End of training
Browse files- README.md +3 -3
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +1088 -0
README.md
CHANGED
@@ -4,7 +4,7 @@ base_model: google/long-t5-tglobal-xl
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
-
- scrolls
|
8 |
model-index:
|
9 |
- name: longt5_xl_govreport_4096
|
10 |
results: []
|
@@ -15,9 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# longt5_xl_govreport_4096
|
17 |
|
18 |
-
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the scrolls dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 1.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
datasets:
|
7 |
+
- tau/scrolls
|
8 |
model-index:
|
9 |
- name: longt5_xl_govreport_4096
|
10 |
results: []
|
|
|
15 |
|
16 |
# longt5_xl_govreport_4096
|
17 |
|
18 |
+
This model is a fine-tuned version of [google/long-t5-tglobal-xl](https://huggingface.co/google/long-t5-tglobal-xl) on the tau/scrolls gov_report dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.3889
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"eval_loss": 1.3889119625091553,
|
4 |
+
"eval_runtime": 333.0151,
|
5 |
+
"eval_samples": 972,
|
6 |
+
"eval_samples_per_second": 2.919,
|
7 |
+
"eval_steps_per_second": 0.73,
|
8 |
+
"train_loss": 1.3779389661901138,
|
9 |
+
"train_runtime": 112099.6799,
|
10 |
+
"train_samples": 17457,
|
11 |
+
"train_samples_per_second": 0.779,
|
12 |
+
"train_steps_per_second": 0.003
|
13 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"eval_loss": 1.3889119625091553,
|
4 |
+
"eval_runtime": 333.0151,
|
5 |
+
"eval_samples": 972,
|
6 |
+
"eval_samples_per_second": 2.919,
|
7 |
+
"eval_steps_per_second": 0.73
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 4.99,
|
3 |
+
"train_loss": 1.3779389661901138,
|
4 |
+
"train_runtime": 112099.6799,
|
5 |
+
"train_samples": 17457,
|
6 |
+
"train_samples_per_second": 0.779,
|
7 |
+
"train_steps_per_second": 0.003
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,1088 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 1.3889119625091553,
|
3 |
+
"best_model_checkpoint": "/home/co-ou1/rds/hpc-work/models/longt5_xl_govreport_4096/checkpoint-272",
|
4 |
+
"epoch": 4.985108820160367,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 340,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.03,
|
13 |
+
"learning_rate": 0.001,
|
14 |
+
"loss": 2.6414,
|
15 |
+
"step": 2
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.06,
|
19 |
+
"learning_rate": 0.001,
|
20 |
+
"loss": 2.4747,
|
21 |
+
"step": 4
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.09,
|
25 |
+
"learning_rate": 0.001,
|
26 |
+
"loss": 1.8708,
|
27 |
+
"step": 6
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.12,
|
31 |
+
"learning_rate": 0.001,
|
32 |
+
"loss": 2.4373,
|
33 |
+
"step": 8
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.15,
|
37 |
+
"learning_rate": 0.001,
|
38 |
+
"loss": 2.2961,
|
39 |
+
"step": 10
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.18,
|
43 |
+
"learning_rate": 0.001,
|
44 |
+
"loss": 2.1959,
|
45 |
+
"step": 12
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.21,
|
49 |
+
"learning_rate": 0.001,
|
50 |
+
"loss": 1.9882,
|
51 |
+
"step": 14
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.23,
|
55 |
+
"learning_rate": 0.001,
|
56 |
+
"loss": 2.0164,
|
57 |
+
"step": 16
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.26,
|
61 |
+
"learning_rate": 0.001,
|
62 |
