adding model files
Browse files- .gitignore +1 -0
- README.md +61 -0
- config.json +29 -0
- pytorch_model.bin +3 -0
- trainer_state.json +675 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
README.md
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
tags:
|
| 4 |
+
- generated_from_trainer
|
| 5 |
+
model-index:
|
| 6 |
+
- name: opt-125m-emailgen-v2_DS-aeslc_Ep-4_Bs-8
|
| 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 |
+
# opt-125m-emailgen-v2_DS-aeslc_Ep-4_Bs-8
|
| 14 |
+
|
| 15 |
+
This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on an unknown dataset.
|
| 16 |
+
It achieves the following results on the evaluation set:
|
| 17 |
+
- Loss: 2.5552
|
| 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: 0.0004
|
| 37 |
+
- train_batch_size: 8
|
| 38 |
+
- eval_batch_size: 8
|
| 39 |
+
- seed: 42
|
| 40 |
+
- distributed_type: multi-GPU
|
| 41 |
+
- gradient_accumulation_steps: 16
|
| 42 |
+
- total_train_batch_size: 128
|
| 43 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 44 |
+
- lr_scheduler_type: cosine
|
| 45 |
+
- num_epochs: 4
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.8245 | 1.0 | 129 | 2.8030 |
|
| 52 |
+
| 2.521 | 2.0 | 258 | 2.6343 |
|
| 53 |
+
| 2.2074 | 3.0 | 387 | 2.5595 |
|
| 54 |
+
| 2.0145 | 4.0 | 516 | 2.5552 |
|
| 55 |
+
|
| 56 |
+
|
| 57 |
+
### Framework versions
|
| 58 |
+
|
| 59 |
+
- Transformers 4.20.1
|
| 60 |
+
- Pytorch 1.11.0+cu113
|
| 61 |
+
- Tokenizers 0.12.1
|
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/opt-125m",
|
| 3 |
+
"_remove_final_layer_norm": false,
|
| 4 |
+
"activation_dropout": 0.0,
|
| 5 |
+
"activation_function": "relu",
|
| 6 |
+
"architectures": [
|
| 7 |
+
"OPTForCausalLM"
|
| 8 |
+
],
|
| 9 |
+
"attention_dropout": 0.0,
|
| 10 |
+
"bos_token_id": 2,
|
| 11 |
+
"do_layer_norm_before": true,
|
| 12 |
+
"dropout": 0.1,
|
| 13 |
+
"eos_token_id": 2,
|
| 14 |
+
"ffn_dim": 3072,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"init_std": 0.02,
|
| 17 |
+
"layerdrop": 0.0,
|
| 18 |
+
"max_position_embeddings": 2048,
|
| 19 |
+
"model_type": "opt",
|
| 20 |
+
"num_attention_heads": 12,
|
| 21 |
+
"num_hidden_layers": 12,
|
| 22 |
+
"pad_token_id": 1,
|
| 23 |
+
"prefix": "</s>",
|
| 24 |
+
"torch_dtype": "float32",
|
| 25 |
+
"transformers_version": "4.20.1",
|
| 26 |
+
"use_cache": false,
|
| 27 |
+
"vocab_size": 50265,
|
| 28 |
+
"word_embed_proj_dim": 768
|
| 29 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5191c336ff36350e9a9dd18e527cf0501eb591c8e0753d5aeef039d9a3c24bca
|
| 3 |
+
size 500962539
|
trainer_state.json
ADDED
|
@@ -0,0 +1,675 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.99758337361044,
|
| 5 |
+
"global_step": 516,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 0.0003999073369028083,
|
| 13 |
+
"loss": 4.4497,
|
| 14 |
+
"step": 5
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"learning_rate": 0.00039962943347572903,
|
| 19 |
+
"loss": 3.7433,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.12,
|
| 24 |
+
"learning_rate": 0.00039916654723268495,
|
| 25 |
+
"loss": 3.4124,
|
| 26 |
+
"step": 15
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.15,
|
| 30 |
+
"learning_rate": 0.0003985191070984053,
|
| 31 |
+
"loss": 3.3596,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.19,
|
| 36 |
+
"learning_rate": 0.000397687713010971,
|
| 37 |
+
"loss": 3.2361,
|
| 38 |
+
"step": 25
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.23,
|
| 42 |
+
"learning_rate": 0.00039667313536589325,
|
| 43 |
+
"loss": 3.2741,
|
| 44 |
+
"step": 30
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.27,
|
| 48 |
+
"learning_rate": 0.0003954763143022415,
|
| 49 |
+
"loss": 3.1754,
|
| 50 |
+
"step": 35
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.31,
|
| 54 |
+
"learning_rate": 0.00039409835883148103,
|
| 55 |
+
"loss": 3.1644,
|
| 56 |
+
"step": 40
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.35,
|
| 60 |
+
"learning_rate": 0.00039254054580982917,
|
| 61 |
+
"loss": 3.158,
|
| 62 |
+
"step": 45
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.39,
|
| 66 |
+
"learning_rate": 0.00039080431875508013,
|
| 67 |
+
"loss": 3.1109,
|
| 68 |
+
"step": 50
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.43,
|
| 72 |
+
"learning_rate": 0.00038889128650899707,
|
| 73 |
+
"loss": 3.1248,
|
| 74 |
+
"step": 55
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.46,
