gokulsrinivasagan
commited on
End of training
Browse files- README.md +16 -4
- all_results.json +16 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1732209583.ki-g0009.3474524.1 +3 -0
- train_results.json +9 -0
- trainer_state.json +920 -0
README.md
CHANGED
@@ -2,11 +2,23 @@
|
|
2 |
library_name: transformers
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
|
|
5 |
metrics:
|
6 |
- accuracy
|
7 |
model-index:
|
8 |
- name: bert_base_lda_5_v1
|
9 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -14,10 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
# bert_base_lda_5_v1
|
16 |
|
17 |
-
This model is a fine-tuned version of [](https://huggingface.co/) on
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 7.
|
20 |
-
- Accuracy: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
2 |
library_name: transformers
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
10 |
- name: bert_base_lda_5_v1
|
11 |
+
results:
|
12 |
+
- task:
|
13 |
+
name: Masked Language Modeling
|
14 |
+
type: fill-mask
|
15 |
+
dataset:
|
16 |
+
name: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5
|
17 |
+
type: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.15604339718596372
|
22 |
---
|
23 |
|
24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
26 |
|
27 |
# bert_base_lda_5_v1
|
28 |
|
29 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-5 dataset.
|
30 |
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 7.2047
|
32 |
+
- Accuracy: 0.1560
|
33 |
|
34 |
## Model description
|
35 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 25.0,
|
3 |
+
"eval_accuracy": 0.15604339718596372,
|
4 |
+
"eval_loss": 7.204704761505127,
|
5 |
+
"eval_runtime": 0.7168,
|
6 |
+
"eval_samples": 479,
|
7 |
+
"eval_samples_per_second": 668.291,
|
8 |
+
"eval_steps_per_second": 6.976,
|
9 |
+
"perplexity": 1345.7473139718898,
|
10 |
+
"total_flos": 1.5149101316039424e+18,
|
11 |
+
"train_loss": 7.379782975178421,
|
12 |
+
"train_runtime": 17091.3155,
|
13 |
+
"train_samples": 228639,
|
14 |
+
"train_samples_per_second": 334.437,
|
15 |
+
"train_steps_per_second": 3.484
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 25.0,
|
3 |
+
"eval_accuracy": 0.15604339718596372,
|
4 |
+
"eval_loss": 7.204704761505127,
|
5 |
+
"eval_runtime": 0.7168,
|
6 |
+
"eval_samples": 479,
|
7 |
+
"eval_samples_per_second": 668.291,
|
8 |
+
"eval_steps_per_second": 6.976,
|
9 |
+
"perplexity": 1345.7473139718898
|
10 |
+
}
|
logs/events.out.tfevents.1732209583.ki-g0009.3474524.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9882727d99c12a37110eb9380de9275a42a31db8c67d9bce461b288c470372a4
|
3 |
+
size 417
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 25.0,
|
3 |
+
"total_flos": 1.5149101316039424e+18,
|
4 |
+
"train_loss": 7.379782975178421,
|
5 |
+
"train_runtime": 17091.3155,
|
6 |
+
"train_samples": 228639,
|
7 |
+
"train_samples_per_second": 334.437,
|
8 |
+
"train_steps_per_second": 3.484
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,920 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 7.248484134674072,
|
3 |
+
"best_model_checkpoint": "bert_base_lda_5_v1/checkpoint-50000",
|
4 |
+
"epoch": 25.0,
|
5 |
+
"eval_steps": 10000,
|
6 |
+
"global_step": 59550,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.20990764063811923,
|
13 |
+
"grad_norm": 2.1255838871002197,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 10.7417,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41981528127623846,
|
20 |
+
"grad_norm": 1.4488760232925415,
|
21 |
+
"learning_rate": 1e-05,
|
22 |
+
"loss": 9.0086,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6297229219143576,
|
27 |
+
"grad_norm": 0.9646936655044556,
|
28 |
+
"learning_rate": 1.5e-05,
|
29 |
+
"loss": 8.498,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8396305625524769,
|
34 |
+
