Upload folder using huggingface_hub
Browse files- README.md +28 -15
- all_results.json +12 -10
- config.json +5 -5
- eval_results.json +8 -6
- pytorch_model.bin +1 -1
- tokenizer.json +2 -2
- train_results.json +5 -5
- trainer_state.json +1298 -104
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,13 +1,32 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: bert-large-cased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
|
|
|
| 8 |
model-index:
|
| 9 |
- name: bert-large-qqp
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,10 +34,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# bert-large-qqp
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
-
- Loss: 0.
|
| 21 |
-
- Accuracy: 0.
|
|
|
|
|
|
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -37,24 +58,16 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate:
|
| 41 |
- train_batch_size: 16
|
| 42 |
-
- eval_batch_size:
|
| 43 |
- seed: 42
|
| 44 |
-
- gradient_accumulation_steps: 8
|
| 45 |
-
- total_train_batch_size: 128
|
| 46 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
- lr_scheduler_type: linear
|
| 48 |
-
- num_epochs:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
| 52 |
-
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|
| 53 |
-
|:-------------:|:-----:|:-----:|:---------------:|:--------:|
|
| 54 |
-
| 0.2866 | 1.0 | 2842 | 0.2589 | 0.8891 |
|
| 55 |
-
| 0.2022 | 2.0 | 5685 | 0.2509 | 0.8970 |
|
| 56 |
-
| 0.1383 | 3.0 | 8527 | 0.2721 | 0.9083 |
|
| 57 |
-
| 0.0938 | 4.0 | 11368 | 0.2742 | 0.9116 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: bert-large-cased
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- glue
|
| 10 |
metrics:
|
| 11 |
- accuracy
|
| 12 |
+
- f1
|
| 13 |
model-index:
|
| 14 |
- name: bert-large-qqp
|
| 15 |
+
results:
|
| 16 |
+
- task:
|
| 17 |
+
name: Text Classification
|
| 18 |
+
type: text-classification
|
| 19 |
+
dataset:
|
| 20 |
+
name: GLUE QQP
|
| 21 |
+
type: glue
|
| 22 |
+
args: qqp
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Accuracy
|
| 25 |
+
type: accuracy
|
| 26 |
+
value: 0.9132574820677715
|
| 27 |
+
- name: F1
|
| 28 |
+
type: f1
|
| 29 |
+
value: 0.8825794354973717
|
| 30 |
---
|
| 31 |
|
| 32 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 34 |
|
| 35 |
# bert-large-qqp
|
| 36 |
|
| 37 |
+
This model is a fine-tuned version of [bert-large-cased](https://huggingface.co/bert-large-cased) on the GLUE QQP dataset.
|
| 38 |
It achieves the following results on the evaluation set:
|
| 39 |
+
- Loss: 0.4196
|
| 40 |
+
- Accuracy: 0.9133
|
| 41 |
+
- F1: 0.8826
|
| 42 |
+
- Combined Score: 0.8979
|
| 43 |
|
| 44 |
## Model description
|
| 45 |
|
|
|
|
| 58 |
### Training hyperparameters
|
| 59 |
|
| 60 |
The following hyperparameters were used during training:
|
| 61 |
+
- learning_rate: 2e-05
|
| 62 |
- train_batch_size: 16
|
| 63 |
+
- eval_batch_size: 8
|
| 64 |
- seed: 42
|
|
|
|
|
|
|
| 65 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 66 |
- lr_scheduler_type: linear
|
| 67 |
+
- num_epochs: 5.0
|
| 68 |
|
| 69 |
### Training results
|
| 70 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
|
| 72 |
|
| 73 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,14 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
|
|
|
| 6 |
"eval_samples": 40430,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
-
"train_loss": 0.
|
| 10 |
-
"train_runtime":
|
| 11 |
"train_samples": 363846,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9132574820677715,
|
| 4 |
+
"eval_combined_score": 0.8979184587825716,
|
| 5 |
+
"eval_f1": 0.8825794354973717,
|
| 6 |
+
"eval_loss": 0.4195607602596283,
|
| 7 |
+
"eval_runtime": 104.4175,
|
| 8 |
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 387.196,
|
| 10 |
+
"eval_steps_per_second": 48.402,
|
| 11 |
+
"train_loss": 0.19827925553449116,
|
| 12 |
+
"train_runtime": 10419.4099,
|
| 13 |
"train_samples": 363846,
|
| 14 |
+
"train_samples_per_second": 174.6,
|
| 15 |
+
"train_steps_per_second": 10.913
|
| 16 |
}
|
config.json
CHANGED
|
@@ -6,20 +6,20 @@
|
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
"directionality": "bidi",
|
| 9 |
-
"finetuning_task": "
|
| 10 |
"gradient_checkpointing": false,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
"hidden_size": 1024,
|
| 14 |
"id2label": {
|
| 15 |
-
"0": "
|
| 16 |
-
"1": "
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 4096,
|
| 20 |
"label2id": {
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
},
|
| 24 |
"layer_norm_eps": 1e-12,
|
| 25 |
"max_position_embeddings": 512,
|
|
|
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
"directionality": "bidi",
|
| 9 |
+
"finetuning_task": "qqp",
|
| 10 |
"gradient_checkpointing": false,
|
| 11 |
"hidden_act": "gelu",
|
| 12 |
"hidden_dropout_prob": 0.1,
|
| 13 |
"hidden_size": 1024,
|
| 14 |
"id2label": {
|
| 15 |
+
"0": "not_duplicate",
|
| 16 |
+
"1": "duplicate"
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 4096,
|
| 20 |
"label2id": {
|
| 21 |
+
"duplicate": 1,
|
| 22 |
+
"not_duplicate": 0
|
| 23 |
},
|
| 24 |
"layer_norm_eps": 1e-12,
|
| 25 |
"max_position_embeddings": 512,
|
eval_results.json
CHANGED
|
@@ -1,9 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_accuracy": 0.
