jssky commited on
Commit
c4724e0
·
verified ·
1 Parent(s): c9e881c

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_config.json CHANGED
@@ -20,13 +20,13 @@
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
23
- "v_proj",
24
  "up_proj",
25
- "down_proj",
26
- "gate_proj",
27
  "o_proj",
28
- "q_proj",
29
- "k_proj"
 
 
 
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
 
20
  "rank_pattern": {},
21
  "revision": null,
22
  "target_modules": [
 
23
  "up_proj",
 
 
24
  "o_proj",
25
+ "gate_proj",
26
+ "v_proj",
27
+ "k_proj",
28
+ "down_proj",
29
+ "q_proj"
30
  ],
31
  "task_type": "CAUSAL_LM",
32
  "use_dora": false,
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:830f1408e610766aa3d62eb7e9a6d0a81fb7d1896723e93e8e96aabafa800685
3
  size 100966336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c0ecc2e9a75d14c753ea2123cc052ce634a5ace8a27427e3887b3bd040ff88f
3
  size 100966336
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76584b789c82d2cac714da399bcd41a3a28377ccb854de9b44bfc70cdfd548c2
3
  size 202110330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73dccc910fc0d80a1f1722383ca6876f72484cabb53773ec050fab503d4d93db
3
  size 202110330
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6818a44327baca2f62f7480d744e23c8e48485d5cc6712a060c92df637850b
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7728bdc59aadde4575bf49e66aeead240846edcc5d34232d62d361f148155bb9
3
  size 15984
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08a83c8131db177581c328e72cdf50c048d4ace8dd5c8da5db507adefb502530
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0f6aa9810f568d5242b8086b6715096370f41ae04c6f7fce8e90bf28d1d078
3
  size 15984
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0aef13fcaa9c11b2ff403f94c1cdc53687b12672d25dc788dff398dc814ac325
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f4b1b172be50c7eb1536ff1a356db20b5ed8e9f9a112c64f2a2474e0f674b62
3
  size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dae48d4c20573f244a234c5908e300f1d4f979f25df3d23f79718ac9899d5e7c
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96651f983387c136db710938e39ce66ce01e99c60572d33cb5a5915b4d600d38
3
  size 15984
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7db73e8ba9e52e2cda7fd0517f655ef1cceb7c2e0b2230076162db088e9aebee
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:771b46dc67ef57d44ce212c468078fe0941f647e784911d98a6c3b594cf7f1f7
3
  size 15984
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eff3ff7be8c81654b7f7487e8cac92c81bd8f7936a1a2ce6a69ff32d9f1362a6
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd405af3005ab89c6b2360578ef2d3462a63c98b69f3dc7c568ed9623f8301bc
3
  size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b168261fc3a41accdca3740fe30ec4ff4ad80baa9f3c310234f21b23d2bccdd8
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3368f68ab162dee8bae262a5ea9aaccab458e9bccd2fd1c659c3b1425a0ed20c
3
  size 15984
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57751c88c0c4bc5bf818be4acf657342366cd129c785f8722d97d25a41a7f863
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:218f683f8c2d535aeb41099db8d2e6f07926b19de7908a0ab4bbb6bbe76a15bd
3
  size 15984
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eae4efc55c9429b91bdc581cf21d4d1e88799c56c267a0959f657aba014828bf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90ba7ee426c710877af00b51544bc25223e2159a4009a97f5f8c523a61cf68ad
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.04240282685512368,
5
  "eval_steps": 5,
6
- "global_step": 15,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -18,9 +18,9 @@
18
  {
19
  "epoch": 0.0028268551236749115,
