Training in progress, step 500
Browse files- README.md +71 -0
- all_results.json +7 -0
- config.json +27 -0
- generation_config.json +5 -0
- mlm_eval_results.json +7 -0
- model.safetensors +3 -0
- trainer_state.json +676 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: dccuchile/bert-base-spanish-wwm-uncased
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: bert-base-spanish-wwm-uncased-2023-11-13-20-51
|
| 7 |
+
results: []
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 11 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 12 |
+
|
| 13 |
+
# bert-base-spanish-wwm-uncased-2023-11-13-20-51
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on the None dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 1.0883
|
| 18 |
+
|
| 19 |
+
## Model description
|
| 20 |
+
|
| 21 |
+
More information needed
|
| 22 |
+
|
| 23 |
+
## Intended uses & limitations
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Training and evaluation data
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training procedure
|
| 32 |
+
|
| 33 |
+
### Training hyperparameters
|
| 34 |
+
|
| 35 |
+
The following hyperparameters were used during training:
|
| 36 |
+
- learning_rate: 5e-05
|
| 37 |
+
- train_batch_size: 16
|
| 38 |
+
- eval_batch_size: 16
|
| 39 |
+
- seed: 42
|
| 40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 41 |
+
- lr_scheduler_type: linear
|
| 42 |
+
- num_epochs: 10
|
| 43 |
+
|
| 44 |
+
### Training results
|
| 45 |
+
|
| 46 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 47 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 48 |
+
| 1.9308 | 0.59 | 500 | 1.7528 |
|
| 49 |
+
| 1.7079 | 1.19 | 1000 | 1.5517 |
|
| 50 |
+
| 1.5614 | 1.78 | 1500 | 1.4558 |
|
| 51 |
+
| 1.4384 | 2.38 | 2000 | 1.3825 |
|
| 52 |
+
| 1.3972 | 2.97 | 2500 | 1.3105 |
|
| 53 |
+
| 1.3532 | 3.56 | 3000 | 1.2872 |
|
| 54 |
+
| 1.3114 | 4.16 | 3500 | 1.2455 |
|
| 55 |
+
| 1.269 | 4.75 | 4000 | 1.2113 |
|
| 56 |
+
| 1.2525 | 5.34 | 4500 | 1.1863 |
|
| 57 |
+
| 1.2171 | 5.94 | 5000 | 1.1597 |
|
| 58 |
+
| 1.1669 | 6.53 | 5500 | 1.1412 |
|
| 59 |
+
| 1.1529 | 7.13 | 6000 | 1.1352 |
|
| 60 |
+
| 1.1532 | 7.72 | 6500 | 1.1115 |
|
| 61 |
+
| 1.1684 | 8.31 | 7000 | 1.1078 |
|
| 62 |
+
| 1.1286 | 8.91 | 7500 | 1.0950 |
|
| 63 |
+
| 1.1416 | 9.5 | 8000 | 1.0948 |
|
| 64 |
+
|
| 65 |
+
|
| 66 |
+
### Framework versions
|
| 67 |
+
|
| 68 |
+
- Transformers 4.35.0
|
| 69 |
+
- Pytorch 2.1.0+cu121
|
| 70 |
+
- Datasets 2.14.6
|
| 71 |
+
- Tokenizers 0.14.1
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.0815315246582031,
|
| 4 |
+
"eval_runtime": 57.2783,
|
| 5 |
+
"eval_samples_per_second": 78.337,
|
| 6 |
+
"eval_steps_per_second": 4.906
|
| 7 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dccuchile/bert-base-spanish-wwm-cased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"gradient_checkpointing": false,
|
| 9 |
+
"hidden_act": "gelu",
|
| 10 |
+
"hidden_dropout_prob": 0.1,
|
| 11 |
+
"hidden_size": 768,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3072,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
+
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 12,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
+
"output_past": true,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.35.0",
|
| 24 |
+
"type_vocab_size": 2,
