amazingvince
commited on
Commit
•
ea9a010
1
Parent(s):
6489207
End of training
Browse files- README.md +3 -3
- all_results.json +15 -0
- eval_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +808 -0
README.md
CHANGED
@@ -14,10 +14,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amazingvince/huggingface/runs/nakztaik)
|
15 |
# jina_embeddings_v2_base_code_multi_regression-simple
|
16 |
|
17 |
-
This model is a fine-tuned version of [jinaai/jina-embeddings-v2-base-code](https://huggingface.co/jinaai/jina-embeddings-v2-base-code) on
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Mse: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
14 |
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/amazingvince/huggingface/runs/nakztaik)
|
15 |
# jina_embeddings_v2_base_code_multi_regression-simple
|
16 |
|
17 |
+
This model is a fine-tuned version of [jinaai/jina-embeddings-v2-base-code](https://huggingface.co/jinaai/jina-embeddings-v2-base-code) on the amazingvince/the-stack-smol-xs-scored-and-annotated-all dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.6201
|
20 |
+
- Mse: 0.6201
|
21 |
|
22 |
## Model description
|
23 |
|
all_results.json
ADDED
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9987902250181466,
|
3 |
+
"eval_loss": 0.6201480627059937,
|
4 |
+
"eval_mse": 0.6201480558548851,
|
5 |
+
"eval_runtime": 12.8132,
|
6 |
+
"eval_samples": 435,
|
7 |
+
"eval_samples_per_second": 33.949,
|
8 |
+
"eval_steps_per_second": 17.014,
|
9 |
+
"total_flos": 8688901375918080.0,
|
10 |
+
"train_loss": 1.1010994948157968,
|
11 |
+
"train_runtime": 478.9806,
|
12 |
+
"train_samples": 8265,
|
13 |
+
"train_samples_per_second": 17.255,
|
14 |
+
"train_steps_per_second": 1.077
|
15 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9987902250181466,
|
3 |
+
"eval_loss": 0.6201480627059937,
|
4 |
+
"eval_mse": 0.6201480558548851,
|
5 |
+
"eval_runtime": 12.8132,
|
6 |
+
"eval_samples": 435,
|
7 |
+
"eval_samples_per_second": 33.949,
|
8 |
+
"eval_steps_per_second": 17.014
|
9 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9987902250181466,
|
3 |
+
"total_flos": 8688901375918080.0,
|
4 |
+
"train_loss": 1.1010994948157968,
|
5 |
+
"train_runtime": 478.9806,
|
6 |
+
"train_samples": 8265,
|
7 |
+
"train_samples_per_second": 17.255,
|
8 |
+
"train_steps_per_second": 1.077
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,808 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9987902250181466,
|
5 |
+
"eval_steps": 100,
|
6 |
+
"global_step": 516,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.009678199854827003,
|
13 |
+
"grad_norm": 135.23733520507812,
|
14 |
+
"learning_rate": 1.9230769230769234e-06,
|
15 |
+
"loss": 12.7676,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.019356399709654006,
|
20 |
+
"grad_norm": 142.41867065429688,
|
21 |
+
"learning_rate": 3.846153846153847e-06,
|
22 |
+
"loss": 12.1736,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.029034599564481005,
|
27 |
+
"grad_norm": 142.9897003173828,
|
28 |
+
"learning_rate": 5.769230769230769e-06,
|
29 |
+
"loss": 11.9754,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.03871279941930801,
|
34 |
+
"grad_norm": 122.53395080566406,
|
35 |
+
"learning_rate": 7.692307692307694e-06,
|
36 |
+
"loss": 7.9422,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.04839099927413501,
|
41 |
+
