End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +952 -0
- training_loss.png +0 -0
README.md
CHANGED
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
5 |
tags:
|
6 |
- llama-factory
|
|
|
7 |
- generated_from_trainer
|
8 |
model-index:
|
9 |
- name: d1_code_long_paragraphs_0.3k
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
15 |
|
16 |
# d1_code_long_paragraphs_0.3k
|
17 |
|
18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
5 |
tags:
|
6 |
- llama-factory
|
7 |
+
- full
|
8 |
- generated_from_trainer
|
9 |
model-index:
|
10 |
- name: d1_code_long_paragraphs_0.3k
|
|
|
16 |
|
17 |
# d1_code_long_paragraphs_0.3k
|
18 |
|
19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/d1_code_long_paragraphs_0.3k dataset.
|
20 |
|
21 |
## Model description
|
22 |
|
all_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"total_flos": 8.969562657652736e+16,
|
4 |
+
"train_loss": 0.4498058209052453,
|
5 |
+
"train_runtime": 2844.3624,
|
6 |
+
"train_samples_per_second": 1.444,
|
7 |
+
"train_steps_per_second": 0.046
|
8 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 13.0,
|
3 |
+
"total_flos": 8.969562657652736e+16,
|
4 |
+
"train_loss": 0.4498058209052453,
|
5 |
+
"train_runtime": 2844.3624,
|
6 |
+
"train_samples_per_second": 1.444,
|
7 |
+
"train_steps_per_second": 0.046
|
8 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,952 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 130,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.1,
|
13 |
+
"grad_norm": 6.355769085572866,
|
14 |
+
"learning_rate": 7.692307692307694e-07,
|
15 |
+
"loss": 1.0538,
|
16 |
+
"step": 1
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.2,
|
20 |
+
"grad_norm": 6.725796217074084,
|
21 |
+
"learning_rate": 1.5384615384615387e-06,
|
22 |
+
"loss": 1.0695,
|
23 |
+
"step": 2
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.3,
|
27 |
+
"grad_norm": 6.459256519255048,
|
28 |
+
"learning_rate": 2.307692307692308e-06,
|
29 |
+
"loss": 1.0423,
|
30 |
+
"step": 3
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.4,
|
34 |
+
"grad_norm": 5.999082264966995,
|
35 |
+
"learning_rate": 3.0769230769230774e-06,
|
36 |
+
"loss": 1.0264,
|
37 |
+
"step": 4
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.5,
|
41 |
+
"grad_norm": 4.525029282049904,
|
42 |
+
"learning_rate": 3.846153846153847e-06,
|
43 |
+
"loss": 0.9858,
|
44 |
+
"step": 5
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.6,
|
48 |
+
"grad_norm": 3.385668428730269,
|
49 |
+
"learning_rate": 4.615384615384616e-06,
|
50 |
+
"loss": 0.9473,
|
51 |
+
"step": 6
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.7,
|
55 |
+
"grad_norm": 2.593967410267031,
|
56 |
+
"learning_rate": 5.384615384615385e-06,
|
57 |
+
"loss": 0.9616,
|
58 |
+
"step": 7
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.8,
|
62 |
+
"grad_norm": 3.4423930422863394,
|
63 |
+
"learning_rate": 6.153846153846155e-06,
|
64 |
+
"loss": 0.9537,
|
65 |
+
"step": 8
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.9,
|
69 |
+
"grad_norm": 4.2939943877977385,
|
70 |
+
"learning_rate": 6.923076923076923e-06,
|
71 |
+
"loss": 0.9712,
|
72 |
+
"step": 9
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 1.0,
|
76 |
+
"grad_norm": 4.134153068892652,
|
77 |
+
"learning_rate": 7.692307692307694e-06,
|
78 |
+
"loss": 0.9329,
|
79 |
+
"step": 10
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 1.1,
|
83 |
