End of training
Browse files- README.md +19 -2
- all_results.json +15 -0
- eval_results.json +10 -0
- logs/events.out.tfevents.1700310358.serv-9207.687883.1 +3 -0
- train_results.json +8 -0
- trainer_state.json +568 -0
README.md
CHANGED
|
@@ -2,9 +2,23 @@
|
|
| 2 |
base_model: gokuls/HBERTv1_L12_H768_A12_ffn_1
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
model-index:
|
| 6 |
- name: HBERTv1_48_L12_H768_A12_ffn_1_KD
|
| 7 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
---
|
| 9 |
|
| 10 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -12,7 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 12 |
|
| 13 |
# HBERTv1_48_L12_H768_A12_ffn_1_KD
|
| 14 |
|
| 15 |
-
This model is a fine-tuned version of [gokuls/HBERTv1_L12_H768_A12_ffn_1](https://huggingface.co/gokuls/HBERTv1_L12_H768_A12_ffn_1) on
|
|
|
|
|
|
|
|
|
|
| 16 |
|
| 17 |
## Model description
|
| 18 |
|
|
|
|
| 2 |
base_model: gokuls/HBERTv1_L12_H768_A12_ffn_1
|
| 3 |
tags:
|
| 4 |
- generated_from_trainer
|
| 5 |
+
datasets:
|
| 6 |
+
- gokuls/wiki_book_corpus_complete_processed_bert_dataset
|
| 7 |
+
metrics:
|
| 8 |
+
- accuracy
|
| 9 |
model-index:
|
| 10 |
- name: HBERTv1_48_L12_H768_A12_ffn_1_KD
|
| 11 |
+
results:
|
| 12 |
+
- task:
|
| 13 |
+
name: Masked Language Modeling
|
| 14 |
+
type: fill-mask
|
| 15 |
+
dataset:
|
| 16 |
+
name: gokuls/wiki_book_corpus_complete_processed_bert_dataset
|
| 17 |
+
type: gokuls/wiki_book_corpus_complete_processed_bert_dataset
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Accuracy
|
| 20 |
+
type: accuracy
|
| 21 |
+
value: 0.4616582527830643
|
| 22 |
---
|
| 23 |
|
| 24 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 26 |
|
| 27 |
# HBERTv1_48_L12_H768_A12_ffn_1_KD
|
| 28 |
|
| 29 |
+
This model is a fine-tuned version of [gokuls/HBERTv1_L12_H768_A12_ffn_1](https://huggingface.co/gokuls/HBERTv1_L12_H768_A12_ffn_1) on the gokuls/wiki_book_corpus_complete_processed_bert_dataset dataset.
|
| 30 |
+
It achieves the following results on the evaluation set:
|
| 31 |
+
- Loss: 132.3779
|
| 32 |
+
- Accuracy: 0.4617
|
| 33 |
|
| 34 |
## Model description
|
| 35 |
|
all_results.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.25,
|
| 3 |
+
"eval_accuracy": 0.4616582527830643,
|
| 4 |
+
"eval_loss": 132.37786865234375,
|
| 5 |
+
"eval_runtime": 4224.7326,
|
| 6 |
+
"eval_samples": 308356,
|
| 7 |
+
"eval_samples_per_second": 72.988,
|
| 8 |
+
"eval_steps_per_second": 2.281,
|
| 9 |
+
"perplexity": 3.0972615548374607e+57,
|
| 10 |
+
"train_loss": 159.1573161326461,
|
| 11 |
+
"train_runtime": 35999.4318,
|
| 12 |
+
"train_samples": 5858758,
|
| 13 |
+
"train_samples_per_second": 16274.585,
|
| 14 |
+
"train_steps_per_second": 508.583
|
| 15 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.25,
|
| 3 |
+
"eval_accuracy": 0.4616582527830643,
|
| 4 |
+
"eval_loss": 132.37786865234375,
|
| 5 |
+
"eval_runtime": 4224.7326,
|
| 6 |
+
"eval_samples": 308356,
|
| 7 |
+
"eval_samples_per_second": 72.988,
|
| 8 |
+
"eval_steps_per_second": 2.281,
|
| 9 |
+
"perplexity": 3.0972615548374607e+57
|
| 10 |
+
}
|
logs/events.out.tfevents.1700310358.serv-9207.687883.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:758744f8ca45086e4fe4df72fb6daa3588d4221bd773ad34911d76280db80651
|
| 3 |
+
size 369
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.25,
|
| 3 |
+
"train_loss": 159.1573161326461,
|
| 4 |
+
"train_runtime": 35999.4318,
|
| 5 |
+
"train_samples": 5858758,
|
| 6 |
+
"train_samples_per_second": 16274.585,
|
| 7 |
+
"train_steps_per_second": 508.583