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
|
|
|
| 6 |
"eval_samples": 40430,
|
| 7 |
-
"eval_samples_per_second":
|
| 8 |
-
"eval_steps_per_second":
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_accuracy": 0.9132574820677715,
|
| 4 |
+
"eval_combined_score": 0.8979184587825716,
|
| 5 |
+
"eval_f1": 0.8825794354973717,
|
| 6 |
+
"eval_loss": 0.4195607602596283,
|
| 7 |
+
"eval_runtime": 104.4175,
|
| 8 |
"eval_samples": 40430,
|
| 9 |
+
"eval_samples_per_second": 387.196,
|
| 10 |
+
"eval_steps_per_second": 48.402
|
| 11 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1334459697
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:206f6341cd568a49e40723864940585e690a707fdf56f6b40eb13933dc4d075e
|
| 3 |
size 1334459697
|
tokenizer.json
CHANGED
|
@@ -2,13 +2,13 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
-
"Fixed":
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
| 9 |
"padding": {
|
| 10 |
"strategy": {
|
| 11 |
+
"Fixed": 128
|
| 12 |
},
|
| 13 |
"direction": "Right",
|
| 14 |
"pad_to_multiple_of": null,
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 363846,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.19827925553449116,
|
| 4 |
+
"train_runtime": 10419.4099,
|
| 5 |
"train_samples": 363846,
|
| 6 |
+
"train_samples_per_second": 174.6,
|
| 7 |
+
"train_steps_per_second": 10.913
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,193 +1,1387 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch": 0.
|
| 12 |
-
"learning_rate":
|
| 13 |
-
"loss": 0.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch": 0.
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 0.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch": 0.
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch": 0.
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch": 0.
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"
|
| 43 |
-
"
|
| 44 |
-
"
|
| 45 |
-
|
| 46 |
-
|
| 47 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 48 |
},
|
| 49 |
{
|
| 50 |
"epoch": 1.06,
|
| 51 |
-
"learning_rate":
|
| 52 |
-
"loss": 0.
|
| 53 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 1.23,
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 0.
|
| 59 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 1.41,
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.58,
|
| 69 |
-
"learning_rate":
|
| 70 |
-
"loss": 0.
|
| 71 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 1.76,
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss": 0.
|
| 77 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 1.93,
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 2.0,
|
| 87 |
-
"
|
| 88 |
-
"
|
| 89 |
-
"
|
| 90 |
-
|
| 91 |
-
|
| 92 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
},
|
| 94 |
{
|
| 95 |
"epoch": 2.11,
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 2.29,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.46,
|
| 108 |
-
"learning_rate": 1.
|
| 109 |
-
"loss": 0.
|
| 110 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 2.64,
|
| 114 |
-
"learning_rate":
|
| 115 |
-
"loss": 0.
|
| 116 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 2.81,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 2.99,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
},
|
| 130 |
{
|
| 131 |
-
"epoch": 3.
|
| 132 |
-
"
|
| 133 |
-
"
|
| 134 |
-
"
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 138 |
},
|
| 139 |
{
|
| 140 |
"epoch": 3.17,
|
| 141 |
-
"learning_rate":
|
| 142 |
-
"loss": 0.
|
| 143 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 3.34,
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 3.52,
|
| 153 |
-
"learning_rate":
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 3.69,
|
| 159 |
-
"learning_rate":
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 3.87,
|
| 165 |
-
"learning_rate":
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
| 168 |
},
|
| 169 |
{
|
| 170 |
-
"epoch":
|
| 171 |
-
"
|
| 172 |
-
"
|
| 173 |
-
"
|
| 174 |
-
|
| 175 |
-
|
| 176 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 177 |
},
|
| 178 |
{
|
| 179 |
"epoch": 4.0,
|
| 180 |
-
"
|
| 181 |
-
"
|
| 182 |
-
"
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 186 |
}
|
| 187 |
],
|
| 188 |
-
"max_steps":
|
| 189 |
-
"num_train_epochs":
|
| 190 |
-
"total_flos":
|
| 191 |
"trial_name": null,
|
| 192 |
"trial_params": null
|
| 193 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 113705,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 1.991258080119608e-05,
|
| 13 |
+
"loss": 0.4639,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.982480981487182e-05,
|
| 19 |
+
"loss": 0.4082,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 1.973686293478739e-05,
|
| 25 |
+
"loss": 0.3774,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.09,
|
| 30 |
+
"learning_rate": 1.964891605470296e-05,
|
| 31 |
+
"loss": 0.3657,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.11,
|
| 36 |
+
"learning_rate": 1.9560969174618532e-05,
|
| 37 |
+
"loss": 0.3592,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.13,
|
| 42 |
+
"learning_rate": 1.9473022294534103e-05,
|
| 43 |
+
"loss": 0.3387,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.15,
|
| 48 |
+
"learning_rate": 1.9385075414449674e-05,
|
| 49 |
+
"loss": 0.33,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.18,
|
| 54 |
+
"learning_rate": 1.9297128534365245e-05,
|
| 55 |
+
"loss": 0.3314,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.2,
|
| 60 |
+
"learning_rate": 1.9209181654280816e-05,