|
| 25 |
+
"use_cache": true,
|
| 26 |
+
"vocab_size": 31002
|
| 27 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"pad_token_id": 1,
|
| 4 |
+
"transformers_version": "4.35.0"
|
| 5 |
+
}
|
mlm_eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 10.0,
|
| 3 |
+
"eval_loss": 1.0815315246582031,
|
| 4 |
+
"eval_runtime": 57.2783,
|
| 5 |
+
"eval_samples_per_second": 78.337,
|
| 6 |
+
"eval_steps_per_second": 4.906
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0dde01a267c227aacc20ff2fc618f39fe1052a07b7cff1ff7840141aeebf4e5f
|
| 3 |
+
size 439557376
|
trainer_state.json
ADDED
|
@@ -0,0 +1,676 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0948013067245483,
|
| 3 |
+
"best_model_checkpoint": "output_dir/checkpoint-8000",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8420,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.12,
|
| 13 |
+
"learning_rate": 4.9406175771971496e-05,
|
| 14 |
+
"loss": 2.9665,
|
| 15 |
+
"step": 100
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.24,
|
| 19 |
+
"learning_rate": 4.8812351543942996e-05,
|
| 20 |
+
"loss": 2.3245,
|
| 21 |
+
"step": 200
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.36,
|
| 25 |
+
"learning_rate": 4.821852731591449e-05,
|
| 26 |
+
"loss": 2.1171,
|
| 27 |
+
"step": 300
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.48,
|
| 31 |
+
"learning_rate": 4.7624703087885984e-05,
|
| 32 |
+
"loss": 2.0118,
|
| 33 |
+
"step": 400
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.59,
|
| 37 |
+
"learning_rate": 4.7030878859857484e-05,
|
| 38 |
+
"loss": 1.9308,
|
| 39 |
+
"step": 500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.59,
|
| 43 |
+
"eval_loss": 1.7528491020202637,
|
| 44 |
+
"eval_runtime": 55.8537,
|
| 45 |
+
"eval_samples_per_second": 80.335,
|
| 46 |
+
"eval_steps_per_second": 5.031,
|
| 47 |
+
"step": 500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.71,
|
| 51 |
+
"learning_rate": 4.643705463182898e-05,
|
| 52 |
+
"loss": 1.8934,
|
| 53 |
+
"step": 600
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.83,
|
| 57 |
+
"learning_rate": 4.584323040380048e-05,
|
| 58 |
+
"loss": 1.7962,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.95,
|
| 63 |
+
"learning_rate": 4.524940617577197e-05,
|
| 64 |
+
"loss": 1.7785,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 1.07,
|
| 69 |
+
"learning_rate": 4.465558194774347e-05,
|
| 70 |
+
"loss": 1.7253,
|
| 71 |
+
"step": 900
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 1.19,
|
| 75 |
+
"learning_rate": 4.406175771971497e-05,
|
| 76 |
+
"loss": 1.7079,
|
| 77 |
+
"step": 1000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.19,
|
| 81 |
+
"eval_loss": 1.5516979694366455,
|
| 82 |
+
"eval_runtime": 56.1057,
|
| 83 |
+
"eval_samples_per_second": 79.974,
|
| 84 |
+
"eval_steps_per_second": 5.008,
|
| 85 |
+
"step": 1000
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 1.31,
|
| 89 |
+
"learning_rate": 4.3467933491686466e-05,
|
| 90 |
+
"loss": 1.629,
|
| 91 |
+
"step": 1100
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.43,
|
| 95 |
+
"learning_rate": 4.287410926365796e-05,
|
| 96 |
+
"loss": 1.6273,
|
| 97 |
+
"step": 1200
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 1.54,
|
| 101 |
+
"learning_rate": 4.228028503562946e-05,
|
| 102 |
