gokulsrinivasagan
commited on
Commit
•
e9eb263
1
Parent(s):
aa4a90c
End of training
Browse files- README.md +16 -4
- all_results.json +16 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1732261180.ki-g0009.689944.1 +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_100_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_100_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:
|
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-100
|
7 |
metrics:
|
8 |
- accuracy
|
9 |
model-index:
|
10 |
- name: bert_base_lda_100_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-100
|
17 |
+
type: gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-100
|
18 |
+
metrics:
|
19 |
+
- name: Accuracy
|
20 |
+
type: accuracy
|
21 |
+
value: 0.42346160366163754
|
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_100_v1
|
28 |
|
29 |
+
This model is a fine-tuned version of [](https://huggingface.co/) on the gokulsrinivasagan/processed_wikitext-103-raw-v1-ld-100 dataset.
|
30 |
It achieves the following results on the evaluation set:
|
31 |
+
- Loss: 6.9999
|
32 |
+
- Accuracy: 0.4235
|
33 |
|
34 |
## Model description
|
35 |
|
all_results.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 25.0,
|
3 |
+
"eval_accuracy": 0.42346160366163754,
|
4 |
+
"eval_loss": 6.99992561340332,
|
5 |
+
"eval_runtime": 0.7858,
|
6 |
+
"eval_samples": 479,
|
7 |
+
"eval_samples_per_second": 609.589,
|
8 |
+
"eval_steps_per_second": 6.363,
|
9 |
+
"perplexity": 1096.5515866539579,
|
10 |
+
"total_flos": 1.5161929390646784e+18,
|
11 |
+
"train_loss": 9.134388991963654,
|
12 |
+
"train_runtime": 17204.0061,
|
13 |
+
"train_samples": 228639,
|
14 |
+
"train_samples_per_second": 332.247,
|
15 |
+
"train_steps_per_second": 3.461
|
16 |
+
}
|
eval_results.json
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 25.0,
|
3 |
+
"eval_accuracy": 0.42346160366163754,
|
4 |
+
"eval_loss": 6.99992561340332,
|
5 |
+
"eval_runtime": 0.7858,
|
6 |
+
"eval_samples": 479,
|
7 |
+
"eval_samples_per_second": 609.589,
|
8 |
+
"eval_steps_per_second": 6.363,
|
9 |
+
"perplexity": 1096.5515866539579
|
10 |
+
}
|
logs/events.out.tfevents.1732261180.ki-g0009.689944.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4ffdfeb53cf4cd5fefd482cfcc33722cb07efce646f4dfbc6eb39f8f2aff1aa
|
3 |
+
size 417
|
train_results.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 25.0,
|
3 |
+
"total_flos": 1.5161929390646784e+18,
|
4 |
+
"train_loss": 9.134388991963654,
|
5 |
+
"train_runtime": 17204.0061,
|
6 |
+
"train_samples": 228639,
|
7 |
+
"train_samples_per_second": 332.247,
|
8 |
+
"train_steps_per_second": 3.461
|
9 |
+
}
|
trainer_state.json
ADDED
@@ -0,0 +1,920 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 7.017268180847168,
|
3 |
+
"best_model_checkpoint": "bert_base_lda_100_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": 2.099632501602173,
|
14 |
+
"learning_rate": 5e-06,
|
15 |
+
"loss": 13.7106,
|
16 |
+
"step": 500
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.41981528127623846,
|
20 |
+
"grad_norm": 1.3332628011703491,
|
21 |
+
"learning_rate": 1e-05,
|
22 |
+
"loss": 11.963,
|
23 |
+
"step": 1000
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.6297229219143576,
|
27 |
+
"grad_norm": 0.9692000150680542,
|
28 |
+
"learning_rate": 1.5e-05,
|
29 |
+
"loss": 11.4559,
|
30 |
+
"step": 1500
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.8396305625524769,
|
34 |
+
"grad_norm": 0.9592443704605103,
|
35 |
+
"learning_rate": 2e-05,
|
36 |
+
"loss": 11.3196,
|
37 |
+
"step": 2000
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 1.0495382031905962,
|
41 |
+
"grad_norm": 1.16844642162323,
|
42 |
+