"grad_norm": 1.0156469345092773,
|
35 |
+
"learning_rate": 2e-05,
|
36 |
+
"loss": 8.3577,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0495382031905962,
|
41 |
+
"grad_norm": 1.371415615081787,
|
42 |
+
"learning_rate": 2.5e-05,
|
43 |
+
"loss": 8.2488,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.2594458438287153,
|
48 |
+
"grad_norm": 0.9908320903778076,
|
49 |
+
"learning_rate": 3e-05,
|
50 |
+
"loss": 8.1487,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.4693534844668346,
|
55 |
+
"grad_norm": 1.1176950931549072,
|
56 |
+
"learning_rate": 3.5e-05,
|
57 |
+
"loss": 8.0726,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.6792611251049538,
|
62 |
+
"grad_norm": 0.8763735294342041,
|
63 |
+
"learning_rate": 4e-05,
|
64 |
+
"loss": 8.0113,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.8891687657430731,
|
69 |
+
"grad_norm": 1.3254985809326172,
|
70 |
+
"learning_rate": 4.5e-05,
|
71 |
+
"loss": 7.9577,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.0990764063811924,
|
76 |
+
"grad_norm": 1.0770165920257568,
|
77 |
+
"learning_rate": 5e-05,
|
78 |
+
"loss": 7.9093,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.3089840470193117,
|
83 |
+
"grad_norm": 1.4271862506866455,
|
84 |
+
"learning_rate": 5.500000000000001e-05,
|
85 |
+
"loss": 7.8686,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.5188916876574305,
|
90 |
+
"grad_norm": 1.2136560678482056,
|
91 |
+
"learning_rate": 6e-05,
|
92 |
+
"loss": 7.8339,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.72879932829555,
|
97 |
+
"grad_norm": 0.9802820682525635,
|
98 |
+
"learning_rate": 6.500000000000001e-05,
|
99 |
+
"loss": 7.8035,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.938706968933669,
|
104 |
+
"grad_norm": 1.314109444618225,
|
105 |
+
"learning_rate": 7e-05,
|
106 |
+
"loss": 7.7753,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1486146095717884,
|
111 |
+
"grad_norm": 0.853410542011261,
|
112 |
+
"learning_rate": 7.500000000000001e-05,
|
113 |
+
"loss": 7.749,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.3585222502099077,
|
118 |
+
"grad_norm": 1.1303246021270752,
|
119 |
+
"learning_rate": 8e-05,
|
120 |
+
"loss": 7.727,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.568429890848027,
|
125 |
+
"grad_norm": 1.5063821077346802,
|
126 |
+
"learning_rate": 8.5e-05,
|
127 |
+
"loss": 7.7015,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.7783375314861463,
|
132 |
+
"grad_norm": 1.3487807512283325,
|
133 |
+
"learning_rate": 9e-05,
|
134 |
+
"loss": 7.622,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.988245172124265,
|
139 |
+
"grad_norm": 0.983832061290741,
|
140 |
+
"learning_rate": 9.5e-05,
|
141 |
+
"loss": 7.5675,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.198152812762385,
|
146 |
+
"grad_norm": 1.388443112373352,
|
147 |
+
"learning_rate": 0.0001,
|
148 |
+
"loss": 7.5336,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.198152812762385,
|
153 |
+
"eval_accuracy": 0.15086674643145329,
|
154 |
+
"eval_loss": 7.482370853424072,
|
155 |
+
"eval_runtime": 0.734,
|
156 |
+
"eval_samples_per_second": 652.615,
|
157 |
+
"eval_steps_per_second": 6.812,
|
158 |
+
"step": 10000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 4.408060453400504,
|
162 |
+
"grad_norm": 1.7055187225341797,
|
163 |
+
"learning_rate": 9.899091826437942e-05,
|
164 |
+
"loss": 7.5161,
|
165 |
+
"step": 10500
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 4.617968094038623,
|
169 |
+
"grad_norm": 1.2820823192596436,
|
170 |
+
"learning_rate": 9.798183652875883e-05,
|
171 |
+
"loss": 7.4951,
|
172 |
+
"step": 11000
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 4.827875734676742,
|
176 |
+
"grad_norm": 1.5211608409881592,
|
177 |
+
"learning_rate": 9.697275479313825e-05,
|
178 |
+
"loss": 7.4839,
|
179 |
+
