Commit
•
7b40374
1
Parent(s):
c7086bd
End of training
Browse files- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +175 -0
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 2.1025146484375,
|
4 |
+
"train_runtime": 54.0138,
|
5 |
+
"train_samples": 303,
|
6 |
+
"train_samples_per_second": 5.61,
|
7 |
+
"train_steps_per_second": 0.185
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 1.0,
|
3 |
+
"train_loss": 2.1025146484375,
|
4 |
+
"train_runtime": 54.0138,
|
5 |
+
"train_samples": 303,
|
6 |
+
"train_samples_per_second": 5.61,
|
7 |
+
"train_steps_per_second": 0.185
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,175 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
+
"global_step": 10,
|
6 |
+
"is_hyper_param_search": false,
|
7 |
+
"is_local_process_zero": true,
|
8 |
+
"is_world_process_zero": true,
|
9 |
+
"log_history": [
|
10 |
+
{
|
11 |
+
"epoch": 0.1,
|
12 |
+
"learning_rate": 3e-05,
|
13 |
+
"loss": 2.0841,
|
14 |
+
"step": 1
|
15 |
+
},
|
16 |
+
{
|
17 |
+
"epoch": 0.1,
|
18 |
+
"eval_accuracy": 0.07586472641552201,
|
19 |
+
"eval_loss": 2.025390625,
|
20 |
+
"eval_runtime": 1.7457,
|
21 |
+
"eval_samples_per_second": 32.651,
|
22 |
+
"eval_steps_per_second": 1.146,
|
23 |
+
"step": 1
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.2,
|
27 |
+
"learning_rate": 3e-05,
|
28 |
+
"loss": 2.062,
|
29 |
+
"step": 2
|
30 |
+
},
|
31 |
+
{
|
32 |
+
"epoch": 0.2,
|
33 |
+
"eval_accuracy": 0.07586472641552201,
|
34 |
+
"eval_loss": 2.025390625,
|
35 |
+
"eval_runtime": 2.5631,
|
36 |
+
"eval_samples_per_second": 22.239,
|
37 |
+
"eval_steps_per_second": 0.78,
|
38 |
+
"step": 2
|
39 |
+
},
|
40 |
+
{
|
41 |
+
"epoch": 0.3,
|
42 |
+
"learning_rate": 2.9265847744427305e-05,
|
43 |
+
"loss": 2.1509,
|
44 |
+
"step": 3
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.3,
|
48 |
+
"eval_accuracy": 0.07613672423953942,
|
49 |
+
"eval_loss": 1.994140625,
|
50 |
+
"eval_runtime": 1.9455,
|
51 |
+
"eval_samples_per_second": 29.298,
|
52 |
+
"eval_steps_per_second": 1.028,
|
53 |
+
"step": 3
|
54 |
+
},
|
55 |
+
{
|
56 |
+
"epoch": 0.4,
|
57 |
+
"learning_rate": 2.7135254915624213e-05,
|
58 |
+
"loss": 2.1206,
|
59 |
+
"step": 4
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 0.4,
|
63 |
+
"eval_accuracy": 0.07563806156217417,
|
64 |
+
"eval_loss": 1.994140625,
|
65 |
+
"eval_runtime": 2.5486,
|
66 |
+
"eval_samples_per_second": 22.365,
|
67 |
+
"eval_steps_per_second": 0.785,
|
68 |
+
"step": 4
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"epoch": 0.5,
|
72 |
+
"learning_rate": 2.3816778784387097e-05,
|
73 |
+
"loss": 2.2087,
|
74 |
+
"step": 5
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.5,
|
78 |
+
"eval_accuracy": 0.07568339453284374,
|
79 |
+
"eval_loss": 1.994140625,
|
80 |
+
"eval_runtime": 2.1509,
|
81 |
+
"eval_samples_per_second": 26.501,
|
82 |
+
"eval_steps_per_second": 0.93,
|
83 |
+
"step": 5
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.6,
|
87 |
+
"learning_rate": 1.963525491562421e-05,
|
88 |
+
"loss": 2.0337,
|
89 |
+
"step": 6
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.6,
|
93 |
+
"eval_accuracy": 0.07550206265016547,
|
94 |
+
"eval_loss": 1.990234375,
|
95 |
+
"eval_runtime": 1.7684,
|
96 |
+
"eval_samples_per_second": 32.232,
|
97 |
+
"eval_steps_per_second": 1.131,
|
98 |
+
"step": 6
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.7,
|
102 |
+
"learning_rate": 1.5e-05,
|
103 |
+
"loss": 2.026,
|
104 |
+
"step": 7
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.7,
|
108 |
+
"eval_accuracy": 0.07552472913550025,
|
109 |
+
"eval_loss": 1.9853515625,
|
110 |
+
"eval_runtime": 1.9602,
|
111 |
+
"eval_samples_per_second": 29.079,
|
112 |
+
"eval_steps_per_second": 1.02,
|
113 |
+
"step": 7
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 0.8,
|
117 |
+
"learning_rate": 1.036474508437579e-05,
|
118 |
+
"loss": 2.1879,
|
119 |
+
"step": 8
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.8,
|
123 |
+
"eval_accuracy": 0.07557006210616982,
|
124 |
+
"eval_loss": 1.9833984375,
|
125 |
+
"eval_runtime": 1.7437,
|
126 |
+
"eval_samples_per_second": 32.69,
|
127 |
+
"eval_steps_per_second": 1.147,
|
128 |
+
"step": 8
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.9,
|
132 |
+
"learning_rate": 6.1832212156129045e-06,
|
133 |
+
"loss": 2.1052,
|
134 |
+
"step": 9
|
135 |
+
},
|
136 |
+
{
|
137 |
+
"epoch": 0.9,
|
138 |
+
"eval_accuracy": 0.07538873022349155,
|
139 |
+
"eval_loss": 1.982421875,
|
140 |
+
"eval_runtime": 2.3577,
|
141 |
+
"eval_samples_per_second": 24.177,
|
142 |
+
"eval_steps_per_second": 0.848,
|
143 |
+
"step": 9
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 1.0,
|
147 |
+
"learning_rate": 2.86474508437579e-06,
|
148 |
+
"loss": 2.046,
|
149 |
+
"step": 10
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 1.0,
|
153 |
+
"eval_accuracy": 0.07541139670882632,
|
154 |
+
"eval_loss": 1.98046875,
|
155 |
+
"eval_runtime": 2.5554,
|
156 |
+
"eval_samples_per_second": 22.306,
|
157 |
+
"eval_steps_per_second": 0.783,
|
158 |
+
"step": 10
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 1.0,
|
162 |
+
"step": 10,
|
163 |
+
"total_flos": 945593647104.0,
|
164 |
+
"train_loss": 2.1025146484375,
|
165 |
+
"train_runtime": 54.0138,
|
166 |
+
"train_samples_per_second": 5.61,
|
167 |
+
"train_steps_per_second": 0.185
|
168 |
+
}
|
169 |
+
],
|
170 |
+
"max_steps": 10,
|
171 |
+
"num_train_epochs": 1,
|
172 |
+
"total_flos": 945593647104.0,
|
173 |
+
"trial_name": null,
|
174 |
+
"trial_params": null
|
175 |
+
}
|