"learning_rate": 2.5e-05,
|
43 |
+
"loss": 11.2143,
|
44 |
+
"step": 2500
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 1.2594458438287153,
|
48 |
+
"grad_norm": 0.9776472449302673,
|
49 |
+
"learning_rate": 3e-05,
|
50 |
+
"loss": 11.1187,
|
51 |
+
"step": 3000
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 1.4693534844668346,
|
55 |
+
"grad_norm": 1.1129740476608276,
|
56 |
+
"learning_rate": 3.5e-05,
|
57 |
+
"loss": 11.0441,
|
58 |
+
"step": 3500
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 1.6792611251049538,
|
62 |
+
"grad_norm": 0.8808595538139343,
|
63 |
+
"learning_rate": 4e-05,
|
64 |
+
"loss": 10.9835,
|
65 |
+
"step": 4000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.8891687657430731,
|
69 |
+
"grad_norm": 0.930133581161499,
|
70 |
+
"learning_rate": 4.5e-05,
|
71 |
+
"loss": 10.9304,
|
72 |
+
"step": 4500
|
73 |
+
},
|
74 |
+
{
|
75 |
+
"epoch": 2.0990764063811924,
|
76 |
+
"grad_norm": 0.9473118782043457,
|
77 |
+
"learning_rate": 5e-05,
|
78 |
+
"loss": 10.8812,
|
79 |
+
"step": 5000
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 2.3089840470193117,
|
83 |
+
"grad_norm": 1.0284568071365356,
|
84 |
+
"learning_rate": 5.500000000000001e-05,
|
85 |
+
"loss": 10.8399,
|
86 |
+
"step": 5500
|
87 |
+
},
|
88 |
+
{
|
89 |
+
"epoch": 2.5188916876574305,
|
90 |
+
"grad_norm": 0.898517906665802,
|
91 |
+
"learning_rate": 6e-05,
|
92 |
+
"loss": 10.8057,
|
93 |
+
"step": 6000
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.72879932829555,
|
97 |
+
"grad_norm": 0.9422119855880737,
|
98 |
+
"learning_rate": 6.500000000000001e-05,
|
99 |
+
"loss": 10.7751,
|
100 |
+
"step": 6500
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 2.938706968933669,
|
104 |
+
"grad_norm": 0.8704677224159241,
|
105 |
+
"learning_rate": 7e-05,
|
106 |
+
"loss": 10.7466,
|
107 |
+
"step": 7000
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 3.1486146095717884,
|
111 |
+
"grad_norm": 0.8451219201087952,
|
112 |
+
"learning_rate": 7.500000000000001e-05,
|
113 |
+
"loss": 10.7197,
|
114 |
+
"step": 7500
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 3.3585222502099077,
|
118 |
+
"grad_norm": 0.8918795585632324,
|
119 |
+
"learning_rate": 8e-05,
|
120 |
+
"loss": 10.6978,
|
121 |
+
"step": 8000
|
122 |
+
},
|
123 |
+
{
|
124 |
+
"epoch": 3.568429890848027,
|
125 |
+
"grad_norm": 0.9373081922531128,
|
126 |
+
"learning_rate": 8.5e-05,
|
127 |
+
"loss": 10.6818,
|
128 |
+
"step": 8500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 3.7783375314861463,
|
132 |
+
"grad_norm": 0.8285127282142639,
|
133 |
+
"learning_rate": 9e-05,
|
134 |
+
"loss": 10.6535,
|
135 |
+
"step": 9000
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 3.988245172124265,
|
139 |
+
"grad_norm": 0.9265228509902954,
|
140 |
+
"learning_rate": 9.5e-05,
|
141 |
+
"loss": 10.6104,
|
142 |
+
"step": 9500
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 4.198152812762385,
|
146 |
+
"grad_norm": 0.9272535443305969,
|
147 |
+
"learning_rate": 0.0001,
|
148 |
+
"loss": 10.4589,
|
149 |
+
"step": 10000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 4.198152812762385,
|
153 |
+
"eval_accuracy": 0.1509780461337266,
|
154 |
+
"eval_loss": 10.293501853942871,
|
155 |
+
"eval_runtime": 0.7304,
|
156 |
+
"eval_samples_per_second": 655.812,
|
157 |
+
"eval_steps_per_second": 6.846,
|
158 |
+
"step": 10000
|
159 |
+
},
|
160 |
+
{
|
161 |
+
"epoch": 4.408060453400504,
|
162 |
+
"grad_norm": 1.1058239936828613,
|
163 |
+
"learning_rate": 9.899091826437942e-05,
|
164 |
+
"loss": 10.2508,
|
165 |
+
"step": 10500
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 4.617968094038623,
|
169 |
+