+
"grad_norm": 3.4101997913922175,
|
84 |
+
"learning_rate": 8.461538461538462e-06,
|
85 |
+
"loss": 0.9116,
|
86 |
+
"step": 11
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 1.2,
|
90 |
+
"grad_norm": 3.4831682884643413,
|
91 |
+
"learning_rate": 9.230769230769232e-06,
|
92 |
+
"loss": 0.8906,
|
93 |
+
"step": 12
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.3,
|
97 |
+
"grad_norm": 2.641980934804885,
|
98 |
+
"learning_rate": 1e-05,
|
99 |
+
"loss": 0.888,
|
100 |
+
"step": 13
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 1.4,
|
104 |
+
"grad_norm": 1.7861730738789814,
|
105 |
+
"learning_rate": 9.998197638354428e-06,
|
106 |
+
"loss": 0.8401,
|
107 |
+
"step": 14
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 1.5,
|
111 |
+
"grad_norm": 1.5706261318322143,
|
112 |
+
"learning_rate": 9.992791852820709e-06,
|
113 |
+
"loss": 0.8405,
|
114 |
+
"step": 15
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 1.6,
|
118 |
+
"grad_norm": 1.3190250051338637,
|
119 |
+
"learning_rate": 9.983786540671052e-06,
|
120 |
+
"loss": 0.7853,
|
121 |
+
"step": 16
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 1.7,
|
125 |
+
"grad_norm": 1.1657856245313856,
|
126 |
+
"learning_rate": 9.971188194237141e-06,
|
127 |
+
"loss": 0.809,
|
128 |
+
"step": 17
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.8,
|
132 |
+
"grad_norm": 1.0936925998213487,
|
133 |
+
"learning_rate": 9.955005896229543e-06,
|
134 |
+
"loss": 0.7964,
|
135 |
+
"step": 18
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.9,
|
139 |
+
"grad_norm": 1.1025321139904043,
|
140 |
+
"learning_rate": 9.935251313189564e-06,
|
141 |
+
"loss": 0.7674,
|
142 |
+
"step": 19
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 2.0,
|
146 |
+
"grad_norm": 0.9637286919181353,
|
147 |
+
"learning_rate": 9.911938687078324e-06,
|
148 |
+
"loss": 0.7592,
|
149 |
+
"step": 20
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 2.1,
|
153 |
+
"grad_norm": 0.7965546052760744,
|
154 |
+
"learning_rate": 9.885084825009085e-06,
|
155 |
+
"loss": 0.7301,
|
156 |
+
"step": 21
|
157 |
+
},
|
158 |
+
{
|
159 |
+
"epoch": 2.2,
|
160 |
+
"grad_norm": 0.9345045295927191,
|
161 |
+
"learning_rate": 9.854709087130261e-06,
|
162 |
+
"loss": 0.7319,
|
163 |
+
"step": 22
|
164 |
+
},
|
165 |
+
{
|
166 |
+
"epoch": 2.3,
|
167 |
+
"grad_norm": 0.827207962931123,
|
168 |
+
"learning_rate": 9.820833372667813e-06,
|
169 |
+
"loss": 0.7022,
|
170 |
+
"step": 23
|
171 |
+
},
|
172 |
+
{
|
173 |
+
"epoch": 2.4,
|
174 |
+
"grad_norm": 0.9353036355923889,
|
175 |
+
"learning_rate": 9.783482104137127e-06,
|
176 |
+
"loss": 0.7054,
|
177 |
+
"step": 24
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 2.5,
|
181 |
+
"grad_norm": 0.8388906024912361,
|
182 |
+
"learning_rate": 9.742682209735727e-06,
|
183 |
+
"loss": 0.6994,
|
184 |
+
"step": 25
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.6,
|
188 |
+
"grad_norm": 1.0256190155173306,
|
189 |
+
"learning_rate": 9.698463103929542e-06,
|
190 |
+
"loss": 0.7086,
|
191 |
+
"step": 26
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 2.7,
|
195 |
+
"grad_norm": 0.9561285472798247,
|
196 |
+
"learning_rate": 9.650856666246693e-06,
|
197 |
+
"loss": 0.7106,
|
198 |
+
"step": 27
|
199 |
+
},
|
200 |
+
{
|
201 |
+
"epoch": 2.8,
|
202 |
+
"grad_norm": 0.813973955699604,
|
203 |
+
"learning_rate": 9.599897218294122e-06,
|
204 |
+
"loss": 0.6605,
|