"step": 11500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 5.037783375314861,
|
183 |
+
"grad_norm": 1.1569567918777466,
|
184 |
+
"learning_rate": 9.596367305751767e-05,
|
185 |
+
"loss": 7.4667,
|
186 |
+
"step": 12000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 5.247691015952981,
|
190 |
+
"grad_norm": 1.1066005229949951,
|
191 |
+
"learning_rate": 9.495459132189707e-05,
|
192 |
+
"loss": 7.4445,
|
193 |
+
"step": 12500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 5.4575986565911,
|
197 |
+
"grad_norm": 1.0754830837249756,
|
198 |
+
"learning_rate": 9.394550958627649e-05,
|
199 |
+
"loss": 7.4334,
|
200 |
+
"step": 13000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 5.667506297229219,
|
204 |
+
"grad_norm": 1.057267665863037,
|
205 |
+
"learning_rate": 9.293642785065591e-05,
|
206 |
+
"loss": 7.4284,
|
207 |
+
"step": 13500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 5.877413937867338,
|
211 |
+
"grad_norm": 0.9008902311325073,
|
212 |
+
"learning_rate": 9.192734611503532e-05,
|
213 |
+
"loss": 7.4144,
|
214 |
+
"step": 14000
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 6.087321578505458,
|
218 |
+
"grad_norm": 1.082311987876892,
|
219 |
+
"learning_rate": 9.091826437941474e-05,
|
220 |
+
"loss": 7.4024,
|
221 |
+
"step": 14500
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 6.297229219143577,
|
225 |
+
"grad_norm": 0.9966408014297485,
|
226 |
+
"learning_rate": 8.990918264379415e-05,
|
227 |
+
"loss": 7.3924,
|
228 |
+
"step": 15000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 6.507136859781696,
|
232 |
+
"grad_norm": 1.070543885231018,
|
233 |
+
"learning_rate": 8.890010090817356e-05,
|
234 |
+
"loss": 7.3824,
|
235 |
+
"step": 15500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 6.717044500419815,
|
239 |
+
"grad_norm": 1.0677157640457153,
|
240 |
+
"learning_rate": 8.789101917255298e-05,
|
241 |
+
"loss": 7.3756,
|
242 |
+
"step": 16000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.926952141057934,
|
246 |
+
"grad_norm": 0.7595410943031311,
|
247 |
+
"learning_rate": 8.68819374369324e-05,
|
248 |
+
"loss": 7.3676,
|
249 |
+
"step": 16500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 7.136859781696054,
|
253 |
+
"grad_norm": 0.7410305738449097,
|
254 |
+
"learning_rate": 8.58728557013118e-05,
|
255 |
+
"loss": 7.353,
|
256 |
+
"step": 17000
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 7.346767422334173,
|
260 |
+
"grad_norm": 1.0340527296066284,
|
261 |
+
"learning_rate": 8.486377396569122e-05,
|
262 |
+
"loss": 7.3437,
|
263 |
+
"step": 17500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 7.5566750629722925,
|
267 |
+
"grad_norm": 0.8954520225524902,
|
268 |
+
"learning_rate": 8.385469223007064e-05,
|
269 |
+
"loss": 7.3442,
|
270 |
+
"step": 18000
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 7.766582703610411,
|
274 |
+
"grad_norm": 0.9272580742835999,
|
275 |
+
"learning_rate": 8.284561049445006e-05,
|
276 |
+
"loss": 7.3372,
|
277 |
+
"step": 18500
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 7.97649034424853,
|
281 |
+
"grad_norm": 1.0480597019195557,
|
282 |
+
"learning_rate": 8.183652875882947e-05,
|
283 |
+
"loss": 7.3358,
|
284 |
+
"step": 19000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 8.18639798488665,
|
288 |
+
"grad_norm": 0.7353398203849792,
|
289 |
+
"learning_rate": 8.082744702320889e-05,
|
290 |
+
"loss": 7.3192,
|
291 |
+
"step": 19500
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 8.39630562552477,
|
295 |
+
"grad_norm": 1.092934012413025,
|
296 |
+
"learning_rate": 7.98183652875883e-05,
|
297 |
+
"loss": 7.3176,
|
298 |
+
"step": 20000
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 8.39630562552477,
|
302 |
+
"eval_accuracy": 0.15244535480793514,
|
303 |
+
"eval_loss": 7.3286027908325195,
|
304 |