"grad_norm": 1.1870856285095215,
|
170 |
+
"learning_rate": 9.798183652875883e-05,
|
171 |
+
"loss": 10.0973,
|
172 |
+
"step": 11000
|
173 |
+
},
|
174 |
+
{
|
175 |
+
"epoch": 4.827875734676742,
|
176 |
+
"grad_norm": 1.0980850458145142,
|
177 |
+
"learning_rate": 9.697275479313825e-05,
|
178 |
+
"loss": 9.9933,
|
179 |
+
"step": 11500
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 5.037783375314861,
|
183 |
+
"grad_norm": 1.1159865856170654,
|
184 |
+
"learning_rate": 9.596367305751767e-05,
|
185 |
+
"loss": 9.9118,
|
186 |
+
"step": 12000
|
187 |
+
},
|
188 |
+
{
|
189 |
+
"epoch": 5.247691015952981,
|
190 |
+
"grad_norm": 1.093456745147705,
|
191 |
+
"learning_rate": 9.495459132189707e-05,
|
192 |
+
"loss": 9.8527,
|
193 |
+
"step": 12500
|
194 |
+
},
|
195 |
+
{
|
196 |
+
"epoch": 5.4575986565911,
|
197 |
+
"grad_norm": 1.0816402435302734,
|
198 |
+
"learning_rate": 9.394550958627649e-05,
|
199 |
+
"loss": 9.8213,
|
200 |
+
"step": 13000
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 5.667506297229219,
|
204 |
+
"grad_norm": 1.061692476272583,
|
205 |
+
"learning_rate": 9.293642785065591e-05,
|
206 |
+
"loss": 9.8016,
|
207 |
+
"step": 13500
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 5.877413937867338,
|
211 |
+
"grad_norm": 1.1223222017288208,
|
212 |
+
"learning_rate": 9.192734611503532e-05,
|
213 |
+
"loss": 9.7785,
|
214 |
+
"step": 14000
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 6.087321578505458,
|
218 |
+
"grad_norm": 1.0292482376098633,
|
219 |
+
"learning_rate": 9.091826437941474e-05,
|
220 |
+
"loss": 9.7528,
|
221 |
+
"step": 14500
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 6.297229219143577,
|
225 |
+
"grad_norm": 1.096860647201538,
|
226 |
+
"learning_rate": 8.990918264379415e-05,
|
227 |
+
"loss": 9.7305,
|
228 |
+
"step": 15000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 6.507136859781696,
|
232 |
+
"grad_norm": 1.0757558345794678,
|
233 |
+
"learning_rate": 8.890010090817356e-05,
|
234 |
+
"loss": 9.7141,
|
235 |
+
"step": 15500
|
236 |
+
},
|
237 |
+
{
|
238 |
+
"epoch": 6.717044500419815,
|
239 |
+
"grad_norm": 1.0448325872421265,
|
240 |
+
"learning_rate": 8.789101917255298e-05,
|
241 |
+
"loss": 9.7031,
|
242 |
+
"step": 16000
|
243 |
+
},
|
244 |
+
{
|
245 |
+
"epoch": 6.926952141057934,
|
246 |
+
"grad_norm": 1.055416464805603,
|
247 |
+
"learning_rate": 8.68819374369324e-05,
|
248 |
+
"loss": 9.6886,
|
249 |
+
"step": 16500
|
250 |
+
},
|
251 |
+
{
|
252 |
+
"epoch": 7.136859781696054,
|
253 |
+
"grad_norm": 1.0751450061798096,
|
254 |
+
"learning_rate": 8.58728557013118e-05,
|
255 |
+
"loss": 9.6648,
|
256 |
+
"step": 17000
|
257 |
+
},
|
258 |
+
{
|
259 |
+
"epoch": 7.346767422334173,
|
260 |
+
"grad_norm": 1.017815113067627,
|
261 |
+
"learning_rate": 8.486377396569122e-05,
|
262 |
+
"loss": 9.6503,
|
263 |
+
"step": 17500
|
264 |
+
},
|
265 |
+
{
|
266 |
+
"epoch": 7.5566750629722925,
|
267 |
+
"grad_norm": 1.0497677326202393,
|
268 |
+
"learning_rate": 8.385469223007064e-05,
|
269 |
+
"loss": 9.6478,
|
270 |
+
"step": 18000
|
271 |
+
},
|
272 |
+
{
|
273 |
+
"epoch": 7.766582703610411,
|
274 |
+
"grad_norm": 1.082327127456665,
|
275 |
+
"learning_rate": 8.284561049445006e-05,
|
276 |
+
"loss": 9.6374,
|
277 |
+
"step": 18500
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 7.97649034424853,
|
281 |
+
"grad_norm": 1.025443196296692,
|
282 |
+
"learning_rate": 8.183652875882947e-05,
|
283 |
+
"loss": 9.6337,
|
284 |
+
"step": 19000
|
285 |
+
},
|
286 |
+
{
|
287 |
+
"epoch": 8.18639798488665,
|
288 |
+
"grad_norm": 1.0154904127120972,
|
289 |
+
"learning_rate": 8.082744702320889e-05,
|
290 |
+
"loss": 9.6079,
|
291 |
+