|
| 61 |
+
"loss": 0.3259,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.22,
|
| 66 |
+
"learning_rate": 1.9121410667956555e-05,
|
| 67 |
+
"loss": 0.3168,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.24,
|
| 72 |
+
"learning_rate": 1.9033815575392464e-05,
|
| 73 |
+
"loss": 0.3161,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.26,
|
| 78 |
+
"learning_rate": 1.8945868695308035e-05,
|
| 79 |
+
"loss": 0.3235,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.29,
|
| 84 |
+
"learning_rate": 1.8857921815223606e-05,
|
| 85 |
+
"loss": 0.3226,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.31,
|
| 90 |
+
"learning_rate": 1.8769974935139177e-05,
|
| 91 |
+
"loss": 0.3136,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.33,
|
| 96 |
+
"learning_rate": 1.8682028055054748e-05,
|
| 97 |
+
"loss": 0.3053,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.35,
|
| 102 |
+
"learning_rate": 1.8594257068730488e-05,
|
| 103 |
+
"loss": 0.3108,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.37,
|
| 108 |
+
"learning_rate": 1.8506486082406228e-05,
|
| 109 |
+
"loss": 0.3164,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.4,
|
| 114 |
+
"learning_rate": 1.84185392023218e-05,
|
| 115 |
+
"loss": 0.3093,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.42,
|
| 120 |
+
"learning_rate": 1.833059232223737e-05,
|
| 121 |
+
"loss": 0.3174,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.44,
|
| 126 |
+
"learning_rate": 1.8242645442152944e-05,
|
| 127 |
+
"loss": 0.3108,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.46,
|
| 132 |
+
"learning_rate": 1.815469856206851e-05,
|
| 133 |
+
"loss": 0.3191,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.48,
|
| 138 |
+
"learning_rate": 1.8066751681984082e-05,
|
| 139 |
+
"loss": 0.3196,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.51,
|
| 144 |
+
"learning_rate": 1.7978804801899653e-05,
|
| 145 |
+
"loss": 0.3,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.53,
|
| 150 |
+
"learning_rate": 1.7890857921815227e-05,
|
| 151 |
+
"loss": 0.3108,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.55,
|
| 156 |
+
"learning_rate": 1.7802911041730798e-05,
|
| 157 |
+
"loss": 0.2959,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.57,
|
| 162 |
+
"learning_rate": 1.7715140055406538e-05,
|
| 163 |
+
"loss": 0.316,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.59,
|
| 168 |
+
"learning_rate": 1.7627193175322105e-05,
|
| 169 |
+
"loss": 0.3083,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.62,
|
| 174 |
+
"learning_rate": 1.753942218899785e-05,
|
| 175 |
+
"loss": 0.3106,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.64,
|
| 180 |
+
"learning_rate": 1.7451475308913416e-05,
|
| 181 |
+
"loss": 0.3212,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.66,
|
| 186 |
+
"learning_rate": 1.7363528428828987e-05,
|
| 187 |
+
"loss": 0.317,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.68,
|
| 192 |
+
"learning_rate": 1.727558154874456e-05,
|
| 193 |
+
"loss": 0.294,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.7,
|
| 198 |
+
"learning_rate": 1.7187634668660132e-05,
|
| 199 |
+
"loss": 0.3095,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.73,
|
| 204 |
+
"learning_rate": 1.70996877885757e-05,
|
| 205 |
+
"loss": 0.301,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.75,
|
| 210 |
+
"learning_rate": 1.701174090849127e-05,
|
| 211 |
+
"loss": 0.3031,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.77,
|
| 216 |
+
"learning_rate": 1.692396992216701e-05,
|
| 217 |
+
"loss": 0.3063,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.79,
|
| 222 |
+
"learning_rate": 1.683619893584275e-05,
|
| 223 |
+
"loss": 0.3068,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.81,
|
| 228 |
+
"learning_rate": 1.674825205575832e-05,
|
| 229 |
+
"loss": 0.3033,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.84,
|
| 234 |
+
"learning_rate": 1.6660305175673895e-05,
|
| 235 |
+
"loss": 0.2883,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.86,
|
| 240 |
+
"learning_rate": 1.6572358295589466e-05,
|
| 241 |
+
"loss": 0.3163,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.88,
|
| 246 |
+
"learning_rate": 1.6484411415505037e-05,
|
| 247 |
+
"loss": 0.3099,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.9,
|
| 252 |
+
"learning_rate": 1.6396464535420608e-05,
|
| 253 |
+
"loss": 0.3067,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.92,
|
| 258 |
+
"learning_rate": 1.630851765533618e-05,
|
| 259 |
+
"loss": 0.2882,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.95,
|
| 264 |
+
"learning_rate": 1.622057077525175e-05,
|
| 265 |
+
"loss": 0.2885,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.97,
|
| 270 |
+
"learning_rate": 1.613279978892749e-05,
|
| 271 |
+
"loss": 0.2953,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.99,
|
| 276 |
+
"learning_rate": 1.604485290884306e-05,
|
| 277 |
+
"loss": 0.2925,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.01,
|
| 282 |
+
"learning_rate": 1.595690602875863e-05,
|
| 283 |
+
"loss": 0.2615,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.03,
|
| 288 |
+
"learning_rate": 1.5868959148674202e-05,
|
| 289 |
+
"loss": 0.24,
|
| 290 |
+
"step": 23500
|
| 291 |
},
|
| 292 |
{
|
| 293 |
"epoch": 1.06,
|
| 294 |
+
"learning_rate": 1.5781188162349942e-05,
|
| 295 |
+
"loss": 0.2509,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.08,
|
| 300 |
+
"learning_rate": 1.5693241282265513e-05,
|
| 301 |
+