+
"loss": 1.8772,
|
63 |
+
"step": 18
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.29,
|
67 |
+
"learning_rate": 0.001,
|
68 |
+
"loss": 1.8516,
|
69 |
+
"step": 20
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.32,
|
73 |
+
"learning_rate": 0.001,
|
74 |
+
"loss": 1.8587,
|
75 |
+
"step": 22
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.35,
|
79 |
+
"learning_rate": 0.001,
|
80 |
+
"loss": 1.729,
|
81 |
+
"step": 24
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.38,
|
85 |
+
"learning_rate": 0.001,
|
86 |
+
"loss": 1.7265,
|
87 |
+
"step": 26
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.41,
|
91 |
+
"learning_rate": 0.001,
|
92 |
+
"loss": 1.7689,
|
93 |
+
"step": 28
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.44,
|
97 |
+
"learning_rate": 0.001,
|
98 |
+
"loss": 1.7899,
|
99 |
+
"step": 30
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.47,
|
103 |
+
"learning_rate": 0.001,
|
104 |
+
"loss": 1.6755,
|
105 |
+
"step": 32
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.5,
|
109 |
+
"learning_rate": 0.001,
|
110 |
+
"loss": 1.6701,
|
111 |
+
"step": 34
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.53,
|
115 |
+
"learning_rate": 0.001,
|
116 |
+
"loss": 1.6626,
|
117 |
+
"step": 36
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.56,
|
121 |
+
"learning_rate": 0.001,
|
122 |
+
"loss": 1.708,
|
123 |
+
"step": 38
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.59,
|
127 |
+
"learning_rate": 0.001,
|
128 |
+
"loss": 1.7019,
|
129 |
+
"step": 40
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.62,
|
133 |
+
"learning_rate": 0.001,
|
134 |
+
"loss": 1.6705,
|
135 |
+
"step": 42
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.65,
|
139 |
+
"learning_rate": 0.001,
|
140 |
+
"loss": 1.6039,
|
141 |
+
"step": 44
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 0.67,
|
145 |
+
"learning_rate": 0.001,
|
146 |
+
"loss": 1.6041,
|
147 |
+
"step": 46
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 0.7,
|
151 |
+
"learning_rate": 0.001,
|
152 |
+
"loss": 1.5829,
|
153 |
+
"step": 48
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 0.73,
|
157 |
+
"learning_rate": 0.001,
|
158 |
+
"loss": 1.6283,
|
159 |
+
"step": 50
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 0.76,
|
163 |
+
"learning_rate": 0.001,
|
164 |
+
"loss": 1.7403,
|
165 |
+
"step": 52
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.79,
|
169 |
+
"learning_rate": 0.001,
|
170 |
+
"loss": 1.6786,
|
171 |
+
"step": 54
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 0.82,
|
175 |
+
"learning_rate": 0.001,
|
176 |
+
"loss": 1.6499,
|
177 |
+
"step": 56
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 0.85,
|
181 |
+
"learning_rate": 0.001,
|
182 |
+
"loss": 1.5641,
|
183 |
+
"step": 58
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.88,
|
187 |
+
"learning_rate": 0.001,
|
188 |
+
"loss": 1.5824,
|
189 |
+
"step": 60
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 0.91,
|
193 |
+
"learning_rate": 0.001,
|
194 |
+
"loss": 1.6462,
|
195 |
+
"step": 62
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 0.94,
|
199 |
+
"learning_rate": 0.001,
|
200 |
+
"loss": 1.5787,
|
201 |
+
"step": 64
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.97,
|
205 |
+
"learning_rate": 0.001,
|
206 |
+
"loss": 1.6053,
|
207 |
+
"step": 66
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.0,