+
"loss": 1.5842,
|
| 103 |
+
"step": 1300
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.66,
|
| 107 |
+
"learning_rate": 4.168646080760095e-05,
|
| 108 |
+
"loss": 1.6089,
|
| 109 |
+
"step": 1400
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.78,
|
| 113 |
+
"learning_rate": 4.109263657957245e-05,
|
| 114 |
+
"loss": 1.5614,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.78,
|
| 119 |
+
"eval_loss": 1.4558075666427612,
|
| 120 |
+
"eval_runtime": 56.2297,
|
| 121 |
+
"eval_samples_per_second": 79.798,
|
| 122 |
+
"eval_steps_per_second": 4.997,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.9,
|
| 127 |
+
"learning_rate": 4.049881235154395e-05,
|
| 128 |
+
"loss": 1.5462,
|
| 129 |
+
"step": 1600
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.02,
|
| 133 |
+
"learning_rate": 3.990498812351544e-05,
|
| 134 |
+
"loss": 1.5253,
|
| 135 |
+
"step": 1700
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.14,
|
| 139 |
+
"learning_rate": 3.9311163895486934e-05,
|
| 140 |
+
"loss": 1.4815,
|
| 141 |
+
"step": 1800
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.26,
|
| 145 |
+
"learning_rate": 3.8717339667458435e-05,
|
| 146 |
+
"loss": 1.5012,
|
| 147 |
+
"step": 1900
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.38,
|
| 151 |
+
"learning_rate": 3.812351543942993e-05,
|
| 152 |
+
"loss": 1.4384,
|
| 153 |
+
"step": 2000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 2.38,
|
| 157 |
+
"eval_loss": 1.3825178146362305,
|
| 158 |
+
"eval_runtime": 56.3145,
|
| 159 |
+
"eval_samples_per_second": 79.678,
|
| 160 |
+
"eval_steps_per_second": 4.99,
|
| 161 |
+
"step": 2000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.49,
|
| 165 |
+
"learning_rate": 3.752969121140142e-05,
|
| 166 |
+
"loss": 1.4401,
|
| 167 |
+
"step": 2100
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.61,
|
| 171 |
+
"learning_rate": 3.693586698337292e-05,
|
| 172 |
+
"loss": 1.4834,
|
| 173 |
+
"step": 2200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 2.73,
|
| 177 |
+
"learning_rate": 3.6342042755344416e-05,
|
| 178 |
+
"loss": 1.4534,
|
| 179 |
+
"step": 2300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.85,
|
| 183 |
+
"learning_rate": 3.5748218527315916e-05,
|
| 184 |
+
"loss": 1.4139,
|
| 185 |
+
"step": 2400
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.97,
|
| 189 |
+
"learning_rate": 3.515439429928741e-05,
|
| 190 |
+
"loss": 1.3972,
|
| 191 |
+
"step": 2500
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.97,
|
| 195 |
+
"eval_loss": 1.3105206489562988,
|
| 196 |
+
"eval_runtime": 56.1399,
|
| 197 |
+
"eval_samples_per_second": 79.925,
|
| 198 |
+
"eval_steps_per_second": 5.005,
|
| 199 |
+
"step": 2500
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.09,
|
| 203 |
+
"learning_rate": 3.456057007125891e-05,
|
| 204 |
+
"loss": 1.4154,
|
| 205 |
+
"step": 2600
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 3.21,
|
| 209 |
+
"learning_rate": 3.396674584323041e-05,
|
| 210 |
+
"loss": 1.3644,
|
| 211 |
+
"step": 2700
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 3.33,
|
| 215 |
+
"learning_rate": 3.3372921615201904e-05,
|
| 216 |
+
"loss": 1.3769,
|
| 217 |
+
"step": 2800
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 3.44,
|
| 221 |
+
"learning_rate": 3.27790973871734e-05,
