Hugging Face's logo

starlineventures
/
outputs

Text Generation
Transformers
Safetensors
qwen2
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
starlineventures commited on
Commit
bfd25d1
·
verified ·
1 Parent(s): 37d15bb

starlineventures/pilot-talk

Browse files
Files changed (7) hide show
  1. README.md +2 -2
  2. adapter_config.json +4 -4
  3. adapter_model.safetensors +1 -1
  4. all_results.json +5 -5
  5. train_results.json +5 -5
  6. trainer_state.json +112 -63
  7. training_args.bin +1 -1
README.md CHANGED
@@ -36,12 +36,12 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0001
39
- - train_batch_size: 10
40
  - eval_batch_size: 16
41
  - seed: 3407
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
- - num_epochs: 2
45
 
46
  ### Training results
47
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 0.0001
39
+ - train_batch_size: 5
40
  - eval_batch_size: 16
41
  - seed: 3407
42
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
  - lr_scheduler_type: linear
44
+ - num_epochs: 3
45
 
46
  ### Training results
47
 
adapter_config.json CHANGED
@@ -23,13 +23,13 @@
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
26
- "v_proj",
27
- "up_proj",
28
  "down_proj",
 
29
  "q_proj",
30
- "o_proj",
31
  "k_proj",
32
- "gate_proj"
 
33
  ],
34
  "task_type": null,
35
  "use_dora": false,
 
23
  "rank_pattern": {},
24
  "revision": null,
25
  "target_modules": [
 
 
26
  "down_proj",
27
+ "v_proj",
28
  "q_proj",
29
+ "gate_proj",
30
  "k_proj",
31
+ "up_proj",
32
+ "o_proj"
33
  ],
34
  "task_type": null,
35
  "use_dora": false,
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e66932712cc6978913634cebf6137e4645ceba968663ffe2270fbf1dc51d50c
3
  size 94422368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:618af00e309753cefbd7ef5740bfcd86b4d7fb319aeec37ac9eb20727dd70fc0
3
  size 94422368
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.625,
3
  "total_flos": 0.0,
4
- "train_loss": 0.2457691999582144,
5
- "train_runtime": 133.1729,
6
- "train_samples_per_second": 12.014,
7
- "train_steps_per_second": 1.201
8
  }
 
1
  {
2
+ "epoch": 1.25,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.2832891649007797,
5
+ "train_runtime": 123.2677,
6
+ "train_samples_per_second": 19.47,
7
+ "train_steps_per_second": 3.894
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.625,
3
  "total_flos": 0.0,
4
- "train_loss": 0.2457691999582144,
5
- "train_runtime": 133.1729,
6
- "train_samples_per_second": 12.014,
7
- "train_steps_per_second": 1.201
8
  }
 