"step": 19500
|
292 |
+
},
|
293 |
+
{
|
294 |
+
"epoch": 8.39630562552477,
|
295 |
+
"grad_norm": 1.035565733909607,
|
296 |
+
"learning_rate": 7.98183652875883e-05,
|
297 |
+
"loss": 9.6043,
|
298 |
+
"step": 20000
|
299 |
+
},
|
300 |
+
{
|
301 |
+
"epoch": 8.39630562552477,
|
302 |
+
"eval_accuracy": 0.15247341395662056,
|
303 |
+
"eval_loss": 9.617895126342773,
|
304 |
+
"eval_runtime": 0.7058,
|
305 |
+
"eval_samples_per_second": 678.693,
|
306 |
+
"eval_steps_per_second": 7.084,
|
307 |
+
"step": 20000
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 8.606213266162888,
|
311 |
+
"grad_norm": 1.037238597869873,
|
312 |
+
"learning_rate": 7.880928355196771e-05,
|
313 |
+
"loss": 9.5952,
|
314 |
+
"step": 20500
|
315 |
+
},
|
316 |
+
{
|
317 |
+
"epoch": 8.816120906801007,
|
318 |
+
"grad_norm": 0.9944680333137512,
|
319 |
+
"learning_rate": 7.780020181634713e-05,
|
320 |
+
"loss": 9.593,
|
321 |
+
"step": 21000
|
322 |
+
},
|
323 |
+
{
|
324 |
+
"epoch": 9.026028547439127,
|
325 |
+
"grad_norm": 1.041021466255188,
|
326 |
+
"learning_rate": 7.679112008072655e-05,
|
327 |
+
"loss": 9.5821,
|
328 |
+
"step": 21500
|
329 |
+
},
|
330 |
+
{
|
331 |
+
"epoch": 9.235936188077247,
|
332 |
+
"grad_norm": 1.036467432975769,
|
333 |
+
"learning_rate": 7.578203834510595e-05,
|
334 |
+
"loss": 9.5663,
|
335 |
+
"step": 22000
|
336 |
+
},
|
337 |
+
{
|
338 |
+
"epoch": 9.445843828715365,
|
339 |
+
"grad_norm": 1.0199445486068726,
|
340 |
+
"learning_rate": 7.477295660948537e-05,
|
341 |
+
"loss": 9.5626,
|
342 |
+
"step": 22500
|
343 |
+
},
|
344 |
+
{
|
345 |
+
"epoch": 9.655751469353484,
|
346 |
+
"grad_norm": 1.0167254209518433,
|
347 |
+
"learning_rate": 7.376387487386479e-05,
|
348 |
+
"loss": 9.5583,
|
349 |
+
"step": 23000
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 9.865659109991604,
|
353 |
+
"grad_norm": 1.0065767765045166,
|
354 |
+
"learning_rate": 7.27547931382442e-05,
|
355 |
+
"loss": 9.553,
|
356 |
+
"step": 23500
|
357 |
+
},
|
358 |
+
{
|
359 |
+
"epoch": 10.075566750629722,
|
360 |
+
"grad_norm": 0.9897018671035767,
|
361 |
+
"learning_rate": 7.174571140262362e-05,
|
362 |
+
"loss": 9.538,
|
363 |
+
"step": 24000
|
364 |
+
},
|
365 |
+
{
|
366 |
+
"epoch": 10.285474391267842,
|
367 |
+
"grad_norm": 0.9982227087020874,
|
368 |
+
"learning_rate": 7.073662966700304e-05,
|
369 |
+
"loss": 9.536,
|
370 |
+
"step": 24500
|
371 |
+
},
|
372 |
+
{
|
373 |
+
"epoch": 10.495382031905962,
|
374 |
+
"grad_norm": 0.9569253921508789,
|
375 |
+
"learning_rate": 6.972754793138244e-05,
|
376 |
+
"loss": 9.5271,
|
377 |
+
"step": 25000
|
378 |
+
},
|
379 |
+
{
|
380 |
+
"epoch": 10.705289672544081,
|
381 |
+
"grad_norm": 0.9898385405540466,
|
382 |
+
"learning_rate": 6.871846619576186e-05,
|
383 |
+
"loss": 9.5276,
|
384 |
+
"step": 25500
|
385 |
+
},
|
386 |
+
{
|
387 |
+
"epoch": 10.9151973131822,
|
388 |
+
"grad_norm": 1.0395140647888184,
|
389 |
+
"learning_rate": 6.770938446014128e-05,
|
390 |
+
"loss": 9.5282,
|
391 |
+
"step": 26000
|
392 |
+
},
|
393 |
+
{
|
394 |
+
"epoch": 11.125104953820319,
|
395 |
+
"grad_norm": 1.00431227684021,
|
396 |
+
"learning_rate": 6.670030272452068e-05,
|
397 |
+
"loss": 9.5134,
|
398 |
+
"step": 26500
|
399 |
+
},
|
400 |
+
{
|
401 |
+
"epoch": 11.335012594458439,
|
402 |
+
"grad_norm": 0.9317150712013245,
|
403 |
+
"learning_rate": 6.56912209889001e-05,
|
404 |
+
"loss": 9.5057,
|
405 |
+
"step": 27000
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 11.544920235096557,
|
409 |
+
"grad_norm": 0.9892732501029968,
|
410 |
+
"learning_rate": 6.468213925327952e-05,
|
411 |
+
"loss": 9.5005,
|
412 |
+
"step": 27500
|
413 |
+
},
|
414 |
+
{
|
415 |
+