"grad_norm": 131.50697326660156,
|
42 |
+
"learning_rate": 9.615384615384616e-06,
|
43 |
+
"loss": 6.1603,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.05806919912896201,
|
48 |
+
"grad_norm": 273.497314453125,
|
49 |
+
"learning_rate": 9.918367346938776e-06,
|
50 |
+
"loss": 1.798,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.06774739898378901,
|
55 |
+
"grad_norm": 17.278669357299805,
|
56 |
+
"learning_rate": 9.816326530612245e-06,
|
57 |
+
"loss": 1.0221,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.07742559883861602,
|
62 |
+
"grad_norm": 17.088966369628906,
|
63 |
+
"learning_rate": 9.714285714285715e-06,
|
64 |
+
"loss": 0.4251,
|
65 |
+
"step": 40
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.08710379869344302,
|
69 |
+
"grad_norm": 58.794822692871094,
|
70 |
+
"learning_rate": 9.612244897959185e-06,
|
71 |
+
"loss": 0.9236,
|
72 |
+
"step": 45
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 0.09678199854827002,
|
76 |
+
"grad_norm": 40.58847427368164,
|
77 |
+
"learning_rate": 9.510204081632653e-06,
|
78 |
+
"loss": 0.4787,
|
79 |
+
"step": 50
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.10646019840309702,
|
83 |
+
"grad_norm": 41.08816146850586,
|
84 |
+
"learning_rate": 9.408163265306123e-06,
|
85 |
+
"loss": 0.6779,
|
86 |
+
"step": 55
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 0.11613839825792402,
|
90 |
+
"grad_norm": 9.461664199829102,
|
91 |
+
"learning_rate": 9.306122448979593e-06,
|
92 |
+
"loss": 0.5731,
|
93 |
+
"step": 60
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.12581659811275103,
|
97 |
+
"grad_norm": 15.421150207519531,
|
98 |
+
"learning_rate": 9.204081632653062e-06,
|
99 |
+
"loss": 0.8264,
|
100 |
+
"step": 65
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 0.13549479796757802,
|
104 |
+
"grad_norm": 36.99074935913086,
|
105 |
+
"learning_rate": 9.102040816326532e-06,
|
106 |
+
"loss": 0.8976,
|
107 |
+
"step": 70
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.14517299782240503,
|
111 |
+
"grad_norm": 12.443870544433594,
|
112 |
+
"learning_rate": 9e-06,
|
113 |
+
"loss": 0.758,
|
114 |
+
"step": 75
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.15485119767723204,
|
118 |
+
"grad_norm": 34.37516784667969,
|
119 |
+
"learning_rate": 8.89795918367347e-06,
|
120 |
+
"loss": 0.4913,
|
121 |
+
"step": 80
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 0.16452939753205903,
|
125 |
+
"grad_norm": 47.92347717285156,
|
126 |
+
"learning_rate": 8.79591836734694e-06,
|
127 |
+
"loss": 0.6342,
|
128 |
+
"step": 85
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 0.17420759738688604,
|
132 |
+
"grad_norm": 19.53640365600586,
|
133 |
+
"learning_rate": 8.69387755102041e-06,
|
134 |
+
"loss": 0.7332,
|
135 |
+
"step": 90
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 0.18388579724171303,
|
139 |
+
"grad_norm": 15.180093765258789,
|
140 |
+
"learning_rate": 8.591836734693878e-06,
|
141 |
+
"loss": 0.8574,
|
142 |
+
"step": 95
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.19356399709654004,
|
146 |
+
"grad_norm": 7.7558770179748535,
|
147 |
+
"learning_rate": 8.489795918367347e-06,
|
148 |
+
"loss": 0.7241,
|
149 |
+
"step": 100
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.19356399709654004,
|
153 |
+
"eval_loss": 0.636104166507721,
|
154 |
+
"eval_mse": 0.6361041891163793,
