Upload folder using huggingface_hub
Browse files- README.md +23 -16
- all_results.json +17 -10
- config.json +7 -7
- eval_results.json +13 -6
- pytorch_model.bin +1 -1
- tokenizer.json +2 -2
- train_results.json +5 -5
- trainer_state.json +1399 -109
- training_args.bin +2 -2
README.md
CHANGED
|
@@ -1,13 +1,28 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
base_model: bert-base-cased
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- accuracy
|
| 8 |
model-index:
|
| 9 |
- name: bert-base-mnli
|
| 10 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -15,10 +30,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# bert-base-mnli
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-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 +52,16 @@ More information needed
|
|
| 37 |
### Training hyperparameters
|
| 38 |
|
| 39 |
The following hyperparameters were used during training:
|
| 40 |
-
- learning_rate:
|
| 41 |
-
- train_batch_size:
|
| 42 |
-
- eval_batch_size:
|
| 43 |
- seed: 42
|
| 44 |
-
- gradient_accumulation_steps: 4
|
| 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 |
-
| 0.4804 | 1.0 | 3068 | 0.4623 | 0.8203 |
|
| 55 |
-
| 0.3583 | 2.0 | 6136 | 0.4524 | 0.8310 |
|
| 56 |
-
| 0.2257 | 3.0 | 9204 | 0.5004 | 0.8346 |
|
| 57 |
-
| 0.1402 | 4.0 | 12272 | 0.6083 | 0.8332 |
|
| 58 |
|
| 59 |
|
| 60 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: apache-2.0
|
| 5 |
base_model: bert-base-cased
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- glue
|
| 10 |
metrics:
|
| 11 |
- accuracy
|
| 12 |
model-index:
|
| 13 |
- name: bert-base-mnli
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Text Classification
|
| 17 |
+
type: text-classification
|
| 18 |
+
dataset:
|
| 19 |
+
name: GLUE MNLI
|
| 20 |
+
type: glue
|
| 21 |
+
args: mnli
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Accuracy
|
| 24 |
+
type: accuracy
|
| 25 |
+
value: 0.8389951179820992
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 30 |
|
| 31 |
# bert-base-mnli
|
| 32 |
|
| 33 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on the GLUE MNLI dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.8833
|
| 36 |
+
- Accuracy: 0.8390
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 52 |
### Training hyperparameters
|
| 53 |
|
| 54 |
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 2e-05
|
| 56 |
+
- train_batch_size: 16
|
| 57 |
+
- eval_batch_size: 8
|
| 58 |
- seed: 42
|
|
|
|
|
|
|
| 59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 60 |
- lr_scheduler_type: linear
|
| 61 |
+
- num_epochs: 5.0
|
| 62 |
|
| 63 |
### Training results
|
| 64 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 65 |
|
| 66 |
|
| 67 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,14 +1,21 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"eval_samples": 9815,
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
|
|
|
|
|
|
| 11 |
"train_samples": 392702,
|
| 12 |
-
"train_samples_per_second":
|
| 13 |
-
"train_steps_per_second":
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"epoch_mm": 5.0,
|
| 4 |
+
"eval_accuracy": 0.8290371879775853,
|
| 5 |
+
"eval_accuracy_mm": 0.8389951179820992,
|
| 6 |
+
"eval_loss": 0.9189786314964294,
|
| 7 |
+
"eval_loss_mm": 0.8832867741584778,
|
| 8 |
+
"eval_runtime": 25.381,
|
| 9 |
+
"eval_runtime_mm": 25.3405,
|
| 10 |
"eval_samples": 9815,
|
| 11 |
+
"eval_samples_mm": 9832,
|
| 12 |
+
"eval_samples_per_second": 386.706,
|
| 13 |
+
"eval_samples_per_second_mm": 387.995,
|
| 14 |
+
"eval_steps_per_second": 48.343,
|
| 15 |
+
"eval_steps_per_second_mm": 48.499,
|
| 16 |
+
"train_loss": 0.2863727584966936,
|
| 17 |
+
"train_runtime": 10219.2193,
|
| 18 |
"train_samples": 392702,
|
| 19 |
+
"train_samples_per_second": 192.139,
|
| 20 |
+
"train_steps_per_second": 12.009
|
| 21 |
}
|
config.json
CHANGED
|
@@ -5,22 +5,22 @@
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
-
"finetuning_task": "
|
| 9 |
"gradient_checkpointing": false,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"id2label": {
|
| 14 |
-
"0": "
|
| 15 |
-
"1": "
|
| 16 |
-
"2": "
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 3072,
|
| 20 |
"label2id": {
|
| 21 |
-
"
|
| 22 |
-
"
|
| 23 |
-
"
|
| 24 |
},
|
| 25 |
"layer_norm_eps": 1e-12,
|
| 26 |
"max_position_embeddings": 512,
|
|
|
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"finetuning_task": "mnli",
|
| 9 |
"gradient_checkpointing": false,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
"hidden_size": 768,
|
| 13 |
"id2label": {
|
| 14 |
+
"0": "entailment",
|
| 15 |
+
"1": "neutral",
|
| 16 |
+
"2": "contradiction"
|
| 17 |
},
|
| 18 |
"initializer_range": 0.02,
|
| 19 |
"intermediate_size": 3072,
|
| 20 |
"label2id": {
|
| 21 |
+
"contradiction": 2,
|
| 22 |
+
"entailment": 0,
|
| 23 |
+
"neutral": 1
|
| 24 |
},
|
| 25 |
"layer_norm_eps": 1e-12,
|
| 26 |
"max_position_embeddings": 512,
|
eval_results.json
CHANGED
|
@@ -1,9 +1,16 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"
|
| 4 |
-
"
|
| 5 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"eval_samples": 9815,
|
| 7 |
-
"
|
| 8 |
-
"
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"epoch_mm": 5.0,
|
| 4 |
+
"eval_accuracy": 0.8290371879775853,
|
| 5 |
+
"eval_accuracy_mm": 0.8389951179820992,
|
| 6 |
+
"eval_loss": 0.9189786314964294,
|
| 7 |
+
"eval_loss_mm": 0.8832867741584778,
|
| 8 |
+
"eval_runtime": 25.381,
|
| 9 |
+
"eval_runtime_mm": 25.3405,
|
| 10 |
"eval_samples": 9815,
|
| 11 |
+
"eval_samples_mm": 9832,
|
| 12 |
+
"eval_samples_per_second": 386.706,
|
| 13 |
+
"eval_samples_per_second_mm": 387.995,
|
| 14 |
+
"eval_steps_per_second": 48.343,
|
| 15 |
+
"eval_steps_per_second_mm": 48.499
|
| 16 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 433318705
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f77934a4045ad9d09f4af0735e7545cf46edb772d7294c897306751f4ff330dc
|
| 3 |
size 433318705
|
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": 392702,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.2863727584966936,
|
| 4 |
+
"train_runtime": 10219.2193,
|
| 5 |
"train_samples": 392702,
|
| 6 |
+
"train_samples_per_second": 192.139,
|
| 7 |
+
"train_steps_per_second": 12.009
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,205 +1,1495 @@
|
|
| 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": 0.