|
211 |
+
"learning_rate": 0.001,
|
212 |
+
"loss": 1.6043,
|
213 |
+
"step": 68
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 1.0,
|
217 |
+
"eval_loss": 1.4757200479507446,
|
218 |
+
"eval_runtime": 333.5276,
|
219 |
+
"eval_samples_per_second": 2.914,
|
220 |
+
"eval_steps_per_second": 0.729,
|
221 |
+
"step": 68
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 1.03,
|
225 |
+
"learning_rate": 0.001,
|
226 |
+
"loss": 1.549,
|
227 |
+
"step": 70
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.06,
|
231 |
+
"learning_rate": 0.001,
|
232 |
+
"loss": 1.4379,
|
233 |
+
"step": 72
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 1.08,
|
237 |
+
"learning_rate": 0.001,
|
238 |
+
"loss": 1.5224,
|
239 |
+
"step": 74
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 1.11,
|
243 |
+
"learning_rate": 0.001,
|
244 |
+
"loss": 1.5106,
|
245 |
+
"step": 76
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 1.14,
|
249 |
+
"learning_rate": 0.001,
|
250 |
+
"loss": 1.4786,
|
251 |
+
"step": 78
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 1.17,
|
255 |
+
"learning_rate": 0.001,
|
256 |
+
"loss": 1.5101,
|
257 |
+
"step": 80
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 1.2,
|
261 |
+
"learning_rate": 0.001,
|
262 |
+
"loss": 1.4835,
|
263 |
+
"step": 82
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 1.23,
|
267 |
+
"learning_rate": 0.001,
|
268 |
+
"loss": 1.4749,
|
269 |
+
"step": 84
|
270 |
+
},
|
271 |
+
{
|
272 |
+
"epoch": 1.26,
|
273 |
+
"learning_rate": 0.001,
|
274 |
+
"loss": 1.488,
|
275 |
+
"step": 86
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 1.29,
|
279 |
+
"learning_rate": 0.001,
|
280 |
+
"loss": 1.4604,
|
281 |
+
"step": 88
|
282 |
+
},
|
283 |
+
{
|
284 |
+
"epoch": 1.32,
|
285 |
+
"learning_rate": 0.001,
|
286 |
+
"loss": 1.5358,
|
287 |
+
"step": 90
|
288 |
+
},
|
289 |
+
{
|
290 |
+
"epoch": 1.35,
|
291 |
+
"learning_rate": 0.001,
|
292 |
+
"loss": 1.5396,
|
293 |
+
"step": 92
|
294 |
+
},
|
295 |
+
{
|
296 |
+
"epoch": 1.38,
|
297 |
+
"learning_rate": 0.001,
|
298 |
+
"loss": 1.5071,
|
299 |
+
"step": 94
|
300 |
+
},
|
301 |
+
{
|
302 |
+
"epoch": 1.41,
|
303 |
+
"learning_rate": 0.001,
|
304 |
+
"loss": 1.5219,
|
305 |
+
"step": 96
|
306 |
+
},
|
307 |
+
{
|
308 |
+
"epoch": 1.44,
|
309 |
+
"learning_rate": 0.001,
|
310 |
+
"loss": 1.4589,
|
311 |
+
"step": 98
|
312 |
+
},
|
313 |
+
{
|
314 |
+
"epoch": 1.47,
|
315 |
+
"learning_rate": 0.001,
|
316 |
+
"loss": 1.4392,
|
317 |
+
"step": 100
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 1.5,
|
321 |
+
"learning_rate": 0.001,
|
322 |
+
"loss": 1.485,
|
323 |
+
"step": 102
|
324 |
+
},
|
325 |
+
{
|
326 |
+
"epoch": 1.52,
|
327 |
+
"learning_rate": 0.001,
|
328 |
+
"loss": 1.4617,
|
329 |
+
"step": 104
|
330 |
+
},
|
331 |
+
{
|
332 |
+
"epoch": 1.55,
|
333 |
+
"learning_rate": 0.001,
|
334 |
+
"loss": 1.4659,
|
335 |
+
"step": 106
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 1.58,
|
339 |
+
"learning_rate": 0.001,
|
340 |
+
"loss": 1.4908,
|
341 |
+
"step": 108
|
342 |
+
},
|
343 |
+
{
|
344 |
+
"epoch": 1.61,
|
345 |
+
"learning_rate": 0.001,
|
346 |
+
"loss": 1.4929,
|
347 |
+
"step": 110
|
348 |
+
},
|
349 |
+
{
|
350 |
+
"epoch": 1.64,
|
351 |
+
"learning_rate": 0.001,
|
352 |
+
"loss": 1.4538,
|
353 |
+
"step": 112
|
354 |
+
},
|
355 |
+
{
|
356 |
+
"epoch": 1.67,
|
357 |
+
"learning_rate": 0.001,
|