205 |
+
"step": 28
|
206 |
+
},
|
207 |
+
{
|
208 |
+
"epoch": 2.9,
|
209 |
+
"grad_norm": 0.9184475533414902,
|
210 |
+
"learning_rate": 9.54562149901362e-06,
|
211 |
+
"loss": 0.6821,
|
212 |
+
"step": 29
|
213 |
+
},
|
214 |
+
{
|
215 |
+
"epoch": 3.0,
|
216 |
+
"grad_norm": 0.8718822822105823,
|
217 |
+
"learning_rate": 9.488068638195072e-06,
|
218 |
+
"loss": 0.6721,
|
219 |
+
"step": 30
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 3.1,
|
223 |
+
"grad_norm": 0.7142973011327313,
|
224 |
+
"learning_rate": 9.427280128266049e-06,
|
225 |
+
"loss": 0.6355,
|
226 |
+
"step": 31
|
227 |
+
},
|
228 |
+
{
|
229 |
+
"epoch": 3.2,
|
230 |
+
"grad_norm": 0.7095705979851111,
|
231 |
+
"learning_rate": 9.363299794378072e-06,
|
232 |
+
"loss": 0.6443,
|
233 |
+
"step": 32
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 3.3,
|
237 |
+
"grad_norm": 0.6168686019002501,
|
238 |
+
"learning_rate": 9.296173762811084e-06,
|
239 |
+
"loss": 0.6372,
|
240 |
+
"step": 33
|
241 |
+
},
|
242 |
+
{
|
243 |
+
"epoch": 3.4,
|
244 |
+
"grad_norm": 0.7282282683402107,
|
245 |
+
"learning_rate": 9.225950427718974e-06,
|
246 |
+
"loss": 0.5841,
|
247 |
+
"step": 34
|
248 |
+
},
|
249 |
+
{
|
250 |
+
"epoch": 3.5,
|
251 |
+
"grad_norm": 0.7295397144841858,
|
252 |
+
"learning_rate": 9.152680416240059e-06,
|
253 |
+
"loss": 0.6316,
|
254 |
+
"step": 35
|
255 |
+
},
|
256 |
+
{
|
257 |
+
"epoch": 3.6,
|
258 |
+
"grad_norm": 0.6732055967428483,
|
259 |
+
"learning_rate": 9.076416551997721e-06,
|
260 |
+
"loss": 0.627,
|
261 |
+
"step": 36
|
262 |
+
},
|
263 |
+
{
|
264 |
+
"epoch": 3.7,
|
265 |
+
"grad_norm": 0.6528840869757524,
|
266 |
+
"learning_rate": 8.997213817017508e-06,
|
267 |
+
"loss": 0.5588,
|
268 |
+
"step": 37
|
269 |
+
},
|
270 |
+
{
|
271 |
+
"epoch": 3.8,
|
272 |
+
"grad_norm": 0.6222655223189079,
|
273 |
+
"learning_rate": 8.915129312088112e-06,
|
274 |
+
"loss": 0.5578,
|
275 |
+
"step": 38
|
276 |
+
},
|
277 |
+
{
|
278 |
+
"epoch": 3.9,
|
279 |
+
"grad_norm": 0.7349520019461258,
|
280 |
+
"learning_rate": 8.83022221559489e-06,
|
281 |
+
"loss": 0.5864,
|
282 |
+
"step": 39
|
283 |
+
},
|
284 |
+
{
|
285 |
+
"epoch": 4.0,
|
286 |
+
"grad_norm": 0.6896190181121432,
|
287 |
+
"learning_rate": 8.742553740855507e-06,
|
288 |
+
"loss": 0.5926,
|
289 |
+
"step": 40
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 4.1,
|
293 |
+
"grad_norm": 0.7123273822187205,
|
294 |
+
"learning_rate": 8.652187091988516e-06,
|
295 |
+
"loss": 0.5602,
|
296 |
+
"step": 41
|
297 |
+
},
|
298 |
+
{
|
299 |
+
"epoch": 4.2,
|
300 |
+
"grad_norm": 0.670018566825503,
|
301 |
+
"learning_rate": 8.559187418346703e-06,
|
302 |
+
"loss": 0.5391,
|
303 |
+
"step": 42
|
304 |
+
},
|
305 |
+
{
|
306 |
+
"epoch": 4.3,
|
307 |
+
"grad_norm": 0.6706421454390135,
|
308 |
+
"learning_rate": 8.463621767547998e-06,
|
309 |
+
"loss": 0.5395,
|
310 |
+
"step": 43
|
311 |
+
},
|
312 |
+
{
|
313 |
+
"epoch": 4.4,
|
314 |
+
"grad_norm": 0.6338543455646916,
|
315 |
+
"learning_rate": 8.36555903713785e-06,
|
316 |
+
"loss": 0.5163,
|
317 |
+
"step": 44
|
318 |
+
},
|
319 |
+
{
|
320 |
+
"epoch": 4.5,
|
321 |
+
"grad_norm": 0.658926893392716,
|
322 |
+
"learning_rate": 8.265069924917925e-06,
|
323 |
+
"loss": 0.5291,
|
324 |
+
"step": 45
|
325 |
+
},
|
326 |
+
{
|
327 |
+
"epoch": 4.6,
|
328 |
+
"grad_norm": 0.6994883784824381,
|
329 |
+
"learning_rate": 8.162226877976886e-06,
|
330 |
+
"loss": 0.5015,