"loss": 0.2507,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.1,
|
| 306 |
+
"learning_rate": 1.5605294402181084e-05,
|
| 307 |
+
"loss": 0.252,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.12,
|
| 312 |
+
"learning_rate": 1.5517523415856824e-05,
|
| 313 |
+
"loss": 0.2545,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.14,
|
| 318 |
+
"learning_rate": 1.5429576535772395e-05,
|
| 319 |
+
"loss": 0.2599,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.17,
|
| 324 |
+
"learning_rate": 1.5341629655687966e-05,
|
| 325 |
+
"loss": 0.2566,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.19,
|
| 330 |
+
"learning_rate": 1.5253682775603538e-05,
|
| 331 |
+
"loss": 0.2484,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.21,
|
| 336 |
+
"learning_rate": 1.5165735895519107e-05,
|
| 337 |
+
"loss": 0.2432,
|
| 338 |
+
"step": 27500
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 1.23,
|
| 342 |
+
"learning_rate": 1.5077789015434678e-05,
|
| 343 |
+
"loss": 0.2415,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.25,
|
| 348 |
+
"learning_rate": 1.4989842135350249e-05,
|
| 349 |
+
"loss": 0.2489,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.28,
|
| 354 |
+
"learning_rate": 1.4902071149025989e-05,
|
| 355 |
+
"loss": 0.2566,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.3,
|
| 360 |
+
"learning_rate": 1.4814124268941562e-05,
|
| 361 |
+
"loss": 0.2382,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.32,
|
| 366 |
+
"learning_rate": 1.4726177388857132e-05,
|
| 367 |
+
"loss": 0.2458,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.34,
|
| 372 |
+
"learning_rate": 1.4638230508772702e-05,
|
| 373 |
+
"loss": 0.2559,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.36,
|
| 378 |
+
"learning_rate": 1.4550283628688272e-05,
|
| 379 |
+
"loss": 0.2402,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.39,
|
| 384 |
+
"learning_rate": 1.4462336748603845e-05,
|
| 385 |
+
"loss": 0.2447,
|
| 386 |
+
"step": 31500
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 1.41,
|
| 390 |
+
"learning_rate": 1.4374565762279585e-05,
|
| 391 |
+
"loss": 0.2605,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.43,
|
| 396 |
+
"learning_rate": 1.4286618882195156e-05,
|
| 397 |
+
"loss": 0.2605,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.45,
|
| 402 |
+
"learning_rate": 1.4198672002110727e-05,
|
| 403 |
+
"loss": 0.2499,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.47,
|
| 408 |
+
"learning_rate": 1.4110725122026296e-05,
|
| 409 |
+
"loss": 0.2409,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.5,
|
| 414 |
+
"learning_rate": 1.4022778241941868e-05,
|
| 415 |
+
"loss": 0.2371,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.52,
|
| 420 |
+
"learning_rate": 1.393483136185744e-05,
|
| 421 |
+
"loss": 0.2496,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.54,
|
| 426 |
+
"learning_rate": 1.384688448177301e-05,
|
| 427 |
+
"loss": 0.2351,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.56,
|
| 432 |
+
"learning_rate": 1.3758937601688583e-05,
|
| 433 |
+
"loss": 0.2348,
|
| 434 |
+
"step": 35500
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 1.58,
|
| 438 |
+
"learning_rate": 1.3670990721604152e-05,
|
| 439 |
+
"loss": 0.2343,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.61,
|
| 444 |
+
"learning_rate": 1.3583043841519723e-05,
|
| 445 |
+
"loss": 0.2425,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.63,
|
| 450 |
+
"learning_rate": 1.3495096961435294e-05,
|
| 451 |
+
"loss": 0.2331,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.65,
|
| 456 |
+
"learning_rate": 1.3407150081350866e-05,
|
| 457 |
+
"loss": 0.2353,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.67,
|
| 462 |
+
"learning_rate": 1.3319203201266435e-05,
|
| 463 |
+
"loss": 0.2353,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.69,
|
| 468 |
+
"learning_rate": 1.3231432214942177e-05,
|
| 469 |
+
"loss": 0.2304,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.71,
|
| 474 |
+
"learning_rate": 1.3143485334857746e-05,
|
| 475 |
+
"loss": 0.2303,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.74,
|
| 480 |
+
"learning_rate": 1.3055714348533486e-05,
|
| 481 |
+
"loss": 0.2327,
|
| 482 |
+
"step": 39500
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 1.76,
|
| 486 |
+
"learning_rate": 1.2967767468449057e-05,
|
| 487 |
+
"loss": 0.2417,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.78,
|
| 492 |
+
"learning_rate": 1.287982058836463e-05,
|
| 493 |
+
"loss": 0.2443,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.8,
|
| 498 |
+
"learning_rate": 1.27918737082802e-05,
|
| 499 |
+
"loss": 0.2372,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.82,
|
| 504 |
+
"learning_rate": 1.2703926828195771e-05,
|
| 505 |
+
"loss": 0.2461,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.85,
|
| 510 |
+
"learning_rate": 1.2616155841871511e-05,
|
| 511 |
+
"loss": 0.232,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.87,
|
| 516 |
+
"learning_rate": 1.2528384855547251e-05,
|
| 517 |
+
"loss": 0.2371,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.89,
|
| 522 |
+
"learning_rate": 1.2440437975462822e-05,
|
| 523 |
+
"loss": 0.2399,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.91,
|
| 528 |
+
"learning_rate": 1.2352491095378391e-05,
|
| 529 |
+
"loss": 0.2299,
|
| 530 |
+
"step": 43500
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 1.93,
|
| 534 |
+
"learning_rate": 1.2264544215293964e-05,
|
| 535 |
+