|
155 |
+
"eval_runtime": 12.3473,
|
156 |
+
"eval_samples_per_second": 35.23,
|
157 |
+
"eval_steps_per_second": 17.656,
|
158 |
+
"step": 100
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 0.20324219695136705,
|
162 |
+
"grad_norm": 6.328822612762451,
|
163 |
+
"learning_rate": 8.387755102040817e-06,
|
164 |
+
"loss": 0.613,
|
165 |
+
"step": 105
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 0.21292039680619404,
|
169 |
+
"grad_norm": 3.98986554145813,
|
170 |
+
"learning_rate": 8.285714285714287e-06,
|
171 |
+
"loss": 0.6963,
|
172 |
+
"step": 110
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 0.22259859666102105,
|
176 |
+
"grad_norm": 6.252445697784424,
|
177 |
+
"learning_rate": 8.183673469387757e-06,
|
178 |
+
"loss": 0.4936,
|
179 |
+
"step": 115
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.23227679651584804,
|
183 |
+
"grad_norm": 11.744823455810547,
|
184 |
+
"learning_rate": 8.081632653061225e-06,
|
185 |
+
"loss": 0.6189,
|
186 |
+
"step": 120
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 0.24195499637067505,
|
190 |
+
"grad_norm": 3.548699378967285,
|
191 |
+
"learning_rate": 7.979591836734695e-06,
|
192 |
+
"loss": 0.6508,
|
193 |
+
"step": 125
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 0.25163319622550206,
|
197 |
+
"grad_norm": 32.78942108154297,
|
198 |
+
"learning_rate": 7.877551020408164e-06,
|
199 |
+
"loss": 0.7334,
|
200 |
+
"step": 130
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.26131139608032905,
|
204 |
+
"grad_norm": 39.87502670288086,
|
205 |
+
"learning_rate": 7.775510204081632e-06,
|
206 |
+
"loss": 0.8856,
|
207 |
+
"step": 135
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 0.27098959593515604,
|
211 |
+
"grad_norm": 25.449832916259766,
|
212 |
+
"learning_rate": 7.673469387755102e-06,
|
213 |
+
"loss": 0.6497,
|
214 |
+
"step": 140
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 0.2806677957899831,
|
218 |
+
"grad_norm": 9.905705451965332,
|
219 |
+
"learning_rate": 7.571428571428572e-06,
|
220 |
+
"loss": 0.6297,
|
221 |
+
"step": 145
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.29034599564481006,
|
225 |
+
"grad_norm": 10.688154220581055,
|
226 |
+
"learning_rate": 7.469387755102041e-06,
|
227 |
+
"loss": 0.5351,
|
228 |
+
"step": 150
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 0.30002419549963705,
|
232 |
+
"grad_norm": 20.666561126708984,
|
233 |
+
"learning_rate": 7.367346938775511e-06,
|
234 |
+
"loss": 0.5918,
|
235 |
+
"step": 155
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 0.3097023953544641,
|
239 |
+
"grad_norm": 44.254947662353516,
|
240 |
+
"learning_rate": 7.2653061224489805e-06,
|
241 |
+
"loss": 0.8516,
|
242 |
+
"step": 160
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 0.3193805952092911,
|
246 |
+
"grad_norm": 18.602283477783203,
|
247 |
+
"learning_rate": 7.16326530612245e-06,
|
248 |
+
"loss": 0.4989,
|
249 |
+
"step": 165
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 0.32905879506411806,
|
253 |
+
"grad_norm": 2.891568660736084,
|
254 |
+
"learning_rate": 7.061224489795919e-06,
|
255 |
+
"loss": 0.4556,
|
256 |
+
"step": 170
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 0.3387369949189451,
|
260 |
+
"grad_norm": 14.327004432678223,
|
261 |
+
"learning_rate": 6.959183673469388e-06,
|
262 |
+
"loss": 0.6965,
|
263 |