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 3000
|
| 45 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 46 |
{
|
| 47 |
"epoch": 1.0,
|
| 48 |
-
"
|
| 49 |
-
"
|
| 50 |
-
"
|
| 51 |
-
|
| 52 |
-
|
| 53 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
},
|
| 55 |
{
|
| 56 |
"epoch": 1.14,
|
| 57 |
-
"learning_rate":
|
| 58 |
-
"loss": 0.
|
| 59 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
},
|
| 61 |
{
|
| 62 |
"epoch": 1.3,
|
| 63 |
-
"learning_rate":
|
| 64 |
-
"loss": 0.
|
| 65 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 66 |
},
|
| 67 |
{
|
| 68 |
"epoch": 1.47,
|
| 69 |
-
"learning_rate":
|
| 70 |
"loss": 0.3614,
|
| 71 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 72 |
},
|
| 73 |
{
|
| 74 |
"epoch": 1.63,
|
| 75 |
-
"learning_rate":
|
| 76 |
-
"loss": 0.
|
| 77 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 78 |
},
|
| 79 |
{
|
| 80 |
"epoch": 1.79,
|
| 81 |
-
"learning_rate":
|
| 82 |
-
"loss": 0.
|
| 83 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
},
|
| 85 |
{
|
| 86 |
"epoch": 1.96,
|
| 87 |
-
"learning_rate":
|
| 88 |
-
"loss": 0.
|
| 89 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 90 |
},
|
| 91 |
{
|
| 92 |
"epoch": 2.0,
|
| 93 |
-
"
|
| 94 |
-
"
|
| 95 |
-
"
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 99 |
},
|
| 100 |
{
|
| 101 |
"epoch": 2.12,
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 105 |
},
|
| 106 |
{
|
| 107 |
"epoch": 2.28,
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 2.44,
|
| 114 |
-
"learning_rate": 1.
|
| 115 |
-
"loss": 0.
|
| 116 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 117 |
},
|
| 118 |
{
|
| 119 |
"epoch": 2.61,
|
| 120 |
-
"learning_rate":
|
| 121 |
-
"loss": 0.
|
| 122 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 123 |
},
|
| 124 |
{
|
| 125 |
"epoch": 2.77,
|
| 126 |
-
"learning_rate":
|
| 127 |
-
"loss": 0.
|
| 128 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 129 |
},
|
| 130 |
{
|
| 131 |
"epoch": 2.93,
|
| 132 |
-
"learning_rate":
|
| 133 |
-
"loss": 0.
|
| 134 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 135 |
},
|
| 136 |
{
|
| 137 |
-
"epoch": 3.
|
| 138 |
-
"
|
| 139 |
-
"
|
| 140 |
-
"
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 144 |
},
|
| 145 |
{
|
| 146 |
"epoch": 3.1,
|
| 147 |
-
"learning_rate":
|
| 148 |
-
"loss": 0.
|
| 149 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 150 |
},
|
| 151 |
{
|
| 152 |
"epoch": 3.26,
|
| 153 |
-
"learning_rate":
|
| 154 |
-
"loss": 0.
|
| 155 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
},
|
| 157 |
{
|
| 158 |
"epoch": 3.42,
|
| 159 |
-
"learning_rate":
|
| 160 |
-
"loss": 0.
|
| 161 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
},
|
| 163 |
{
|
| 164 |
"epoch": 3.59,
|
| 165 |
-
"learning_rate": 5.
|
| 166 |
-
"loss": 0.
|
| 167 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 168 |
},
|
| 169 |
{
|
| 170 |
"epoch": 3.75,
|
| 171 |
-
"learning_rate":
|
| 172 |
-
"loss": 0.
|
| 173 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
},
|
| 175 |
{
|
| 176 |
"epoch": 3.91,
|
| 177 |
-
"learning_rate":
|
| 178 |
-
"loss": 0.
|
| 179 |
-
"step":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 180 |
},
|
| 181 |
{
|
| 182 |
-
"epoch": 4.
|
| 183 |
-
"
|
| 184 |
-
"
|
| 185 |
-
"
|
| 186 |
-
"eval_samples_per_second": 318.04,
|
| 187 |
-
"eval_steps_per_second": 4.99,
|
| 188 |
-
"step": 12272
|
| 189 |
},
|
| 190 |
{
|
| 191 |
-
"epoch":
|
| 192 |
-
"step":
|
| 193 |
-
"total_flos":
|
| 194 |
-
"train_loss": 0.
|
| 195 |
-
"train_runtime":
|
| 196 |
-
"train_samples_per_second":
|
| 197 |
-
"train_steps_per_second":
|
| 198 |
}
|
| 199 |
],
|
| 200 |
-
"max_steps":
|
| 201 |
-
"num_train_epochs":
|
| 202 |
-
"total_flos":
|
| 203 |
"trial_name": null,
|
| 204 |
"trial_params": null
|
| 205 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"global_step": 122720,
|
| 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": 1.991900260756193e-05,
|
| 13 |
+
"loss": 0.8698,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.983751629726206e-05,
|
| 19 |
+
"loss": 0.7184,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 0.06,
|
| 24 |
+
"learning_rate": 1.9756029986962192e-05,
|
| 25 |
+
"loss": 0.6715,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 0.08,
|
| 30 |
+
"learning_rate": 1.9674543676662323e-05,
|
| 31 |
+
"loss": 0.6418,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 0.1,
|
| 36 |
+
"learning_rate": 1.9593057366362454e-05,
|
| 37 |
+
"loss": 0.6175,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"learning_rate": 1.9511734028683183e-05,
|
| 43 |
+
"loss": 0.6239,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14,
|
| 48 |
+
"learning_rate": 1.9430247718383314e-05,
|
| 49 |
+
"loss": 0.5822,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.16,
|
| 54 |
+
"learning_rate": 1.9348761408083442e-05,
|
| 55 |
+
"loss": 0.5878,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.18,
|
| 60 |
+
"learning_rate": 1.9267275097783573e-05,
|
| 61 |
+
"loss": 0.5581,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.2,
|
| 66 |
+
"learning_rate": 1.9185788787483704e-05,
|
| 67 |
+
"loss": 0.5579,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.22,
|
| 72 |
+
"learning_rate": 1.9104302477183832e-05,
|
| 73 |
+
"loss": 0.5577,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.24,
|
| 78 |
+
"learning_rate": 1.9022816166883967e-05,
|
| 79 |
+
"loss": 0.5564,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.26,
|
| 84 |
+
"learning_rate": 1.8941329856584098e-05,
|
| 85 |
+
"loss": 0.5554,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.29,
|
| 90 |
+
"learning_rate": 1.8860006518904827e-05,
|
| 91 |
+
"loss": 0.5376,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.31,
|
| 96 |
+
"learning_rate": 1.8778520208604955e-05,
|
| 97 |
+
"loss": 0.5277,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.33,
|
| 102 |
+
"learning_rate": 1.8697033898305086e-05,
|
| 103 |
+
"loss": 0.5205,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.35,
|
| 108 |
+
"learning_rate": 1.8615547588005217e-05,
|
| 109 |
+
"loss": 0.5252,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.37,
|
| 114 |
+