"epoch": 11.754827875734676,
|
416 |
+
"grad_norm": 1.0242632627487183,
|
417 |
+
"learning_rate": 6.367305751765893e-05,
|
418 |
+
"loss": 9.4975,
|
419 |
+
"step": 28000
|
420 |
+
},
|
421 |
+
{
|
422 |
+
"epoch": 11.964735516372796,
|
423 |
+
"grad_norm": 1.0226876735687256,
|
424 |
+
"learning_rate": 6.266397578203835e-05,
|
425 |
+
"loss": 9.4968,
|
426 |
+
"step": 28500
|
427 |
+
},
|
428 |
+
{
|
429 |
+
"epoch": 12.174643157010916,
|
430 |
+
"grad_norm": 0.984201967716217,
|
431 |
+
"learning_rate": 6.165489404641777e-05,
|
432 |
+
"loss": 9.4866,
|
433 |
+
"step": 29000
|
434 |
+
},
|
435 |
+
{
|
436 |
+
"epoch": 12.384550797649034,
|
437 |
+
"grad_norm": 0.9562113285064697,
|
438 |
+
"learning_rate": 6.064581231079718e-05,
|
439 |
+
"loss": 9.4767,
|
440 |
+
"step": 29500
|
441 |
+
},
|
442 |
+
{
|
443 |
+
"epoch": 12.594458438287154,
|
444 |
+
"grad_norm": 0.9997998476028442,
|
445 |
+
"learning_rate": 5.963673057517659e-05,
|
446 |
+
"loss": 9.48,
|
447 |
+
"step": 30000
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 12.594458438287154,
|
451 |
+
"eval_accuracy": 0.156084730111649,
|
452 |
+
"eval_loss": 9.544936180114746,
|
453 |
+
"eval_runtime": 0.7085,
|
454 |
+
"eval_samples_per_second": 676.096,
|
455 |
+
"eval_steps_per_second": 7.057,
|
456 |
+
"step": 30000
|
457 |
+
},
|
458 |
+
{
|
459 |
+
"epoch": 12.804366078925273,
|
460 |
+
"grad_norm": 0.988662600517273,
|
461 |
+
"learning_rate": 5.8627648839556e-05,
|
462 |
+
"loss": 9.4762,
|
463 |
+
"step": 30500
|
464 |
+
},
|
465 |
+
{
|
466 |
+
"epoch": 13.014273719563391,
|
467 |
+
"grad_norm": 0.9693503379821777,
|
468 |
+
"learning_rate": 5.7618567103935416e-05,
|
469 |
+
"loss": 9.4768,
|
470 |
+
"step": 31000
|
471 |
+
},
|
472 |
+
{
|
473 |
+
"epoch": 13.224181360201511,
|
474 |
+
"grad_norm": 0.9838449358940125,
|
475 |
+
"learning_rate": 5.660948536831484e-05,
|
476 |
+
"loss": 9.4605,
|
477 |
+
"step": 31500
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 13.43408900083963,
|
481 |
+
"grad_norm": 0.985416054725647,
|
482 |
+
"learning_rate": 5.5600403632694254e-05,
|
483 |
+
"loss": 9.4605,
|
484 |
+
"step": 32000
|
485 |
+
},
|
486 |
+
{
|
487 |
+
"epoch": 13.64399664147775,
|
488 |
+
"grad_norm": 0.9869274497032166,
|
489 |
+
"learning_rate": 5.4591321897073666e-05,
|
490 |
+
"loss": 9.4617,
|
491 |
+
"step": 32500
|
492 |
+
},
|
493 |
+
{
|
494 |
+
"epoch": 13.853904282115868,
|
495 |
+
"grad_norm": 0.9963878393173218,
|
496 |
+
"learning_rate": 5.358224016145308e-05,
|
497 |
+
"loss": 9.4569,
|
498 |
+
"step": 33000
|
499 |
+
},
|
500 |
+
{
|
501 |
+
"epoch": 14.063811922753988,
|
502 |
+
"grad_norm": 0.9579880833625793,
|
503 |
+
"learning_rate": 5.257315842583249e-05,
|
504 |
+
"loss": 9.4508,
|
505 |
+
"step": 33500
|
506 |
+
},
|
507 |
+
{
|
508 |
+
"epoch": 14.273719563392108,
|
509 |
+
"grad_norm": 0.9933662414550781,
|
510 |
+
"learning_rate": 5.15640766902119e-05,
|
511 |
+
"loss": 9.4407,
|
512 |
+
"step": 34000
|
513 |
+
},
|
514 |
+
{
|
515 |
+
"epoch": 14.483627204030226,
|
516 |
+
"grad_norm": 0.966357409954071,
|
517 |
+
"learning_rate": 5.055499495459133e-05,
|
518 |
+
"loss": 9.4404,
|
519 |
+
"step": 34500
|
520 |
+
},
|
521 |
+
{
|
522 |
+
"epoch": 14.693534844668346,
|
523 |
+
"grad_norm": 1.005331039428711,
|
524 |
+
"learning_rate": 4.954591321897074e-05,
|
525 |
+
"loss": 9.4389,
|
526 |
+
"step": 35000
|
527 |
+
},
|
528 |
+
{
|
529 |
+
"epoch": 14.903442485306465,
|
530 |
+
"grad_norm": 0.9809695482254028,
|
531 |
+
"learning_rate": 4.853683148335015e-05,
|
532 |
+
"loss": 9.4387,
|
533 |
+
"step": 35500
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 15.113350125944585,
|
537 |
+