+
"step": 175
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 0.3484151947737721,
|
267 |
+
"grad_norm": 3.936084032058716,
|
268 |
+
"learning_rate": 6.857142857142858e-06,
|
269 |
+
"loss": 0.6425,
|
270 |
+
"step": 180
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 0.35809339462859907,
|
274 |
+
"grad_norm": 6.193188667297363,
|
275 |
+
"learning_rate": 6.755102040816327e-06,
|
276 |
+
"loss": 0.5081,
|
277 |
+
"step": 185
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.36777159448342606,
|
281 |
+
"grad_norm": 21.818361282348633,
|
282 |
+
"learning_rate": 6.653061224489797e-06,
|
283 |
+
"loss": 0.6029,
|
284 |
+
"step": 190
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 0.3774497943382531,
|
288 |
+
"grad_norm": 20.763904571533203,
|
289 |
+
"learning_rate": 6.5510204081632656e-06,
|
290 |
+
"loss": 0.4717,
|
291 |
+
"step": 195
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 0.3871279941930801,
|
295 |
+
"grad_norm": 15.887273788452148,
|
296 |
+
"learning_rate": 6.4489795918367345e-06,
|
297 |
+
"loss": 0.575,
|
298 |
+
"step": 200
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 0.3871279941930801,
|
302 |
+
"eval_loss": 0.6364156603813171,
|
303 |
+
"eval_mse": 0.6364156788793104,
|
304 |
+
"eval_runtime": 12.8511,
|
305 |
+
"eval_samples_per_second": 33.849,
|
306 |
+
"eval_steps_per_second": 16.964,
|
307 |
+
"step": 200
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.39680619404790707,
|
311 |
+
"grad_norm": 6.549495220184326,
|
312 |
+
"learning_rate": 6.346938775510204e-06,
|
313 |
+
"loss": 0.6062,
|
314 |
+
"step": 205
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 0.4064843939027341,
|
318 |
+
"grad_norm": 2.362842082977295,
|
319 |
+
"learning_rate": 6.244897959183675e-06,
|
320 |
+
"loss": 0.5902,
|
321 |
+
"step": 210
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 0.4161625937575611,
|
325 |
+
"grad_norm": 6.210005760192871,
|
326 |
+
"learning_rate": 6.142857142857144e-06,
|
327 |
+
"loss": 0.6235,
|
328 |
+
"step": 215
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 0.4258407936123881,
|
332 |
+
"grad_norm": 0.35702061653137207,
|
333 |
+
"learning_rate": 6.040816326530613e-06,
|
334 |
+
"loss": 0.6959,
|
335 |
+
"step": 220
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 0.4355189934672151,
|
339 |
+
"grad_norm": 7.42579460144043,
|
340 |
+
"learning_rate": 5.9387755102040825e-06,
|
341 |
+
"loss": 0.8113,
|
342 |
+
"step": 225
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 0.4451971933220421,
|
346 |
+
"grad_norm": 15.467649459838867,
|
347 |
+
"learning_rate": 5.8367346938775515e-06,
|
348 |
+
"loss": 0.753,
|
349 |
+
"step": 230
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.4548753931768691,
|
353 |
+
"grad_norm": 5.005227565765381,
|
354 |
+
"learning_rate": 5.73469387755102e-06,
|
355 |
+
"loss": 0.423,
|
356 |
+
"step": 235
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 0.4645535930316961,
|
360 |
+
"grad_norm": 9.86463737487793,
|
361 |
+
"learning_rate": 5.63265306122449e-06,
|
362 |
+
"loss": 0.5652,
|
363 |
+
"step": 240
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 0.4742317928865231,
|
367 |
+
"grad_norm": 0.07020189613103867,
|
368 |
+
"learning_rate": 5.530612244897959e-06,
|
369 |
+
"loss": 0.508,
|
370 |
+
"step": 245
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 0.4839099927413501,