|
| 78 |
+
"learning_rate": 0.0003868032217465096,
|
| 79 |
+
"loss": 3.01,
|
| 80 |
+
"step": 60
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5,
|
| 84 |
+
"learning_rate": 0.00038454205933309793,
|
| 85 |
+
"loss": 3.1002,
|
| 86 |
+
"step": 65
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.54,
|
| 90 |
+
"learning_rate": 0.0003821098945318869,
|
| 91 |
+
"loss": 3.001,
|
| 92 |
+
"step": 70
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.58,
|
| 96 |
+
"learning_rate": 0.0003795089810621101,
|
| 97 |
+
"loss": 3.0187,
|
| 98 |
+
"step": 75
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.62,
|
| 102 |
+
"learning_rate": 0.00037674172901074385,
|
| 103 |
+
"loss": 2.9759,
|
| 104 |
+
"step": 80
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.66,
|
| 108 |
+
"learning_rate": 0.0003738107025992461,
|
| 109 |
+
"loss": 2.8984,
|
| 110 |
+
"step": 85
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.7,
|
| 114 |
+
"learning_rate": 0.0003707186178074693,
|
| 115 |
+
"loss": 2.9715,
|
| 116 |
+
"step": 90
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.73,
|
| 120 |
+
"learning_rate": 0.0003674683398569492,
|
| 121 |
+
"loss": 3.0181,
|
| 122 |
+
"step": 95
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.77,
|
| 126 |
+
"learning_rate": 0.0003640628805559022,
|
| 127 |
+
"loss": 3.0082,
|
| 128 |
+
"step": 100
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.81,
|
| 132 |
+
"learning_rate": 0.00036050539550839015,
|
| 133 |
+
"loss": 2.9286,
|
| 134 |
+
"step": 105
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.85,
|
| 138 |
+
"learning_rate": 0.0003567991811902403,
|
| 139 |
+
"loss": 2.9238,
|
| 140 |
+
"step": 110
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.89,
|
| 144 |
+
"learning_rate": 0.0003529476718944283,
|
| 145 |
+
"loss": 2.9692,
|
| 146 |
+
"step": 115
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.93,
|
| 150 |
+
"learning_rate": 0.0003489544365487564,
|
| 151 |
+
"loss": 2.9091,
|
| 152 |
+
"step": 120
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.97,
|
| 156 |
+
"learning_rate": 0.000344823175408774,
|
| 157 |
+
"loss": 2.8245,
|
| 158 |
+
"step": 125
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.0,
|
| 162 |
+
"eval_loss": 2.8029613494873047,
|
| 163 |
+
"eval_runtime": 57.7962,
|
| 164 |
+
"eval_samples_per_second": 33.013,
|
| 165 |
+
"eval_steps_per_second": 4.135,
|
| 166 |
+
"step": 129
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.01,
|
| 170 |
+
"learning_rate": 0.00034055771662900637,
|
| 171 |
+
"loss": 3.0457,
|
| 172 |
+
"step": 130
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.05,
|
| 176 |
+
"learning_rate": 0.00033616201271566845,
|
| 177 |
+
"loss": 2.5236,
|
| 178 |
+
"step": 135
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.09,
|
| 182 |
+
"learning_rate": 0.0003316401368641496,
|
| 183 |
+
"loss": 2.6179,
|
| 184 |
+
"step": 140
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.12,
|
| 188 |
+
"learning_rate": 0.0003269962791846651,
|
| 189 |
+
"loss": 2.5468,
|
| 190 |
+
"step": 145
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.16,
|
| 194 |
+
"learning_rate": 0.00032223474281956987,
|
| 195 |
+
"loss": 2.6191,
|
| 196 |
+
"step": 150
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.2,
|
| 200 |
+
"learning_rate": 0.0003173599399559337,
|
| 201 |
+
"loss": 2.639,
|
| 202 |
+
"step": 155
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.24,
|
| 206 |
+
"learning_rate": 0.0003123763877370721,
|
| 207 |
+
"loss": 2.6327,
|
| 208 |
+
"step": 160
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.28,
|
| 212 |
+
"learning_rate": 0.00030728870407682117,
|
| 213 |
+
"loss": 2.6121,
|
| 214 |
+
"step": 165
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.32,
|
| 218 |
+
"learning_rate": 0.0003021016033804358,
|
| 219 |
+
"loss": 2.465,
|
| 220 |
+
"step": 170
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.36,
|
| 224 |
+
"learning_rate": 0.0002968198921760758,
|
| 225 |
+
"loss": 2.619,
|
| 226 |
+
"step": 175
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.39,
|
| 230 |
+
"learning_rate": 0.0002914484646609277,
|
| 231 |
+
"loss": 2.5499,
|
| 232 |
+
"step": 180
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.43,
|
| 236 |
+
"learning_rate": 0.0002859922981660906,
|
| 237 |
+
"loss": 2.5248,
|
| 238 |
+