"grad_norm": 0.954156219959259,
|
538 |
+
"learning_rate": 4.7527749747729566e-05,
|
539 |
+
"loss": 9.4283,
|
540 |
+
"step": 36000
|
541 |
+
},
|
542 |
+
{
|
543 |
+
"epoch": 15.323257766582703,
|
544 |
+
"grad_norm": 1.000462293624878,
|
545 |
+
"learning_rate": 4.6518668012108985e-05,
|
546 |
+
"loss": 9.423,
|
547 |
+
"step": 36500
|
548 |
+
},
|
549 |
+
{
|
550 |
+
"epoch": 15.533165407220823,
|
551 |
+
"grad_norm": 0.9715126752853394,
|
552 |
+
"learning_rate": 4.55095862764884e-05,
|
553 |
+
"loss": 9.4215,
|
554 |
+
"step": 37000
|
555 |
+
},
|
556 |
+
{
|
557 |
+
"epoch": 15.743073047858942,
|
558 |
+
"grad_norm": 0.9889194369316101,
|
559 |
+
"learning_rate": 4.450050454086781e-05,
|
560 |
+
"loss": 9.4211,
|
561 |
+
"step": 37500
|
562 |
+
},
|
563 |
+
{
|
564 |
+
"epoch": 15.95298068849706,
|
565 |
+
"grad_norm": 0.9900258183479309,
|
566 |
+
"learning_rate": 4.349142280524723e-05,
|
567 |
+
"loss": 9.4147,
|
568 |
+
"step": 38000
|
569 |
+
},
|
570 |
+
{
|
571 |
+
"epoch": 16.162888329135182,
|
572 |
+
"grad_norm": 0.9751452207565308,
|
573 |
+
"learning_rate": 4.248234106962664e-05,
|
574 |
+
"loss": 9.3913,
|
575 |
+
"step": 38500
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 16.3727959697733,
|
579 |
+
"grad_norm": 1.0791572332382202,
|
580 |
+
"learning_rate": 4.147325933400605e-05,
|
581 |
+
"loss": 9.3417,
|
582 |
+
"step": 39000
|
583 |
+
},
|
584 |
+
{
|
585 |
+
"epoch": 16.582703610411418,
|
586 |
+
"grad_norm": 1.1733478307724,
|
587 |
+
"learning_rate": 4.046417759838547e-05,
|
588 |
+
"loss": 9.2246,
|
589 |
+
"step": 39500
|
590 |
+
},
|
591 |
+
{
|
592 |
+
"epoch": 16.79261125104954,
|
593 |
+
"grad_norm": 1.2456886768341064,
|
594 |
+
"learning_rate": 3.9455095862764884e-05,
|
595 |
+
"loss": 8.9658,
|
596 |
+
"step": 40000
|
597 |
+
},
|
598 |
+
{
|
599 |
+
"epoch": 16.79261125104954,
|
600 |
+
"eval_accuracy": 0.23029045643153526,
|
601 |
+
"eval_loss": 8.832155227661133,
|
602 |
+
"eval_runtime": 0.7062,
|
603 |
+
"eval_samples_per_second": 678.27,
|
604 |
+
"eval_steps_per_second": 7.08,
|
605 |
+
"step": 40000
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 17.002518891687657,
|
609 |
+
"grad_norm": 1.308842658996582,
|
610 |
+
"learning_rate": 3.84460141271443e-05,
|
611 |
+
"loss": 8.7837,
|
612 |
+
"step": 40500
|
613 |
+
},
|
614 |
+
{
|
615 |
+
"epoch": 17.212426532325775,
|
616 |
+
"grad_norm": 1.3732590675354004,
|
617 |
+
"learning_rate": 3.7436932391523715e-05,
|
618 |
+
"loss": 8.6164,
|
619 |
+
"step": 41000
|
620 |
+
},
|
621 |
+
{
|
622 |
+
"epoch": 17.422334172963897,
|
623 |
+
"grad_norm": 1.4219366312026978,
|
624 |
+
"learning_rate": 3.642785065590313e-05,
|
625 |
+
"loss": 8.4975,
|
626 |
+
"step": 41500
|
627 |
+
},
|
628 |
+
{
|
629 |
+
"epoch": 17.632241813602015,
|
630 |
+
"grad_norm": 1.481255292892456,
|
631 |
+
"learning_rate": 3.541876892028255e-05,
|
632 |
+
"loss": 8.4114,
|
633 |
+
"step": 42000
|
634 |
+
},
|
635 |
+
{
|
636 |
+
"epoch": 17.842149454240133,
|
637 |
+
"grad_norm": 1.408211588859558,
|
638 |
+
"learning_rate": 3.440968718466196e-05,
|
639 |
+
"loss": 8.3358,
|
640 |
+
"step": 42500
|
641 |
+
},
|
642 |
+
{
|
643 |
+
"epoch": 18.052057094878254,
|
644 |
+
"grad_norm": 1.456390619277954,
|
645 |
+
"learning_rate": 3.340060544904137e-05,
|
646 |
+
"loss": 8.2576,
|
647 |
+
"step": 43000
|
648 |
+
},
|
649 |
+
{
|
650 |
+
"epoch": 18.261964735516372,
|
651 |
+
"grad_norm": 1.5487608909606934,
|
652 |
+
"learning_rate": 3.239152371342079e-05,
|
653 |
+
"loss": 8.1819,
|
654 |
+
"step": 43500
|
655 |
+
},
|
656 |
+
{
|
657 |
+
"epoch": 18.471872376154494,
|
658 |
+
"grad_norm": 1.5488317012786865,
|
659 |
+