|
331 |
+
"step": 46
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 4.7,
|
335 |
+
"grad_norm": 0.6942846700993004,
|
336 |
+
"learning_rate": 8.057104040460062e-06,
|
337 |
+
"loss": 0.4983,
|
338 |
+
"step": 47
|
339 |
+
},
|
340 |
+
{
|
341 |
+
"epoch": 4.8,
|
342 |
+
"grad_norm": 0.6827714015671297,
|
343 |
+
"learning_rate": 7.949777200115617e-06,
|
344 |
+
"loss": 0.5043,
|
345 |
+
"step": 48
|
346 |
+
},
|
347 |
+
{
|
348 |
+
"epoch": 4.9,
|
349 |
+
"grad_norm": 0.6347734217894093,
|
350 |
+
"learning_rate": 7.84032373365578e-06,
|
351 |
+
"loss": 0.5499,
|
352 |
+
"step": 49
|
353 |
+
},
|
354 |
+
{
|
355 |
+
"epoch": 5.0,
|
356 |
+
"grad_norm": 0.7225122670017611,
|
357 |
+
"learning_rate": 7.728822550972523e-06,
|
358 |
+
"loss": 0.487,
|
359 |
+
"step": 50
|
360 |
+
},
|
361 |
+
{
|
362 |
+
"epoch": 5.1,
|
363 |
+
"grad_norm": 0.6640326473766751,
|
364 |
+
"learning_rate": 7.615354038247889e-06,
|
365 |
+
"loss": 0.4486,
|
366 |
+
"step": 51
|
367 |
+
},
|
368 |
+
{
|
369 |
+
"epoch": 5.2,
|
370 |
+
"grad_norm": 0.6245036549599394,
|
371 |
+
"learning_rate": 7.500000000000001e-06,
|
372 |
+
"loss": 0.4577,
|
373 |
+
"step": 52
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 5.3,
|
377 |
+
"grad_norm": 0.799949180993253,
|
378 |
+
"learning_rate": 7.382843600106539e-06,
|
379 |
+
"loss": 0.4712,
|
380 |
+
"step": 53
|
381 |
+
},
|
382 |
+
{
|
383 |
+
"epoch": 5.4,
|
384 |
+
"grad_norm": 0.6272988073596274,
|
385 |
+
"learning_rate": 7.263969301848188e-06,
|
386 |
+
"loss": 0.4452,
|
387 |
+
"step": 54
|
388 |
+
},
|
389 |
+
{
|
390 |
+
"epoch": 5.5,
|
391 |
+
"grad_norm": 0.8123590971594787,
|
392 |
+
"learning_rate": 7.143462807015271e-06,
|
393 |
+
"loss": 0.4339,
|
394 |
+
"step": 55
|
395 |
+
},
|
396 |
+
{
|
397 |
+
"epoch": 5.6,
|
398 |
+
"grad_norm": 0.6902047358374217,
|
399 |
+
"learning_rate": 7.021410994121525e-06,
|
400 |
+
"loss": 0.4274,
|
401 |
+
"step": 56
|
402 |
+
},
|
403 |
+
{
|
404 |
+
"epoch": 5.7,
|
405 |
+
"grad_norm": 0.6451724904881029,
|
406 |
+
"learning_rate": 6.897901855769483e-06,
|
407 |
+
"loss": 0.4314,
|
408 |
+
"step": 57
|
409 |
+
},
|
410 |
+
{
|
411 |
+
"epoch": 5.8,
|
412 |
+
"grad_norm": 0.7810229654484437,
|
413 |
+
"learning_rate": 6.773024435212678e-06,
|
414 |
+
"loss": 0.4373,
|
415 |
+
"step": 58
|
416 |
+
},
|
417 |
+
{
|
418 |
+
"epoch": 5.9,
|
419 |
+
"grad_norm": 0.6851866802377342,
|
420 |
+
"learning_rate": 6.646868762160399e-06,
|
421 |
+
"loss": 0.4397,
|
422 |
+
"step": 59
|
423 |
+
},
|
424 |
+
{
|
425 |
+
"epoch": 6.0,
|
426 |
+
"grad_norm": 0.5659145554154605,
|
427 |
+
"learning_rate": 6.519525787871235e-06,
|
428 |
+
"loss": 0.4499,
|
429 |
+
"step": 60
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 6.1,
|
433 |
+
"grad_norm": 0.8733716275115586,
|
434 |
+
"learning_rate": 6.391087319582264e-06,
|
435 |
+
"loss": 0.4084,
|
436 |
+
"step": 61
|
437 |
+
},
|
438 |
+
{
|
439 |
+
"epoch": 6.2,
|
440 |
+
"grad_norm": 0.5673193273908216,
|
441 |
+
"learning_rate": 6.261645954321109e-06,
|
442 |
+
"loss": 0.3811,
|
443 |
+
"step": 62
|
444 |
+
},
|
445 |
+
{
|
446 |
+
"epoch": 6.3,
|
447 |
+
"grad_norm": 1.082939657326654,
|
448 |
+
"learning_rate": 6.131295012148613e-06,
|
449 |
+
"loss": 0.4065,
|
450 |
+
"step": 63
|
451 |
+
},
|
452 |
+
{
|
453 |
+
"epoch": 6.4,
|
454 |
+
"grad_norm": 0.7293073710983305,
|
455 |
+
"learning_rate": 6.000128468880223e-06,
|
456 |
+