|
| 222 |
+
"loss": 1.3772,
|
| 223 |
+
"step": 2900
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 3.56,
|
| 227 |
+
"learning_rate": 3.21852731591449e-05,
|
| 228 |
+
"loss": 1.3532,
|
| 229 |
+
"step": 3000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.56,
|
| 233 |
+
"eval_loss": 1.2871623039245605,
|
| 234 |
+
"eval_runtime": 56.4013,
|
| 235 |
+
"eval_samples_per_second": 79.555,
|
| 236 |
+
"eval_steps_per_second": 4.982,
|
| 237 |
+
"step": 3000
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 3.68,
|
| 241 |
+
"learning_rate": 3.159144893111639e-05,
|
| 242 |
+
"loss": 1.3614,
|
| 243 |
+
"step": 3100
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.8,
|
| 247 |
+
"learning_rate": 3.0997624703087885e-05,
|
| 248 |
+
"loss": 1.3531,
|
| 249 |
+
"step": 3200
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 3.92,
|
| 253 |
+
"learning_rate": 3.0403800475059386e-05,
|
| 254 |
+
"loss": 1.3365,
|
| 255 |
+
"step": 3300
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.04,
|
| 259 |
+
"learning_rate": 2.980997624703088e-05,
|
| 260 |
+
"loss": 1.3075,
|
| 261 |
+
"step": 3400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.16,
|
| 265 |
+
"learning_rate": 2.9216152019002373e-05,
|
| 266 |
+
"loss": 1.3114,
|
| 267 |
+
"step": 3500
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.16,
|
| 271 |
+
"eval_loss": 1.2454777956008911,
|
| 272 |
+
"eval_runtime": 56.1952,
|
| 273 |
+
"eval_samples_per_second": 79.847,
|
| 274 |
+
"eval_steps_per_second": 5.0,
|
| 275 |
+
"step": 3500
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 4.28,
|
| 279 |
+
"learning_rate": 2.8622327790973873e-05,
|
| 280 |
+
"loss": 1.2952,
|
| 281 |
+
"step": 3600
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 4.39,
|
| 285 |
+
"learning_rate": 2.8028503562945367e-05,
|
| 286 |
+
"loss": 1.3133,
|
| 287 |
+
"step": 3700
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 4.51,
|
| 291 |
+
"learning_rate": 2.7434679334916867e-05,
|
| 292 |
+
"loss": 1.3225,
|
| 293 |
+
"step": 3800
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 4.63,
|
| 297 |
+
"learning_rate": 2.6840855106888364e-05,
|
| 298 |
+
"loss": 1.2958,
|
| 299 |
+
"step": 3900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 4.75,
|
| 303 |
+
"learning_rate": 2.6247030878859858e-05,
|
| 304 |
+
"loss": 1.269,
|
| 305 |
+
"step": 4000
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 4.75,
|
| 309 |
+
"eval_loss": 1.2113255262374878,
|
| 310 |
+
"eval_runtime": 57.2608,
|
| 311 |
+
"eval_samples_per_second": 78.361,
|
| 312 |
+
"eval_steps_per_second": 4.907,
|
| 313 |
+
"step": 4000
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 4.87,
|
| 317 |
+
"learning_rate": 2.5653206650831358e-05,
|
| 318 |
+
"loss": 1.2693,
|
| 319 |
+
"step": 4100
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 4.99,
|
| 323 |
+
"learning_rate": 2.5059382422802852e-05,
|
| 324 |
+
"loss": 1.2646,
|
| 325 |
+
"step": 4200
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 5.11,
|
| 329 |
+
"learning_rate": 2.446555819477435e-05,
|
| 330 |
+
"loss": 1.2702,
|
| 331 |
+
"step": 4300
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 5.23,
|
| 335 |
+
"learning_rate": 2.3871733966745842e-05,
|
| 336 |
+
"loss": 1.2568,
|
| 337 |
+