"learning_rate": 3.13824419778002e-05,
|
660 |
+
"loss": 8.1052,
|
661 |
+
"step": 44000
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 18.68178001679261,
|
665 |
+
"grad_norm": 1.4640696048736572,
|
666 |
+
"learning_rate": 3.0373360242179615e-05,
|
667 |
+
"loss": 7.9731,
|
668 |
+
"step": 44500
|
669 |
+
},
|
670 |
+
{
|
671 |
+
"epoch": 18.89168765743073,
|
672 |
+
"grad_norm": 1.416163682937622,
|
673 |
+
"learning_rate": 2.9364278506559034e-05,
|
674 |
+
"loss": 7.8276,
|
675 |
+
"step": 45000
|
676 |
+
},
|
677 |
+
{
|
678 |
+
"epoch": 19.10159529806885,
|
679 |
+
"grad_norm": 1.3770819902420044,
|
680 |
+
"learning_rate": 2.8355196770938446e-05,
|
681 |
+
"loss": 7.7208,
|
682 |
+
"step": 45500
|
683 |
+
},
|
684 |
+
{
|
685 |
+
"epoch": 19.31150293870697,
|
686 |
+
"grad_norm": 1.4795335531234741,
|
687 |
+
"learning_rate": 2.734611503531786e-05,
|
688 |
+
"loss": 7.6359,
|
689 |
+
"step": 46000
|
690 |
+
},
|
691 |
+
{
|
692 |
+
"epoch": 19.521410579345087,
|
693 |
+
"grad_norm": 1.4281933307647705,
|
694 |
+
"learning_rate": 2.6337033299697278e-05,
|
695 |
+
"loss": 7.5747,
|
696 |
+
"step": 46500
|
697 |
+
},
|
698 |
+
{
|
699 |
+
"epoch": 19.73131821998321,
|
700 |
+
"grad_norm": 1.414133906364441,
|
701 |
+
"learning_rate": 2.532795156407669e-05,
|
702 |
+
"loss": 7.5191,
|
703 |
+
"step": 47000
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 19.941225860621326,
|
707 |
+
"grad_norm": 1.489829182624817,
|
708 |
+
"learning_rate": 2.4318869828456106e-05,
|
709 |
+
"loss": 7.4639,
|
710 |
+
"step": 47500
|
711 |
+
},
|
712 |
+
{
|
713 |
+
"epoch": 20.151133501259444,
|
714 |
+
"grad_norm": 1.4401626586914062,
|
715 |
+
"learning_rate": 2.330978809283552e-05,
|
716 |
+
"loss": 7.4126,
|
717 |
+
"step": 48000
|
718 |
+
},
|
719 |
+
{
|
720 |
+
"epoch": 20.361041141897566,
|
721 |
+
"grad_norm": 1.5048668384552002,
|
722 |
+
"learning_rate": 2.2300706357214934e-05,
|
723 |
+
"loss": 7.3737,
|
724 |
+
"step": 48500
|
725 |
+
},
|
726 |
+
{
|
727 |
+
"epoch": 20.570948782535684,
|
728 |
+
"grad_norm": 1.5247819423675537,
|
729 |
+
"learning_rate": 2.129162462159435e-05,
|
730 |
+
"loss": 7.3287,
|
731 |
+
"step": 49000
|
732 |
+
},
|
733 |
+
{
|
734 |
+
"epoch": 20.7808564231738,
|
735 |
+
"grad_norm": 1.531874179840088,
|
736 |
+
"learning_rate": 2.0282542885973765e-05,
|
737 |
+
"loss": 7.2904,
|
738 |
+
"step": 49500
|
739 |
+
},
|
740 |
+
{
|
741 |
+
"epoch": 20.990764063811923,
|
742 |
+
"grad_norm": 1.5145772695541382,
|
743 |
+
"learning_rate": 1.927346115035318e-05,
|
744 |
+
"loss": 7.2614,
|
745 |
+
"step": 50000
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 20.990764063811923,
|
749 |
+
"eval_accuracy": 0.4201082232876328,
|
750 |
+
"eval_loss": 7.017268180847168,
|
751 |
+
"eval_runtime": 0.7142,
|
752 |
+
"eval_samples_per_second": 670.716,
|
753 |
+
"eval_steps_per_second": 7.001,
|
754 |
+
"step": 50000
|
755 |
+
},
|
756 |
+
{
|
757 |
+
"epoch": 21.20067170445004,
|
758 |
+
"grad_norm": 1.5500428676605225,
|
759 |
+
"learning_rate": 1.8264379414732593e-05,
|
760 |
+
"loss": 7.2181,
|
761 |
+
"step": 50500
|
762 |
+
},
|
763 |
+
{
|
764 |
+
"epoch": 21.410579345088163,
|
765 |
+
"grad_norm": 1.5977363586425781,
|
766 |
+
"learning_rate": 1.725529767911201e-05,
|
767 |
+
"loss": 7.1958,
|
768 |
+
"step": 51000
|
769 |
+
},
|
770 |
+
{
|
771 |
+
"epoch": 21.62048698572628,
|
772 |
+
"grad_norm": 1.5731196403503418,
|
773 |
+
"learning_rate": 1.6246215943491424e-05,
|
774 |
+
"loss": 7.1656,
|
775 |
+
"step": 51500
|
776 |
+
},
|
777 |
+
{
|
778 |
+
"epoch": 21.8303946263644,
|
779 |
+
"grad_norm": 1.6346486806869507,
|
780 |
+
"learning_rate": 1.5237134207870837e-05,