358 |
+
"loss": 1.4815,
|
359 |
+
"step": 114
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 1.7,
|
363 |
+
"learning_rate": 0.001,
|
364 |
+
"loss": 1.4525,
|
365 |
+
"step": 116
|
366 |
+
},
|
367 |
+
{
|
368 |
+
"epoch": 1.73,
|
369 |
+
"learning_rate": 0.001,
|
370 |
+
"loss": 1.4664,
|
371 |
+
"step": 118
|
372 |
+
},
|
373 |
+
{
|
374 |
+
"epoch": 1.76,
|
375 |
+
"learning_rate": 0.001,
|
376 |
+
"loss": 1.4498,
|
377 |
+
"step": 120
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 1.79,
|
381 |
+
"learning_rate": 0.001,
|
382 |
+
"loss": 1.5247,
|
383 |
+
"step": 122
|
384 |
+
},
|
385 |
+
{
|
386 |
+
"epoch": 1.82,
|
387 |
+
"learning_rate": 0.001,
|
388 |
+
"loss": 1.5033,
|
389 |
+
"step": 124
|
390 |
+
},
|
391 |
+
{
|
392 |
+
"epoch": 1.85,
|
393 |
+
"learning_rate": 0.001,
|
394 |
+
"loss": 1.4434,
|
395 |
+
"step": 126
|
396 |
+
},
|
397 |
+
{
|
398 |
+
"epoch": 1.88,
|
399 |
+
"learning_rate": 0.001,
|
400 |
+
"loss": 1.4806,
|
401 |
+
"step": 128
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 1.91,
|
405 |
+
"learning_rate": 0.001,
|
406 |
+
"loss": 1.4551,
|
407 |
+
"step": 130
|
408 |
+
},
|
409 |
+
{
|
410 |
+
"epoch": 1.94,
|
411 |
+
"learning_rate": 0.001,
|
412 |
+
"loss": 1.4359,
|
413 |
+
"step": 132
|
414 |
+
},
|
415 |
+
{
|
416 |
+
"epoch": 1.96,
|
417 |
+
"learning_rate": 0.001,
|
418 |
+
"loss": 1.4424,
|
419 |
+
"step": 134
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 1.99,
|
423 |
+
"learning_rate": 0.001,
|
424 |
+
"loss": 1.4471,
|
425 |
+
"step": 136
|
426 |
+
},
|
427 |
+
{
|
428 |
+
"epoch": 1.99,
|
429 |
+
"eval_loss": 1.401979923248291,
|
430 |
+
"eval_runtime": 333.5413,
|
431 |
+
"eval_samples_per_second": 2.914,
|
432 |
+
"eval_steps_per_second": 0.729,
|
433 |
+
"step": 136
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 2.02,
|
437 |
+
"learning_rate": 0.001,
|
438 |
+
"loss": 1.3704,
|
439 |
+
"step": 138
|
440 |
+
},
|
441 |
+
{
|
442 |
+
"epoch": 2.05,
|
443 |
+
"learning_rate": 0.001,
|
444 |
+
"loss": 1.3246,
|
445 |
+
"step": 140
|
446 |
+
},
|
447 |
+
{
|
448 |
+
"epoch": 2.08,
|
449 |
+
"learning_rate": 0.001,
|
450 |
+
"loss": 1.3714,
|
451 |
+
"step": 142
|
452 |
+
},
|
453 |
+
{
|
454 |
+
"epoch": 2.11,
|
455 |
+
"learning_rate": 0.001,
|
456 |
+
"loss": 1.3134,
|
457 |
+
"step": 144
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 2.14,
|
461 |
+
"learning_rate": 0.001,
|
462 |
+
"loss": 1.2998,
|
463 |
+
"step": 146
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 2.17,
|
467 |
+
"learning_rate": 0.001,
|
468 |
+
"loss": 1.3643,
|
469 |
+
"step": 148
|
470 |
+
},
|
471 |
+
{
|
472 |
+
"epoch": 2.2,
|
473 |
+
"learning_rate": 0.001,
|
474 |
+
"loss": 1.306,
|
475 |
+
"step": 150
|
476 |
+
},
|
477 |
+
{
|
478 |
+
"epoch": 2.23,
|
479 |
+
"learning_rate": 0.001,
|
480 |
+
"loss": 1.3152,
|
481 |
+
"step": 152
|
482 |
+
},
|
483 |
+
{
|
484 |
+
"epoch": 2.26,
|
485 |
+
"learning_rate": 0.001,
|
486 |
+
"loss": 1.3086,
|
487 |
+
"step": 154
|
488 |
+
},
|
489 |
+
{
|
490 |
+
"epoch": 2.29,
|
491 |
+
"learning_rate": 0.001,
|
492 |
+
"loss": 1.3033,
|
493 |
+
"step": 156
|
494 |
+
},
|
495 |
+
{
|
496 |
+
"epoch": 2.32,
|
497 |
+
"learning_rate": 0.001,
|
498 |
+
"loss": 1.343,
|
499 |
+
"step": 158
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 2.35,
|
503 |
+
"learning_rate": 0.001,
|
504 |
+
"loss": 1.3399,
|
505 |
+
"step": 160