|
374 |
+
"grad_norm": 1.7268608808517456,
|
375 |
+
"learning_rate": 5.428571428571429e-06,
|
376 |
+
"loss": 0.7836,
|
377 |
+
"step": 250
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 0.4935881925961771,
|
381 |
+
"grad_norm": 15.658587455749512,
|
382 |
+
"learning_rate": 5.326530612244898e-06,
|
383 |
+
"loss": 0.6653,
|
384 |
+
"step": 255
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 0.5032663924510041,
|
388 |
+
"grad_norm": 3.4803199768066406,
|
389 |
+
"learning_rate": 5.2244897959183684e-06,
|
390 |
+
"loss": 0.7674,
|
391 |
+
"step": 260
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 0.5129445923058311,
|
395 |
+
"grad_norm": 5.9674506187438965,
|
396 |
+
"learning_rate": 5.122448979591837e-06,
|
397 |
+
"loss": 0.5348,
|
398 |
+
"step": 265
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 0.5226227921606581,
|
402 |
+
"grad_norm": 8.432785034179688,
|
403 |
+
"learning_rate": 5.020408163265307e-06,
|
404 |
+
"loss": 0.678,
|
405 |
+
"step": 270
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.5323009920154851,
|
409 |
+
"grad_norm": 13.345314025878906,
|
410 |
+
"learning_rate": 4.918367346938776e-06,
|
411 |
+
"loss": 0.5572,
|
412 |
+
"step": 275
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 0.5419791918703121,
|
416 |
+
"grad_norm": 12.001265525817871,
|
417 |
+
"learning_rate": 4.816326530612245e-06,
|
418 |
+
"loss": 0.5397,
|
419 |
+
"step": 280
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 0.5516573917251392,
|
423 |
+
"grad_norm": 1.87912118434906,
|
424 |
+
"learning_rate": 4.714285714285715e-06,
|
425 |
+
"loss": 0.4944,
|
426 |
+
"step": 285
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 0.5613355915799662,
|
430 |
+
"grad_norm": 3.5236661434173584,
|
431 |
+
"learning_rate": 4.612244897959184e-06,
|
432 |
+
"loss": 0.5333,
|
433 |
+
"step": 290
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 0.5710137914347931,
|
437 |
+
"grad_norm": 12.931561470031738,
|
438 |
+
"learning_rate": 4.5102040816326535e-06,
|
439 |
+
"loss": 0.5476,
|
440 |
+
"step": 295
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 0.5806919912896201,
|
444 |
+
"grad_norm": 6.103638172149658,
|
445 |
+
"learning_rate": 4.408163265306123e-06,
|
446 |
+
"loss": 0.6298,
|
447 |
+
"step": 300
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.5806919912896201,
|
451 |
+
"eval_loss": 0.6253479719161987,
|
452 |
+
"eval_mse": 0.625347970545977,
|
453 |
+
"eval_runtime": 12.7924,
|
454 |
+
"eval_samples_per_second": 34.005,
|
455 |
+
"eval_steps_per_second": 17.041,
|
456 |
+
"step": 300
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 0.5903701911444471,
|
460 |
+
"grad_norm": 7.156700611114502,
|
461 |
+
"learning_rate": 4.306122448979592e-06,
|
462 |
+
"loss": 0.8688,
|
463 |
+
"step": 305
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 0.6000483909992741,
|
467 |
+
"grad_norm": 1.5767498016357422,
|
468 |
+
"learning_rate": 4.204081632653061e-06,
|
469 |
+
"loss": 0.6039,
|
470 |
+
"step": 310
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 0.6097265908541012,
|
474 |
+
"grad_norm": 10.190150260925293,
|
475 |
+
"learning_rate": 4.102040816326531e-06,
|
476 |
+
"loss": 0.5012,
|
477 |
+
"step": 315
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.6194047907089282,
|
481 |
+