1
  {
2
+ "epoch": 1.25,
3
  "total_flos": 0.0,
4
+ "train_loss": 0.2832891649007797,
5
+ "train_runtime": 123.2677,
6
+ "train_samples_per_second": 19.47,
7
+ "train_steps_per_second": 3.894
8
  }
trainer_state.json CHANGED
@@ -1,118 +1,167 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 1.625,
5
  "eval_steps": 500,
6
- "global_step": 130,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.125,
13
- "grad_norm": 21.495697021484375,
14
- "learning_rate": 9.375e-05,
15
- "loss": 1.2248,
16
  "step": 10
17
  },
18
  {
19
- "epoch": 0.25,
20
- "grad_norm": 24.887985229492188,
21
- "learning_rate": 8.75e-05,
22
- "loss": 0.3582,
23
  "step": 20
24
  },
25
  {
26
- "epoch": 0.375,
27
- "grad_norm": 19.630859375,
28
- "learning_rate": 8.125000000000001e-05,
29
- "loss": 0.2253,
30
  "step": 30
31
  },
32
  {
33
- "epoch": 0.5,
34
- "grad_norm": 20.30435562133789,
35
- "learning_rate": 7.500000000000001e-05,
36
- "loss": 0.1816,
37
  "step": 40
38
  },
39
  {
40
- "epoch": 0.625,
41
- "grad_norm": 24.925588607788086,
42
- "learning_rate": 6.875e-05,
43
- "loss": 0.1588,
44
  "step": 50
45
  },
46
  {
47
- "epoch": 0.75,
48
- "grad_norm": 24.958547592163086,
49
- "learning_rate": 6.25e-05,
50
- "loss": 0.1508,
51
  "step": 60
52
  },
53
  {
54
- "epoch": 0.875,
55
- "grad_norm": 25.598276138305664,
56
- "learning_rate": 5.6250000000000005e-05,
57
- "loss": 0.1384,
58
  "step": 70
59
  },
60
  {
61
- "epoch": 1.0,
62
- "grad_norm": 25.500638961791992,
63
- "learning_rate": 5e-05,
64
- "loss": 0.1316,
65
  "step": 80
66
  },
67
  {
68
- "epoch": 1.125,
69
- "grad_norm": 26.4311466217041,
70
- "learning_rate": 4.375e-05,
71
- "loss": 0.127,
72
  "step": 90
73
  },
74
  {
75
- "epoch": 1.25,
76
- "grad_norm": 27.138051986694336,
77
- "learning_rate": 3.7500000000000003e-05,
78
- "loss": 0.1265,
79
  "step": 100
80
  },
81
  {
82
- "epoch": 1.375,
83
- "grad_norm": 27.014684677124023,
84
- "learning_rate": 3.125e-05,
85
- "loss": 0.1247,
86
  "step": 110
87
  },
88
  {
89
- "epoch": 1.5,
90
- "grad_norm": 26.983625411987305,
91
- "learning_rate": 2.5e-05,
92
- "loss": 0.125,
93
  "step": 120
94
  },
95
  {
96
- "epoch": 1.625,
97
- "grad_norm": 27.20880126953125,
98
- "learning_rate": 1.8750000000000002e-05,
99
- "loss": 0.1223,
100
  "step": 130
101
  },
102
  {
103
- "epoch": 1.625,
104
- "step": 130,
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  "total_flos": 0.0,
106
- "train_loss": 0.2457691999582144,
107
- "train_runtime": 133.1729,
108
- "train_samples_per_second": 12.014,
109
- "train_steps_per_second": 1.201
110
  }
111
  ],
112
  "logging_steps": 10,
113
- "max_steps": 160,
114
  "num_input_tokens_seen": 0,
115
- "num_train_epochs": 2,
116
  "save_steps": 500,
117
  "stateful_callbacks": {
118
  "TrainerControl": {
@@ -127,7 +176,7 @@
127
  }
128
  },
129
  "total_flos": 0.0,
130
- "train_batch_size": 10,
131
  "trial_name": null,
132
  "trial_params": null
133
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.25,
5
  "eval_steps": 500,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.0625,
13
+ "grad_norm": 42.53068923950195,
14
+ "learning_rate": 9.791666666666667e-05,
15
+ "loss": 1.6155,
16
  "step": 10
17
  },
18
  {
19
+ "epoch": 0.125,
20
+ "grad_norm": 43.14527130126953,
21
+ "learning_rate": 9.583333333333334e-05,
22
+ "loss": 0.7779,
23
  "step": 20
24
  },
25
  {
26
+ "epoch": 0.1875,
27
+ "grad_norm": 42.024879455566406,
28
+ "learning_rate": 9.375e-05,
29
+ "loss": 0.3742,
30
  "step": 30
31
  },
32
  {
33