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,568 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.24742881799363145,
|
| 5 |
+
"eval_steps": 1000000,
|
| 6 |
+
"global_step": 45301,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 5.000000000000001e-07,
|
| 14 |
+
"loss": 431.6959,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 1.0000000000000002e-06,
|
| 20 |
+
"loss": 297.4225,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 1.5e-06,
|
| 26 |
+
"loss": 252.127,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 32 |
+
"loss": 228.3056,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.01,
|
| 37 |
+
"learning_rate": 2.5e-06,
|
| 38 |
+
"loss": 214.1223,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 3e-06,
|
| 44 |
+
"loss": 204.62,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 3.5e-06,
|
| 50 |
+
"loss": 197.7543,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 4.000000000000001e-06,
|
| 56 |
+
"loss": 192.3316,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.02,
|
| 61 |
+
"learning_rate": 4.5e-06,
|
| 62 |
+
"loss": 188.5246,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 5e-06,
|
| 68 |
+
"loss": 184.3941,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 5.500000000000001e-06,
|
| 74 |
+
"loss": 181.4647,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.03,
|
| 79 |
+
"learning_rate": 6e-06,
|
| 80 |
+
"loss": 179.2321,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 6.5000000000000004e-06,
|
| 86 |
+
"loss": 176.7608,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 7e-06,
|
| 92 |
+
"loss": 175.437,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.04,
|
| 97 |
+
"learning_rate": 7.500000000000001e-06,
|
| 98 |
+
"loss": 172.9957,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.04,
|
| 103 |
+
"learning_rate": 8.000000000000001e-06,
|
| 104 |
+
"loss": 171.3707,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 8.5e-06,
|
| 110 |
+
"loss": 170.2551,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.05,
|
| 115 |
+
"learning_rate": 9e-06,
|
| 116 |
+
"loss": 168.7796,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.05,
|
| 121 |
+
"learning_rate": 9.5e-06,
|
| 122 |
+
"loss": 167.1022,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.05,
|
| 127 |
+
"learning_rate": 1e-05,
|
| 128 |
+
"loss": 166.1143,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 9.999726756545549e-06,
|
| 134 |
+
"loss": 164.6779,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.06,
|
| 139 |
+
"learning_rate": 9.999453513091095e-06,
|
| 140 |
+
"loss": 163.4033,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.06,
|
| 145 |
+
"learning_rate": 9.999180269636641e-06,
|
| 146 |
+
"loss": 162.5638,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.07,
|
| 151 |
+
"learning_rate": 9.998907026182189e-06,
|
| 152 |
+
"loss": 161.2811,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.07,
|
| 157 |
+
"learning_rate": 9.998633782727735e-06,
|
| 158 |
+
"loss": 160.2764,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.07,
|
| 163 |
+
"learning_rate": 9.998360539273283e-06,
|
| 164 |
+
"loss": 159.5492,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.07,
|
| 169 |
+
"learning_rate": 9.99808729581883e-06,
|
| 170 |
+
"loss": 158.2019,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.08,
|
| 175 |
+
"learning_rate": 9.997814052364376e-06,
|
| 176 |
+
"loss": 158.0253,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.08,
|
| 181 |
+