"learning_rate": 1.8534061277705345e-05,
|
| 115 |
+
"loss": 0.5378,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.39,
|
| 120 |
+
"learning_rate": 1.8452737940026077e-05,
|
| 121 |
+
"loss": 0.5264,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.41,
|
| 126 |
+
"learning_rate": 1.837125162972621e-05,
|
| 127 |
+
"loss": 0.524,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.43,
|
| 132 |
+
"learning_rate": 1.828976531942634e-05,
|
| 133 |
+
"loss": 0.5101,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.45,
|
| 138 |
+
"learning_rate": 1.8208279009126467e-05,
|
| 139 |
+
"loss": 0.5028,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.47,
|
| 144 |
+
"learning_rate": 1.81267926988266e-05,
|
| 145 |
+
"loss": 0.5145,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.49,
|
| 150 |
+
"learning_rate": 1.804546936114733e-05,
|
| 151 |
+
"loss": 0.5175,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.51,
|
| 156 |
+
"learning_rate": 1.796398305084746e-05,
|
| 157 |
+
"loss": 0.5091,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.53,
|
| 162 |
+
"learning_rate": 1.788249674054759e-05,
|
| 163 |
+
"loss": 0.502,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.55,
|
| 168 |
+
"learning_rate": 1.780101043024772e-05,
|
| 169 |
+
"loss": 0.5066,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.57,
|
| 174 |
+
"learning_rate": 1.7719524119947852e-05,
|
| 175 |
+
"loss": 0.5093,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 0.59,
|
| 180 |
+
"learning_rate": 1.763803780964798e-05,
|
| 181 |
+
"loss": 0.5021,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.61,
|
| 186 |
+
"learning_rate": 1.755655149934811e-05,
|
| 187 |
+
"loss": 0.5129,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.63,
|
| 192 |
+
"learning_rate": 1.747522816166884e-05,
|
| 193 |
+
"loss": 0.4993,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.65,
|
| 198 |
+
"learning_rate": 1.739374185136897e-05,
|
| 199 |
+
"loss": 0.4913,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.67,
|
| 204 |
+
"learning_rate": 1.7312255541069102e-05,
|
| 205 |
+
"loss": 0.4961,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.69,
|
| 210 |
+
"learning_rate": 1.7230769230769234e-05,
|
| 211 |
+
"loss": 0.4865,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.71,
|
| 216 |
+
"learning_rate": 1.7149282920469365e-05,
|
| 217 |
+
"loss": 0.5059,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.73,
|
| 222 |
+
"learning_rate": 1.7067796610169493e-05,
|
| 223 |
+
"loss": 0.5019,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.75,
|
| 228 |
+
"learning_rate": 1.6986310299869624e-05,
|
| 229 |
+
"loss": 0.4809,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.77,
|
| 234 |
+
"learning_rate": 1.6904823989569755e-05,
|
| 235 |
+
"loss": 0.484,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.79,
|
| 240 |
+
"learning_rate": 1.6823500651890484e-05,
|
| 241 |
+
"loss": 0.4843,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.81,
|
| 246 |
+
"learning_rate": 1.6742014341590612e-05,
|
| 247 |
+
"loss": 0.4647,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.84,
|
| 252 |
+
"learning_rate": 1.6660528031290743e-05,
|
| 253 |
+
"loss": 0.4703,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.86,
|
| 258 |
+
"learning_rate": 1.6579204693611475e-05,
|
| 259 |
+
"loss": 0.4732,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.88,
|
| 264 |
+
"learning_rate": 1.6497718383311606e-05,
|
| 265 |
+
"loss": 0.4914,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.9,
|
| 270 |
+
"learning_rate": 1.6416232073011734e-05,
|
| 271 |
+
"loss": 0.4647,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.92,
|
| 276 |
+
"learning_rate": 1.6334745762711865e-05,
|
| 277 |
+
"loss": 0.4749,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.94,
|
| 282 |
+
"learning_rate": 1.6253259452411997e-05,
|
| 283 |
+
"loss": 0.4835,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.96,
|
| 288 |
+
"learning_rate": 1.6171936114732725e-05,
|
| 289 |
+
"loss": 0.4741,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.98,
|
| 294 |
+
"learning_rate": 1.6090449804432857e-05,
|
| 295 |
+
"loss": 0.4649,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
{
|
| 299 |
"epoch": 1.0,
|
| 300 |
+
"learning_rate": 1.6008963494132988e-05,
|
| 301 |
+
"loss": 0.4664,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.02,
|
| 306 |
+
"learning_rate": 1.592747718383312e-05,
|
| 307 |
+
"loss": 0.3638,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.04,
|
| 312 |
+
"learning_rate": 1.5845990873533247e-05,
|
| 313 |
+
"loss": 0.3646,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.06,
|
| 318 |
+
"learning_rate": 1.5764504563233378e-05,
|
| 319 |
+
"loss": 0.3599,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1.08,
|
| 324 |
+
"learning_rate": 1.568301825293351e-05,
|
| 325 |
+
"loss": 0.3495,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.1,
|
| 330 |
+
"learning_rate": 1.5601694915254238e-05,
|
| 331 |
+
"loss": 0.3495,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.12,
|
| 336 |
+
"learning_rate": 1.552020860495437e-05,
|
| 337 |
+
"loss": 0.3526,
|
| 338 |
+
"step": 27500
|
| 339 |
},
|
| 340 |
{
|
| 341 |
"epoch": 1.14,
|
| 342 |
+
"learning_rate": 1.54387222946545e-05,
|
| 343 |
+
"loss": 0.3608,
|
| 344 |
+
"step": 28000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.16,
|
| 348 |
+
"learning_rate": 1.5357235984354632e-05,
|
| 349 |
+
"loss": 0.349,
|
| 350 |
+
"step": 28500
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 1.18,
|
| 354 |
+
"learning_rate": 1.527591264667536e-05,
|
| 355 |
+
"loss": 0.3538,
|
| 356 |
+
"step": 29000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 1.2,
|
| 360 |
+
"learning_rate": 1.519442633637549e-05,
|
| 361 |
+
"loss": 0.3482,
|
| 362 |
+
"step": 29500
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 1.22,
|
| 366 |
+
"learning_rate": 1.511294002607562e-05,
|
| 367 |
+
"loss": 0.3652,
|
| 368 |
+
"step": 30000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.24,
|
| 372 |
+
"learning_rate": 1.503145371577575e-05,
|
| 373 |
+
"loss": 0.3665,
|
| 374 |
+
"step": 30500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.26,
|