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 2.38,
|
509 |
+
"learning_rate": 0.001,
|
510 |
+
"loss": 1.3134,
|
511 |
+
"step": 162
|
512 |
+
},
|
513 |
+
{
|
514 |
+
"epoch": 2.4,
|
515 |
+
"learning_rate": 0.001,
|
516 |
+
"loss": 1.3472,
|
517 |
+
"step": 164
|
518 |
+
},
|
519 |
+
{
|
520 |
+
"epoch": 2.43,
|
521 |
+
"learning_rate": 0.001,
|
522 |
+
"loss": 1.3261,
|
523 |
+
"step": 166
|
524 |
+
},
|
525 |
+
{
|
526 |
+
"epoch": 2.46,
|
527 |
+
"learning_rate": 0.001,
|
528 |
+
"loss": 1.3162,
|
529 |
+
"step": 168
|
530 |
+
},
|
531 |
+
{
|
532 |
+
"epoch": 2.49,
|
533 |
+
"learning_rate": 0.001,
|
534 |
+
"loss": 1.3194,
|
535 |
+
"step": 170
|
536 |
+
},
|
537 |
+
{
|
538 |
+
"epoch": 2.52,
|
539 |
+
"learning_rate": 0.001,
|
540 |
+
"loss": 1.3236,
|
541 |
+
"step": 172
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 2.55,
|
545 |
+
"learning_rate": 0.001,
|
546 |
+
"loss": 1.3033,
|
547 |
+
"step": 174
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 2.58,
|
551 |
+
"learning_rate": 0.001,
|
552 |
+
"loss": 1.3212,
|
553 |
+
"step": 176
|
554 |
+
},
|
555 |
+
{
|
556 |
+
"epoch": 2.61,
|
557 |
+
"learning_rate": 0.001,
|
558 |
+
"loss": 1.3433,
|
559 |
+
"step": 178
|
560 |
+
},
|
561 |
+
{
|
562 |
+
"epoch": 2.64,
|
563 |
+
"learning_rate": 0.001,
|
564 |
+
"loss": 1.34,
|
565 |
+
"step": 180
|
566 |
+
},
|
567 |
+
{
|
568 |
+
"epoch": 2.67,
|
569 |
+
"learning_rate": 0.001,
|
570 |
+
"loss": 1.3306,
|
571 |
+
"step": 182
|
572 |
+
},
|
573 |
+
{
|
574 |
+
"epoch": 2.7,
|
575 |
+
"learning_rate": 0.001,
|
576 |
+
"loss": 1.3377,
|
577 |
+
"step": 184
|
578 |
+
},
|
579 |
+
{
|
580 |
+
"epoch": 2.73,
|
581 |
+
"learning_rate": 0.001,
|
582 |
+
"loss": 1.3048,
|
583 |
+
"step": 186
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 2.76,
|
587 |
+
"learning_rate": 0.001,
|
588 |
+
"loss": 1.3186,
|
589 |
+
"step": 188
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 2.79,
|
593 |
+
"learning_rate": 0.001,
|
594 |
+
"loss": 1.3405,
|
595 |
+
"step": 190
|
596 |
+
},
|
597 |
+
{
|
598 |
+
"epoch": 2.82,
|
599 |
+
"learning_rate": 0.001,
|
600 |
+
"loss": 1.3266,
|
601 |
+
"step": 192
|
602 |
+
},
|
603 |
+
{
|
604 |
+
"epoch": 2.84,
|
605 |
+
"learning_rate": 0.001,
|
606 |
+
"loss": 1.3182,
|
607 |
+
"step": 194
|
608 |
+
},
|
609 |
+
{
|
610 |
+
"epoch": 2.87,
|
611 |
+
"learning_rate": 0.001,
|
612 |
+
"loss": 1.3755,
|
613 |
+
"step": 196
|
614 |
+
},
|
615 |
+
{
|
616 |
+
"epoch": 2.9,
|
617 |
+
"learning_rate": 0.001,
|
618 |
+
"loss": 1.3422,
|
619 |
+
"step": 198
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 2.93,
|
623 |
+
"learning_rate": 0.001,
|
624 |
+
"loss": 1.3247,
|
625 |
+
"step": 200
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 2.96,
|
629 |
+
"learning_rate": 0.001,
|
630 |
+
"loss": 1.312,
|
631 |
+
"step": 202
|
632 |
+
},
|
633 |
+
{
|
634 |
+
"epoch": 2.99,
|
635 |
+
"learning_rate": 0.001,
|
636 |
+
"loss": 1.315,
|
637 |
+
"step": 204
|
638 |
+
},
|
639 |
+
{
|
640 |
+
"epoch": 2.99,
|
641 |
+
"eval_loss": 1.3935041427612305,
|
642 |
+
"eval_runtime": 333.777,
|
643 |
+
"eval_samples_per_second": 2.912,
|
644 |
+
"eval_steps_per_second": 0.728,
|
645 |
+
"step": 204
|
646 |
+
},
|
647 |
+
{
|
648 |
+
"epoch": 3.02,
|
649 |
+
"learning_rate": 0.001,
|
650 |
+
"loss": 1.2264,
|
651 |
+
"step": 206
|
652 |
+
},
|
653 |
+
{
|
654 |
+
"epoch": 3.05,
|
655 |
+
"learning_rate": 0.001,
|
656 |
+
"loss": 1.1606,
