Model save
Browse files- all_results.json +5 -5
- tokenizer.json +6 -1
- train_results.json +5 -5
- trainer_state.json +12 -150
- training_args.bin +1 -1
all_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 62107,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.01,
|
3 |
+
"train_loss": 3.6924142456054687,
|
4 |
+
"train_runtime": 10.341,
|
5 |
"train_samples": 62107,
|
6 |
+
"train_samples_per_second": 77.362,
|
7 |
+
"train_steps_per_second": 9.67
|
8 |
}
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 128,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
train_results.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"epoch":
|
3 |
-
"train_loss":
|
4 |
-
"train_runtime":
|
5 |
"train_samples": 62107,
|
6 |
-
"train_samples_per_second":
|
7 |
-
"train_steps_per_second":
|
8 |
}
|
|
|
1 |
{
|
2 |
+
"epoch": 0.01,
|
3 |
+
"train_loss": 3.6924142456054687,
|
4 |
+
"train_runtime": 10.341,
|
5 |
"train_samples": 62107,
|
6 |
+
"train_samples_per_second": 77.362,
|
7 |
+
"train_steps_per_second": 9.67
|
8 |
}
|
trainer_state.json
CHANGED
@@ -1,163 +1,25 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
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.
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
|
16 |
-
|
17 |
-
"
|
18 |
-
"learning_rate": 4.570668040528937e-05,
|
19 |
-
"loss": 2.7354,
|
20 |
-
"step": 1000
|
21 |
-
},
|
22 |
-
{
|
23 |
-
"epoch": 0.39,
|
24 |
-
"learning_rate": 4.356002060793406e-05,
|
25 |
-
"loss": 2.5217,
|
26 |
-
"step": 1500
|
27 |
-
},
|
28 |
-
{
|
29 |
-
"epoch": 0.52,
|
30 |
-
"learning_rate": 4.1413360810578746e-05,
|
31 |
-
"loss": 2.3945,
|
32 |
-
"step": 2000
|
33 |
-
},
|
34 |
-
{
|
35 |
-
"epoch": 0.64,
|
36 |
-
"learning_rate": 3.926670101322343e-05,
|
37 |
-
"loss": 2.2924,
|
38 |
-
"step": 2500
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"epoch": 0.77,
|
42 |
-
"learning_rate": 3.712004121586811e-05,
|
43 |
-
"loss": 2.2309,
|
44 |
-
"step": 3000
|
45 |
-
},
|
46 |
-
{
|
47 |
-
"epoch": 0.9,
|
48 |
-
"learning_rate": 3.4973381418512793e-05,
|
49 |
-
"loss": 2.1581,
|
50 |
-
"step": 3500
|
51 |
-
},
|
52 |
-
{
|
53 |
-
"epoch": 1.03,
|
54 |
-
"learning_rate": 3.282672162115748e-05,
|
55 |
-
"loss": 2.1062,
|
56 |
-
"step": 4000
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"epoch": 1.16,
|
60 |
-
"learning_rate": 3.0680061823802165e-05,
|
61 |
-
"loss": 2.0668,
|
62 |
-
"step": 4500
|
63 |
-
},
|
64 |
-
{
|
65 |
-
"epoch": 1.29,
|
66 |
-
"learning_rate": 2.8533402026446848e-05,
|
67 |
-
"loss": 2.017,
|
68 |
-
"step": 5000
|
69 |
-
},
|
70 |
-
{
|
71 |
-
"epoch": 1.42,
|
72 |
-
"learning_rate": 2.6386742229091534e-05,
|
73 |
-
"loss": 1.9905,
|
74 |
-
"step": 5500
|
75 |
-
},
|
76 |
-
{
|
77 |
-
"epoch": 1.55,
|
78 |
-
"learning_rate": 2.424008243173622e-05,
|
79 |
-
"loss": 1.9665,
|
80 |
-
"step": 6000
|
81 |
-
},
|
82 |
-
{
|
83 |
-
"epoch": 1.67,