+
"eval_runtime": 0.7088,
|
305 |
+
"eval_samples_per_second": 675.754,
|
306 |
+
"eval_steps_per_second": 7.054,
|
307 |
+
"step": 20000
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 8.606213266162888,
|
311 |
+
"grad_norm": 0.8529198169708252,
|
312 |
+
"learning_rate": 7.880928355196771e-05,
|
313 |
+
"loss": 7.3111,
|
314 |
+
"step": 20500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 8.816120906801007,
|
318 |
+
"grad_norm": 0.8961474299430847,
|
319 |
+
"learning_rate": 7.780020181634713e-05,
|
320 |
+
"loss": 7.3097,
|
321 |
+
"step": 21000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 9.026028547439127,
|
325 |
+
"grad_norm": 1.184098720550537,
|
326 |
+
"learning_rate": 7.679112008072655e-05,
|
327 |
+
"loss": 7.3022,
|
328 |
+
"step": 21500
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 9.235936188077247,
|
332 |
+
"grad_norm": 0.8562668561935425,
|
333 |
+
"learning_rate": 7.578203834510595e-05,
|
334 |
+
"loss": 7.2918,
|
335 |
+
"step": 22000
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 9.445843828715365,
|
339 |
+
"grad_norm": 0.8222872018814087,
|
340 |
+
"learning_rate": 7.477295660948537e-05,
|
341 |
+
"loss": 7.2894,
|
342 |
+
"step": 22500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 9.655751469353484,
|
346 |
+
"grad_norm": 0.8184618949890137,
|
347 |
+
"learning_rate": 7.376387487386479e-05,
|
348 |
+
"loss": 7.2879,
|
349 |
+
"step": 23000
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 9.865659109991604,
|
353 |
+
"grad_norm": 0.9152312874794006,
|
354 |
+
"learning_rate": 7.27547931382442e-05,
|
355 |
+
"loss": 7.2822,
|
356 |
+
"step": 23500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 10.075566750629722,
|
360 |
+
"grad_norm": 0.8646574020385742,
|
361 |
+
"learning_rate": 7.174571140262362e-05,
|
362 |
+
"loss": 7.2715,
|
363 |
+
"step": 24000
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 10.285474391267842,
|
367 |
+
"grad_norm": 0.9313002228736877,
|
368 |
+
"learning_rate": 7.073662966700304e-05,
|
369 |
+
"loss": 7.2725,
|
370 |
+
"step": 24500
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 10.495382031905962,
|
374 |
+
"grad_norm": 0.8215687870979309,
|
375 |
+
"learning_rate": 6.972754793138244e-05,
|
376 |
+
"loss": 7.2634,
|
377 |
+
"step": 25000
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 10.705289672544081,
|
381 |
+
"grad_norm": 1.0029321908950806,
|
382 |
+
"learning_rate": 6.871846619576186e-05,
|
383 |
+
"loss": 7.2653,
|
384 |
+
"step": 25500
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 10.9151973131822,
|
388 |
+
"grad_norm": 0.797988772392273,
|
389 |
+
"learning_rate": 6.770938446014128e-05,
|
390 |
+
"loss": 7.2673,
|
391 |
+
"step": 26000
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 11.125104953820319,
|
395 |
+
"grad_norm": 1.0155805349349976,
|
396 |
+
"learning_rate": 6.670030272452068e-05,
|
397 |
+
"loss": 7.2549,
|
398 |
+
"step": 26500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 11.335012594458439,
|
402 |
+
"grad_norm": 0.8314929604530334,
|
403 |
+
"learning_rate": 6.56912209889001e-05,
|
404 |
+
"loss": 7.252,
|
405 |
+
"step": 27000
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 11.544920235096557,
|
409 |
+
"grad_norm": 0.9168637990951538,
|
410 |
+
"learning_rate": 6.468213925327952e-05,
|
411 |
+
"loss": 7.2459,
|
412 |
+
"step": 27500
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 11.754827875734676,
|
416 |
+
"grad_norm": 0.8579038977622986,
|
417 |
+
"learning_rate": 6.367305751765893e-05,
|
418 |
+
"loss": 7.2438,
|
419 |
+
"step": 28000
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 11.964735516372796,
|
423 |
+
"grad_norm": 0.8211594223976135,
|
424 |
+
"learning_rate": 6.266397578203835e-05,
|
425 |
+
"loss": 7.243,
|
426 |
+
"step": 28500