"loss": 0.2376,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.96,
|
| 540 |
+
"learning_rate": 1.2176597335209535e-05,
|
| 541 |
+
"loss": 0.2448,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.98,
|
| 546 |
+
"learning_rate": 1.2088650455125105e-05,
|
| 547 |
+
"loss": 0.2233,
|
| 548 |
+
"step": 45000
|
| 549 |
},
|
| 550 |
{
|
| 551 |
"epoch": 2.0,
|
| 552 |
+
"learning_rate": 1.2000703575040678e-05,
|
| 553 |
+
"loss": 0.2241,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.02,
|
| 558 |
+
"learning_rate": 1.1912756694956247e-05,
|
| 559 |
+
"loss": 0.1942,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.04,
|
| 564 |
+
"learning_rate": 1.1824985708631987e-05,
|
| 565 |
+
"loss": 0.1831,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.07,
|
| 570 |
+
"learning_rate": 1.1737038828547558e-05,
|
| 571 |
+
"loss": 0.1868,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.09,
|
| 576 |
+
"learning_rate": 1.1649091948463129e-05,
|
| 577 |
+
"loss": 0.2034,
|
| 578 |
+
"step": 47500
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 2.11,
|
| 582 |
+
"learning_rate": 1.1561145068378701e-05,
|
| 583 |
+
"loss": 0.1946,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 2.13,
|
| 588 |
+
"learning_rate": 1.1473198188294272e-05,
|
| 589 |
+
"loss": 0.194,
|
| 590 |
+
"step": 48500
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 2.15,
|
| 594 |
+
"learning_rate": 1.1385251308209841e-05,
|
| 595 |
+
"loss": 0.2068,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.18,
|
| 600 |
+
"learning_rate": 1.1297304428125412e-05,
|
| 601 |
+
"loss": 0.1832,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.2,
|
| 606 |
+
"learning_rate": 1.1209357548040985e-05,
|
| 607 |
+
"loss": 0.2023,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.22,
|
| 612 |
+
"learning_rate": 1.1121586561716725e-05,
|
| 613 |
+
"loss": 0.1985,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.24,
|
| 618 |
+
"learning_rate": 1.1033639681632296e-05,
|
| 619 |
+
"loss": 0.191,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.26,
|
| 624 |
+
"learning_rate": 1.0945692801547867e-05,
|
| 625 |
+
"loss": 0.208,
|
| 626 |
+
"step": 51500
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 2.29,
|
| 630 |
+
"learning_rate": 1.0857745921463436e-05,
|
| 631 |
+
"loss": 0.1998,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.31,
|
| 636 |
+
"learning_rate": 1.0769799041379008e-05,
|
| 637 |
+
"loss": 0.1927,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.33,
|
| 642 |
+
"learning_rate": 1.068185216129458e-05,
|
| 643 |
+
"loss": 0.2054,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.35,
|
| 648 |
+
"learning_rate": 1.059390528121015e-05,
|
| 649 |
+
"loss": 0.2038,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.37,
|
| 654 |
+
"learning_rate": 1.050613429488589e-05,
|
| 655 |
+
"loss": 0.193,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.4,
|
| 660 |
+
"learning_rate": 1.0418187414801462e-05,
|
| 661 |
+
"loss": 0.1929,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.42,
|
| 666 |
+
"learning_rate": 1.0330240534717032e-05,
|
| 667 |
+
"loss": 0.1936,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.44,
|
| 672 |
+
"learning_rate": 1.024246954839277e-05,
|
| 673 |
+
"loss": 0.1928,
|
| 674 |
+
"step": 55500
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 2.46,
|
| 678 |
+
"learning_rate": 1.0154522668308342e-05,
|
| 679 |
+
"loss": 0.1948,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.48,
|
| 684 |
+
"learning_rate": 1.0066575788223913e-05,
|
| 685 |
+
"loss": 0.2021,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.51,
|
| 690 |
+
"learning_rate": 9.978628908139484e-06,
|
| 691 |
+
"loss": 0.193,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.53,
|
| 696 |
+
"learning_rate": 9.890682028055055e-06,
|
| 697 |
+
"loss": 0.2027,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.55,
|
| 702 |
+
"learning_rate": 9.802911041730795e-06,
|
| 703 |
+
"loss": 0.2008,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.57,
|
| 708 |
+
"learning_rate": 9.714964161646366e-06,
|
| 709 |
+
"loss": 0.2006,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.59,
|
| 714 |
+
"learning_rate": 9.627017281561938e-06,
|
| 715 |
+
"loss": 0.1887,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.62,
|
| 720 |
+
"learning_rate": 9.539070401477508e-06,
|
| 721 |
+
"loss": 0.1946,
|
| 722 |
+
"step": 59500
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 2.64,
|
| 726 |
+
"learning_rate": 9.45112352139308e-06,
|
| 727 |
+
"loss": 0.1936,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.66,
|
| 732 |
+
"learning_rate": 9.36317664130865e-06,
|
| 733 |
+
"loss": 0.1924,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.68,
|
| 738 |
+
"learning_rate": 9.275229761224222e-06,
|
| 739 |
+
"loss": 0.184,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.7,
|
| 744 |
+
"learning_rate": 9.187282881139791e-06,
|
| 745 |
+
"loss": 0.1768,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.73,
|
| 750 |
+
"learning_rate": 9.099336001055364e-06,
|
| 751 |
+
"loss": 0.1845,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.75,
|
| 756 |
+
"learning_rate": 9.011565014731104e-06,
|
| 757 |
+
"loss": 0.1965,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.77,
|
| 762 |
+
"learning_rate": 8.923618134646674e-06,
|
| 763 |
+
"loss": 0.2004,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.79,
|
| 768 |
+
"learning_rate": 8.835671254562245e-06,
|
| 769 |
+
"loss": 0.1911,
|
| 770 |
+
"step": 63500
|