"step": 4400
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 5.34,
|
| 341 |
+
"learning_rate": 2.327790973871734e-05,
|
| 342 |
+
"loss": 1.2525,
|
| 343 |
+
"step": 4500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"epoch": 5.34,
|
| 347 |
+
"eval_loss": 1.1863404512405396,
|
| 348 |
+
"eval_runtime": 56.357,
|
| 349 |
+
"eval_samples_per_second": 79.617,
|
| 350 |
+
"eval_steps_per_second": 4.986,
|
| 351 |
+
"step": 4500
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 5.46,
|
| 355 |
+
"learning_rate": 2.2684085510688836e-05,
|
| 356 |
+
"loss": 1.2343,
|
| 357 |
+
"step": 4600
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 5.58,
|
| 361 |
+
"learning_rate": 2.2090261282660333e-05,
|
| 362 |
+
"loss": 1.2289,
|
| 363 |
+
"step": 4700
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 5.7,
|
| 367 |
+
"learning_rate": 2.149643705463183e-05,
|
| 368 |
+
"loss": 1.2091,
|
| 369 |
+
"step": 4800
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 5.82,
|
| 373 |
+
"learning_rate": 2.0902612826603327e-05,
|
| 374 |
+
"loss": 1.2231,
|
| 375 |
+
"step": 4900
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 5.94,
|
| 379 |
+
"learning_rate": 2.0308788598574824e-05,
|
| 380 |
+
"loss": 1.2171,
|
| 381 |
+
"step": 5000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 5.94,
|
| 385 |
+
"eval_loss": 1.1596688032150269,
|
| 386 |
+
"eval_runtime": 56.2736,
|
| 387 |
+
"eval_samples_per_second": 79.735,
|
| 388 |
+
"eval_steps_per_second": 4.993,
|
| 389 |
+
"step": 5000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 6.06,
|
| 393 |
+
"learning_rate": 1.9714964370546318e-05,
|
| 394 |
+
"loss": 1.1989,
|
| 395 |
+
"step": 5100
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 6.18,
|
| 399 |
+
"learning_rate": 1.9121140142517815e-05,
|
| 400 |
+
"loss": 1.2272,
|
| 401 |
+
"step": 5200
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 6.29,
|
| 405 |
+
"learning_rate": 1.8527315914489312e-05,
|
| 406 |
+
"loss": 1.2426,
|
| 407 |
+
"step": 5300
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 6.41,
|
| 411 |
+
"learning_rate": 1.793349168646081e-05,
|
| 412 |
+
"loss": 1.1808,
|
| 413 |
+
"step": 5400
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 6.53,
|
| 417 |
+
"learning_rate": 1.7339667458432306e-05,
|
| 418 |
+
"loss": 1.1669,
|
| 419 |
+
"step": 5500
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 6.53,
|
| 423 |
+
"eval_loss": 1.141239047050476,
|
| 424 |
+
"eval_runtime": 56.1754,
|
| 425 |
+
"eval_samples_per_second": 79.875,
|
| 426 |
+
"eval_steps_per_second": 5.002,
|
| 427 |
+
"step": 5500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 6.65,
|
| 431 |
+
"learning_rate": 1.6745843230403803e-05,
|
| 432 |
+
"loss": 1.2044,
|
| 433 |
+
"step": 5600
|
| 434 |
+
},
|
| 435 |
+
{
|
| 436 |
+
"epoch": 6.77,
|
| 437 |
+
"learning_rate": 1.61520190023753e-05,
|
| 438 |
+
"loss": 1.1781,
|
| 439 |
+
"step": 5700
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 6.89,
|
| 443 |
+
"learning_rate": 1.5558194774346793e-05,
|
| 444 |
+
"loss": 1.1757,
|
| 445 |
+
"step": 5800
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 7.01,
|
| 449 |
+
"learning_rate": 1.496437054631829e-05,
|
| 450 |
+
"loss": 1.1777,
|
| 451 |
+
"step": 5900
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 7.13,