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 12.174643157010916,
|
430 |
+
"grad_norm": 1.0437767505645752,
|
431 |
+
"learning_rate": 6.165489404641777e-05,
|
432 |
+
"loss": 7.2366,
|
433 |
+
"step": 29000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 12.384550797649034,
|
437 |
+
"grad_norm": 0.9614302515983582,
|
438 |
+
"learning_rate": 6.064581231079718e-05,
|
439 |
+
"loss": 7.2297,
|
440 |
+
"step": 29500
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 12.594458438287154,
|
444 |
+
"grad_norm": 0.8940654397010803,
|
445 |
+
"learning_rate": 5.963673057517659e-05,
|
446 |
+
"loss": 7.2331,
|
447 |
+
"step": 30000
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 12.594458438287154,
|
451 |
+
"eval_accuracy": 0.15541315723200044,
|
452 |
+
"eval_loss": 7.2804460525512695,
|
453 |
+
"eval_runtime": 0.7124,
|
454 |
+
"eval_samples_per_second": 672.404,
|
455 |
+
"eval_steps_per_second": 7.019,
|
456 |
+
"step": 30000
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 12.804366078925273,
|
460 |
+
"grad_norm": 0.7710630297660828,
|
461 |
+
"learning_rate": 5.8627648839556e-05,
|
462 |
+
"loss": 7.228,
|
463 |
+
"step": 30500
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 13.014273719563391,
|
467 |
+
"grad_norm": 0.8717989921569824,
|
468 |
+
"learning_rate": 5.7618567103935416e-05,
|
469 |
+
"loss": 7.2311,
|
470 |
+
"step": 31000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 13.224181360201511,
|
474 |
+
"grad_norm": 0.9049319624900818,
|
475 |
+
"learning_rate": 5.660948536831484e-05,
|
476 |
+
"loss": 7.2201,
|
477 |
+
"step": 31500
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 13.43408900083963,
|
481 |
+
"grad_norm": 0.8338859677314758,
|
482 |
+
"learning_rate": 5.5600403632694254e-05,
|
483 |
+
"loss": 7.218,
|
484 |
+
"step": 32000
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 13.64399664147775,
|
488 |
+
"grad_norm": 0.8981912732124329,
|
489 |
+
"learning_rate": 5.4591321897073666e-05,
|
490 |
+
"loss": 7.2201,
|
491 |
+
"step": 32500
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 13.853904282115868,
|
495 |
+
"grad_norm": 0.9057620763778687,
|
496 |
+
"learning_rate": 5.358224016145308e-05,
|
497 |
+
"loss": 7.2166,
|
498 |
+
"step": 33000
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 14.063811922753988,
|
502 |
+
"grad_norm": 0.8201689124107361,
|
503 |
+
"learning_rate": 5.257315842583249e-05,
|
504 |
+
"loss": 7.2122,
|
505 |
+
"step": 33500
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 14.273719563392108,
|
509 |
+
"grad_norm": 0.97395259141922,
|
510 |
+
"learning_rate": 5.15640766902119e-05,
|
511 |
+
"loss": 7.2045,
|
512 |
+
"step": 34000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 14.483627204030226,
|
516 |
+
"grad_norm": 1.0435025691986084,
|
517 |
+
"learning_rate": 5.055499495459133e-05,
|
518 |
+
"loss": 7.2061,
|
519 |
+
"step": 34500
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 14.693534844668346,
|
523 |
+
"grad_norm": 0.9251586198806763,
|
524 |
+
"learning_rate": 4.954591321897074e-05,
|
525 |
+
"loss": 7.2045,
|
526 |
+
"step": 35000
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 14.903442485306465,
|
530 |
+
"grad_norm": 0.826401948928833,
|
531 |
+
"learning_rate": 4.853683148335015e-05,
|
532 |
+
"loss": 7.2044,
|
533 |
+
"step": 35500
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 15.113350125944585,
|
537 |
+
"grad_norm": 0.8331254124641418,
|
538 |
+
"learning_rate": 4.7527749747729566e-05,
|
539 |
+
"loss": 7.1978,
|
540 |
+
"step": 36000
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 15.323257766582703,
|
544 |
+
"grad_norm": 1.0407625436782837,
|
545 |
+
"learning_rate": 4.6518668012108985e-05,
|
546 |
+
"loss": 7.1956,
|
547 |
+
"step": 36500
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 15.533165407220823,