20
  "eval_loss": 7.129258632659912,
21
- "eval_runtime": 20.9973,
22
- "eval_samples_per_second": 28.385,
23
- "eval_steps_per_second": 3.572,
24
  "step": 1
25
  },
26
  {
@@ -32,14 +32,14 @@
32
  },
33
  {
34
  "epoch": 0.008480565371024734,
35
- "grad_norm": 5.082520484924316,
36
  "learning_rate": 2e-05,
37
  "loss": 7.4669,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.011307420494699646,
42
- "grad_norm": 4.920047760009766,
43
  "learning_rate": 4e-05,
44
  "loss": 7.1521,
45
  "step": 4
@@ -48,102 +48,145 @@
48
  "epoch": 0.014134275618374558,
49
  "grad_norm": NaN,
50
  "learning_rate": 4e-05,
51
- "loss": 7.7426,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.014134275618374558,
56
- "eval_loss": 7.097348213195801,
57
- "eval_runtime": 20.8903,
58
- "eval_samples_per_second": 28.53,
59
- "eval_steps_per_second": 3.59,
60
  "step": 5
61
  },
62
  {
63
  "epoch": 0.01696113074204947,
64
- "grad_norm": 4.500086784362793,
65
  "learning_rate": 6e-05,
66
- "loss": 7.1859,
67
  "step": 6
68
  },
69
  {
70
  "epoch": 0.019787985865724382,
71
- "grad_norm": 3.6024482250213623,
72
  "learning_rate": 8e-05,
73
- "loss": 6.9672,
74
  "step": 7
75
  },
76
  {
77
  "epoch": 0.022614840989399292,
78
- "grad_norm": 4.331362724304199,
79
  "learning_rate": 0.0001,
80
- "loss": 7.2915,
81
  "step": 8
82
  },
83
  {
84
  "epoch": 0.025441696113074206,
85
- "grad_norm": 3.071237564086914,
86
  "learning_rate": 0.00012,
87
- "loss": 7.2579,
88
  "step": 9
89
  },
90
  {
91
  "epoch": 0.028268551236749116,
92
- "grad_norm": 3.218928813934326,
93
  "learning_rate": 0.00014,
94
- "loss": 7.0417,
95
  "step": 10
96
  },
97
  {
98
  "epoch": 0.028268551236749116,
99
- "eval_loss": 6.332116603851318,
100
- "eval_runtime": 20.7973,
101
- "eval_samples_per_second": 28.658,
102
- "eval_steps_per_second": 3.606,
103
  "step": 10
104
  },
105
  {
106
  "epoch": 0.03109540636042403,
107
- "grad_norm": 2.1495420932769775,
108
  "learning_rate": 0.00016,
109
- "loss": 6.1519,
110
  "step": 11
111
  },
112
  {
113
  "epoch": 0.03392226148409894,
114
- "grad_norm": 2.033008337020874,
115
  "learning_rate": 0.00018,
116
- "loss": 6.6133,
117
  "step": 12
118
  },
119
  {
120
  "epoch": 0.03674911660777385,
121
- "grad_norm": 2.2604849338531494,
122
  "learning_rate": 0.0002,
123
- "loss": 6.1704,
124
  "step": 13
125
  },
126
  {
127
  "epoch": 0.039575971731448764,
128
- "grad_norm": 1.981244683265686,
129
  "learning_rate": 0.00019510565162951537,
130
- "loss": 6.0664,
131
  "step": 14
132
  },
133
  {
134
  "epoch": 0.04240282685512368,
135
- "grad_norm": 1.9168858528137207,
136
  "learning_rate": 0.00018090169943749476,
137
- "loss": 5.7705,
138
  "step": 15
139
  },
140
  {
141
  "epoch": 0.04240282685512368,
142
- "eval_loss": 5.497771263122559,
143
- "eval_runtime": 20.7925,
144
- "eval_samples_per_second": 28.664,
145
- "eval_steps_per_second": 3.607,
146
  "step": 15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  ],
149
  "logging_steps": 1,
@@ -158,12 +201,12 @@
158
  "should_evaluate": false,
159
  "should_log": false,
160
  "should_save": true,
161
- "should_training_stop": false
162
  },
163
  "attributes": {}
164
  }
165
  },
166
- "total_flos": 1.989781642805248e+16,
167
  "train_batch_size": 1,
168
  "trial_name": null,
169
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05653710247349823,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
18
  {
19
  "epoch": 0.0028268551236749115,
20
  "eval_loss": 7.129258632659912,
21
+ "eval_runtime": 13.6697,
22
+ "eval_samples_per_second": 43.6,
23
+ "eval_steps_per_second": 5.487,
24
  "step": 1
25
  },
26
  {
 