|
781 |
+
"loss": 7.1388,
|
782 |
+
"step": 52000
|
783 |
+
},
|
784 |
+
{
|
785 |
+
"epoch": 22.04030226700252,
|
786 |
+
"grad_norm": 1.6242817640304565,
|
787 |
+
"learning_rate": 1.4228052472250252e-05,
|
788 |
+
"loss": 7.1167,
|
789 |
+
"step": 52500
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 22.250209907640638,
|
793 |
+
"grad_norm": 1.6085208654403687,
|
794 |
+
"learning_rate": 1.3218970736629668e-05,
|
795 |
+
"loss": 7.0882,
|
796 |
+
"step": 53000
|
797 |
+
},
|
798 |
+
{
|
799 |
+
"epoch": 22.460117548278756,
|
800 |
+
"grad_norm": 1.5465388298034668,
|
801 |
+
"learning_rate": 1.2209889001009082e-05,
|
802 |
+
"loss": 7.0714,
|
803 |
+
"step": 53500
|
804 |
+
},
|
805 |
+
{
|
806 |
+
"epoch": 22.670025188916878,
|
807 |
+
"grad_norm": 1.604613184928894,
|
808 |
+
"learning_rate": 1.1200807265388496e-05,
|
809 |
+
"loss": 7.0556,
|
810 |
+
"step": 54000
|
811 |
+
},
|
812 |
+
{
|
813 |
+
"epoch": 22.879932829554996,
|
814 |
+
"grad_norm": 1.6013134717941284,
|
815 |
+
"learning_rate": 1.0191725529767912e-05,
|
816 |
+
"loss": 7.0381,
|
817 |
+
"step": 54500
|
818 |
+
},
|
819 |
+
{
|
820 |
+
"epoch": 23.089840470193113,
|
821 |
+
"grad_norm": 1.671255111694336,
|
822 |
+
"learning_rate": 9.182643794147326e-06,
|
823 |
+
"loss": 7.0206,
|
824 |
+
"step": 55000
|
825 |
+
},
|
826 |
+
{
|
827 |
+
"epoch": 23.299748110831235,
|
828 |
+
"grad_norm": 1.6133580207824707,
|
829 |
+
"learning_rate": 8.173562058526741e-06,
|
830 |
+
"loss": 7.0051,
|
831 |
+
"step": 55500
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 23.509655751469353,
|
835 |
+
"grad_norm": 1.6531249284744263,
|
836 |
+
"learning_rate": 7.164480322906156e-06,
|
837 |
+
"loss": 6.9929,
|
838 |
+
"step": 56000
|
839 |
+
},
|
840 |
+
{
|
841 |
+
"epoch": 23.719563392107474,
|
842 |
+
"grad_norm": 1.6123356819152832,
|
843 |
+
"learning_rate": 6.155398587285571e-06,
|
844 |
+
"loss": 6.9788,
|
845 |
+
"step": 56500
|
846 |
+
},
|
847 |
+
{
|
848 |
+
"epoch": 23.929471032745592,
|
849 |
+
"grad_norm": 1.5911654233932495,
|
850 |
+
"learning_rate": 5.146316851664986e-06,
|
851 |
+
"loss": 6.9751,
|
852 |
+
"step": 57000
|
853 |
+
},
|
854 |
+
{
|
855 |
+
"epoch": 24.13937867338371,
|
856 |
+
"grad_norm": 1.6447371244430542,
|
857 |
+
"learning_rate": 4.1372351160444e-06,
|
858 |
+
"loss": 6.9654,
|
859 |
+
"step": 57500
|
860 |
+
},
|
861 |
+
{
|
862 |
+
"epoch": 24.349286314021832,
|
863 |
+
"grad_norm": 1.599005103111267,
|
864 |
+
"learning_rate": 3.1281533804238145e-06,
|
865 |
+
"loss": 6.9591,
|
866 |
+
"step": 58000
|
867 |
+
},
|
868 |
+
{
|
869 |
+
"epoch": 24.55919395465995,
|
870 |
+
"grad_norm": 1.6058322191238403,
|
871 |
+
"learning_rate": 2.1190716448032293e-06,
|
872 |
+
"loss": 6.9498,
|
873 |
+
"step": 58500
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 24.769101595298068,
|
877 |
+
"grad_norm": 1.5888394117355347,
|
878 |
+
"learning_rate": 1.109989909182644e-06,
|
879 |
+
"loss": 6.9459,
|
880 |
+
"step": 59000
|
881 |
+
},
|
882 |
+
{
|
883 |
+
"epoch": 24.97900923593619,
|
884 |
+
"grad_norm": 1.6043498516082764,
|
885 |
+
"learning_rate": 1.0090817356205853e-07,
|
886 |
+
"loss": 6.9472,
|
887 |
+
"step": 59500
|
888 |
+
},
|
889 |
+
{
|
890 |
+
"epoch": 25.0,
|
891 |
+
"step": 59550,
|
892 |
+
"total_flos": 1.5161929390646784e+18,
|
893 |
+
"train_loss": 9.134388991963654,
|
894 |
+
"train_runtime": 17204.0061,
|
895 |
+
"train_samples_per_second": 332.247,
|
896 |
+
"train_steps_per_second": 3.461
|
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": 1.5161929390646784e+18,
|
917 |
+
"train_batch_size": 96,
|
918 |
+
"trial_name": null,
|
919 |
+
"trial_params": null
|
920 |
+
}
|