|
551 |
+
"grad_norm": 0.8447533249855042,
|
552 |
+
"learning_rate": 4.55095862764884e-05,
|
553 |
+
"loss": 7.1927,
|
554 |
+
"step": 37000
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 15.743073047858942,
|
558 |
+
"grad_norm": 0.9017349481582642,
|
559 |
+
"learning_rate": 4.450050454086781e-05,
|
560 |
+
"loss": 7.1936,
|
561 |
+
"step": 37500
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 15.95298068849706,
|
565 |
+
"grad_norm": 0.8850695490837097,
|
566 |
+
"learning_rate": 4.349142280524723e-05,
|
567 |
+
"loss": 7.1919,
|
568 |
+
"step": 38000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 16.162888329135182,
|
572 |
+
"grad_norm": 0.8294333219528198,
|
573 |
+
"learning_rate": 4.248234106962664e-05,
|
574 |
+
"loss": 7.1896,
|
575 |
+
"step": 38500
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 16.3727959697733,
|
579 |
+
"grad_norm": 0.8609002828598022,
|
580 |
+
"learning_rate": 4.147325933400605e-05,
|
581 |
+
"loss": 7.1819,
|
582 |
+
"step": 39000
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 16.582703610411418,
|
586 |
+
"grad_norm": 0.7830792665481567,
|
587 |
+
"learning_rate": 4.046417759838547e-05,
|
588 |
+
"loss": 7.1851,
|
589 |
+
"step": 39500
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 16.79261125104954,
|
593 |
+
"grad_norm": 0.7615496516227722,
|
594 |
+
"learning_rate": 3.9455095862764884e-05,
|
595 |
+
"loss": 7.1765,
|
596 |
+
"step": 40000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 16.79261125104954,
|
600 |
+
"eval_accuracy": 0.15439609734215543,
|
601 |
+
"eval_loss": 7.25421667098999,
|
602 |
+
"eval_runtime": 0.7294,
|
603 |
+
"eval_samples_per_second": 656.742,
|
604 |
+
"eval_steps_per_second": 6.855,
|
605 |
+
"step": 40000
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 17.002518891687657,
|
609 |
+
"grad_norm": 0.7594569325447083,
|
610 |
+
"learning_rate": 3.84460141271443e-05,
|
611 |
+
"loss": 7.1826,
|
612 |
+
"step": 40500
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 17.212426532325775,
|
616 |
+
"grad_norm": 0.7539288401603699,
|
617 |
+
"learning_rate": 3.7436932391523715e-05,
|
618 |
+
"loss": 7.1734,
|
619 |
+
"step": 41000
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 17.422334172963897,
|
623 |
+
"grad_norm": 0.9915943741798401,
|
624 |
+
"learning_rate": 3.642785065590313e-05,
|
625 |
+
"loss": 7.1718,
|
626 |
+
"step": 41500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 17.632241813602015,
|
630 |
+
"grad_norm": 2.3651840686798096,
|
631 |
+
"learning_rate": 3.541876892028255e-05,
|
632 |
+
"loss": 7.1728,
|
633 |
+
"step": 42000
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 17.842149454240133,
|
637 |
+
"grad_norm": 0.9876560568809509,
|
638 |
+
"learning_rate": 3.440968718466196e-05,
|
639 |
+
"loss": 7.1721,
|
640 |
+
"step": 42500
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 18.052057094878254,
|
644 |
+
"grad_norm": 0.8784790635108948,
|
645 |
+
"learning_rate": 3.340060544904137e-05,
|
646 |
+
"loss": 7.1685,
|
647 |
+
"step": 43000
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 18.261964735516372,
|
651 |
+
"grad_norm": 0.7426952719688416,
|
652 |
+
"learning_rate": 3.239152371342079e-05,
|
653 |
+
"loss": 7.1623,
|
654 |
+
"step": 43500
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 18.471872376154494,
|
658 |
+
"grad_norm": 0.8913703560829163,
|
659 |
+
"learning_rate": 3.13824419778002e-05,
|
660 |
+
"loss": 7.1636,
|
661 |
+
"step": 44000
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 18.68178001679261,
|
665 |
+
"grad_norm": 0.7314404845237732,
|
666 |
+
"learning_rate": 3.0373360242179615e-05,
|
667 |
+
"loss": 7.1626,
|
668 |
+
"step": 44500
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 18.89168765743073,
|
672 |
+
"grad_norm": 0.8047787547111511,
|
673 |
+