"learning_rate": 9.997540808909924e-06,
|
| 182 |
+
"loss": 156.8733,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.08,
|
| 187 |
+
"learning_rate": 9.99726756545547e-06,
|
| 188 |
+
"loss": 156.8639,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.08,
|
| 193 |
+
"learning_rate": 9.996994322001016e-06,
|
| 194 |
+
"loss": 156.0519,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.09,
|
| 199 |
+
"learning_rate": 9.996721078546564e-06,
|
| 200 |
+
"loss": 155.0571,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.09,
|
| 205 |
+
"learning_rate": 9.996447835092112e-06,
|
| 206 |
+
"loss": 154.6748,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.09,
|
| 211 |
+
"learning_rate": 9.996174591637658e-06,
|
| 212 |
+
"loss": 153.1673,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1,
|
| 217 |
+
"learning_rate": 9.995901348183204e-06,
|
| 218 |
+
"loss": 153.309,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.1,
|
| 223 |
+
"learning_rate": 9.995628104728752e-06,
|
| 224 |
+
"loss": 152.58,
|
| 225 |
+
"step": 18000
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.1,
|
| 229 |
+
"learning_rate": 9.995354861274299e-06,
|
| 230 |
+
"loss": 152.1333,
|
| 231 |
+
"step": 18500
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.1,
|
| 235 |
+
"learning_rate": 9.995081617819847e-06,
|
| 236 |
+
"loss": 151.4704,
|
| 237 |
+
"step": 19000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.11,
|
| 241 |
+
"learning_rate": 9.994808374365393e-06,
|
| 242 |
+
"loss": 151.0387,
|
| 243 |
+
"step": 19500
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.11,
|
| 247 |
+
"learning_rate": 9.994535130910939e-06,
|
| 248 |
+
"loss": 150.4169,
|
| 249 |
+
"step": 20000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.11,
|
| 253 |
+
"learning_rate": 9.994261887456487e-06,
|
| 254 |
+
"loss": 150.5139,
|
| 255 |
+
"step": 20500
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.11,
|
| 259 |
+
"learning_rate": 9.993988644002033e-06,
|
| 260 |
+
"loss": 149.6021,
|
| 261 |
+
"step": 21000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.12,
|
| 265 |
+
"learning_rate": 9.993715400547581e-06,
|
| 266 |
+
"loss": 149.0417,
|
| 267 |
+
"step": 21500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.12,
|
| 271 |
+
"learning_rate": 9.993442157093127e-06,
|
| 272 |
+
"loss": 148.4873,
|
| 273 |
+
"step": 22000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.12,
|
| 277 |
+
"learning_rate": 9.993168913638675e-06,
|
| 278 |
+
"loss": 148.4089,
|
| 279 |
+
"step": 22500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.13,
|
| 283 |
+
"learning_rate": 9.992895670184221e-06,
|
| 284 |
+
"loss": 147.7362,
|
| 285 |
+
"step": 23000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.13,
|
| 289 |
+
"learning_rate": 9.99262242672977e-06,
|
| 290 |
+
"loss": 147.1884,
|
| 291 |
+
"step": 23500
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.13,
|
| 295 |
+
"learning_rate": 9.992349183275316e-06,
|
| 296 |
+
"loss": 147.1985,
|
| 297 |
+
"step": 24000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.13,
|
| 301 |
+
"learning_rate": 9.992075939820862e-06,
|
| 302 |
+
"loss": 147.2833,
|
| 303 |
+
"step": 24500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.14,
|
| 307 |
+
"learning_rate": 9.99180269636641e-06,
|
| 308 |
+
"loss": 146.4076,
|
| 309 |
+
"step": 25000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.14,
|
| 313 |
+
"learning_rate": 9.991529452911956e-06,
|
| 314 |
+
"loss": 146.2133,
|
| 315 |
+