| 378 |
+
"learning_rate": 1.494996740547588e-05,
|
| 379 |
+
"loss": 0.3628,
|
| 380 |
+
"step": 31000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 1.28,
|
| 384 |
+
"learning_rate": 1.4868644067796611e-05,
|
| 385 |
+
"loss": 0.356,
|
| 386 |
+
"step": 31500
|
| 387 |
},
|
| 388 |
{
|
| 389 |
"epoch": 1.3,
|
| 390 |
+
"learning_rate": 1.4787157757496742e-05,
|
| 391 |
+
"loss": 0.3613,
|
| 392 |
+
"step": 32000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 1.32,
|
| 396 |
+
"learning_rate": 1.4705834419817473e-05,
|
| 397 |
+
"loss": 0.3662,
|
| 398 |
+
"step": 32500
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.34,
|
| 402 |
+
"learning_rate": 1.4624348109517604e-05,
|
| 403 |
+
"loss": 0.3461,
|
| 404 |
+
"step": 33000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.36,
|
| 408 |
+
"learning_rate": 1.4542861799217733e-05,
|
| 409 |
+
"loss": 0.3552,
|
| 410 |
+
"step": 33500
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.39,
|
| 414 |
+
"learning_rate": 1.4461375488917863e-05,
|
| 415 |
+
"loss": 0.3655,
|
| 416 |
+
"step": 34000
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.41,
|
| 420 |
+
"learning_rate": 1.4379889178617994e-05,
|
| 421 |
+
"loss": 0.3433,
|
| 422 |
+
"step": 34500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 1.43,
|
| 426 |
+
"learning_rate": 1.4298402868318124e-05,
|
| 427 |
+
"loss": 0.3578,
|
| 428 |
+
"step": 35000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.45,
|
| 432 |
+
"learning_rate": 1.4216916558018255e-05,
|
| 433 |
+
"loss": 0.3497,
|
| 434 |
+
"step": 35500
|
| 435 |
},
|
| 436 |
{
|
| 437 |
"epoch": 1.47,
|
| 438 |
+
"learning_rate": 1.4135430247718384e-05,
|
| 439 |
"loss": 0.3614,
|
| 440 |
+
"step": 36000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.49,
|
| 444 |
+
"learning_rate": 1.4053943937418515e-05,
|
| 445 |
+
"loss": 0.3488,
|
| 446 |
+
"step": 36500
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.51,
|
| 450 |
+
"learning_rate": 1.3972457627118645e-05,
|
| 451 |
+
"loss": 0.3531,
|
| 452 |
+
"step": 37000
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.53,
|
| 456 |
+
"learning_rate": 1.3890971316818776e-05,
|
| 457 |
+
"loss": 0.3595,
|
| 458 |
+
"step": 37500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.55,
|
| 462 |
+
"learning_rate": 1.3809647979139507e-05,
|
| 463 |
+
"loss": 0.353,
|
| 464 |
+
"step": 38000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.57,
|
| 468 |
+
"learning_rate": 1.3728161668839636e-05,
|
| 469 |
+
"loss": 0.3523,
|
| 470 |
+
"step": 38500
|
| 471 |
+
},
|
| 472 |
+
{
|
| 473 |
+
"epoch": 1.59,
|
| 474 |
+
"learning_rate": 1.3646675358539767e-05,
|
| 475 |
+
"loss": 0.3652,
|
| 476 |
+
"step": 39000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 1.61,
|
| 480 |
+
"learning_rate": 1.3565189048239897e-05,
|
| 481 |
+
"loss": 0.3504,
|
| 482 |
+
"step": 39500
|
| 483 |
},
|
| 484 |
{
|
| 485 |
"epoch": 1.63,
|
| 486 |
+
"learning_rate": 1.3483865710560626e-05,
|
| 487 |
+
"loss": 0.355,
|
| 488 |
+
"step": 40000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.65,
|
| 492 |
+
"learning_rate": 1.3402379400260757e-05,
|
| 493 |
+
"loss": 0.3391,
|
| 494 |
+
"step": 40500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.67,
|
| 498 |
+
"learning_rate": 1.3320893089960886e-05,
|
| 499 |
+
"loss": 0.3525,
|
| 500 |
+
"step": 41000
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.69,
|
| 504 |
+
"learning_rate": 1.3239569752281619e-05,
|
| 505 |
+
"loss": 0.345,
|
| 506 |
+
"step": 41500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 1.71,
|
| 510 |
+
"learning_rate": 1.3158083441981748e-05,
|
| 511 |
+
"loss": 0.3582,
|
| 512 |
+
"step": 42000
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 1.73,
|
| 516 |
+
"learning_rate": 1.3076597131681878e-05,
|
| 517 |
+
"loss": 0.3578,
|
| 518 |
+
"step": 42500
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.75,
|
| 522 |
+
"learning_rate": 1.2995110821382009e-05,
|
| 523 |
+
"loss": 0.3525,
|
| 524 |
+
"step": 43000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.77,
|
| 528 |
+
"learning_rate": 1.2913624511082138e-05,
|
| 529 |
+
"loss": 0.3504,
|
| 530 |
+
"step": 43500
|
| 531 |
},
|
| 532 |
{
|
| 533 |
"epoch": 1.79,
|
| 534 |
+
"learning_rate": 1.283213820078227e-05,
|
| 535 |
+
"loss": 0.3531,
|
| 536 |
+
"step": 44000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.81,
|
| 540 |
+
"learning_rate": 1.27506518904824e-05,
|
| 541 |
+
"loss": 0.3661,
|
| 542 |
+
"step": 44500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.83,
|
| 546 |
+
"learning_rate": 1.266916558018253e-05,
|
| 547 |
+
"loss": 0.3519,
|
| 548 |
+
"step": 45000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.85,
|
| 552 |
+
"learning_rate": 1.258767926988266e-05,
|
| 553 |
+
"loss": 0.3459,
|
| 554 |
+
"step": 45500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.87,
|
| 558 |
+
"learning_rate": 1.250635593220339e-05,
|
| 559 |
+
"loss": 0.3635,
|
| 560 |
+
"step": 46000
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 1.89,
|
| 564 |
+
"learning_rate": 1.242503259452412e-05,
|
| 565 |
+
"loss": 0.3617,
|
| 566 |
+
"step": 46500
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 1.91,
|
| 570 |
+
"learning_rate": 1.234354628422425e-05,
|
| 571 |
+
"loss": 0.3668,
|
| 572 |
+
"step": 47000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 1.94,
|
| 576 |
+
"learning_rate": 1.226205997392438e-05,
|
| 577 |
+
"loss": 0.3416,
|
| 578 |
+
"step": 47500
|
| 579 |
},
|
| 580 |
{
|
| 581 |
"epoch": 1.96,
|
| 582 |
+
"learning_rate": 1.2180573663624513e-05,
|
| 583 |
+
"loss": 0.3568,
|
| 584 |
+
"step": 48000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.98,
|
| 588 |
+
"learning_rate": 1.2099087353324644e-05,
|
| 589 |
+
"loss": 0.3688,
|
| 590 |
+
"step": 48500
|
| 591 |
},
|
| 592 |
{
|
| 593 |
"epoch": 2.0,
|
| 594 |
+
"learning_rate": 1.2017601043024774e-05,
|
| 595 |
+
"loss": 0.3383,
|
| 596 |
+
"step": 49000
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 2.02,
|
| 600 |
+
"learning_rate": 1.1936114732724903e-05,
|
| 601 |
+
"loss": 0.2534,
|
| 602 |
+
"step": 49500
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 2.04,
|
| 606 |
+