|
657 |
+
"step": 208
|
658 |
+
},
|
659 |
+
{
|
660 |
+
"epoch": 3.08,
|
661 |
+
"learning_rate": 0.001,
|
662 |
+
"loss": 1.1569,
|
663 |
+
"step": 210
|
664 |
+
},
|
665 |
+
{
|
666 |
+
"epoch": 3.11,
|
667 |
+
"learning_rate": 0.001,
|
668 |
+
"loss": 1.1434,
|
669 |
+
"step": 212
|
670 |
+
},
|
671 |
+
{
|
672 |
+
"epoch": 3.14,
|
673 |
+
"learning_rate": 0.001,
|
674 |
+
"loss": 1.1736,
|
675 |
+
"step": 214
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 3.17,
|
679 |
+
"learning_rate": 0.001,
|
680 |
+
"loss": 1.17,
|
681 |
+
"step": 216
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 3.2,
|
685 |
+
"learning_rate": 0.001,
|
686 |
+
"loss": 1.1802,
|
687 |
+
"step": 218
|
688 |
+
},
|
689 |
+
{
|
690 |
+
"epoch": 3.23,
|
691 |
+
"learning_rate": 0.001,
|
692 |
+
"loss": 1.1856,
|
693 |
+
"step": 220
|
694 |
+
},
|
695 |
+
{
|
696 |
+
"epoch": 3.25,
|
697 |
+
"learning_rate": 0.001,
|
698 |
+
"loss": 1.1918,
|
699 |
+
"step": 222
|
700 |
+
},
|
701 |
+
{
|
702 |
+
"epoch": 3.28,
|
703 |
+
"learning_rate": 0.001,
|
704 |
+
"loss": 1.1751,
|
705 |
+
"step": 224
|
706 |
+
},
|
707 |
+
{
|
708 |
+
"epoch": 3.31,
|
709 |
+
"learning_rate": 0.001,
|
710 |
+
"loss": 1.1896,
|
711 |
+
"step": 226
|
712 |
+
},
|
713 |
+
{
|
714 |
+
"epoch": 3.34,
|
715 |
+
"learning_rate": 0.001,
|
716 |
+
"loss": 1.1837,
|
717 |
+
"step": 228
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 3.37,
|
721 |
+
"learning_rate": 0.001,
|
722 |
+
"loss": 1.2053,
|
723 |
+
"step": 230
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 3.4,
|
727 |
+
"learning_rate": 0.001,
|
728 |
+
"loss": 1.2031,
|
729 |
+
"step": 232
|
730 |
+
},
|
731 |
+
{
|
732 |
+
"epoch": 3.43,
|
733 |
+
"learning_rate": 0.001,
|
734 |
+
"loss": 1.1886,
|
735 |
+
"step": 234
|
736 |
+
},
|
737 |
+
{
|
738 |
+
"epoch": 3.46,
|
739 |
+
"learning_rate": 0.001,
|
740 |
+
"loss": 1.1769,
|
741 |
+
"step": 236
|
742 |
+
},
|
743 |
+
{
|
744 |
+
"epoch": 3.49,
|
745 |
+
"learning_rate": 0.001,
|
746 |
+
"loss": 1.1951,
|
747 |
+
"step": 238
|
748 |
+
},
|
749 |
+
{
|
750 |
+
"epoch": 3.52,
|
751 |
+
"learning_rate": 0.001,
|
752 |
+
"loss": 1.1943,
|
753 |
+
"step": 240
|
754 |
+
},
|
755 |
+
{
|
756 |
+
"epoch": 3.55,
|
757 |
+
"learning_rate": 0.001,
|
758 |
+
"loss": 1.1816,
|
759 |
+
"step": 242
|
760 |
+
},
|
761 |
+
{
|
762 |
+
"epoch": 3.58,
|
763 |
+
"learning_rate": 0.001,
|
764 |
+
"loss": 1.1763,
|
765 |
+
"step": 244
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 3.61,
|
769 |
+
"learning_rate": 0.001,
|
770 |
+
"loss": 1.2028,
|
771 |
+
"step": 246
|
772 |
+
},
|
773 |
+
{
|
774 |
+
"epoch": 3.64,
|
775 |
+
"learning_rate": 0.001,
|
776 |
+
"loss": 1.2199,
|
777 |
+
"step": 248
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 3.67,
|
781 |
+
"learning_rate": 0.001,
|
782 |
+
"loss": 1.1948,
|
783 |
+
"step": 250
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 3.69,
|
787 |
+
"learning_rate": 0.001,
|
788 |
+
"loss": 1.1859,
|
789 |
+
"step": 252
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 3.72,
|
793 |
+
"learning_rate": 0.001,
|
794 |
+
"loss": 1.1864,
|
795 |
+
"step": 254
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 3.75,
|
799 |
+
"learning_rate": 0.001,
|
800 |
+
"loss": 1.2012,
|
801 |
+
"step": 256
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 3.78,
|
805 |
+
"learning_rate": 0.001,
|
806 |
+
"loss": 1.2177,
|
807 |
+