|
| 455 |
+
"learning_rate": 1.4370546318289787e-05,
|
| 456 |
+
"loss": 1.1529,
|
| 457 |
+
"step": 6000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 7.13,
|
| 461 |
+
"eval_loss": 1.1352198123931885,
|
| 462 |
+
"eval_runtime": 56.8461,
|
| 463 |
+
"eval_samples_per_second": 78.932,
|
| 464 |
+
"eval_steps_per_second": 4.943,
|
| 465 |
+
"step": 6000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 7.24,
|
| 469 |
+
"learning_rate": 1.3776722090261283e-05,
|
| 470 |
+
"loss": 1.1854,
|
| 471 |
+
"step": 6100
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 7.36,
|
| 475 |
+
"learning_rate": 1.318289786223278e-05,
|
| 476 |
+
"loss": 1.1736,
|
| 477 |
+
"step": 6200
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 7.48,
|
| 481 |
+
"learning_rate": 1.2589073634204277e-05,
|
| 482 |
+
"loss": 1.1932,
|
| 483 |
+
"step": 6300
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 7.6,
|
| 487 |
+
"learning_rate": 1.1995249406175772e-05,
|
| 488 |
+
"loss": 1.1431,
|
| 489 |
+
"step": 6400
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 7.72,
|
| 493 |
+
"learning_rate": 1.1401425178147269e-05,
|
| 494 |
+
"loss": 1.1532,
|
| 495 |
+
"step": 6500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 7.72,
|
| 499 |
+
"eval_loss": 1.1115353107452393,
|
| 500 |
+
"eval_runtime": 56.4012,
|
| 501 |
+
"eval_samples_per_second": 79.555,
|
| 502 |
+
"eval_steps_per_second": 4.982,
|
| 503 |
+
"step": 6500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 7.84,
|
| 507 |
+
"learning_rate": 1.0807600950118766e-05,
|
| 508 |
+
"loss": 1.1762,
|
| 509 |
+
"step": 6600
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 7.96,
|
| 513 |
+
"learning_rate": 1.0213776722090261e-05,
|
| 514 |
+
"loss": 1.1327,
|
| 515 |
+
"step": 6700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 8.08,
|
| 519 |
+
"learning_rate": 9.619952494061758e-06,
|
| 520 |
+
"loss": 1.1492,
|
| 521 |
+
"step": 6800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 8.19,
|
| 525 |
+
"learning_rate": 9.026128266033253e-06,
|
| 526 |
+
"loss": 1.1214,
|
| 527 |
+
"step": 6900
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 8.31,
|
| 531 |
+
"learning_rate": 8.432304038004752e-06,
|
| 532 |
+
"loss": 1.1684,
|
| 533 |
+
"step": 7000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 8.31,
|
| 537 |
+
"eval_loss": 1.1077940464019775,
|
| 538 |
+
"eval_runtime": 56.2764,
|
| 539 |
+
"eval_samples_per_second": 79.731,
|
| 540 |
+
"eval_steps_per_second": 4.993,
|
| 541 |
+
"step": 7000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 8.43,
|
| 545 |
+
"learning_rate": 7.838479809976247e-06,
|
| 546 |
+
"loss": 1.154,
|
| 547 |
+
"step": 7100
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 8.55,
|
| 551 |
+
"learning_rate": 7.244655581947744e-06,
|
| 552 |
+
"loss": 1.1439,
|
| 553 |
+
"step": 7200
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 8.67,
|
| 557 |
+
"learning_rate": 6.6508313539192404e-06,
|
| 558 |
+
"loss": 1.1398,
|
| 559 |
+
"step": 7300
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 8.79,
|
| 563 |
+
"learning_rate": 6.0570071258907366e-06,
|
| 564 |
+
"loss": 1.117,
|
| 565 |
+
"step": 7400
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 8.91,
|
| 569 |
+
"learning_rate": 5.4631828978622335e-06,