"learning_rate": 1.1854628422425034e-05,
|
| 607 |
+
"loss": 0.242,
|
| 608 |
+
"step": 50000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 2.06,
|
| 612 |
+
"learning_rate": 1.1773305084745763e-05,
|
| 613 |
+
"loss": 0.2292,
|
| 614 |
+
"step": 50500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.08,
|
| 618 |
+
"learning_rate": 1.1691981747066494e-05,
|
| 619 |
+
"loss": 0.2383,
|
| 620 |
+
"step": 51000
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.1,
|
| 624 |
+
"learning_rate": 1.1610495436766625e-05,
|
| 625 |
+
"loss": 0.2377,
|
| 626 |
+
"step": 51500
|
| 627 |
},
|
| 628 |
{
|
| 629 |
"epoch": 2.12,
|
| 630 |
+
"learning_rate": 1.1529009126466754e-05,
|
| 631 |
+
"loss": 0.2391,
|
| 632 |
+
"step": 52000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 2.14,
|
| 636 |
+
"learning_rate": 1.1447685788787483e-05,
|
| 637 |
+
"loss": 0.235,
|
| 638 |
+
"step": 52500
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 2.16,
|
| 642 |
+
"learning_rate": 1.1366199478487615e-05,
|
| 643 |
+
"loss": 0.2349,
|
| 644 |
+
"step": 53000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 2.18,
|
| 648 |
+
"learning_rate": 1.1284713168187746e-05,
|
| 649 |
+
"loss": 0.2543,
|
| 650 |
+
"step": 53500
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 2.2,
|
| 654 |
+
"learning_rate": 1.1203226857887877e-05,
|
| 655 |
+
"loss": 0.24,
|
| 656 |
+
"step": 54000
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.22,
|
| 660 |
+
"learning_rate": 1.1121740547588006e-05,
|
| 661 |
+
"loss": 0.2421,
|
| 662 |
+
"step": 54500
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.24,
|
| 666 |
+
"learning_rate": 1.1040254237288138e-05,
|
| 667 |
+
"loss": 0.2528,
|
| 668 |
+
"step": 55000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 2.26,
|
| 672 |
+
"learning_rate": 1.0958767926988267e-05,
|
| 673 |
+
"loss": 0.2447,
|
| 674 |
+
"step": 55500
|
| 675 |
},
|
| 676 |
{
|
| 677 |
"epoch": 2.28,
|
| 678 |
+
"learning_rate": 1.0877281616688398e-05,
|
| 679 |
+
"loss": 0.2375,
|
| 680 |
+
"step": 56000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 2.3,
|
| 684 |
+
"learning_rate": 1.0795795306388528e-05,
|
| 685 |
+
"loss": 0.2414,
|
| 686 |
+
"step": 56500
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 2.32,
|
| 690 |
+
"learning_rate": 1.0714308996088657e-05,
|
| 691 |
+
"loss": 0.2362,
|
| 692 |
+
"step": 57000
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 2.34,
|
| 696 |
+
"learning_rate": 1.0632822685788789e-05,
|
| 697 |
+
"loss": 0.2319,
|
| 698 |
+
"step": 57500
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.36,
|
| 702 |
+
"learning_rate": 1.0551499348109517e-05,
|
| 703 |
+
"loss": 0.2485,
|
| 704 |
+
"step": 58000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.38,
|
| 708 |
+
"learning_rate": 1.047001303780965e-05,
|
| 709 |
+
"loss": 0.238,
|
| 710 |
+
"step": 58500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 2.4,
|
| 714 |
+
"learning_rate": 1.038852672750978e-05,
|
| 715 |
+
"loss": 0.2423,
|
| 716 |
+
"step": 59000
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 2.42,
|
| 720 |
+
"learning_rate": 1.0307040417209911e-05,
|
| 721 |
+
"loss": 0.2451,
|
| 722 |
+
"step": 59500
|
| 723 |
},
|
| 724 |
{
|
| 725 |
"epoch": 2.44,
|
| 726 |
+
"learning_rate": 1.022555410691004e-05,
|
| 727 |
+
"loss": 0.2468,
|
| 728 |
+
"step": 60000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 2.46,
|
| 732 |
+
"learning_rate": 1.014423076923077e-05,
|
| 733 |
+
"loss": 0.238,
|
| 734 |
+
"step": 60500
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 2.49,
|
| 738 |
+
"learning_rate": 1.00627444589309e-05,
|
| 739 |
+
"loss": 0.2414,
|
| 740 |
+
"step": 61000
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.51,
|
| 744 |
+
"learning_rate": 9.981258148631032e-06,
|
| 745 |
+
"loss": 0.2559,
|
| 746 |
+
"step": 61500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.53,
|
| 750 |
+
"learning_rate": 9.899771838331161e-06,
|
| 751 |
+
"loss": 0.2489,
|
| 752 |
+
"step": 62000
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 2.55,
|
| 756 |
+
"learning_rate": 9.818285528031292e-06,
|
| 757 |
+
"loss": 0.2485,
|
| 758 |
+
"step": 62500
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 2.57,
|
| 762 |
+
"learning_rate": 9.736799217731422e-06,
|
| 763 |
+
"loss": 0.2477,
|
| 764 |
+
"step": 63000
|
| 765 |
+
},
|
| 766 |
+
{
|
| 767 |
+
"epoch": 2.59,
|
| 768 |
+
"learning_rate": 9.655312907431551e-06,
|
| 769 |
+
"loss": 0.2515,
|
| 770 |
+
"step": 63500
|
| 771 |
},
|
| 772 |
{
|
| 773 |
"epoch": 2.61,
|
| 774 |
+
"learning_rate": 9.573826597131683e-06,
|
| 775 |
+
"loss": 0.2442,
|
| 776 |
+
"step": 64000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.63,
|
| 780 |
+
"learning_rate": 9.492503259452413e-06,
|
| 781 |
+
"loss": 0.234,
|
| 782 |
+
"step": 64500
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.65,
|
| 786 |
+
"learning_rate": 9.411179921773142e-06,
|
| 787 |
+
"loss": 0.2615,
|
| 788 |
+
"step": 65000
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.67,
|
| 792 |
+
"learning_rate": 9.329693611473273e-06,
|
| 793 |
+
"loss": 0.2369,
|
| 794 |
+
"step": 65500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 2.69,
|
| 798 |
+
"learning_rate": 9.248207301173405e-06,
|
| 799 |
+
"loss": 0.247,
|
| 800 |
+
"step": 66000
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 2.71,
|
| 804 |
+
"learning_rate": 9.166720990873534e-06,
|
| 805 |
+
"loss": 0.2511,
|
| 806 |
+
"step": 66500
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 2.73,
|
| 810 |
+
"learning_rate": 9.085397653194265e-06,
|
| 811 |
+
"loss": 0.2351,
|
| 812 |
+
"step": 67000
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.75,
|
| 816 |
+
"learning_rate": 9.003911342894394e-06,
|
| 817 |
+
"loss": 0.2503,
|
| 818 |
+
"step": 67500
|
| 819 |
},
|
| 820 |
{
|
| 821 |
"epoch": 2.77,
|
| 822 |
+
"learning_rate": 8.922425032594525e-06,
|
| 823 |
+
"loss": 0.2464,
|
| 824 |
+
"step": 68000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.79,
|
| 828 |
+
"learning_rate": 8.840938722294655e-06,
|
| 829 |
+
"loss": 0.2415,
|
| 830 |
+
"step": 68500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.81,
|
| 834 |
+
"learning_rate": 8.759452411994786e-06,