"loss": 0.3793,
|
457 |
+
"step": 64
|
458 |
+
},
|
459 |
+
{
|
460 |
+
"epoch": 6.5,
|
461 |
+
"grad_norm": 0.8026538763909412,
|
462 |
+
"learning_rate": 5.8682408883346535e-06,
|
463 |
+
"loss": 0.3871,
|
464 |
+
"step": 65
|
465 |
+
},
|
466 |
+
{
|
467 |
+
"epoch": 6.6,
|
468 |
+
"grad_norm": 0.8307824369586567,
|
469 |
+
"learning_rate": 5.735727354158581e-06,
|
470 |
+
"loss": 0.3209,
|
471 |
+
"step": 66
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 6.7,
|
475 |
+
"grad_norm": 0.8391055191788069,
|
476 |
+
"learning_rate": 5.6026834012766155e-06,
|
477 |
+
"loss": 0.3437,
|
478 |
+
"step": 67
|
479 |
+
},
|
480 |
+
{
|
481 |
+
"epoch": 6.8,
|
482 |
+
"grad_norm": 0.700258127801532,
|
483 |
+
"learning_rate": 5.469204947015897e-06,
|
484 |
+
"loss": 0.3581,
|
485 |
+
"step": 68
|
486 |
+
},
|
487 |
+
{
|
488 |
+
"epoch": 6.9,
|
489 |
+
"grad_norm": 0.729209063683552,
|
490 |
+
"learning_rate": 5.335388221955012e-06,
|
491 |
+
"loss": 0.3967,
|
492 |
+
"step": 69
|
493 |
+
},
|
494 |
+
{
|
495 |
+
"epoch": 7.0,
|
496 |
+
"grad_norm": 0.6477712484608066,
|
497 |
+
"learning_rate": 5.201329700547077e-06,
|
498 |
+
"loss": 0.3498,
|
499 |
+
"step": 70
|
500 |
+
},
|
501 |
+
{
|
502 |
+
"epoch": 7.1,
|
503 |
+
"grad_norm": 0.8240736558496558,
|
504 |
+
"learning_rate": 5.067126031566988e-06,
|
505 |
+
"loss": 0.3236,
|
506 |
+
"step": 71
|
507 |
+
},
|
508 |
+
{
|
509 |
+
"epoch": 7.2,
|
510 |
+
"grad_norm": 0.7866852557309202,
|
511 |
+
"learning_rate": 4.932873968433014e-06,
|
512 |
+
"loss": 0.2949,
|
513 |
+
"step": 72
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 7.3,
|
517 |
+
"grad_norm": 0.7666470015059026,
|
518 |
+
"learning_rate": 4.798670299452926e-06,
|
519 |
+
"loss": 0.2926,
|
520 |
+
"step": 73
|
521 |
+
},
|
522 |
+
{
|
523 |
+
"epoch": 7.4,
|
524 |
+
"grad_norm": 0.751803291907828,
|
525 |
+
"learning_rate": 4.664611778044988e-06,
|
526 |
+
"loss": 0.3526,
|
527 |
+
"step": 74
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 7.5,
|
531 |
+
"grad_norm": 0.9441667657147972,
|
532 |
+
"learning_rate": 4.530795052984104e-06,
|
533 |
+
"loss": 0.3286,
|
534 |
+
"step": 75
|
535 |
+
},
|
536 |
+
{
|
537 |
+
"epoch": 7.6,
|
538 |
+
"grad_norm": 0.6614312063551343,
|
539 |
+
"learning_rate": 4.397316598723385e-06,
|
540 |
+
"loss": 0.2884,
|
541 |
+
"step": 76
|
542 |
+
},
|
543 |
+
{
|
544 |
+
"epoch": 7.7,
|
545 |
+
"grad_norm": 0.6782553591922619,
|
546 |
+
"learning_rate": 4.264272645841419e-06,
|
547 |
+
"loss": 0.3176,
|
548 |
+
"step": 77
|
549 |
+
},
|
550 |
+
{
|
551 |
+
"epoch": 7.8,
|
552 |
+
"grad_norm": 0.8020010115543638,
|
553 |
+
"learning_rate": 4.131759111665349e-06,
|
554 |
+
"loss": 0.3128,
|
555 |
+
"step": 78
|
556 |
+
},
|
557 |
+
{
|
558 |
+
"epoch": 7.9,
|
559 |
+
"grad_norm": 0.6047840534546456,
|
560 |
+
"learning_rate": 3.999871531119779e-06,
|
561 |
+
"loss": 0.3264,
|
562 |
+
"step": 79
|
563 |
+
},
|
564 |
+
{
|
565 |
+
"epoch": 8.0,
|
566 |
+
"grad_norm": 0.7006317191840805,
|
567 |
+
"learning_rate": 3.86870498785139e-06,
|
568 |
+
"loss": 0.2925,
|
569 |
+
"step": 80
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 8.1,
|
573 |
+
"grad_norm": 0.8175785828483745,
|
574 |
+
"learning_rate": 3.7383540456788915e-06,
|
575 |
+
"loss": 0.2609,
|
576 |
+
"step": 81
|
577 |
+
},
|
578 |
+
{
|
579 |
+
"epoch": 8.2,
|
580 |
+
"grad_norm": 0.6252429936534438,
|
581 |
+
"learning_rate": 3.6089126804177373e-06,