"grad_norm": 7.6610026359558105,
|
482 |
+
"learning_rate": 4.000000000000001e-06,
|
483 |
+
"loss": 0.6778,
|
484 |
+
"step": 320
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 0.6290829905637552,
|
488 |
+
"grad_norm": 9.915760040283203,
|
489 |
+
"learning_rate": 3.89795918367347e-06,
|
490 |
+
"loss": 0.4987,
|
491 |
+
"step": 325
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 0.6387611904185821,
|
495 |
+
"grad_norm": 11.606775283813477,
|
496 |
+
"learning_rate": 3.795918367346939e-06,
|
497 |
+
"loss": 0.4232,
|
498 |
+
"step": 330
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 0.6484393902734091,
|
502 |
+
"grad_norm": 0.6899937987327576,
|
503 |
+
"learning_rate": 3.6938775510204083e-06,
|
504 |
+
"loss": 0.3689,
|
505 |
+
"step": 335
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 0.6581175901282361,
|
509 |
+
"grad_norm": 2.4227399826049805,
|
510 |
+
"learning_rate": 3.5918367346938777e-06,
|
511 |
+
"loss": 0.7523,
|
512 |
+
"step": 340
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 0.6677957899830631,
|
516 |
+
"grad_norm": 6.039433479309082,
|
517 |
+
"learning_rate": 3.4897959183673474e-06,
|
518 |
+
"loss": 0.8179,
|
519 |
+
"step": 345
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 0.6774739898378902,
|
523 |
+
"grad_norm": 1.8034197092056274,
|
524 |
+
"learning_rate": 3.3877551020408168e-06,
|
525 |
+
"loss": 0.7031,
|
526 |
+
"step": 350
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 0.6871521896927172,
|
530 |
+
"grad_norm": 9.077332496643066,
|
531 |
+
"learning_rate": 3.285714285714286e-06,
|
532 |
+
"loss": 0.6106,
|
533 |
+
"step": 355
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.6968303895475442,
|
537 |
+
"grad_norm": 1.226553201675415,
|
538 |
+
"learning_rate": 3.183673469387755e-06,
|
539 |
+
"loss": 0.68,
|
540 |
+
"step": 360
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 0.7065085894023712,
|
544 |
+
"grad_norm": 2.4295260906219482,
|
545 |
+
"learning_rate": 3.0816326530612244e-06,
|
546 |
+
"loss": 0.5769,
|
547 |
+
"step": 365
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 0.7161867892571981,
|
551 |
+
"grad_norm": 17.398645401000977,
|
552 |
+
"learning_rate": 2.979591836734694e-06,
|
553 |
+
"loss": 0.7025,
|
554 |
+
"step": 370
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 0.7258649891120251,
|
558 |
+
"grad_norm": 1.2020399570465088,
|
559 |
+
"learning_rate": 2.8775510204081636e-06,
|
560 |
+
"loss": 0.7725,
|
561 |
+
"step": 375
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 0.7355431889668521,
|
565 |
+
"grad_norm": 16.19696807861328,
|
566 |
+
"learning_rate": 2.775510204081633e-06,
|
567 |
+
"loss": 0.5855,
|
568 |
+
"step": 380
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 0.7452213888216792,
|
572 |
+
"grad_norm": 5.417294979095459,
|
573 |
+
"learning_rate": 2.6734693877551023e-06,
|
574 |
+
"loss": 0.5507,
|
575 |
+
"step": 385
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.7548995886765062,
|
579 |
+
"grad_norm": 3.608414649963379,
|
580 |
+
"learning_rate": 2.571428571428571e-06,
|
581 |
+
"loss": 0.6533,
|
582 |
+
"step": 390
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 0.7645777885313332,
|
586 |
+
"grad_norm": 7.825292110443115,
|
587 |
+
"learning_rate": 2.469387755102041e-06,
|
588 |
+
"loss": 0.6263,
|
589 |
+
"step": 395