"step": 25500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.14,
|
| 319 |
+
"learning_rate": 9.991256209457502e-06,
|
| 320 |
+
"loss": 145.7042,
|
| 321 |
+
"step": 26000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.14,
|
| 325 |
+
"learning_rate": 9.99098296600305e-06,
|
| 326 |
+
"loss": 146.1063,
|
| 327 |
+
"step": 26500
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.15,
|
| 331 |
+
"learning_rate": 9.990709722548596e-06,
|
| 332 |
+
"loss": 145.0671,
|
| 333 |
+
"step": 27000
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.15,
|
| 337 |
+
"learning_rate": 9.990436479094144e-06,
|
| 338 |
+
"loss": 144.2784,
|
| 339 |
+
"step": 27500
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.15,
|
| 343 |
+
"learning_rate": 9.990163235639692e-06,
|
| 344 |
+
"loss": 144.2024,
|
| 345 |
+
"step": 28000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.16,
|
| 349 |
+
"learning_rate": 9.989889992185238e-06,
|
| 350 |
+
"loss": 143.9278,
|
| 351 |
+
"step": 28500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.16,
|
| 355 |
+
"learning_rate": 9.989616748730785e-06,
|
| 356 |
+
"loss": 143.8407,
|
| 357 |
+
"step": 29000
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.16,
|
| 361 |
+
"learning_rate": 9.989343505276333e-06,
|
| 362 |
+
"loss": 143.22,
|
| 363 |
+
"step": 29500
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.16,
|
| 367 |
+
"learning_rate": 9.989070261821879e-06,
|
| 368 |
+
"loss": 142.6727,
|
| 369 |
+
"step": 30000
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.17,
|
| 373 |
+
"learning_rate": 9.988797018367425e-06,
|
| 374 |
+
"loss": 142.5397,
|
| 375 |
+
"step": 30500
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.17,
|
| 379 |
+
"learning_rate": 9.988523774912973e-06,
|
| 380 |
+
"loss": 142.2751,
|
| 381 |
+
"step": 31000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.17,
|
| 385 |
+
"learning_rate": 9.98825053145852e-06,
|
| 386 |
+
"loss": 142.4529,
|
| 387 |
+
"step": 31500
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.17,
|
| 391 |
+
"learning_rate": 9.987977288004067e-06,
|
| 392 |
+
"loss": 141.3284,
|
| 393 |
+
"step": 32000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.18,
|
| 397 |
+
"learning_rate": 9.987704044549613e-06,
|
| 398 |
+
"loss": 141.185,
|
| 399 |
+
"step": 32500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.18,
|
| 403 |
+
"learning_rate": 9.98743080109516e-06,
|
| 404 |
+
"loss": 141.4491,
|
| 405 |
+
"step": 33000
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.18,
|
| 409 |
+
"learning_rate": 9.987157557640708e-06,
|
| 410 |
+
"loss": 140.3137,
|
| 411 |
+
"step": 33500
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.19,
|
| 415 |
+
"learning_rate": 9.986884314186255e-06,
|
| 416 |
+
"loss": 140.5562,
|
| 417 |
+
"step": 34000
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.19,
|
| 421 |
+
"learning_rate": 9.986611070731802e-06,
|
| 422 |
+
"loss": 140.5535,
|
| 423 |
+
"step": 34500
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.19,
|
| 427 |
+
"learning_rate": 9.986337827277348e-06,
|
| 428 |
+
"loss": 139.9692,
|
| 429 |
+
"step": 35000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.19,
|
| 433 |
+
"learning_rate": 9.986064583822896e-06,
|
| 434 |
+
"loss": 139.3751,
|
| 435 |
+
"step": 35500
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.2,
|
| 439 |
+
"learning_rate": 9.985791340368442e-06,
|
| 440 |
+
"loss": 139.6697,
|
| 441 |
+
"step": 36000
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.2,
|