|
| 835 |
+
"loss": 0.2564,
|
| 836 |
+
"step": 69000
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 2.83,
|
| 840 |
+
"learning_rate": 8.678129074315515e-06,
|
| 841 |
+
"loss": 0.2434,
|
| 842 |
+
"step": 69500
|
| 843 |
+
},
|
| 844 |
+
{
|
| 845 |
+
"epoch": 2.85,
|
| 846 |
+
"learning_rate": 8.596642764015646e-06,
|
| 847 |
+
"loss": 0.2448,
|
| 848 |
+
"step": 70000
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.87,
|
| 852 |
+
"learning_rate": 8.515156453715776e-06,
|
| 853 |
+
"loss": 0.2488,
|
| 854 |
+
"step": 70500
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 2.89,
|
| 858 |
+
"learning_rate": 8.433670143415907e-06,
|
| 859 |
+
"loss": 0.2349,
|
| 860 |
+
"step": 71000
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 2.91,
|
| 864 |
+
"learning_rate": 8.352183833116038e-06,
|
| 865 |
+
"loss": 0.2553,
|
| 866 |
+
"step": 71500
|
| 867 |
},
|
| 868 |
{
|
| 869 |
"epoch": 2.93,
|
| 870 |
+
"learning_rate": 8.270697522816167e-06,
|
| 871 |
+
"loss": 0.2416,
|
| 872 |
+
"step": 72000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.95,
|
| 876 |
+
"learning_rate": 8.189211212516299e-06,
|
| 877 |
+
"loss": 0.2438,
|
| 878 |
+
"step": 72500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.97,
|
| 882 |
+
"learning_rate": 8.107724902216428e-06,
|
| 883 |
+
"loss": 0.2478,
|
| 884 |
+
"step": 73000
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.99,
|
| 888 |
+
"learning_rate": 8.026401564537159e-06,
|
| 889 |
+
"loss": 0.2412,
|
| 890 |
+
"step": 73500
|
| 891 |
},
|
| 892 |
{
|
| 893 |
+
"epoch": 3.01,
|
| 894 |
+
"learning_rate": 7.944915254237288e-06,
|
| 895 |
+
"loss": 0.1833,
|
| 896 |
+
"step": 74000
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 3.04,
|
| 900 |
+
"learning_rate": 7.86342894393742e-06,
|
| 901 |
+
"loss": 0.1688,
|
| 902 |
+
"step": 74500
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.06,
|
| 906 |
+
"learning_rate": 7.781942633637549e-06,
|
| 907 |
+
"loss": 0.1683,
|
| 908 |
+
"step": 75000
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 3.08,
|
| 912 |
+
"learning_rate": 7.70045632333768e-06,
|
| 913 |
+
"loss": 0.1695,
|
| 914 |
+
"step": 75500
|
| 915 |
},
|
| 916 |
{
|
| 917 |
"epoch": 3.1,
|
| 918 |
+
"learning_rate": 7.61913298565841e-06,
|
| 919 |
+
"loss": 0.1667,
|
| 920 |
+
"step": 76000
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 3.12,
|
| 924 |
+
"learning_rate": 7.53780964797914e-06,
|
| 925 |
+
"loss": 0.1758,
|
| 926 |
+
"step": 76500
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 3.14,
|
| 930 |
+
"learning_rate": 7.456323337679271e-06,
|
| 931 |
+
"loss": 0.1734,
|
| 932 |
+
"step": 77000
|
| 933 |
+
},
|
| 934 |
+
{
|
| 935 |
+
"epoch": 3.16,
|
| 936 |
+
"learning_rate": 7.374837027379401e-06,
|
| 937 |
+
"loss": 0.174,
|
| 938 |
+
"step": 77500
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 3.18,
|
| 942 |
+
"learning_rate": 7.2933507170795315e-06,
|
| 943 |
+
"loss": 0.1824,
|
| 944 |
+
"step": 78000
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.2,
|
| 948 |
+
"learning_rate": 7.212027379400261e-06,
|
| 949 |
+
"loss": 0.1622,
|
| 950 |
+
"step": 78500
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.22,
|
| 954 |
+
"learning_rate": 7.130541069100392e-06,
|
| 955 |
+
"loss": 0.1887,
|
| 956 |
+
"step": 79000
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 3.24,
|
| 960 |
+
"learning_rate": 7.049054758800522e-06,
|
| 961 |
+
"loss": 0.1878,
|
| 962 |
+
"step": 79500
|
| 963 |
},
|
| 964 |
{
|
| 965 |
"epoch": 3.26,
|
| 966 |
+
"learning_rate": 6.967568448500652e-06,
|
| 967 |
+
"loss": 0.1722,
|
| 968 |
+
"step": 80000
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"epoch": 3.28,
|
| 972 |
+
"learning_rate": 6.886082138200783e-06,
|
| 973 |
+
"loss": 0.1736,
|
| 974 |
+
"step": 80500
|
| 975 |
+
},
|
| 976 |
+
{
|
| 977 |
+
"epoch": 3.3,
|
| 978 |
+
"learning_rate": 6.804595827900913e-06,
|
| 979 |
+
"loss": 0.1866,
|
| 980 |
+
"step": 81000
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 3.32,
|
| 984 |
+
"learning_rate": 6.723109517601043e-06,
|
| 985 |
+
"loss": 0.1774,
|
| 986 |
+
"step": 81500
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.34,
|
| 990 |
+
"learning_rate": 6.6416232073011745e-06,
|
| 991 |
+
"loss": 0.1675,
|
| 992 |
+
"step": 82000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.36,
|
| 996 |
+
"learning_rate": 6.560136897001305e-06,
|
| 997 |
+
"loss": 0.1875,
|
| 998 |
+
"step": 82500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 3.38,
|
| 1002 |
+
"learning_rate": 6.478650586701435e-06,
|
| 1003 |
+
"loss": 0.1884,
|
| 1004 |
+
"step": 83000
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 3.4,
|
| 1008 |
+
"learning_rate": 6.397164276401565e-06,
|
| 1009 |
+
"loss": 0.1846,
|
| 1010 |
+
"step": 83500
|
| 1011 |
},
|
| 1012 |
{
|
| 1013 |
"epoch": 3.42,
|
| 1014 |
+
"learning_rate": 6.315677966101695e-06,
|
| 1015 |
+
"loss": 0.1778,
|
| 1016 |
+
"step": 84000
|
| 1017 |
+
},
|
| 1018 |
+
{
|
| 1019 |
+
"epoch": 3.44,
|
| 1020 |
+
"learning_rate": 6.234354628422426e-06,
|
| 1021 |
+
"loss": 0.1692,
|
| 1022 |
+
"step": 84500
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 3.46,
|
| 1026 |
+
"learning_rate": 6.152868318122556e-06,
|
| 1027 |
+
"loss": 0.1748,
|
| 1028 |
+
"step": 85000
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.48,
|
| 1032 |
+
"learning_rate": 6.071382007822686e-06,
|
| 1033 |
+
"loss": 0.172,
|
| 1034 |
+
"step": 85500
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.5,
|
| 1038 |
+
"learning_rate": 5.989895697522816e-06,
|
| 1039 |
+
"loss": 0.1856,
|
| 1040 |
+
"step": 86000
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 3.52,
|
| 1044 |
+
"learning_rate": 5.908572359843546e-06,
|
| 1045 |
+
"loss": 0.1588,
|
| 1046 |
+
"step": 86500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 3.54,
|
| 1050 |
+
"learning_rate": 5.827086049543678e-06,
|
| 1051 |
+
"loss": 0.1923,
|
| 1052 |
+
"step": 87000
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 3.57,
|
| 1056 |
+
"learning_rate": 5.745599739243808e-06,
|
| 1057 |
+
"loss": 0.1648,
|
| 1058 |
+
"step": 87500
|
| 1059 |
},
|
| 1060 |
{
|
| 1061 |
"epoch": 3.59,
|
| 1062 |
+
