd33502ae4d0ab2a6cbd8cc5e3c
3
  size 302007584
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7912d8e411f5d7d80336613b03f57c0f3182d3cb4cbf910d47468050d35c07b
3
  size 302007584
trainer_state.json ADDED
@@ -0,0 +1,162 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.67741935483871,
5
+ "eval_steps": 40,
6
+ "global_step": 150,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6451612903225806,
13
+ "grad_norm": 0.8625742793083191,
14
+ "learning_rate": 4e-05,
15
+ "loss": 0.7057,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 1.2903225806451613,
20
+ "grad_norm": 0.7124119400978088,
21
+ "learning_rate": 8e-05,
22
+ "loss": 0.6741,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 1.935483870967742,
27
+ "grad_norm": 0.7693650126457214,
28
+ "learning_rate": 0.00012,
29
+ "loss": 0.5941,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 2.5806451612903225,
34
+ "grad_norm": 0.6899323463439941,
35
+ "learning_rate": 0.00016,
36
+ "loss": 0.547,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 2.5806451612903225,
41
+ "eval_loss": 0.48405569791793823,
42
+ "eval_runtime": 2.1967,
43
+ "eval_samples_per_second": 0.455,
44
+ "eval_steps_per_second": 0.455,
45
+ "step": 40
46
+ },
47
+ {
48
+ "epoch": 3.225806451612903,
49
+ "grad_norm": 0.564319908618927,
50
+ "learning_rate": 0.0002,
51
+ "loss": 0.5046,
52
+ "step": 50
53
+ },
54
+ {
55
+ "epoch": 3.870967741935484,
56
+ "grad_norm": 0.6034739017486572,
57
+ "learning_rate": 0.00024,
58
+ "loss": 0.4842,
59
+ "step": 60
60
+ },
61
+ {
62
+ "epoch": 4.516129032258064,
63
+ "grad_norm": 0.6102902293205261,
64
+ "learning_rate": 0.00028,
65
+ "loss": 0.4531,
66
+ "step": 70
67
+ },
68
+ {
69
+ "epoch": 5.161290322580645,
70
+ "grad_norm": 0.7875820398330688,
71
+ "learning_rate": 0.00032,
72
+ "loss": 0.4389,
73
+ "step": 80
74
+ },
75
+ {
76
+ "epoch": 5.161290322580645,
77
+ "eval_loss": 0.4346591830253601,
78
+ "eval_runtime": 2.1674,
79
+ "eval_samples_per_second": 0.461,
80
+ "eval_steps_per_second": 0.461,
81
+ "step": 80
82
+ },
83
+ {
84
+ "epoch": 5.806451612903226,
85
+ "grad_norm": 0.8663121461868286,
86
+ "learning_rate": 0.00036,
87
+ "loss": 0.4177,
88
+ "step": 90
89
+ },
90
+ {
91
+ "epoch": 6.451612903225806,
92
+ "grad_norm": 0.9721035957336426,
93
+ "learning_rate": 0.0004,
94
+ "loss": 0.4046,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 7.096774193548387,
99
+ "grad_norm": 0.9510289430618286,
100
+ "learning_rate": 0.00032,
101
+ "loss": 0.3788,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 7.741935483870968,
106
+ "grad_norm": 1.0126413106918335,
107
+ "learning_rate": 0.00024,
108
+ "loss": 0.3673,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 7.741935483870968,
113
+ "eval_loss": 0.4241188168525696,
114
+ "eval_runtime": 2.195,
115
+ "eval_samples_per_second": 0.456,
116
+ "eval_steps_per_second": 0.456,
117
+ "step": 120
118
+ },
119
+ {
120
+ "epoch": 8.387096774193548,
121
+ "grad_norm": 1.116309642791748,
122
+ "learning_rate": 0.00016,
123
+ "loss": 0.3449,
124
+ "step": 130
125
+ },
126
+ {
127
+ "epoch": 9.03225806451613,
128
+ "grad_norm": 0.9966815710067749,
129
+ "learning_rate": 8e-05,
130
+ "loss": 0.3338,
131
+ "step": 140
132
+ },
133
+ {
134
+ "epoch": 9.67741935483871,
135
+ "grad_norm": 1.0189791917800903,
136
+ "learning_rate": 0.0,
137
+ "loss": 0.3202,
138
+ "step": 150
139
+ }
140
+ ],
141
+ "logging_steps": 10,
142
+ "max_steps": 150,
143
+ "num_input_tokens_seen": 0,
144
+ "num_train_epochs": 10,
145
+ "save_steps": 40,
146
+ "stateful_callbacks": {
147
+ "TrainerControl": {
148
+ "args": {
149
+ "should_epoch_stop": false,
150
+ "should_evaluate": false,
151
+ "should_log": false,
152
+ "should_save": true,
153
+ "should_training_stop": true
154
+ },
155
+ "attributes": {}
156
+ }
157
+ },
158
+ "total_flos": 3.946319309952778e+17,
159
+ "train_batch_size": 4,
160
+ "trial_name": null,
161
+ "trial_params": null
162
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c76a307f875d3d5c33881e8a66d5cdafba4e34a4b8c8fa27b1d5006539590f23
3
  size 5560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5882aff5f742df4d7dd91ec7f9cb107a4384cedbeb2dcf0f7bb37cffd4a7ad
3
  size 5560