"step": 258
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 3.81,
|
811 |
+
"learning_rate": 0.001,
|
812 |
+
"loss": 1.2156,
|
813 |
+
"step": 260
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 3.84,
|
817 |
+
"learning_rate": 0.001,
|
818 |
+
"loss": 1.204,
|
819 |
+
"step": 262
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 3.87,
|
823 |
+
"learning_rate": 0.001,
|
824 |
+
"loss": 1.2053,
|
825 |
+
"step": 264
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 3.9,
|
829 |
+
"learning_rate": 0.001,
|
830 |
+
"loss": 1.2138,
|
831 |
+
"step": 266
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 3.93,
|
835 |
+
"learning_rate": 0.001,
|
836 |
+
"loss": 1.1992,
|
837 |
+
"step": 268
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 3.96,
|
841 |
+
"learning_rate": 0.001,
|
842 |
+
"loss": 1.1903,
|
843 |
+
"step": 270
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 3.99,
|
847 |
+
"learning_rate": 0.001,
|
848 |
+
"loss": 1.2098,
|
849 |
+
"step": 272
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 3.99,
|
853 |
+
"eval_loss": 1.3889119625091553,
|
854 |
+
"eval_runtime": 333.5624,
|
855 |
+
"eval_samples_per_second": 2.914,
|
856 |
+
"eval_steps_per_second": 0.728,
|
857 |
+
"step": 272
|
858 |
+
},
|
859 |
+
{
|
860 |
+
"epoch": 4.02,
|
861 |
+
"learning_rate": 0.001,
|
862 |
+
"loss": 1.1135,
|
863 |
+
"step": 274
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 4.05,
|
867 |
+
"learning_rate": 0.001,
|
868 |
+
"loss": 1.0318,
|
869 |
+
"step": 276
|
870 |
+
},
|
871 |
+
{
|
872 |
+
"epoch": 4.08,
|
873 |
+
"learning_rate": 0.001,
|
874 |
+
"loss": 1.068,
|
875 |
+
"step": 278
|
876 |
+
},
|
877 |
+
{
|
878 |
+
"epoch": 4.11,
|
879 |
+
"learning_rate": 0.001,
|
880 |
+
"loss": 1.0386,
|
881 |
+
"step": 280
|
882 |
+
},
|
883 |
+
{
|
884 |
+
"epoch": 4.13,
|
885 |
+
"learning_rate": 0.001,
|
886 |
+
"loss": 1.0727,
|
887 |
+
"step": 282
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 4.16,
|
891 |
+
"learning_rate": 0.001,
|
892 |
+
"loss": 1.0592,
|
893 |
+
"step": 284
|
894 |
+
},
|
895 |
+
{
|
896 |
+
"epoch": 4.19,
|
897 |
+
"learning_rate": 0.001,
|
898 |
+
"loss": 1.0348,
|
899 |
+
"step": 286
|
900 |
+
},
|
901 |
+
{
|
902 |
+
"epoch": 4.22,
|
903 |
+
"learning_rate": 0.001,
|
904 |
+
"loss": 1.045,
|
905 |
+
"step": 288
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 4.25,
|
909 |
+
"learning_rate": 0.001,
|
910 |
+
"loss": 1.0535,
|
911 |
+
"step": 290
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 4.28,
|
915 |
+
"learning_rate": 0.001,
|
916 |
+
"loss": 1.0628,
|
917 |
+
"step": 292
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 4.31,
|
921 |
+
"learning_rate": 0.001,
|
922 |
+
"loss": 1.0699,
|
923 |
+
"step": 294
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 4.34,
|
927 |
+
"learning_rate": 0.001,
|
928 |
+
"loss": 1.0482,
|
929 |
+
"step": 296
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 4.37,
|
933 |
+
"learning_rate": 0.001,
|
934 |
+
"loss": 1.0703,
|
935 |
+
"step": 298
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 4.4,
|
939 |
+
"learning_rate": 0.001,
|
940 |
+
"loss": 1.0498,
|
941 |
+
"step": 300
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 4.43,
|
945 |
+
"learning_rate": 0.001,
|
946 |
+
"loss": 1.0775,
|
947 |
+
"step": 302
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 4.46,
|
951 |
+
"learning_rate": 0.001,
|
952 |