"learning_rate": 2.9364278506559034e-05,
|
674 |
+
"loss": 7.1668,
|
675 |
+
"step": 45000
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 19.10159529806885,
|
679 |
+
"grad_norm": 0.7927625179290771,
|
680 |
+
"learning_rate": 2.8355196770938446e-05,
|
681 |
+
"loss": 7.1633,
|
682 |
+
"step": 45500
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 19.31150293870697,
|
686 |
+
"grad_norm": 0.8079816102981567,
|
687 |
+
"learning_rate": 2.734611503531786e-05,
|
688 |
+
"loss": 7.1514,
|
689 |
+
"step": 46000
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 19.521410579345087,
|
693 |
+
"grad_norm": 0.9051825404167175,
|
694 |
+
"learning_rate": 2.6337033299697278e-05,
|
695 |
+
"loss": 7.1542,
|
696 |
+
"step": 46500
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 19.73131821998321,
|
700 |
+
"grad_norm": 0.852149248123169,
|
701 |
+
"learning_rate": 2.532795156407669e-05,
|
702 |
+
"loss": 7.1555,
|
703 |
+
"step": 47000
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 19.941225860621326,
|
707 |
+
"grad_norm": 0.9161846041679382,
|
708 |
+
"learning_rate": 2.4318869828456106e-05,
|
709 |
+
"loss": 7.1539,
|
710 |
+
"step": 47500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 20.151133501259444,
|
714 |
+
"grad_norm": 0.7693049311637878,
|
715 |
+
"learning_rate": 2.330978809283552e-05,
|
716 |
+
"loss": 7.15,
|
717 |
+
"step": 48000
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 20.361041141897566,
|
721 |
+
"grad_norm": 0.773891806602478,
|
722 |
+
"learning_rate": 2.2300706357214934e-05,
|
723 |
+
"loss": 7.1472,
|
724 |
+
"step": 48500
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 20.570948782535684,
|
728 |
+
"grad_norm": 0.8220585584640503,
|
729 |
+
"learning_rate": 2.129162462159435e-05,
|
730 |
+
"loss": 7.1452,
|
731 |
+
"step": 49000
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 20.7808564231738,
|
735 |
+
"grad_norm": 0.7439760565757751,
|
736 |
+
"learning_rate": 2.0282542885973765e-05,
|
737 |
+
"loss": 7.1451,
|
738 |
+
"step": 49500
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 20.990764063811923,
|
742 |
+
"grad_norm": 0.8007863759994507,
|
743 |
+
"learning_rate": 1.927346115035318e-05,
|
744 |
+
"loss": 7.1457,
|
745 |
+
"step": 50000
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 20.990764063811923,
|
749 |
+
"eval_accuracy": 0.15246586480500182,
|
750 |
+
"eval_loss": 7.248484134674072,
|
751 |
+
"eval_runtime": 0.7082,
|
752 |
+
"eval_samples_per_second": 676.396,
|
753 |
+
"eval_steps_per_second": 7.06,
|
754 |
+
"step": 50000
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 21.20067170445004,
|
758 |
+
"grad_norm": 0.7827761769294739,
|
759 |
+
"learning_rate": 1.8264379414732593e-05,
|
760 |
+
"loss": 7.14,
|
761 |
+
"step": 50500
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 21.410579345088163,
|
765 |
+
"grad_norm": 0.8271605372428894,
|
766 |
+
"learning_rate": 1.725529767911201e-05,
|
767 |
+
"loss": 7.1411,
|
768 |
+
"step": 51000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 21.62048698572628,
|
772 |
+
"grad_norm": 0.7786771655082703,
|
773 |
+
"learning_rate": 1.6246215943491424e-05,
|
774 |
+
"loss": 7.1403,
|
775 |
+
"step": 51500
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 21.8303946263644,
|
779 |
+
"grad_norm": 0.8063676357269287,
|
780 |
+
"learning_rate": 1.5237134207870837e-05,
|
781 |
+
"loss": 7.1401,
|
782 |
+
"step": 52000
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 22.04030226700252,
|
786 |
+
"grad_norm": 0.7963306307792664,
|
787 |
+
"learning_rate": 1.4228052472250252e-05,
|
788 |
+
"loss": 7.1395,
|
789 |
+
"step": 52500
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 22.250209907640638,
|
793 |
+
"grad_norm": 0.7689283490180969,
|
794 |
+
"learning_rate": 1.3218970736629668e-05,
|
795 |
+