| 771 |
},
|
| 772 |
{
|
| 773 |
"epoch": 2.81,
|
| 774 |
+
"learning_rate": 8.747724374477816e-06,
|
| 775 |
+
"loss": 0.1842,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.84,
|
| 780 |
+
"learning_rate": 8.659777494393387e-06,
|
| 781 |
+
"loss": 0.1907,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.86,
|
| 786 |
+
"learning_rate": 8.571830614308958e-06,
|
| 787 |
+
"loss": 0.1883,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.88,
|
| 792 |
+
"learning_rate": 8.484059627984698e-06,
|
| 793 |
+
"loss": 0.1876,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.9,
|
| 798 |
+
"learning_rate": 8.396112747900269e-06,
|
| 799 |
+
"loss": 0.1846,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.92,
|
| 804 |
+
"learning_rate": 8.308341761576009e-06,
|
| 805 |
+
"loss": 0.1939,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.95,
|
| 810 |
+
"learning_rate": 8.22039488149158e-06,
|
| 811 |
+
"loss": 0.1896,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.97,
|
| 816 |
+
"learning_rate": 8.13244800140715e-06,
|
| 817 |
+
"loss": 0.1957,
|
| 818 |
+
"step": 67500
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 2.99,
|
| 822 |
+
"learning_rate": 8.044501121322721e-06,
|
| 823 |
+
"loss": 0.1881,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.01,
|
| 828 |
+
"learning_rate": 7.956554241238292e-06,
|
| 829 |
+
"loss": 0.1611,
|
| 830 |
+
"step": 68500
|
| 831 |
},
|
| 832 |
{
|
| 833 |
+
"epoch": 3.03,
|
| 834 |
+
"learning_rate": 7.868607361153865e-06,
|
| 835 |
+
"loss": 0.1423,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 3.06,
|
| 840 |
+
"learning_rate": 7.780660481069434e-06,
|
| 841 |
+
"loss": 0.1419,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 3.08,
|
| 846 |
+
"learning_rate": 7.692889494745175e-06,
|
| 847 |
+
"loss": 0.1384,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 3.1,
|
| 852 |
+
"learning_rate": 7.6051185084209144e-06,
|
| 853 |
+
"loss": 0.1436,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 3.12,
|
| 858 |
+
"learning_rate": 7.5171716283364845e-06,
|
| 859 |
+
"loss": 0.1357,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 3.14,
|
| 864 |
+
"learning_rate": 7.429224748252056e-06,
|
| 865 |
+
"loss": 0.1481,
|
| 866 |
+
"step": 71500
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 3.17,
|
| 870 |
+
"learning_rate": 7.341277868167628e-06,
|
| 871 |
+
"loss": 0.1402,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 3.19,
|
| 876 |
+
"learning_rate": 7.253330988083198e-06,
|
| 877 |
+
"loss": 0.142,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 3.21,
|
| 882 |
+
"learning_rate": 7.16538410799877e-06,
|
| 883 |
+
"loss": 0.1518,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 3.23,
|
| 888 |
+
"learning_rate": 7.07743722791434e-06,
|
| 889 |
+
"loss": 0.1507,
|
| 890 |
+
"step": 73500
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 3.25,
|
| 894 |
+
"learning_rate": 6.9894903478299114e-06,
|
| 895 |
+
"loss": 0.1481,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.28,
|
| 900 |
+
"learning_rate": 6.9015434677454815e-06,
|
| 901 |
+
"loss": 0.1415,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.3,
|
| 906 |
+
"learning_rate": 6.813596587661053e-06,
|
| 907 |
+
"loss": 0.1392,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.32,
|
| 912 |
+
"learning_rate": 6.725649707576625e-06,
|
| 913 |
+
"loss": 0.1374,
|
| 914 |
+
"step": 75500
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 3.34,
|
| 918 |
+
"learning_rate": 6.637878721252364e-06,
|
| 919 |
+
"loss": 0.1434,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.36,
|
| 924 |
+
"learning_rate": 6.549931841167935e-06,
|
| 925 |
+
"loss": 0.1423,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.39,
|
| 930 |
+
"learning_rate": 6.4619849610835065e-06,
|
| 931 |
+
"loss": 0.1455,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.41,
|
| 936 |
+
"learning_rate": 6.374038080999077e-06,
|
| 937 |
+
"loss": 0.1464,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.43,
|
| 942 |
+
"learning_rate": 6.286091200914648e-06,
|
| 943 |
+
"loss": 0.1461,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.45,
|
| 948 |
+
"learning_rate": 6.198144320830219e-06,
|
| 949 |
+
"loss": 0.1385,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.47,
|
| 954 |
+
"learning_rate": 6.11019744074579e-06,
|
| 955 |
+
"loss": 0.1474,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.5,
|
| 960 |
+
"learning_rate": 6.022250560661361e-06,
|
| 961 |
+
"loss": 0.1498,
|
| 962 |
+
"step": 79500
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 3.52,
|
| 966 |
+
"learning_rate": 5.934303680576932e-06,
|
| 967 |
+
"loss": 0.1375,
|
| 968 |
+
"step": 80000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.54,
|
| 972 |
+
"learning_rate": 5.8465326942526725e-06,
|
| 973 |
+
"loss": 0.1407,
|
| 974 |
+
"step": 80500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.56,
|
| 978 |
+
"learning_rate": 5.7585858141682426e-06,
|
| 979 |
+
"loss": 0.1389,
|
| 980 |
+
"step": 81000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.58,
|
| 984 |
+
"learning_rate": 5.670638934083814e-06,
|
| 985 |
+
"loss": 0.139,
|
| 986 |
+
"step": 81500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.61,
|
| 990 |
+
"learning_rate": 5.582692053999384e-06,
|
| 991 |
+
"loss": 0.142,
|
| 992 |
+
"step": 82000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.63,
|
| 996 |
+
"learning_rate": 5.494921067675124e-06,
|
| 997 |
+
"loss": 0.1346,
|
| 998 |
+