|
84 |
-
"learning_rate": 2.2093422634380902e-05,
|
85 |
-
"loss": 1.9443,
|
86 |
-
"step": 6500
|
87 |
-
},
|
88 |
-
{
|
89 |
-
"epoch": 1.8,
|
90 |
-
"learning_rate": 1.994676283702559e-05,
|
91 |
-
"loss": 1.9293,
|
92 |
-
"step": 7000
|
93 |
-
},
|
94 |
-
{
|
95 |
-
"epoch": 1.93,
|
96 |
-
"learning_rate": 1.7800103039670274e-05,
|
97 |
-
"loss": 1.8996,
|
98 |
-
"step": 7500
|
99 |
-
},
|
100 |
-
{
|
101 |
-
"epoch": 2.06,
|
102 |
-
"learning_rate": 1.5653443242314956e-05,
|
103 |
-
"loss": 1.8974,
|
104 |
-
"step": 8000
|
105 |
-
},
|
106 |
-
{
|
107 |
-
"epoch": 2.19,
|
108 |
-
"learning_rate": 1.3506783444959644e-05,
|
109 |
-
"loss": 1.8627,
|
110 |
-
"step": 8500
|
111 |
-
},
|
112 |
-
{
|
113 |
-
"epoch": 2.32,
|
114 |
-
"learning_rate": 1.1360123647604328e-05,
|
115 |
-
"loss": 1.868,
|
116 |
-
"step": 9000
|
117 |
-
},
|
118 |
-
{
|
119 |
-
"epoch": 2.45,
|
120 |
-
"learning_rate": 9.213463850249012e-06,
|
121 |
-
"loss": 1.8579,
|
122 |
-
"step": 9500
|
123 |
-
},
|
124 |
-
{
|
125 |
-
"epoch": 2.58,
|
126 |
-
"learning_rate": 7.066804052893698e-06,
|
127 |
-
"loss": 1.8435,
|
128 |
-
"step": 10000
|
129 |
-
},
|
130 |
-
{
|
131 |
-
"epoch": 2.7,
|
132 |
-
"learning_rate": 4.9201442555383824e-06,
|
133 |
-
"loss": 1.8395,
|
134 |
-
"step": 10500
|
135 |
-
},
|
136 |
-
{
|
137 |
-
"epoch": 2.83,
|
138 |
-
"learning_rate": 2.7734844581830675e-06,
|
139 |
-
"loss": 1.8345,
|
140 |
-
"step": 11000
|
141 |
-
},
|
142 |
-
{
|
143 |
-
"epoch": 2.96,
|
144 |
-
"learning_rate": 6.26824660827752e-07,
|
145 |
-
"loss": 1.8475,
|
146 |
-
"step": 11500
|
147 |
-
},
|
148 |
-
{
|
149 |
-
"epoch": 3.0,
|
150 |
-
"step": 11646,
|
151 |
-
"total_flos": 5065259927605248.0,
|
152 |
-
"train_loss": 2.0967203749837324,
|
153 |
-
"train_runtime": 2434.7534,
|
154 |
-
"train_samples_per_second": 76.526,
|
155 |
-
"train_steps_per_second": 4.783
|
156 |
}
|
157 |
],
|
158 |
-
"max_steps":
|
159 |
-
"num_train_epochs":
|
160 |
-
"total_flos":
|
161 |
"trial_name": null,
|
162 |
"trial_params": null
|
163 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.01287995878413189,
|
5 |
+
"global_step": 100,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
9 |
"log_history": [
|
10 |
{
|
11 |
+
"epoch": 0.01,
|
12 |
+
"step": 100,
|
13 |
+
"total_flos": 19701488959488.0,
|
14 |
+
"train_loss": 3.6924142456054687,
|
15 |
+
"train_runtime": 10.341,
|
16 |
+
"train_samples_per_second": 77.362,
|
17 |
+
"train_steps_per_second": 9.67
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
}
|
19 |
],
|
20 |
+
"max_steps": 100,
|
21 |
+
"num_train_epochs": 1,
|
22 |
+
"total_flos": 19701488959488.0,
|
23 |
"trial_name": null,
|
24 |
"trial_params": null
|
25 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3515
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d190fa24deb5ce9547e445f8d59cb6f296f3e35503e5600f11ef2b45a7ff4532
|
3 |
size 3515
|