|
582 |
+
"loss": 0.2625,
|
583 |
+
"step": 82
|
584 |
+
},
|
585 |
+
{
|
586 |
+
"epoch": 8.3,
|
587 |
+
"grad_norm": 0.9757027403168241,
|
588 |
+
"learning_rate": 3.480474212128766e-06,
|
589 |
+
"loss": 0.2625,
|
590 |
+
"step": 83
|
591 |
+
},
|
592 |
+
{
|
593 |
+
"epoch": 8.4,
|
594 |
+
"grad_norm": 0.787826173262127,
|
595 |
+
"learning_rate": 3.3531312378396026e-06,
|
596 |
+
"loss": 0.2508,
|
597 |
+
"step": 84
|
598 |
+
},
|
599 |
+
{
|
600 |
+
"epoch": 8.5,
|
601 |
+
"grad_norm": 0.6119860664769008,
|
602 |
+
"learning_rate": 3.226975564787322e-06,
|
603 |
+
"loss": 0.271,
|
604 |
+
"step": 85
|
605 |
+
},
|
606 |
+
{
|
607 |
+
"epoch": 8.6,
|
608 |
+
"grad_norm": 0.7120003182441815,
|
609 |
+
"learning_rate": 3.1020981442305187e-06,
|
610 |
+
"loss": 0.2599,
|
611 |
+
"step": 86
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 8.7,
|
615 |
+
"grad_norm": 0.6035509962137439,
|
616 |
+
"learning_rate": 2.978589005878476e-06,
|
617 |
+
"loss": 0.259,
|
618 |
+
"step": 87
|
619 |
+
},
|
620 |
+
{
|
621 |
+
"epoch": 8.8,
|
622 |
+
"grad_norm": 0.6189259053460058,
|
623 |
+
"learning_rate": 2.8565371929847286e-06,
|
624 |
+
"loss": 0.2786,
|
625 |
+
"step": 88
|
626 |
+
},
|
627 |
+
{
|
628 |
+
"epoch": 8.9,
|
629 |
+
"grad_norm": 0.6364448262362423,
|
630 |
+
"learning_rate": 2.736030698151815e-06,
|
631 |
+
"loss": 0.2535,
|
632 |
+
"step": 89
|
633 |
+
},
|
634 |
+
{
|
635 |
+
"epoch": 9.0,
|
636 |
+
"grad_norm": 0.5779075096186825,
|
637 |
+
"learning_rate": 2.6171563998934605e-06,
|
638 |
+
"loss": 0.2686,
|
639 |
+
"step": 90
|
640 |
+
},
|
641 |
+
{
|
642 |
+
"epoch": 9.1,
|
643 |
+
"grad_norm": 0.8187626507294279,
|
644 |
+
"learning_rate": 2.5000000000000015e-06,
|
645 |
+
"loss": 0.2543,
|
646 |
+
"step": 91
|
647 |
+
},
|
648 |
+
{
|
649 |
+
"epoch": 9.2,
|
650 |
+
"grad_norm": 0.6290212293797883,
|
651 |
+
"learning_rate": 2.384645961752113e-06,
|
652 |
+
"loss": 0.224,
|
653 |
+
"step": 92
|
654 |
+
},
|
655 |
+
{
|
656 |
+
"epoch": 9.3,
|
657 |
+
"grad_norm": 0.5105484741650185,
|
658 |
+
"learning_rate": 2.2711774490274767e-06,
|
659 |
+
"loss": 0.243,
|
660 |
+
"step": 93
|
661 |
+
},
|
662 |
+
{
|
663 |
+
"epoch": 9.4,
|
664 |
+
"grad_norm": 0.6525111719625585,
|
665 |
+
"learning_rate": 2.159676266344222e-06,
|
666 |
+
"loss": 0.1934,
|
667 |
+
"step": 94
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 9.5,
|
671 |
+
"grad_norm": 0.8135620179358877,
|
672 |
+
"learning_rate": 2.050222799884387e-06,
|
673 |
+
"loss": 0.2434,
|
674 |
+
"step": 95
|
675 |
+
},
|
676 |
+
{
|
677 |
+
"epoch": 9.6,
|
678 |
+
"grad_norm": 0.6136430854939934,
|
679 |
+
"learning_rate": 1.942895959539939e-06,
|
680 |
+
"loss": 0.2389,
|
681 |
+
"step": 96
|
682 |
+
},
|
683 |
+
{
|
684 |
+
"epoch": 9.7,
|
685 |
+
"grad_norm": 0.5621277796125248,
|
686 |
+
"learning_rate": 1.8377731220231144e-06,
|
687 |
+
"loss": 0.2246,
|
688 |
+
"step": 97
|
689 |
+
},
|
690 |
+
{
|
691 |
+
"epoch": 9.8,
|
692 |
+
"grad_norm": 0.6153238847848149,
|
693 |
+
"learning_rate": 1.7349300750820758e-06,
|
694 |
+
"loss": 0.1852,
|
695 |
+
"step": 98
|
696 |
+
},
|
697 |
+
{
|
698 |
+
"epoch": 9.9,
|
699 |
+
"grad_norm": 0.5749792494703895,
|
700 |
+
"learning_rate": 1.6344409628621482e-06,
|
701 |
+
"loss": 0.215,
|
702 |
+
"step": 99
|
703 |
+
},
|
704 |
+
{
|
705 |
+
"epoch": 10.0,
|
706 |
+
"grad_norm": 0.5490782621363017,
|
707 |
+