|
| 570 |
+
"loss": 1.1286,
|
| 571 |
+
"step": 7500
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 8.91,
|
| 575 |
+
"eval_loss": 1.0950287580490112,
|
| 576 |
+
"eval_runtime": 56.0134,
|
| 577 |
+
"eval_samples_per_second": 80.106,
|
| 578 |
+
"eval_steps_per_second": 5.017,
|
| 579 |
+
"step": 7500
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.03,
|
| 583 |
+
"learning_rate": 4.86935866983373e-06,
|
| 584 |
+
"loss": 1.1485,
|
| 585 |
+
"step": 7600
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 9.14,
|
| 589 |
+
"learning_rate": 4.275534441805226e-06,
|
| 590 |
+
"loss": 1.1273,
|
| 591 |
+
"step": 7700
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 9.26,
|
| 595 |
+
"learning_rate": 3.681710213776722e-06,
|
| 596 |
+
"loss": 1.1412,
|
| 597 |
+
"step": 7800
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 9.38,
|
| 601 |
+
"learning_rate": 3.0878859857482185e-06,
|
| 602 |
+
"loss": 1.1206,
|
| 603 |
+
"step": 7900
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 9.5,
|
| 607 |
+
"learning_rate": 2.494061757719715e-06,
|
| 608 |
+
"loss": 1.1416,
|
| 609 |
+
"step": 8000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 9.5,
|
| 613 |
+
"eval_loss": 1.0948013067245483,
|
| 614 |
+
"eval_runtime": 56.75,
|
| 615 |
+
"eval_samples_per_second": 79.066,
|
| 616 |
+
"eval_steps_per_second": 4.952,
|
| 617 |
+
"step": 8000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 9.62,
|
| 621 |
+
"learning_rate": 1.9002375296912116e-06,
|
| 622 |
+
"loss": 1.1101,
|
| 623 |
+
"step": 8100
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 9.74,
|
| 627 |
+
"learning_rate": 1.306413301662708e-06,
|
| 628 |
+
"loss": 1.1181,
|
| 629 |
+
"step": 8200
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 9.86,
|
| 633 |
+
"learning_rate": 7.125890736342043e-07,
|
| 634 |
+
"loss": 1.0831,
|
| 635 |
+
"step": 8300
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 9.98,
|
| 639 |
+
"learning_rate": 1.1876484560570073e-07,
|
| 640 |
+
"loss": 1.1164,
|
| 641 |
+
"step": 8400
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 10.0,
|
| 645 |
+
"step": 8420,
|
| 646 |
+
"total_flos": 3.5427566278656e+16,
|
| 647 |
+
"train_loss": 1.365048002347244,
|
| 648 |
+
"train_runtime": 5770.015,
|
| 649 |
+
"train_samples_per_second": 23.327,
|
| 650 |
+
"train_steps_per_second": 1.459
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 10.0,
|
| 654 |
+
"eval_loss": 1.0815315246582031,
|
| 655 |
+
"eval_runtime": 57.2783,
|
| 656 |
+
"eval_samples_per_second": 78.337,
|
| 657 |
+
"eval_steps_per_second": 4.906,
|
| 658 |
+
"step": 8420
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 10.0,
|
| 662 |
+
"eval_loss": 1.0882647037506104,
|
| 663 |
+
"eval_runtime": 56.9424,
|
| 664 |
+
"eval_samples_per_second": 78.799,
|
| 665 |
+
"eval_steps_per_second": 4.935,
|
| 666 |
+
"step": 8420
|
| 667 |
+
}
|
| 668 |
+
],
|
| 669 |
+
"logging_steps": 100,
|
| 670 |
+
"max_steps": 8420,
|
| 671 |
+
"num_train_epochs": 10,
|
| 672 |
+
"save_steps": 500,
|
| 673 |
+
"total_flos": 3.5427566278656e+16,
|
| 674 |
+
"trial_name": null,
|
| 675 |
+
"trial_params": null
|
| 676 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc58ec884710a9804ea436ffd5576afa5b61e98db1e7c3c80492c31276243bf7
|
| 3 |
+
size 4600
|