TinyPixel commited on
Commit
87f731a
1 Parent(s): 30e5618

Upload folder using huggingface_hub

Browse files
adapter_config.json CHANGED
@@ -19,13 +19,13 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "up_proj",
23
- "down_proj",
24
  "o_proj",
 
 
 
25
  "v_proj",
26
  "k_proj",
27
- "q_proj",
28
- "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
 
 
22
  "o_proj",
23
+ "up_proj",
24
+ "q_proj",
25
+ "gate_proj",
26
  "v_proj",
27
  "k_proj",
28
+ "down_proj"
 
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a4bdfe21901b0e7f28208c1ff82244cdeca9afb0e3b600d06f0dbe0aae6f02db
3
  size 276869160
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8bafd3a985567d67290cc07b5ebe5f27e83549efae700a39e677272a413156ec
3
  size 276869160
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7278ab5383fb73f156876b77a470c29973f44e2a8f22b09fcd6c0923de141368
3
  size 553854714
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e1ee127ea3e984d65847f9f3f210e1c0ca73e881f8a0823b364a658868ef78
3
  size 553854714
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e319566a894c1c789e0dc6938468bf9d165f0503bd5dd83febd67de675e0453e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:007b19f8cc7363dbd119b3a310ca27de8a43abefca81f682d933eed470b6b184
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea6e04a1d21943153bccd8fabf6e768143cbd324f058ed3a0b5adbbae648857c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b519929af133aadaab5e54d422c1341c550e265b55d133dc489fa6313be6ad6
3
  size 1064
trainer_state.json CHANGED
@@ -11,145 +11,145 @@
11
  {
12
  "epoch": 0.04,
13
  "learning_rate": 0.0,
14
- "loss": 1.9142,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.08,
19
  "learning_rate": 0.0,
20
- "loss": 2.2468,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.12,
25
  "learning_rate": 1e-05,
26
- "loss": 2.3153,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.16,
31
  "learning_rate": 1.9976687691905394e-05,
32
- "loss": 2.3005,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.21,
37
  "learning_rate": 1.9906859460363307e-05,
38
- "loss": 2.4715,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.25,
43
- "learning_rate": 1.9906859460363307e-05,
44
- "loss": 2.6328,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.29,
49
- "learning_rate": 1.9629172873477995e-05,
50
- "loss": 1.9654,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.33,
55
- "learning_rate": 1.917211301505453e-05,
56
- "loss": 2.1935,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.37,
61
- "learning_rate": 1.8544194045464888e-05,
62
- "loss": 2.1805,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.41,
67
- "learning_rate": 1.77571129070442e-05,
68
- "loss": 2.2827,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.45,
73
- "learning_rate": 1.6825531432186545e-05,
74
- "loss": 2.3124,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.49,
79
- "learning_rate": 1.5766803221148676e-05,
80
- "loss": 2.6128,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.53,
85
- "learning_rate": 1.4600650377311523e-05,
86
- "loss": 1.8219,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.57,
91
- "learning_rate": 1.3348796121709862e-05,
92
- "loss": 2.096,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.62,
97
- "learning_rate": 1.2034560130526341e-05,
98
- "loss": 2.176,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.66,
103
- "learning_rate": 1.0682424133646712e-05,
104
- "loss": 2.0975,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.7,
109
- "learning_rate": 9.317575866353293e-06,
110
- "loss": 2.0707,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.74,
115
- "learning_rate": 7.965439869473664e-06,
116
- "loss": 2.3809,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.78,
121
- "learning_rate": 6.651203878290139e-06,
122
- "loss": 1.7672,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.82,
127
- "learning_rate": 5.399349622688479e-06,
128
- "loss": 2.1201,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.86,
133
- "learning_rate": 4.2331967788513295e-06,
134
- "loss": 2.1698,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.9,
139
- "learning_rate": 3.174468567813461e-06,
140
- "loss": 2.0884,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.94,
145
- "learning_rate": 2.2428870929558012e-06,
146
- "loss": 2.2344,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.98,
151
- "learning_rate": 1.4558059545351144e-06,
152
- "loss": 2.3548,
153
  "step": 48
154
  }
155
  ],
@@ -158,7 +158,7 @@
158
  "num_input_tokens_seen": 0,
159
  "num_train_epochs": 1,
160
  "save_steps": 500,
161
- "total_flos": 4209565323866112.0,
162
  "train_batch_size": 1,
163
  "trial_name": null,
164
  "trial_params": null
 