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 0.7742559883861602,
|
593 |
+
"grad_norm": 3.606358289718628,
|
594 |
+
"learning_rate": 2.3673469387755103e-06,
|
595 |
+
"loss": 0.4298,
|
596 |
+
"step": 400
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 0.7742559883861602,
|
600 |
+
"eval_loss": 0.611698567867279,
|
601 |
+
"eval_mse": 0.6116985452586207,
|
602 |
+
"eval_runtime": 12.4253,
|
603 |
+
"eval_samples_per_second": 35.009,
|
604 |
+
"eval_steps_per_second": 17.545,
|
605 |
+
"step": 400
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.7839341882409872,
|
609 |
+
"grad_norm": 0.6020415425300598,
|
610 |
+
"learning_rate": 2.2653061224489797e-06,
|
611 |
+
"loss": 0.5142,
|
612 |
+
"step": 405
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 0.7936123880958141,
|
616 |
+
"grad_norm": 1.7960638999938965,
|
617 |
+
"learning_rate": 2.1632653061224495e-06,
|
618 |
+
"loss": 0.531,
|
619 |
+
"step": 410
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 0.8032905879506412,
|
623 |
+
"grad_norm": 6.039422988891602,
|
624 |
+
"learning_rate": 2.0612244897959184e-06,
|
625 |
+
"loss": 0.6542,
|
626 |
+
"step": 415
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 0.8129687878054682,
|
630 |
+
"grad_norm": 4.238173007965088,
|
631 |
+
"learning_rate": 1.9591836734693877e-06,
|
632 |
+
"loss": 0.6658,
|
633 |
+
"step": 420
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 0.8226469876602952,
|
637 |
+
"grad_norm": 12.702580451965332,
|
638 |
+
"learning_rate": 1.8571428571428573e-06,
|
639 |
+
"loss": 0.5881,
|
640 |
+
"step": 425
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 0.8323251875151222,
|
644 |
+
"grad_norm": 2.6721410751342773,
|
645 |
+
"learning_rate": 1.7551020408163267e-06,
|
646 |
+
"loss": 0.4565,
|
647 |
+
"step": 430
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 0.8420033873699492,
|
651 |
+
"grad_norm": 10.180371284484863,
|
652 |
+
"learning_rate": 1.6530612244897962e-06,
|
653 |
+
"loss": 0.7646,
|
654 |
+
"step": 435
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 0.8516815872247762,
|
658 |
+
"grad_norm": 14.619568824768066,
|
659 |
+
"learning_rate": 1.5510204081632654e-06,
|
660 |
+
"loss": 0.5797,
|
661 |
+
"step": 440
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.8613597870796031,
|
665 |
+
"grad_norm": 3.0513336658477783,
|
666 |
+
"learning_rate": 1.4489795918367347e-06,
|
667 |
+
"loss": 0.6342,
|
668 |
+
"step": 445
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 0.8710379869344302,
|
672 |
+
"grad_norm": 2.8715620040893555,
|
673 |
+
"learning_rate": 1.3469387755102043e-06,
|
674 |
+
"loss": 0.4666,
|
675 |
+
"step": 450
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 0.8807161867892572,
|
679 |
+
"grad_norm": 12.445976257324219,
|
680 |
+
"learning_rate": 1.2448979591836734e-06,
|
681 |
+
"loss": 0.6886,
|
682 |
+
"step": 455
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 0.8903943866440842,
|
686 |
+
"grad_norm": 9.058150291442871,
|
687 |
+
"learning_rate": 1.142857142857143e-06,
|
688 |
+
"loss": 0.4226,
|
689 |
+
"step": 460
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 0.9000725864989112,
|
693 |
+
"grad_norm": 3.5630202293395996,
|
694 |
+
"learning_rate": 1.0408163265306123e-06,
|
695 |
+
"loss": 0.5195,
|
696 |
+
"step": 465
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 0.9097507863537382,