32
  },
33
  {
34
  "epoch": 0.008480565371024734,
35
+ "grad_norm": 5.114774703979492,
36
  "learning_rate": 2e-05,
37
  "loss": 7.4669,
38
  "step": 3
39
  },
40
  {
41
  "epoch": 0.011307420494699646,
42
+ "grad_norm": 4.991275310516357,
43
  "learning_rate": 4e-05,
44
  "loss": 7.1521,
45
  "step": 4
 
48
  "epoch": 0.014134275618374558,
49
  "grad_norm": NaN,
50
  "learning_rate": 4e-05,
51
+ "loss": 7.7429,
52
  "step": 5
53
  },
54
  {
55
  "epoch": 0.014134275618374558,
56
+ "eval_loss": 7.097643852233887,
57
+ "eval_runtime": 20.7137,
58
+ "eval_samples_per_second": 28.773,
59
+ "eval_steps_per_second": 3.621,
60
  "step": 5
61
  },
62
  {
63
  "epoch": 0.01696113074204947,
64
+ "grad_norm": 4.559197902679443,
65
  "learning_rate": 6e-05,
66
+ "loss": 7.1861,
67
  "step": 6
68
  },
69
  {
70
  "epoch": 0.019787985865724382,
71
+ "grad_norm": 3.6284019947052,
72
  "learning_rate": 8e-05,
73
+ "loss": 6.9673,
74
  "step": 7
75
  },
76
  {
77
  "epoch": 0.022614840989399292,
78
+ "grad_norm": 4.3491082191467285,
79
  "learning_rate": 0.0001,
80
+ "loss": 7.2919,
81
  "step": 8
82
  },
83
  {
84
  "epoch": 0.025441696113074206,
85
+ "grad_norm": 3.08682918548584,
86
  "learning_rate": 0.00012,
87
+ "loss": 7.258,
88
  "step": 9
89
  },
90
  {
91
  "epoch": 0.028268551236749116,
92
+ "grad_norm": 3.268092393875122,
93
  "learning_rate": 0.00014,
94
+ "loss": 7.0434,
95
  "step": 10
96
  },
97
  {
98
  "epoch": 0.028268551236749116,
99
+ "eval_loss": 6.333721160888672,
100
+ "eval_runtime": 20.9199,
101
+ "eval_samples_per_second": 28.49,
102
+ "eval_steps_per_second": 3.585,
103
  "step": 10
104
  },
105
  {
106
  "epoch": 0.03109540636042403,
107
+ "grad_norm": 2.161461114883423,
108
  "learning_rate": 0.00016,
109
+ "loss": 6.1538,
110
  "step": 11
111
  },
112
  {
113
  "epoch": 0.03392226148409894,
114
+ "grad_norm": 2.0395100116729736,
115
  "learning_rate": 0.00018,
116
+ "loss": 6.6144,
117
  "step": 12
118
  },
119
  {
120
  "epoch": 0.03674911660777385,
121
+ "grad_norm": 2.263904094696045,
122
  "learning_rate": 0.0002,
123
+ "loss": 6.1712,
124
  "step": 13
125
  },
126
  {
127
  "epoch": 0.039575971731448764,
128
+ "grad_norm": 1.9835869073867798,
129
  "learning_rate": 0.00019510565162951537,
130
+ "loss": 6.0672,
131
  "step": 14
132
  },
133
  {
134
  "epoch": 0.04240282685512368,
135
+ "grad_norm": 1.9458274841308594,
136
  "learning_rate": 0.00018090169943749476,
137
+ "loss": 5.7719,
138
  "step": 15
139
  },
140
  {
141
  "epoch": 0.04240282685512368,
142
+ "eval_loss": 5.498767375946045,
143
+ "eval_runtime": 20.8896,
144
+ "eval_samples_per_second": 28.531,
145
+ "eval_steps_per_second": 3.59,
146
  "step": 15
147
+ },
148
+ {
149
+ "epoch": 0.045229681978798585,
150
+ "grad_norm": 1.6456574201583862,
151
+ "learning_rate": 0.00015877852522924732,
152
+ "loss": 5.6195,
153
+ "step": 16
154
+ },
155
+ {
156
+ "epoch": 0.0480565371024735,
157
+ "grad_norm": 1.413881540298462,
158
+ "learning_rate": 0.00013090169943749476,
159
+ "loss": 5.3649,
160
+ "step": 17
161
+ },
162
+ {
163
+ "epoch": 0.05088339222614841,
164
+ "grad_norm": 1.8699934482574463,
165
+ "learning_rate": 0.0001,
166
+ "loss": 5.6544,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.05371024734982332,
171
+ "grad_norm": 2.320040464401245,
172
+ "learning_rate": 6.909830056250527e-05,
173
+ "loss": 5.3966,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.05653710247349823,
178
+ "grad_norm": 1.5797550678253174,
179
+ "learning_rate": 4.12214747707527e-05,
180
+ "loss": 5.695,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.05653710247349823,
185
+ "eval_loss": 5.102807998657227,
186
+ "eval_runtime": 20.9456,
187
+ "eval_samples_per_second": 28.455,
188
+ "eval_steps_per_second": 3.581,
189
+ "step": 20
190
  }
191
  ],
192
  "logging_steps": 1,
 
201
  "should_evaluate": false,
202
  "should_log": false,
203
  "should_save": true,
204
+ "should_training_stop": true
205
  },
206
  "attributes": {}
207
  }
208
  },
209
+ "total_flos": 2.638283774571315e+16,
210
  "train_batch_size": 1,
211
  "trial_name": null,
212
  "trial_params": null
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b55d7424e01d2da7c827809f0e75e814ca3307809331f5d1880db7934ea6a65
3
  size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:676c5b957839737d77485c6332fc96de69385066f3eef0d74b47f677462f11dc
3
  size 6712