| 445 |
+
"learning_rate": 9.98551809691399e-06,
|
| 446 |
+
"loss": 138.6528,
|
| 447 |
+
"step": 36500
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.2,
|
| 451 |
+
"learning_rate": 9.985244853459536e-06,
|
| 452 |
+
"loss": 138.9591,
|
| 453 |
+
"step": 37000
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.2,
|
| 457 |
+
"learning_rate": 9.984971610005082e-06,
|
| 458 |
+
"loss": 138.7952,
|
| 459 |
+
"step": 37500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.21,
|
| 463 |
+
"learning_rate": 9.98469836655063e-06,
|
| 464 |
+
"loss": 138.2421,
|
| 465 |
+
"step": 38000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.21,
|
| 469 |
+
"learning_rate": 9.984425123096178e-06,
|
| 470 |
+
"loss": 138.5417,
|
| 471 |
+
"step": 38500
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.21,
|
| 475 |
+
"learning_rate": 9.984151879641723e-06,
|
| 476 |
+
"loss": 138.0299,
|
| 477 |
+
"step": 39000
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.22,
|
| 481 |
+
"learning_rate": 9.98387863618727e-06,
|
| 482 |
+
"loss": 137.7599,
|
| 483 |
+
"step": 39500
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.22,
|
| 487 |
+
"learning_rate": 9.983605392732819e-06,
|
| 488 |
+
"loss": 137.606,
|
| 489 |
+
"step": 40000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.22,
|
| 493 |
+
"learning_rate": 9.983332149278365e-06,
|
| 494 |
+
"loss": 136.8119,
|
| 495 |
+
"step": 40500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.22,
|
| 499 |
+
"learning_rate": 9.983058905823911e-06,
|
| 500 |
+
"loss": 136.5174,
|
| 501 |
+
"step": 41000
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.23,
|
| 505 |
+
"learning_rate": 9.982785662369459e-06,
|
| 506 |
+
"loss": 136.5812,
|
| 507 |
+
"step": 41500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.23,
|
| 511 |
+
"learning_rate": 9.982512418915005e-06,
|
| 512 |
+
"loss": 136.5835,
|
| 513 |
+
"step": 42000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.23,
|
| 517 |
+
"learning_rate": 9.982239175460553e-06,
|
| 518 |
+
"loss": 136.2487,
|
| 519 |
+
"step": 42500
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.23,
|
| 523 |
+
"learning_rate": 9.9819659320061e-06,
|
| 524 |
+
"loss": 135.6395,
|
| 525 |
+
"step": 43000
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.24,
|
| 529 |
+
"learning_rate": 9.981692688551646e-06,
|
| 530 |
+
"loss": 136.295,
|
| 531 |
+
"step": 43500
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.24,
|
| 535 |
+
"learning_rate": 9.981419445097194e-06,
|
| 536 |
+
"loss": 135.4576,
|
| 537 |
+
"step": 44000
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.24,
|
| 541 |
+
"learning_rate": 9.981146201642742e-06,
|
| 542 |
+
"loss": 135.6909,
|
| 543 |
+
"step": 44500
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.25,
|
| 547 |
+
"learning_rate": 9.980872958188288e-06,
|
| 548 |
+
"loss": 135.0495,
|
| 549 |
+
"step": 45000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.25,
|
| 553 |
+
"step": 45301,
|
| 554 |
+
"total_flos": 2.4014284010815488e+17,
|
| 555 |
+
"train_loss": 159.1573161326461,
|
| 556 |
+
"train_runtime": 35999.4318,
|
| 557 |
+
"train_samples_per_second": 16274.585,
|
| 558 |
+
"train_steps_per_second": 508.583
|
| 559 |
+
}
|
| 560 |
+
],
|
| 561 |
+
"logging_steps": 500,
|
| 562 |
+
"max_steps": 18308700,
|
| 563 |
+
"num_train_epochs": 100,
|
| 564 |
+
"save_steps": 1000000,
|
| 565 |
+
"total_flos": 2.4014284010815488e+17,
|
| 566 |
+
"trial_name": null,
|
| 567 |
+
"trial_params": null
|
| 568 |
+
}
|