rahul7star commited on
Commit
d81cfb9
·
verified ·
1 Parent(s): 23f8b08

LoRA checkpoint step 10

Browse files
adapter_config.json CHANGED
@@ -29,8 +29,8 @@
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
- "v_proj",
33
- "q_proj"
34
  ],
35
  "target_parameters": null,
36
  "task_type": "CAUSAL_LM",
 
29
  "rank_pattern": {},
30
  "revision": null,
31
  "target_modules": [
32
+ "q_proj",
33
+ "v_proj"
34
  ],
35
  "target_parameters": null,
36
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11c97f4501a385bf1df172c821d774f38afc5500ef0c0b5172e3330227b619c8
3
  size 18365064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f888b6b3a4052e009eb3e0ea020b5e04b812380410a649e8756ed4a2776eaba
3
  size 18365064
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0fcce545eb66e45e0de3225cc88e00ccca134dbdf8695455c2800ede82dd965
3
  size 36796427
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f00e14dda69de9c90df1d937afda3e780f45283c250d8e473fcdf0c513fcf04
3
  size 36796427
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8045680cd0b0da3a46edfb15f7b9326902d12ec80a772f2c8cee5226f40102ac
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2cad12e7330dde5d600642494526045807112b5902f585e81357ae4e18a3777
3
  size 14645
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2942a487ee32840b184efa1f28ee3b970aed024c3e152d1d21ecf1df5f7f9166
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f6cb6003c360c5b7afae4918a32c9d360b05785e8b0d5f99e6044d9cf74615
3
  size 1465
trainer_state.json CHANGED
@@ -2,158 +2,88 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 20.0,
6
  "eval_steps": 500,
7
- "global_step": 20,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 1.0,
14
- "grad_norm": 13.383371353149414,
15
  "learning_rate": 0.0001,
16
- "loss": 15.8124,
17
  "step": 1
18
  },
19
  {
20
- "epoch": 2.0,
21
- "grad_norm": 12.606584548950195,
22
- "learning_rate": 9.5e-05,
23
- "loss": 15.5181,
24
- "step": 2
25
- },
26
- {
27
- "epoch": 3.0,
28
- "grad_norm": 13.850770950317383,
29
  "learning_rate": 9e-05,
30
- "loss": 15.1824,
31
- "step": 3
32
- },
33
- {
34
- "epoch": 4.0,
35
- "grad_norm": 13.93728256225586,
36
- "learning_rate": 8.5e-05,
37
- "loss": 14.8461,
38
- "step": 4
39
  },
40
  {
41
- "epoch": 5.0,
42
- "grad_norm": 15.150458335876465,
43
  "learning_rate": 8e-05,
44
- "loss": 14.4621,
45
- "step": 5
46
- },
47
- {
48
- "epoch": 6.0,
49
- "grad_norm": 15.022994995117188,
50
- "learning_rate": 7.500000000000001e-05,
51
- "loss": 14.1166,
52
- "step": 6
53
  },
54
  {
55
- "epoch": 7.0,
56
- "grad_norm": 14.39227294921875,
57
  "learning_rate": 7e-05,
58
- "loss": 13.7894,
59
- "step": 7
60
- },
61
- {
62
- "epoch": 8.0,
63
- "grad_norm": 13.548099517822266,
64
- "learning_rate": 6.500000000000001e-05,
65
- "loss": 13.5018,
66
- "step": 8
67
  },
68
  {
69
- "epoch": 9.0,
70
- "grad_norm": 12.666287422180176,
71
  "learning_rate": 6e-05,
72
- "loss": 13.2573,
73
- "step": 9
74
- },
75
- {
76
- "epoch": 10.0,
77
- "grad_norm": 11.866293907165527,
78
- "learning_rate": 5.500000000000001e-05,
79
- "loss": 12.9813,
80
- "step": 10
81
  },
82
  {
83
- "epoch": 11.0,
84
- "grad_norm": 11.042235374450684,
85
  "learning_rate": 5e-05,
86
- "loss": 12.835,
87
- "step": 11
88
- },
89
- {
90
- "epoch": 12.0,
91
- "grad_norm": 10.063555717468262,
92
- "learning_rate": 4.5e-05,
93
- "loss": 12.6259,
94
- "step": 12
95
  },
96
  {
97
- "epoch": 13.0,
98
- "grad_norm": 10.178994178771973,
99
  "learning_rate": 4e-05,
100
- "loss": 12.4115,
101
- "step": 13
102
- },
103
- {
104
- "epoch": 14.0,
105
- "grad_norm": 10.010645866394043,
106
- "learning_rate": 3.5e-05,
107
- "loss": 12.3229,
108
- "step": 14
109
  },
110
  {
111
- "epoch": 15.0,
112
- "grad_norm": 9.389053344726562,
113
  "learning_rate": 3e-05,
114
- "loss": 12.1327,
115
- "step": 15
116
- },
117
- {
118
- "epoch": 16.0,
119
- "grad_norm": 8.83408260345459,
120
- "learning_rate": 2.5e-05,
121
- "loss": 12.0424,
122
- "step": 16
123
  },
124
  {
125
- "epoch": 17.0,
126
- "grad_norm": 8.485236167907715,
127
  "learning_rate": 2e-05,
128
- "loss": 11.9666,
129
- "step": 17
130
- },
131
- {
132
- "epoch": 18.0,
133
- "grad_norm": 8.385706901550293,
134
- "learning_rate": 1.5e-05,
135
- "loss": 11.9032,
136
- "step": 18
137
  },
138
  {
139
- "epoch": 19.0,
140
- "grad_norm": 8.39928913116455,
141
  "learning_rate": 1e-05,
142
- "loss": 11.8244,
143
- "step": 19
144
- },
145
- {
146
- "epoch": 20.0,
147
- "grad_norm": 8.347794532775879,
148
- "learning_rate": 5e-06,
149
- "loss": 11.7931,
150
- "step": 20
151
  }
152
  ],
153
  "logging_steps": 1,
154
- "max_steps": 20,
155
  "num_input_tokens_seen": 0,
156
- "num_train_epochs": 20,
157
  "save_steps": 10,
158
  "stateful_callbacks": {
159
  "TrainerControl": {
@@ -167,7 +97,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 1734656969932800.0,
171
  "train_batch_size": 10,
172
  "trial_name": null,
173
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
  "eval_steps": 500,
7
+ "global_step": 10,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 0.1,
14
+ "grad_norm": 14.800739288330078,
15
  "learning_rate": 0.0001,
16
+ "loss": 15.3207,
17
  "step": 1
18
  },
19
  {
20
+ "epoch": 0.2,
21
+ "grad_norm": 14.96125602722168,
 