11
  {
12
  "epoch": 0.04,
13
  "learning_rate": 0.0,
14
+ "loss": 1.9361,
15
  "step": 2
16
  },
17
  {
18
  "epoch": 0.08,
19
  "learning_rate": 0.0,
20
+ "loss": 2.1523,
21
  "step": 4
22
  },
23
  {
24
  "epoch": 0.12,
25
  "learning_rate": 1e-05,
26
+ "loss": 2.2792,
27
  "step": 6
28
  },
29
  {
30
  "epoch": 0.16,
31
  "learning_rate": 1.9976687691905394e-05,
32
+ "loss": 2.2289,
33
  "step": 8
34
  },
35
  {
36
  "epoch": 0.21,
37
  "learning_rate": 1.9906859460363307e-05,
38
+ "loss": 2.2699,
39
  "step": 10
40
  },
41
  {
42
  "epoch": 0.25,
43
+ "learning_rate": 1.979084087682323e-05,
44
+ "loss": 2.5859,
45
  "step": 12
46
  },
47
  {
48
  "epoch": 0.29,
49
+ "learning_rate": 1.9422609221188208e-05,
50
+ "loss": 1.8846,
51
  "step": 14
52
  },
53
  {
54
  "epoch": 0.33,
55
+ "learning_rate": 1.8878852184023754e-05,
56
+ "loss": 2.2629,
57
  "step": 16
58
  },
59
  {
60
  "epoch": 0.37,
61
+ "learning_rate": 1.816969893010442e-05,
62
+ "loss": 2.1982,
63
  "step": 18
64
  },
65
  {
66
  "epoch": 0.41,
67
+ "learning_rate": 1.730835964278124e-05,
68
+ "loss": 2.2893,
69
  "step": 20
70
  },
71
  {
72
  "epoch": 0.45,
73
+ "learning_rate": 1.631087944326053e-05,
74
+ "loss": 2.1624,
75
  "step": 22
76
  },
77
  {
78
  "epoch": 0.49,
79
+ "learning_rate": 1.5195839500354337e-05,
80
+ "loss": 2.5566,
81
  "step": 24
82
  },
83
  {
84
  "epoch": 0.53,
85
+ "learning_rate": 1.3984010898462417e-05,
86
+ "loss": 1.9081,
87
  "step": 26
88
  },
89
  {
90
  "epoch": 0.57,
91
+ "learning_rate": 1.2697967711570243e-05,
92
+ "loss": 1.9444,
93
  "step": 28
94
  },
95
  {
96
  "epoch": 0.62,
97
+ "learning_rate": 1.1361666490962468e-05,
98
+ "loss": 2.1857,
99
  "step": 30
100
  },
101
  {
102
  "epoch": 0.66,
103
+ "learning_rate": 1e-05,
104
+ "loss": 2.1617,
105
  "step": 32
106
  },
107
  {
108
  "epoch": 0.7,
109
+ "learning_rate": 8.638333509037537e-06,
110
+ "loss": 2.3324,
111
  "step": 34
112
  },
113
  {
114
  "epoch": 0.74,
115
+ "learning_rate": 7.3020322884297565e-06,
116
+ "loss": 2.5691,
117
  "step": 36
118
  },
119
  {
120
  "epoch": 0.78,
121
+ "learning_rate": 6.015989101537586e-06,
122
+ "loss": 1.7745,
123
  "step": 38
124
  },
125
  {
126
  "epoch": 0.82,
127
+ "learning_rate": 4.804160499645667e-06,
128
+ "loss": 2.1199,
129
  "step": 40
130
  },
131
  {
132
  "epoch": 0.86,
133
+ "learning_rate": 3.689120556739475e-06,
134
+ "loss": 2.3115,
135
  "step": 42
136
  },
137
  {
138
  "epoch": 0.9,
139
+ "learning_rate": 2.691640357218759e-06,
140
+ "loss": 2.1067,
141
  "step": 44
142
  },
143
  {
144
  "epoch": 0.94,
145
+ "learning_rate": 1.8303010698955803e-06,
146
+ "loss": 2.1117,
147
  "step": 46
148
  },
149
  {
150
  "epoch": 0.98,
151
+ "learning_rate": 1.121147815976248e-06,
152
+ "loss": 2.3375,
153
  "step": 48
154
  }
155
  ],
 
158
  "num_input_tokens_seen": 0,
159
  "num_train_epochs": 1,
160
  "save_steps": 500,
161
+ "total_flos": 4218566835981312.0,
162
  "train_batch_size": 1,
163
  "trial_name": null,
164
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb5fa794dd085c12ddd3821b61ce97da7a0bd8dc5401ea148d9aa0574571e0ce
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27fc96fad5c4fb474362bc6a16da79d507da334907928c28f9c40352501fcf72
3
  size 4728