"learning_rate": 5.664113428943938e-06,
|
| 1063 |
+
"loss": 0.162,
|
| 1064 |
+
"step": 88000
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 3.61,
|
| 1068 |
+
"learning_rate": 5.582790091264668e-06,
|
| 1069 |
+
"loss": 0.1809,
|
| 1070 |
+
"step": 88500
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.63,
|
| 1074 |
+
"learning_rate": 5.501466753585399e-06,
|
| 1075 |
+
"loss": 0.1782,
|
| 1076 |
+
"step": 89000
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.65,
|
| 1080 |
+
"learning_rate": 5.419980443285528e-06,
|
| 1081 |
+
"loss": 0.176,
|
| 1082 |
+
"step": 89500
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 3.67,
|
| 1086 |
+
"learning_rate": 5.3384941329856585e-06,
|
| 1087 |
+
"loss": 0.1841,
|
| 1088 |
+
"step": 90000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 3.69,
|
| 1092 |
+
"learning_rate": 5.257007822685789e-06,
|
| 1093 |
+
"loss": 0.1849,
|
| 1094 |
+
"step": 90500
|
| 1095 |
+
},
|
| 1096 |
+
{
|
| 1097 |
+
"epoch": 3.71,
|
| 1098 |
+
"learning_rate": 5.175521512385919e-06,
|
| 1099 |
+
"loss": 0.1708,
|
| 1100 |
+
"step": 91000
|
| 1101 |
+
},
|
| 1102 |
+
{
|
| 1103 |
+
"epoch": 3.73,
|
| 1104 |
+
"learning_rate": 5.0940352020860495e-06,
|
| 1105 |
+
"loss": 0.1832,
|
| 1106 |
+
"step": 91500
|
| 1107 |
},
|
| 1108 |
{
|
| 1109 |
"epoch": 3.75,
|
| 1110 |
+
"learning_rate": 5.012548891786181e-06,
|
| 1111 |
+
"loss": 0.1765,
|
| 1112 |
+
"step": 92000
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 3.77,
|
| 1116 |
+
"learning_rate": 4.93106258148631e-06,
|
| 1117 |
+
"loss": 0.1833,
|
| 1118 |
+
"step": 92500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.79,
|
| 1122 |
+
"learning_rate": 4.8495762711864405e-06,
|
| 1123 |
+
"loss": 0.1775,
|
| 1124 |
+
"step": 93000
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 3.81,
|
| 1128 |
+
"learning_rate": 4.768252933507171e-06,
|
| 1129 |
+
"loss": 0.1919,
|
| 1130 |
+
"step": 93500
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 3.83,
|
| 1134 |
+
"learning_rate": 4.6867666232073015e-06,
|
| 1135 |
+
"loss": 0.1739,
|
| 1136 |
+
"step": 94000
|
| 1137 |
+
},
|
| 1138 |
+
{
|
| 1139 |
+
"epoch": 3.85,
|
| 1140 |
+
"learning_rate": 4.605280312907432e-06,
|
| 1141 |
+
"loss": 0.172,
|
| 1142 |
+
"step": 94500
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 3.87,
|
| 1146 |
+
"learning_rate": 4.523794002607562e-06,
|
| 1147 |
+
"loss": 0.181,
|
| 1148 |
+
"step": 95000
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 3.89,
|
| 1152 |
+
"learning_rate": 4.442470664928292e-06,
|
| 1153 |
+
"loss": 0.1637,
|
| 1154 |
+
"step": 95500
|
| 1155 |
},
|
| 1156 |
{
|
| 1157 |
"epoch": 3.91,
|
| 1158 |
+
"learning_rate": 4.360984354628422e-06,
|
| 1159 |
+
"loss": 0.1885,
|
| 1160 |
+
"step": 96000
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.93,
|
| 1164 |
+
"learning_rate": 4.2794980443285535e-06,
|
| 1165 |
+
"loss": 0.1902,
|
| 1166 |
+
"step": 96500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 3.95,
|
| 1170 |
+
"learning_rate": 4.198011734028684e-06,
|
| 1171 |
+
"loss": 0.1764,
|
| 1172 |
+
"step": 97000
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 3.97,
|
| 1176 |
+
"learning_rate": 4.1166883963494135e-06,
|
| 1177 |
+
"loss": 0.1653,
|
| 1178 |
+
"step": 97500
|
| 1179 |
+
},
|
| 1180 |
+
{
|
| 1181 |
+
"epoch": 3.99,
|
| 1182 |
+
"learning_rate": 4.035202086049544e-06,
|
| 1183 |
+
"loss": 0.1733,
|
| 1184 |
+
"step": 98000
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 4.01,
|
| 1188 |
+
"learning_rate": 3.953715775749674e-06,
|
| 1189 |
+
"loss": 0.135,
|
| 1190 |
+
"step": 98500
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 4.03,
|
| 1194 |
+
"learning_rate": 3.872392438070404e-06,
|
| 1195 |
+
"loss": 0.1212,
|
| 1196 |
+
"step": 99000
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 4.05,
|
| 1200 |
+
"learning_rate": 3.790906127770535e-06,
|
| 1201 |
+
"loss": 0.1349,
|
| 1202 |
+
"step": 99500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 4.07,
|
| 1206 |
+
"learning_rate": 3.709419817470665e-06,
|
| 1207 |
+
"loss": 0.1152,
|
| 1208 |
+
"step": 100000
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 4.09,
|
| 1212 |
+
"learning_rate": 3.6279335071707954e-06,
|
| 1213 |
+
"loss": 0.1307,
|
| 1214 |
+
"step": 100500
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 4.12,
|
| 1218 |
+
"learning_rate": 3.5464471968709258e-06,
|
| 1219 |
+
"loss": 0.1244,
|
| 1220 |
+
"step": 101000
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 4.14,
|
| 1224 |
+
"learning_rate": 3.4649608865710565e-06,
|
| 1225 |
+
"loss": 0.1292,
|
| 1226 |
+
"step": 101500
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 4.16,
|
| 1230 |
+
"learning_rate": 3.3836375488917867e-06,
|
| 1231 |
+
"loss": 0.1246,
|
| 1232 |
+
"step": 102000
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.18,
|
| 1236 |
+
"learning_rate": 3.302151238591917e-06,
|
| 1237 |
+
"loss": 0.1318,
|
| 1238 |
+
"step": 102500
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 4.2,
|
| 1242 |
+
"learning_rate": 3.220664928292047e-06,
|
| 1243 |
+
"loss": 0.1125,
|
| 1244 |
+
"step": 103000
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 4.22,
|
| 1248 |
+
"learning_rate": 3.1391786179921773e-06,
|
| 1249 |
+
"loss": 0.1328,
|
| 1250 |
+
"step": 103500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 4.24,
|
| 1254 |
+
"learning_rate": 3.057692307692308e-06,
|
| 1255 |
+
"loss": 0.1391,
|
| 1256 |
+
"step": 104000
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 4.26,
|
| 1260 |
+
"learning_rate": 2.9763689700130383e-06,
|
| 1261 |
+
"loss": 0.129,
|
| 1262 |
+
"step": 104500
|
| 1263 |
+
},
|
| 1264 |
+
{
|
| 1265 |
+
"epoch": 4.28,
|
| 1266 |
+
"learning_rate": 2.8948826597131686e-06,
|
| 1267 |
+
"loss": 0.1314,
|
| 1268 |
+
"step": 105000
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"epoch": 4.3,
|
| 1272 |
+
"learning_rate": 2.813396349413299e-06,
|
| 1273 |
+
"loss": 0.1398,
|
| 1274 |
+
"step": 105500
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.32,
|
| 1278 |
+
"learning_rate": 2.731910039113429e-06,
|
| 1279 |
+
"loss": 0.1177,
|
| 1280 |
+
"step": 106000
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.34,
|
| 1284 |