 
 
 
 
 
 
22
  "learning_rate": 9e-05,
23
+ "loss": 16.127,
24
+ "step": 2
 
 
 
 
 
 
 
25
  },
26
  {
27
+ "epoch": 0.3,
28
+ "grad_norm": 13.516273498535156,
29
  "learning_rate": 8e-05,
30
+ "loss": 15.5743,
31
+ "step": 3
 
 
 
 
 
 
 
32
  },
33
  {
34
+ "epoch": 0.4,
35
+ "grad_norm": 15.074135780334473,
36
  "learning_rate": 7e-05,
37
+ "loss": 15.1249,
38
+ "step": 4
 
 
 
 
 
 
 
39
  },
40
  {
41
+ "epoch": 0.5,
42
+ "grad_norm": 12.500387191772461,
43
  "learning_rate": 6e-05,
44
+ "loss": 15.3016,
45
+ "step": 5
 
 
 
 
 
 
 
46
  },
47
  {
48
+ "epoch": 0.6,
49
+ "grad_norm": 12.868051528930664,
50
  "learning_rate": 5e-05,
51
+ "loss": 13.8441,
52
+ "step": 6
 
 
 
 
 
 
 
53
  },
54
  {
55
+ "epoch": 0.7,
56
+ "grad_norm": 12.014676094055176,
57
  "learning_rate": 4e-05,
58
+ "loss": 14.4305,
59
+ "step": 7
 
 
 
 
 
 
 
60
  },
61
  {
62
+ "epoch": 0.8,
63
+ "grad_norm": 12.44831657409668,
64
  "learning_rate": 3e-05,
65
+ "loss": 13.5286,
66
+ "step": 8
 
 
 
 
 
 
 
67
  },
68
  {
69
+ "epoch": 0.9,
70
+ "grad_norm": 11.084362030029297,
71
  "learning_rate": 2e-05,
72
+ "loss": 15.0303,
73
+ "step": 9
 
 
 
 
 
 
 
74
  },
75
  {
76
+ "epoch": 1.0,
77
+ "grad_norm": 14.512312889099121,
78
  "learning_rate": 1e-05,
79
+ "loss": 12.5946,
80
+ "step": 10
 
 
 
 
 
 
 
81
  }
82
  ],
83
  "logging_steps": 1,
84
+ "max_steps": 10,
85
  "num_input_tokens_seen": 0,
86
+ "num_train_epochs": 1,
87
  "save_steps": 10,
88
  "stateful_callbacks": {
89
  "TrainerControl": {
 
97
  "attributes": {}
98
  }
99
  },
100
+ "total_flos": 867328484966400.0,
101
  "train_batch_size": 10,
102
  "trial_name": null,
103
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccdc84464664929d3e317e161b941977f55e11b137a084048b6bd8bed7d6cc96
3
  size 5841
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5dd29078e167b1ffeebe30da97a0ff60ebe4e307d6c39f62d60c8c91f75eca6
3
  size 5841