"loss": 7.1308,
|
796 |
+
"step": 53000
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 22.460117548278756,
|
800 |
+
"grad_norm": 0.8235142230987549,
|
801 |
+
"learning_rate": 1.2209889001009082e-05,
|
802 |
+
"loss": 7.1338,
|
803 |
+
"step": 53500
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 22.670025188916878,
|
807 |
+
"grad_norm": 0.7854271531105042,
|
808 |
+
"learning_rate": 1.1200807265388496e-05,
|
809 |
+
"loss": 7.1361,
|
810 |
+
"step": 54000
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 22.879932829554996,
|
814 |
+
"grad_norm": 0.7933940887451172,
|
815 |
+
"learning_rate": 1.0191725529767912e-05,
|
816 |
+
"loss": 7.1324,
|
817 |
+
"step": 54500
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 23.089840470193113,
|
821 |
+
"grad_norm": 0.7498176693916321,
|
822 |
+
"learning_rate": 9.182643794147326e-06,
|
823 |
+
"loss": 7.1309,
|
824 |
+
"step": 55000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 23.299748110831235,
|
828 |
+
"grad_norm": 0.7532030940055847,
|
829 |
+
"learning_rate": 8.173562058526741e-06,
|
830 |
+
"loss": 7.1293,
|
831 |
+
"step": 55500
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 23.509655751469353,
|
835 |
+
"grad_norm": 0.9057742953300476,
|
836 |
+
"learning_rate": 7.164480322906156e-06,
|
837 |
+
"loss": 7.1291,
|
838 |
+
"step": 56000
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 23.719563392107474,
|
842 |
+
"grad_norm": 0.8138079047203064,
|
843 |
+
"learning_rate": 6.155398587285571e-06,
|
844 |
+
"loss": 7.1246,
|
845 |
+
"step": 56500
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 23.929471032745592,
|
849 |
+
"grad_norm": 0.8002745509147644,
|
850 |
+
"learning_rate": 5.146316851664986e-06,
|
851 |
+
"loss": 7.1282,
|
852 |
+
"step": 57000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 24.13937867338371,
|
856 |
+
"grad_norm": 0.7847145199775696,
|
857 |
+
"learning_rate": 4.1372351160444e-06,
|
858 |
+
"loss": 7.1268,
|
859 |
+
"step": 57500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 24.349286314021832,
|
863 |
+
"grad_norm": 0.8464835286140442,
|
864 |
+
"learning_rate": 3.1281533804238145e-06,
|
865 |
+
"loss": 7.1263,
|
866 |
+
"step": 58000
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 24.55919395465995,
|
870 |
+
"grad_norm": 0.7655928730964661,
|
871 |
+
"learning_rate": 2.1190716448032293e-06,
|
872 |
+
"loss": 7.1229,
|
873 |
+
"step": 58500
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 24.769101595298068,
|
877 |
+
"grad_norm": 0.8248621225357056,
|
878 |
+
"learning_rate": 1.109989909182644e-06,
|
879 |
+
"loss": 7.1237,
|
880 |
+
"step": 59000
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 24.97900923593619,
|
884 |
+
"grad_norm": 0.736918032169342,
|
885 |
+
"learning_rate": 1.0090817356205853e-07,
|
886 |
+
"loss": 7.1229,
|
887 |
+
"step": 59500
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 25.0,
|
891 |
+
"step": 59550,
|
892 |
+
"total_flos": 1.5149101316039424e+18,
|
893 |
+
"train_loss": 7.379782975178421,
|
894 |
+
"train_runtime": 17091.3155,
|
895 |
+
"train_samples_per_second": 334.437,
|
896 |
+
"train_steps_per_second": 3.484
|
897 |
+
}
|
898 |
+
],
|
899 |
+
"logging_steps": 500,
|
900 |
+
"max_steps": 59550,
|
901 |
+
"num_input_tokens_seen": 0,
|
902 |
+
"num_train_epochs": 25,
|
903 |
+
"save_steps": 10000,
|
904 |
+
"stateful_callbacks": {
|
905 |
+
"TrainerControl": {
|
906 |
+
"args": {
|
907 |
+
"should_epoch_stop": false,
|
908 |
+
"should_evaluate": false,
|
909 |
+
"should_log": false,
|
910 |
+
"should_save": true,
|
911 |
+
"should_training_stop": true
|
912 |
+
},
|
913 |
+
"attributes": {}
|
914 |
+
}
|
915 |
+
},
|
916 |
+
"total_flos": 1.5149101316039424e+18,
|
917 |
+
"train_batch_size": 96,
|
918 |
+
"trial_name": null,
|
919 |
+
"trial_params": null
|
920 |
+
}
|