"step": 82500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.65,
|
| 1002 |
+
"learning_rate": 5.406974187590696e-06,
|
| 1003 |
+
"loss": 0.1462,
|
| 1004 |
+
"step": 83000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.67,
|
| 1008 |
+
"learning_rate": 5.319027307506267e-06,
|
| 1009 |
+
"loss": 0.131,
|
| 1010 |
+
"step": 83500
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 3.69,
|
| 1014 |
+
"learning_rate": 5.231080427421838e-06,
|
| 1015 |
+
"loss": 0.1475,
|
| 1016 |
+
"step": 84000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.72,
|
| 1020 |
+
"learning_rate": 5.1431335473374086e-06,
|
| 1021 |
+
"loss": 0.137,
|
| 1022 |
+
"step": 84500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.74,
|
| 1026 |
+
"learning_rate": 5.0551866672529794e-06,
|
| 1027 |
+
"loss": 0.1337,
|
| 1028 |
+
"step": 85000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.76,
|
| 1032 |
+
"learning_rate": 4.96723978716855e-06,
|
| 1033 |
+
"loss": 0.1399,
|
| 1034 |
+
"step": 85500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.78,
|
| 1038 |
+
"learning_rate": 4.879292907084122e-06,
|
| 1039 |
+
"loss": 0.1404,
|
| 1040 |
+
"step": 86000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.8,
|
| 1044 |
+
"learning_rate": 4.791346026999693e-06,
|
| 1045 |
+
"loss": 0.1428,
|
| 1046 |
+
"step": 86500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.83,
|
| 1050 |
+
"learning_rate": 4.703399146915264e-06,
|
| 1051 |
+
"loss": 0.1446,
|
| 1052 |
+
"step": 87000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.85,
|
| 1056 |
+
"learning_rate": 4.615452266830835e-06,
|
| 1057 |
+
"loss": 0.1384,
|
| 1058 |
+
"step": 87500
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 3.87,
|
| 1062 |
+
"learning_rate": 4.5275053867464056e-06,
|
| 1063 |
+
"loss": 0.1483,
|
| 1064 |
+
"step": 88000
|
| 1065 |
},
|
| 1066 |
{
|
| 1067 |
+
"epoch": 3.89,
|
| 1068 |
+
"learning_rate": 4.4397344004221454e-06,
|
| 1069 |
+
"loss": 0.1473,
|
| 1070 |
+
"step": 88500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.91,
|
| 1074 |
+
"learning_rate": 4.351787520337716e-06,
|
| 1075 |
+
"loss": 0.1446,
|
| 1076 |
+
"step": 89000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.94,
|
| 1080 |
+
"learning_rate": 4.263840640253287e-06,
|
| 1081 |
+
"loss": 0.1419,
|
| 1082 |
+
"step": 89500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.96,
|
| 1086 |
+
"learning_rate": 4.175893760168858e-06,
|
| 1087 |
+
"loss": 0.133,
|
| 1088 |
+
"step": 90000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.98,
|
| 1092 |
+
"learning_rate": 4.087946880084429e-06,
|
| 1093 |
+
"loss": 0.144,
|
| 1094 |
+
"step": 90500
|
| 1095 |
},
|
| 1096 |
{
|
| 1097 |
"epoch": 4.0,
|
| 1098 |
+
"learning_rate": 4.000000000000001e-06,
|
| 1099 |
+
"loss": 0.1252,
|
| 1100 |
+
"step": 91000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 4.02,
|
| 1104 |
+
"learning_rate": 3.9122290136757405e-06,
|
| 1105 |
+
"loss": 0.1003,
|
| 1106 |
+
"step": 91500
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 4.05,
|
| 1110 |
+
"learning_rate": 3.8244580273514796e-06,
|
| 1111 |
+
"loss": 0.0883,
|
| 1112 |
+
"step": 92000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 4.07,
|
| 1116 |
+
"learning_rate": 3.7365111472670513e-06,
|
| 1117 |
+
"loss": 0.0914,
|
| 1118 |
+
"step": 92500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 4.09,
|
| 1122 |
+
"learning_rate": 3.648564267182622e-06,
|
| 1123 |
+
"loss": 0.1104,
|
| 1124 |
+
"step": 93000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 4.11,
|
| 1128 |
+
"learning_rate": 3.560617387098193e-06,
|
| 1129 |
+
"loss": 0.0859,
|
| 1130 |
+
"step": 93500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 4.13,
|
| 1134 |
+
"learning_rate": 3.472670507013764e-06,
|
| 1135 |
+
"loss": 0.0992,
|
| 1136 |
+
"step": 94000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 4.16,
|
| 1140 |
+
"learning_rate": 3.384723626929335e-06,
|
| 1141 |
+
"loss": 0.088,
|
| 1142 |
+
"step": 94500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 4.18,
|
| 1146 |
+
"learning_rate": 3.296952640605075e-06,
|
| 1147 |
+
"loss": 0.0973,
|
| 1148 |
+
"step": 95000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 4.2,
|
| 1152 |
+
"learning_rate": 3.209005760520646e-06,
|
| 1153 |
+
"loss": 0.0972,
|
| 1154 |
+
"step": 95500
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 4.22,
|
| 1158 |
+
"learning_rate": 3.121058880436217e-06,
|
| 1159 |
+
"loss": 0.0971,
|
| 1160 |
+
"step": 96000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 4.24,
|
| 1164 |
+
"learning_rate": 3.0331120003517877e-06,
|
| 1165 |
+
"loss": 0.096,
|
| 1166 |
+
"step": 96500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 4.27,
|
| 1170 |
+
"learning_rate": 2.9451651202673586e-06,
|
| 1171 |
+
"loss": 0.1011,
|
| 1172 |
+
"step": 97000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 4.29,
|
| 1176 |
+
"learning_rate": 2.857394133943099e-06,
|
| 1177 |
+
"loss": 0.094,
|
| 1178 |
+
"step": 97500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 4.31,
|
| 1182 |
+
"learning_rate": 2.76944725385867e-06,
|
| 1183 |
+
"loss": 0.0998,
|
| 1184 |
+
"step": 98000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.33,
|
| 1188 |
+
"learning_rate": 2.6815003737742407e-06,
|
| 1189 |
+
"loss": 0.0833,
|
| 1190 |
+
"step": 98500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 4.35,
|
| 1194 |
+
"learning_rate": 2.5935534936898116e-06,
|
| 1195 |
+
"loss": 0.103,
|
| 1196 |
+
"step": 99000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 4.38,