"learning_rate": 1.5363782324520033e-06,
|
708 |
+
"loss": 0.2478,
|
709 |
+
"step": 100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 10.1,
|
713 |
+
"grad_norm": 0.5370472408719152,
|
714 |
+
"learning_rate": 1.4408125816532981e-06,
|
715 |
+
"loss": 0.1738,
|
716 |
+
"step": 101
|
717 |
+
},
|
718 |
+
{
|
719 |
+
"epoch": 10.2,
|
720 |
+
"grad_norm": 0.5103995369294385,
|
721 |
+
"learning_rate": 1.347812908011485e-06,
|
722 |
+
"loss": 0.2316,
|
723 |
+
"step": 102
|
724 |
+
},
|
725 |
+
{
|
726 |
+
"epoch": 10.3,
|
727 |
+
"grad_norm": 0.5384926824814891,
|
728 |
+
"learning_rate": 1.257446259144494e-06,
|
729 |
+
"loss": 0.2121,
|
730 |
+
"step": 103
|
731 |
+
},
|
732 |
+
{
|
733 |
+
"epoch": 10.4,
|
734 |
+
"grad_norm": 0.5436679337039739,
|
735 |
+
"learning_rate": 1.1697777844051105e-06,
|
736 |
+
"loss": 0.1843,
|
737 |
+
"step": 104
|
738 |
+
},
|
739 |
+
{
|
740 |
+
"epoch": 10.5,
|
741 |
+
"grad_norm": 0.5938010326332525,
|
742 |
+
"learning_rate": 1.0848706879118893e-06,
|
743 |
+
"loss": 0.2388,
|
744 |
+
"step": 105
|
745 |
+
},
|
746 |
+
{
|
747 |
+
"epoch": 10.6,
|
748 |
+
"grad_norm": 0.5929265334853338,
|
749 |
+
"learning_rate": 1.0027861829824953e-06,
|
750 |
+
"loss": 0.2056,
|
751 |
+
"step": 106
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 10.7,
|
755 |
+
"grad_norm": 0.47011857774401083,
|
756 |
+
"learning_rate": 9.235834480022788e-07,
|
757 |
+
"loss": 0.2002,
|
758 |
+
"step": 107
|
759 |
+
},
|
760 |
+
{
|
761 |
+
"epoch": 10.8,
|
762 |
+
"grad_norm": 0.49385701661144776,
|
763 |
+
"learning_rate": 8.473195837599419e-07,
|
764 |
+
"loss": 0.1744,
|
765 |
+
"step": 108
|
766 |
+
},
|
767 |
+
{
|
768 |
+
"epoch": 10.9,
|
769 |
+
"grad_norm": 0.506010826084403,
|
770 |
+
"learning_rate": 7.740495722810271e-07,
|
771 |
+
"loss": 0.1999,
|
772 |
+
"step": 109
|
773 |
+
},
|
774 |
+
{
|
775 |
+
"epoch": 11.0,
|
776 |
+
"grad_norm": 0.5074223422486763,
|
777 |
+
"learning_rate": 7.03826237188916e-07,
|
778 |
+
"loss": 0.1918,
|
779 |
+
"step": 110
|
780 |
+
},
|
781 |
+
{
|
782 |
+
"epoch": 11.1,
|
783 |
+
"grad_norm": 0.5371363986037742,
|
784 |
+
"learning_rate": 6.367002056219285e-07,
|
785 |
+
"loss": 0.1796,
|
786 |
+
"step": 111
|
787 |
+
},
|
788 |
+
{
|
789 |
+
"epoch": 11.2,
|
790 |
+
"grad_norm": 0.5210587656041868,
|
791 |
+
"learning_rate": 5.727198717339511e-07,
|
792 |
+
"loss": 0.1738,
|
793 |
+
"step": 112
|
794 |
+
},
|
795 |
+
{
|
796 |
+
"epoch": 11.3,
|
797 |
+
"grad_norm": 0.47561484117135805,
|
798 |
+
"learning_rate": 5.119313618049309e-07,
|
799 |
+
"loss": 0.2078,
|
800 |
+
"step": 113
|
801 |
+
},
|
802 |
+
{
|
803 |
+
"epoch": 11.4,
|
804 |
+
"grad_norm": 0.46168861486892365,
|
805 |
+
"learning_rate": 4.54378500986381e-07,
|
806 |
+
"loss": 0.2093,
|
807 |
+
"step": 114
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 11.5,
|
811 |
+
"grad_norm": 0.5524412647638766,
|
812 |
+
"learning_rate": 4.001027817058789e-07,
|
813 |
+
"loss": 0.2172,
|
814 |
+
"step": 115
|
815 |
+
},
|
816 |
+
{
|
817 |
+
"epoch": 11.6,
|
818 |
+
"grad_norm": 0.45594210195911783,
|
819 |
+
"learning_rate": 3.49143333753309e-07,
|
820 |
+
"loss": 0.1675,
|
821 |
+
"step": 116
|
822 |
+
},
|
823 |
+
{
|
824 |
+
"epoch": 11.7,
|
825 |
+
"grad_norm": 0.5516466886946935,
|
826 |
+
"learning_rate": 3.015368960704584e-07,
|
827 |
+
"loss": 0.1739,
|
828 |
+
"step": 117
|
829 |
+
},
|
830 |
+
{
|
831 |
+
"epoch": 11.8,
|
832 |
+