|
700 |
+
"grad_norm": 14.264552116394043,
|
701 |
+
"learning_rate": 9.387755102040817e-07,
|
702 |
+
"loss": 0.8617,
|
703 |
+
"step": 470
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.9194289862085652,
|
707 |
+
"grad_norm": 7.2072062492370605,
|
708 |
+
"learning_rate": 8.367346938775512e-07,
|
709 |
+
"loss": 0.5227,
|
710 |
+
"step": 475
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 0.9291071860633922,
|
714 |
+
"grad_norm": 7.209239482879639,
|
715 |
+
"learning_rate": 7.346938775510205e-07,
|
716 |
+
"loss": 0.7242,
|
717 |
+
"step": 480
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 0.9387853859182193,
|
721 |
+
"grad_norm": 7.206480026245117,
|
722 |
+
"learning_rate": 6.326530612244898e-07,
|
723 |
+
"loss": 0.4023,
|
724 |
+
"step": 485
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 0.9484635857730462,
|
728 |
+
"grad_norm": 14.362146377563477,
|
729 |
+
"learning_rate": 5.306122448979592e-07,
|
730 |
+
"loss": 0.6686,
|
731 |
+
"step": 490
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 0.9581417856278732,
|
735 |
+
"grad_norm": 2.965012550354004,
|
736 |
+
"learning_rate": 4.285714285714286e-07,
|
737 |
+
"loss": 0.4549,
|
738 |
+
"step": 495
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 0.9678199854827002,
|
742 |
+
"grad_norm": 4.2699127197265625,
|
743 |
+
"learning_rate": 3.2653061224489803e-07,
|
744 |
+
"loss": 0.5672,
|
745 |
+
"step": 500
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.9678199854827002,
|
749 |
+
"eval_loss": 0.621571958065033,
|
750 |
+
"eval_mse": 0.6215719288793103,
|
751 |
+
"eval_runtime": 12.4978,
|
752 |
+
"eval_samples_per_second": 34.806,
|
753 |
+
"eval_steps_per_second": 17.443,
|
754 |
+
"step": 500
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 0.9774981853375272,
|
758 |
+
"grad_norm": 23.406326293945312,
|
759 |
+
"learning_rate": 2.2448979591836735e-07,
|
760 |
+
"loss": 0.7287,
|
761 |
+
"step": 505
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 0.9871763851923542,
|
765 |
+
"grad_norm": 8.980780601501465,
|
766 |
+
"learning_rate": 1.2244897959183673e-07,
|
767 |
+
"loss": 0.5979,
|
768 |
+
"step": 510
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 0.9968545850471813,
|
772 |
+
"grad_norm": 1.8055081367492676,
|
773 |
+
"learning_rate": 2.0408163265306127e-08,
|
774 |
+
"loss": 0.5709,
|
775 |
+
"step": 515
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 0.9987902250181466,
|
779 |
+
"step": 516,
|
780 |
+
"total_flos": 8688901375918080.0,
|
781 |
+
"train_loss": 1.1010994948157968,
|
782 |
+
"train_runtime": 478.9806,
|
783 |
+
"train_samples_per_second": 17.255,
|
784 |
+
"train_steps_per_second": 1.077
|
785 |
+
}
|
786 |
+
],
|
787 |
+
"logging_steps": 5,
|
788 |
+
"max_steps": 516,
|
789 |
+
"num_input_tokens_seen": 0,
|
790 |
+
"num_train_epochs": 1,
|
791 |
+
"save_steps": 100,
|
792 |
+
"stateful_callbacks": {
|
793 |
+
"TrainerControl": {
|
794 |
+
"args": {
|
795 |
+
"should_epoch_stop": false,
|
796 |
+
"should_evaluate": false,
|
797 |
+
"should_log": false,
|
798 |
+
"should_save": true,
|
799 |
+
"should_training_stop": true
|
800 |
+
},
|
801 |
+
"attributes": {}
|
802 |
+
}
|
803 |
+
},
|
804 |
+
"total_flos": 8688901375918080.0,
|
805 |
+
"train_batch_size": 2,
|
806 |
+
"trial_name": null,
|
807 |
+
"trial_params": null
|
808 |
+
}
|