+ "epoch": 0.25,
34
+ "grad_norm": 40.460575103759766,
35
+ "learning_rate": 9.166666666666667e-05,
36
+ "loss": 0.2596,
37
  "step": 40
38
  },
39
  {
40
+ "epoch": 0.3125,
41
+ "grad_norm": 29.57782554626465,
42
+ "learning_rate": 8.958333333333335e-05,
43
+ "loss": 0.2438,
44
  "step": 50
45
  },
46
  {
47
+ "epoch": 0.375,
48
+ "grad_norm": 29.711307525634766,
49
+ "learning_rate": 8.75e-05,
50
+ "loss": 0.2827,
51
  "step": 60
52
  },
53
  {
54
+ "epoch": 0.4375,
55
+ "grad_norm": 31.016084671020508,
56
+ "learning_rate": 8.541666666666666e-05,
57
+ "loss": 0.2664,
58
  "step": 70
59
  },
60
  {
61
+ "epoch": 0.5,
62
+ "grad_norm": 36.58619689941406,
63
+ "learning_rate": 8.333333333333334e-05,
64
+ "loss": 0.2032,
65
  "step": 80
66
  },
67
  {
68
+ "epoch": 0.5625,
69
+ "grad_norm": 32.24593734741211,
70
+ "learning_rate": 8.125000000000001e-05,
71
+ "loss": 0.1676,
72
  "step": 90
73
  },
74
  {
75
+ "epoch": 0.625,
76
+ "grad_norm": 30.47890853881836,
77
+ "learning_rate": 7.916666666666666e-05,
78
+ "loss": 0.1566,
79
  "step": 100
80
  },
81
  {
82
+ "epoch": 0.6875,
83
+ "grad_norm": 32.572731018066406,
84
+ "learning_rate": 7.708333333333334e-05,
85
+ "loss": 0.148,
86
  "step": 110
87
  },
88
  {
89
+ "epoch": 0.75,
90
+ "grad_norm": 36.662147521972656,
91
+ "learning_rate": 7.500000000000001e-05,
92
+ "loss": 0.1436,
93
  "step": 120
94
  },
95
  {
96
+ "epoch": 0.8125,
97
+ "grad_norm": 36.703155517578125,
98
+ "learning_rate": 7.291666666666667e-05,
99
+ "loss": 0.1374,
100
  "step": 130
101
  },
102
  {
103
+ "epoch": 0.875,
104
+ "grad_norm": 36.09929656982422,
105
+ "learning_rate": 7.083333333333334e-05,
106
+ "loss": 0.1344,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.9375,
111
+ "grad_norm": 36.28221893310547,
112
+ "learning_rate": 6.875e-05,
113
+ "loss": 0.1314,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 1.0,
118
+ "grad_norm": 34.68128967285156,
119
+ "learning_rate": 6.666666666666667e-05,
120
+ "loss": 0.1282,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 1.0625,
125
+ "grad_norm": 34.41044616699219,
126
+ "learning_rate": 6.458333333333334e-05,
127
+ "loss": 0.1253,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 1.125,
132
+ "grad_norm": 34.5189323425293,
133
+ "learning_rate": 6.25e-05,
134
+ "loss": 0.1241,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 1.1875,
139
+ "grad_norm": 34.811683654785156,
140
+ "learning_rate": 6.041666666666667e-05,
141
+ "loss": 0.1229,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 1.25,
146
+ "grad_norm": 34.972721099853516,
147
+ "learning_rate": 5.833333333333334e-05,
148
+ "loss": 0.1231,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 1.25,
153
+ "step": 200,
154
  "total_flos": 0.0,
155
+ "train_loss": 0.2832891649007797,
156
+ "train_runtime": 123.2677,
157
+ "train_samples_per_second": 19.47,
158
+ "train_steps_per_second": 3.894
159
  }
160
  ],
161
  "logging_steps": 10,
162
+ "max_steps": 480,
163
  "num_input_tokens_seen": 0,
164
+ "num_train_epochs": 3,
165
  "save_steps": 500,
166
  "stateful_callbacks": {
167
  "TrainerControl": {
 
176
  }
177
  },
178
  "total_flos": 0.0,
179
+ "train_batch_size": 5,
180
  "trial_name": null,
181
  "trial_params": null
182
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14cc783a36dee3704e3da79bae3b11eb2d9a5095150f30b44c6a202027ac8ba5
3
  size 5432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:616fe51dd08a3eefcb7f6e92081d212fc4108fce67e30260302d2ab6ea932d65
3
  size 5432