"grad_norm": 0.5231450036431963,
|
833 |
+
"learning_rate": 2.573177902642726e-07,
|
834 |
+
"loss": 0.187,
|
835 |
+
"step": 118
|
836 |
+
},
|
837 |
+
{
|
838 |
+
"epoch": 11.9,
|
839 |
+
"grad_norm": 0.5363110524794331,
|
840 |
+
"learning_rate": 2.1651789586287442e-07,
|
841 |
+
"loss": 0.1757,
|
842 |
+
"step": 119
|
843 |
+
},
|
844 |
+
{
|
845 |
+
"epoch": 12.0,
|
846 |
+
"grad_norm": 0.519753376130612,
|
847 |
+
"learning_rate": 1.7916662733218848e-07,
|
848 |
+
"loss": 0.2041,
|
849 |
+
"step": 120
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 12.1,
|
853 |
+
"grad_norm": 0.43503074772379297,
|
854 |
+
"learning_rate": 1.4529091286973994e-07,
|
855 |
+
"loss": 0.1679,
|
856 |
+
"step": 121
|
857 |
+
},
|
858 |
+
{
|
859 |
+
"epoch": 12.2,
|
860 |
+
"grad_norm": 0.43985553309723496,
|
861 |
+
"learning_rate": 1.1491517499091498e-07,
|
862 |
+
"loss": 0.1927,
|
863 |
+
"step": 122
|
864 |
+
},
|
865 |
+
{
|
866 |
+
"epoch": 12.3,
|
867 |
+
"grad_norm": 0.4299185889135424,
|
868 |
+
"learning_rate": 8.80613129216762e-08,
|
869 |
+
"loss": 0.1882,
|
870 |
+
"step": 123
|
871 |
+
},
|
872 |
+
{
|
873 |
+
"epoch": 12.4,
|
874 |
+
"grad_norm": 0.4115820901227382,
|
875 |
+
"learning_rate": 6.474868681043578e-08,
|
876 |
+
"loss": 0.161,
|
877 |
+
"step": 124
|
878 |
+
},
|
879 |
+
{
|
880 |
+
"epoch": 12.5,
|
881 |
+
"grad_norm": 0.43869984814330887,
|
882 |
+
"learning_rate": 4.499410377045765e-08,
|
883 |
+
"loss": 0.1831,
|
884 |
+
"step": 125
|
885 |
+
},
|
886 |
+
{
|
887 |
+
"epoch": 12.6,
|
888 |
+
"grad_norm": 0.42332984157222775,
|
889 |
+
"learning_rate": 2.8811805762860578e-08,
|
890 |
+
"loss": 0.1807,
|
891 |
+
"step": 126
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 12.7,
|
895 |
+
"grad_norm": 0.4292928319812678,
|
896 |
+
"learning_rate": 1.6213459328950355e-08,
|
897 |
+
"loss": 0.2008,
|
898 |
+
"step": 127
|
899 |
+
},
|
900 |
+
{
|
901 |
+
"epoch": 12.8,
|
902 |
+
"grad_norm": 0.4296689410354326,
|
903 |
+
"learning_rate": 7.2081471792911914e-09,
|
904 |
+
"loss": 0.1804,
|
905 |
+
"step": 128
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 12.9,
|
909 |
+
"grad_norm": 0.429020498516221,
|
910 |
+
"learning_rate": 1.8023616455731253e-09,
|
911 |
+
"loss": 0.1886,
|
912 |
+
"step": 129
|
913 |
+
},
|
914 |
+
{
|
915 |
+
"epoch": 13.0,
|
916 |
+
"grad_norm": 0.4428955411596461,
|
917 |
+
"learning_rate": 0.0,
|
918 |
+
"loss": 0.2065,
|
919 |
+
"step": 130
|
920 |
+
},
|
921 |
+
{
|
922 |
+
"epoch": 13.0,
|
923 |
+
"step": 130,
|
924 |
+
"total_flos": 8.969562657652736e+16,
|
925 |
+
"train_loss": 0.4498058209052453,
|
926 |
+
"train_runtime": 2844.3624,
|
927 |
+
"train_samples_per_second": 1.444,
|
928 |
+
"train_steps_per_second": 0.046
|
929 |
+
}
|
930 |
+
],
|
931 |
+
"logging_steps": 1,
|
932 |
+
"max_steps": 130,
|
933 |
+
"num_input_tokens_seen": 0,
|
934 |
+
"num_train_epochs": 13,
|
935 |
+
"save_steps": 500,
|
936 |
+
"stateful_callbacks": {
|
937 |
+
"TrainerControl": {
|
938 |
+
"args": {
|
939 |
+
"should_epoch_stop": false,
|
940 |
+
"should_evaluate": false,
|
941 |
+
"should_log": false,
|
942 |
+
"should_save": true,
|
943 |
+
"should_training_stop": true
|
944 |
+
},
|
945 |
+
"attributes": {}
|
946 |
+
}
|
947 |
+
},
|
948 |
+
"total_flos": 8.969562657652736e+16,
|
949 |
+
"train_batch_size": 1,
|
950 |
+
"trial_name": null,
|
951 |
+
"trial_params": null
|
952 |
+
}
|
training_loss.png
ADDED
![]() |