+
"learning_rate": 2.650586701434159e-06,
|
| 1285 |
+
"loss": 0.1321,
|
| 1286 |
+
"step": 106500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 4.36,
|
| 1290 |
+
"learning_rate": 2.56910039113429e-06,
|
| 1291 |
+
"loss": 0.1126,
|
| 1292 |
+
"step": 107000
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 4.38,
|
| 1296 |
+
"learning_rate": 2.48761408083442e-06,
|
| 1297 |
+
"loss": 0.1313,
|
| 1298 |
+
"step": 107500
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 4.4,
|
| 1302 |
+
"learning_rate": 2.4061277705345505e-06,
|
| 1303 |
+
"loss": 0.1346,
|
| 1304 |
+
"step": 108000
|
| 1305 |
+
},
|
| 1306 |
+
{
|
| 1307 |
+
"epoch": 4.42,
|
| 1308 |
+
"learning_rate": 2.324641460234681e-06,
|
| 1309 |
+
"loss": 0.107,
|
| 1310 |
+
"step": 108500
|
| 1311 |
+
},
|
| 1312 |
+
{
|
| 1313 |
+
"epoch": 4.44,
|
| 1314 |
+
"learning_rate": 2.243155149934811e-06,
|
| 1315 |
+
"loss": 0.1301,
|
| 1316 |
+
"step": 109000
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.46,
|
| 1320 |
+
"learning_rate": 2.1616688396349415e-06,
|
| 1321 |
+
"loss": 0.1159,
|
| 1322 |
+
"step": 109500
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.48,
|
| 1326 |
+
"learning_rate": 2.080182529335072e-06,
|
| 1327 |
+
"loss": 0.1224,
|
| 1328 |
+
"step": 110000
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 4.5,
|
| 1332 |
+
"learning_rate": 1.998859191655802e-06,
|
| 1333 |
+
"loss": 0.1253,
|
| 1334 |
+
"step": 110500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 4.52,
|
| 1338 |
+
"learning_rate": 1.917535853976532e-06,
|
| 1339 |
+
"loss": 0.1163,
|
| 1340 |
+
"step": 111000
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 4.54,
|
| 1344 |
+
"learning_rate": 1.8360495436766626e-06,
|
| 1345 |
+
"loss": 0.1129,
|
| 1346 |
+
"step": 111500
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 4.56,
|
| 1350 |
+
"learning_rate": 1.754563233376793e-06,
|
| 1351 |
+
"loss": 0.1409,
|
| 1352 |
+
"step": 112000
|
| 1353 |
+
},
|
| 1354 |
+
{
|
| 1355 |
+
"epoch": 4.58,
|
| 1356 |
+
"learning_rate": 1.673076923076923e-06,
|
| 1357 |
+
"loss": 0.1208,
|
| 1358 |
+
"step": 112500
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.6,
|
| 1362 |
+
"learning_rate": 1.5917535853976534e-06,
|
| 1363 |
+
"loss": 0.1276,
|
| 1364 |
+
"step": 113000
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 4.62,
|
| 1368 |
+
"learning_rate": 1.5102672750977838e-06,
|
| 1369 |
+
"loss": 0.1182,
|
| 1370 |
+
"step": 113500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 4.64,
|
| 1374 |
+
"learning_rate": 1.4287809647979139e-06,
|
| 1375 |
+
"loss": 0.1236,
|
| 1376 |
+
"step": 114000
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 4.67,
|
| 1380 |
+
"learning_rate": 1.3472946544980445e-06,
|
| 1381 |
+
"loss": 0.1309,
|
| 1382 |
+
"step": 114500
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 4.69,
|
| 1386 |
+
"learning_rate": 1.2658083441981748e-06,
|
| 1387 |
+
"loss": 0.1219,
|
| 1388 |
+
"step": 115000
|
| 1389 |
+
},
|
| 1390 |
+
{
|
| 1391 |
+
"epoch": 4.71,
|
| 1392 |
+
"learning_rate": 1.1843220338983051e-06,
|
| 1393 |
+
"loss": 0.1292,
|
| 1394 |
+
"step": 115500
|
| 1395 |
+
},
|
| 1396 |
+
{
|
| 1397 |
+
"epoch": 4.73,
|
| 1398 |
+
"learning_rate": 1.1028357235984355e-06,
|
| 1399 |
+
"loss": 0.1262,
|
| 1400 |
+
"step": 116000
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 4.75,
|
| 1404 |
+
"learning_rate": 1.0213494132985658e-06,
|
| 1405 |
+
"loss": 0.1148,
|
| 1406 |
+
"step": 116500
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 4.77,
|
| 1410 |
+
"learning_rate": 9.400260756192961e-07,
|
| 1411 |
+
"loss": 0.117,
|
| 1412 |
+
"step": 117000
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 4.79,
|
| 1416 |
+
"learning_rate": 8.587027379400262e-07,
|
| 1417 |
+
"loss": 0.128,
|
| 1418 |
+
"step": 117500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 4.81,
|
| 1422 |
+
"learning_rate": 7.772164276401566e-07,
|
| 1423 |
+
"loss": 0.128,
|
| 1424 |
+
"step": 118000
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 4.83,
|
| 1428 |
+
"learning_rate": 6.95730117340287e-07,
|
| 1429 |
+
"loss": 0.1416,
|
| 1430 |
+
"step": 118500
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 4.85,
|
| 1434 |
+
"learning_rate": 6.142438070404173e-07,
|
| 1435 |
+
"loss": 0.1209,
|
| 1436 |
+
"step": 119000
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 4.87,
|
| 1440 |
+
"learning_rate": 5.327574967405477e-07,
|
| 1441 |
+
"loss": 0.134,
|
| 1442 |
+
"step": 119500
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 4.89,
|
| 1446 |
+
"learning_rate": 4.5127118644067805e-07,
|
| 1447 |
+
"loss": 0.1199,
|
| 1448 |
+
"step": 120000
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 4.91,
|
| 1452 |
+
"learning_rate": 3.6978487614080835e-07,
|
| 1453 |
+
"loss": 0.1169,
|
| 1454 |
+
"step": 120500
|
| 1455 |
+
},
|
| 1456 |
+
{
|
| 1457 |
+
"epoch": 4.93,
|
| 1458 |
+
"learning_rate": 2.8829856584093875e-07,
|
| 1459 |
+
"loss": 0.1204,
|
| 1460 |
+
"step": 121000
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 4.95,
|
| 1464 |
+
"learning_rate": 2.0697522816166886e-07,
|
| 1465 |
+
"loss": 0.1298,
|
| 1466 |
+
"step": 121500
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 4.97,
|
| 1470 |
+
"learning_rate": 1.2548891786179923e-07,
|
| 1471 |
+
"loss": 0.1317,
|
| 1472 |
+
"step": 122000
|
| 1473 |
},
|
| 1474 |
{
|
| 1475 |
+
"epoch": 4.99,
|
| 1476 |
+
"learning_rate": 4.416558018252933e-08,
|
| 1477 |
+
"loss": 0.1255,
|
| 1478 |
+
"step": 122500
|
|
|
|
|
|
|
|
|
|
| 1479 |
},
|
| 1480 |
{
|
| 1481 |
+
"epoch": 5.0,
|
| 1482 |
+
"step": 122720,
|
| 1483 |
+
"total_flos": 1.2915645671077632e+17,
|
| 1484 |
+
"train_loss": 0.2863727584966936,
|
| 1485 |
+
"train_runtime": 10219.2193,
|
| 1486 |
+
"train_samples_per_second": 192.139,
|
| 1487 |
+
"train_steps_per_second": 12.009
|
| 1488 |
}
|
| 1489 |
],
|
| 1490 |
+
"max_steps": 122720,
|
| 1491 |
+
"num_train_epochs": 5,
|
| 1492 |
+
"total_flos": 1.2915645671077632e+17,
|
| 1493 |
"trial_name": null,
|
| 1494 |
"trial_params": null
|
| 1495 |
}
|
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:b57564893464995d3f692fb1e2fd92dbaff0074aeda3e6c7bb6091681ab654fe
|
| 3 |
+
size 3963
|