|
| 1200 |
+
"learning_rate": 2.5056066136053824e-06,
|
| 1201 |
+
"loss": 0.0897,
|
| 1202 |
+
"step": 99500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.4,
|
| 1206 |
+
"learning_rate": 2.4176597335209537e-06,
|
| 1207 |
+
"loss": 0.1012,
|
| 1208 |
+
"step": 100000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 4.42,
|
| 1212 |
+
"learning_rate": 2.3297128534365246e-06,
|
| 1213 |
+
"loss": 0.0923,
|
| 1214 |
+
"step": 100500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.44,
|
| 1218 |
+
"learning_rate": 2.2419418671122645e-06,
|
| 1219 |
+
"loss": 0.0899,
|
| 1220 |
+
"step": 101000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.46,
|
| 1224 |
+
"learning_rate": 2.1539949870278354e-06,
|
| 1225 |
+
"loss": 0.0842,
|
| 1226 |
+
"step": 101500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 4.49,
|
| 1230 |
+
"learning_rate": 2.0660481069434063e-06,
|
| 1231 |
+
"loss": 0.0961,
|
| 1232 |
+
"step": 102000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.51,
|
| 1236 |
+
"learning_rate": 1.978101226858977e-06,
|
| 1237 |
+
"loss": 0.0979,
|
| 1238 |
+
"step": 102500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 4.53,
|
| 1242 |
+
"learning_rate": 1.890330240534717e-06,
|
| 1243 |
+
"loss": 0.0957,
|
| 1244 |
+
"step": 103000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 4.55,
|
| 1248 |
+
"learning_rate": 1.8025592542104569e-06,
|
| 1249 |
+
"loss": 0.0897,
|
| 1250 |
+
"step": 103500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.57,
|
| 1254 |
+
"learning_rate": 1.7146123741260282e-06,
|
| 1255 |
+
"loss": 0.0739,
|
| 1256 |
+
"step": 104000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.6,
|
| 1260 |
+
"learning_rate": 1.626665494041599e-06,
|
| 1261 |
+
"loss": 0.094,
|
| 1262 |
+
"step": 104500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.62,
|
| 1266 |
+
"learning_rate": 1.53871861395717e-06,
|
| 1267 |
+
"loss": 0.0981,
|
| 1268 |
+
"step": 105000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.64,
|
| 1272 |
+
"learning_rate": 1.4507717338727408e-06,
|
| 1273 |
+
"loss": 0.0828,
|
| 1274 |
+
"step": 105500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.66,
|
| 1278 |
+
"learning_rate": 1.3628248537883121e-06,
|
| 1279 |
+
"loss": 0.0993,
|
| 1280 |
+
"step": 106000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.68,
|
| 1284 |
+
"learning_rate": 1.274877973703883e-06,
|
| 1285 |
+
"loss": 0.0916,
|
| 1286 |
+
"step": 106500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 4.71,
|
| 1290 |
+
"learning_rate": 1.1869310936194539e-06,
|
| 1291 |
+
"loss": 0.1046,
|
| 1292 |
+
"step": 107000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 4.73,
|
| 1296 |
+
"learning_rate": 1.0991601072951938e-06,
|
| 1297 |
+
"loss": 0.0912,
|
| 1298 |
+
"step": 107500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.75,
|
| 1302 |
+
"learning_rate": 1.0112132272107648e-06,
|
| 1303 |
+
"loss": 0.0969,
|
| 1304 |
+
"step": 108000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.77,
|
| 1308 |
+
"learning_rate": 9.232663471263357e-07,
|
| 1309 |
+
"loss": 0.0879,
|
| 1310 |
+
"step": 108500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.79,
|
| 1314 |
+
"learning_rate": 8.353194670419068e-07,
|
| 1315 |
+
"loss": 0.0982,
|
| 1316 |
+
"step": 109000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.82,
|
| 1320 |
+
"learning_rate": 7.473725869574777e-07,
|
| 1321 |
+
"loss": 0.0853,
|
| 1322 |
+
"step": 109500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.84,
|
| 1326 |
+
"learning_rate": 6.594257068730488e-07,
|
| 1327 |
+
"loss": 0.0958,
|
| 1328 |
+
"step": 110000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 4.86,
|
| 1332 |
+
"learning_rate": 5.714788267886198e-07,
|
| 1333 |
+
"loss": 0.1026,
|
| 1334 |
+
"step": 110500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 4.88,
|
| 1338 |
+
"learning_rate": 4.835319467041907e-07,
|
| 1339 |
+
"loss": 0.0867,
|
| 1340 |
+
"step": 111000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 4.9,
|
| 1344 |
+
"learning_rate": 3.9558506661976173e-07,
|
| 1345 |
+
"loss": 0.0976,
|
| 1346 |
+
"step": 111500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.93,
|
| 1350 |
+
"learning_rate": 3.076381865353327e-07,
|
| 1351 |
+
"loss": 0.0966,
|
| 1352 |
+
"step": 112000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 4.95,
|
| 1356 |
+
"learning_rate": 2.1986720021107254e-07,
|
| 1357 |
+
"loss": 0.0911,
|
| 1358 |
+
"step": 112500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.97,
|
| 1362 |
+
"learning_rate": 1.3209621388681237e-07,
|
| 1363 |
+
"loss": 0.0931,
|
| 1364 |
+
"step": 113000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 4.99,
|
| 1368 |
+
"learning_rate": 4.414933380238336e-08,
|
| 1369 |
+
"loss": 0.0943,
|
| 1370 |
+
"step": 113500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 5.0,
|
| 1374 |
+
"step": 113705,
|
| 1375 |
+
"total_flos": 4.2384937352679936e+17,
|
| 1376 |
+
"train_loss": 0.19827925553449116,
|
| 1377 |
+
"train_runtime": 10419.4099,
|
| 1378 |
+
"train_samples_per_second": 174.6,
|
| 1379 |
+
"train_steps_per_second": 10.913
|
| 1380 |
}
|
| 1381 |
],
|
| 1382 |
+
"max_steps": 113705,
|
| 1383 |
+
"num_train_epochs": 5,
|
| 1384 |
+
"total_flos": 4.2384937352679936e+17,
|
| 1385 |
"trial_name": null,
|
| 1386 |
"trial_params": null
|
| 1387 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:760fe693984347cb90ffd1b835dab78653fb190c76695d0548197b645f8c8c4d
|
| 3 |
+
size 3963
|