+
"loss": 1.0609,
|
953 |
+
"step": 304
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 4.49,
|
957 |
+
"learning_rate": 0.001,
|
958 |
+
"loss": 1.0985,
|
959 |
+
"step": 306
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 4.52,
|
963 |
+
"learning_rate": 0.001,
|
964 |
+
"loss": 1.081,
|
965 |
+
"step": 308
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 4.55,
|
969 |
+
"learning_rate": 0.001,
|
970 |
+
"loss": 1.0942,
|
971 |
+
"step": 310
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 4.57,
|
975 |
+
"learning_rate": 0.001,
|
976 |
+
"loss": 1.0789,
|
977 |
+
"step": 312
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 4.6,
|
981 |
+
"learning_rate": 0.001,
|
982 |
+
"loss": 1.0897,
|
983 |
+
"step": 314
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 4.63,
|
987 |
+
"learning_rate": 0.001,
|
988 |
+
"loss": 1.0869,
|
989 |
+
"step": 316
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 4.66,
|
993 |
+
"learning_rate": 0.001,
|
994 |
+
"loss": 1.1108,
|
995 |
+
"step": 318
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 4.69,
|
999 |
+
"learning_rate": 0.001,
|
1000 |
+
"loss": 1.0687,
|
1001 |
+
"step": 320
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 4.72,
|
1005 |
+
"learning_rate": 0.001,
|
1006 |
+
"loss": 1.1109,
|
1007 |
+
"step": 322
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 4.75,
|
1011 |
+
"learning_rate": 0.001,
|
1012 |
+
"loss": 1.0838,
|
1013 |
+
"step": 324
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 4.78,
|
1017 |
+
"learning_rate": 0.001,
|
1018 |
+
"loss": 1.0932,
|
1019 |
+
"step": 326
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 4.81,
|
1023 |
+
"learning_rate": 0.001,
|
1024 |
+
"loss": 1.0923,
|
1025 |
+
"step": 328
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 4.84,
|
1029 |
+
"learning_rate": 0.001,
|
1030 |
+
"loss": 1.0662,
|
1031 |
+
"step": 330
|
1032 |
+
},
|
1033 |
+
{
|
1034 |
+
"epoch": 4.87,
|
1035 |
+
"learning_rate": 0.001,
|
1036 |
+
"loss": 1.0727,
|
1037 |
+
"step": 332
|
1038 |
+
},
|
1039 |
+
{
|
1040 |
+
"epoch": 4.9,
|
1041 |
+
"learning_rate": 0.001,
|
1042 |
+
"loss": 1.0809,
|
1043 |
+
"step": 334
|
1044 |
+
},
|
1045 |
+
{
|
1046 |
+
"epoch": 4.93,
|
1047 |
+
"learning_rate": 0.001,
|
1048 |
+
"loss": 1.1087,
|
1049 |
+
"step": 336
|
1050 |
+
},
|
1051 |
+
{
|
1052 |
+
"epoch": 4.96,
|
1053 |
+
"learning_rate": 0.001,
|
1054 |
+
"loss": 1.0912,
|
1055 |
+
"step": 338
|
1056 |
+
},
|
1057 |
+
{
|
1058 |
+
"epoch": 4.99,
|
1059 |
+
"learning_rate": 0.001,
|
1060 |
+
"loss": 1.0888,
|
1061 |
+
"step": 340
|
1062 |
+
},
|
1063 |
+
{
|
1064 |
+
"epoch": 4.99,
|
1065 |
+
"eval_loss": 1.4388501644134521,
|
1066 |
+
"eval_runtime": 333.5483,
|
1067 |
+
"eval_samples_per_second": 2.914,
|
1068 |
+
"eval_steps_per_second": 0.729,
|
1069 |
+
"step": 340
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 4.99,
|
1073 |
+
"step": 340,
|
1074 |
+
"total_flos": 5.95419516573578e+18,
|
1075 |
+
"train_loss": 1.3779389661901138,
|
1076 |
+
"train_runtime": 112099.6799,
|
1077 |
+
"train_samples_per_second": 0.779,
|
1078 |
+
"train_steps_per_second": 0.003
|
1079 |
+
}
|
1080 |
+
],
|
1081 |
+
"logging_steps": 2,
|
1082 |
+
"max_steps": 340,
|
1083 |
+
"num_train_epochs": 5,
|
1084 |
+
"save_steps": 500,
|
1085 |
+
"total_flos": 5.95419516573578e+18,
|
1086 |
+
"trial_name": null,
|
1087 |
+
"trial_params": null
|
1088 |
+
}
|