"step": 185
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 1.47,
|
| 242 |
+
"learning_rate": 0.0002804564485444265,
|
| 243 |
+
"loss": 2.6074,
|
| 244 |
+
"step": 190
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 1.51,
|
| 248 |
+
"learning_rate": 0.00027484604548565065,
|
| 249 |
+
"loss": 2.5412,
|
| 250 |
+
"step": 195
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.55,
|
| 254 |
+
"learning_rate": 0.0002691662877630023,
|
| 255 |
+
"loss": 2.5677,
|
| 256 |
+
"step": 200
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.59,
|
| 260 |
+
"learning_rate": 0.0002634224384159003,
|
| 261 |
+
"loss": 2.5344,
|
| 262 |
+
"step": 205
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.63,
|
| 266 |
+
"learning_rate": 0.00025761981987304755,
|
| 267 |
+
"loss": 2.5655,
|
| 268 |
+
"step": 210
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.67,
|
| 272 |
+
"learning_rate": 0.00025176380902050413,
|
| 273 |
+
"loss": 2.5598,
|
| 274 |
+
"step": 215
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.7,
|
| 278 |
+
"learning_rate": 0.00024585983221929805,
|
| 279 |
+
"loss": 2.5926,
|
| 280 |
+
"step": 220
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 1.74,
|
| 284 |
+
"learning_rate": 0.00023991336027719059,
|
| 285 |
+
"loss": 2.4798,
|
| 286 |
+
"step": 225
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 1.78,
|
| 290 |
+
"learning_rate": 0.00023392990337925694,
|
| 291 |
+
"loss": 2.4976,
|
| 292 |
+
"step": 230
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.82,
|
| 296 |
+
"learning_rate": 0.000227915005981978,
|
| 297 |
+
"loss": 2.5969,
|
| 298 |
+
"step": 235
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.86,
|
| 302 |
+
"learning_rate": 0.00022187424167557492,
|
| 303 |
+
"loss": 2.5677,
|
| 304 |
+
"step": 240
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.9,
|
| 308 |
+
"learning_rate": 0.000215813208019348,
|
| 309 |
+
"loss": 2.6221,
|
| 310 |
+
"step": 245
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.94,
|
| 314 |
+
"learning_rate": 0.00020973752135480505,
|
| 315 |
+
"loss": 2.5241,
|
| 316 |
+
"step": 250
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.97,
|
| 320 |
+
"learning_rate": 0.000203652811601385,
|
| 321 |
+
"loss": 2.521,
|
| 322 |
+
"step": 255
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.0,
|
| 326 |
+
"eval_loss": 2.634265899658203,
|
| 327 |
+
"eval_runtime": 57.8082,
|
| 328 |
+
"eval_samples_per_second": 33.006,
|
| 329 |
+
"eval_steps_per_second": 4.134,
|
| 330 |
+
"step": 258
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.02,
|
| 334 |
+
"learning_rate": 0.0001975647170396005,
|
| 335 |
+
"loss": 2.5802,
|
| 336 |
+
"step": 260
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.05,
|
| 340 |
+
"learning_rate": 0.00019147887908643253,
|
| 341 |
+
"loss": 2.2447,
|
| 342 |
+
"step": 265
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.09,
|
| 346 |
+
"learning_rate": 0.0001854009370678185,
|
| 347 |
+
"loss": 2.2409,
|
| 348 |
+
"step": 270
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.13,
|
| 352 |
+
"learning_rate": 0.00017933652299307847,
|
| 353 |
+
"loss": 2.2383,
|
| 354 |
+
"step": 275
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.17,
|
| 358 |
+
"learning_rate": 0.00017329125633612044,
|
| 359 |
+
"loss": 2.2028,
|
| 360 |
+
"step": 280
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 2.21,
|
| 364 |
+
"learning_rate": 0.00016727073882826242,
|
| 365 |
+
"loss": 2.1655,
|
| 366 |
+
"step": 285
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 2.25,
|
| 370 |
+
"learning_rate": 0.00016128054926749404,
|
| 371 |
+
"loss": 2.2198,
|
| 372 |
+
"step": 290
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 2.29,
|
| 376 |
+
"learning_rate": 0.00015532623834899002,
|
| 377 |
+
"loss": 2.2186,
|
| 378 |
+
"step": 295
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 2.32,
|
| 382 |
+
"learning_rate": 0.00014941332352166385,
|
| 383 |
+
"loss": 2.2225,
|
| 384 |
+
"step": 300
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.36,
|
| 388 |
+
"learning_rate": 0.00014354728387552882,
|
| 389 |
+
"loss": 2.2135,
|
| 390 |
+
"step": 305
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.4,
|
| 394 |
+
"learning_rate": 0.00013773355506460367,
|
| 395 |
+
"loss": 2.1537,
|
| 396 |
+
"step": 310
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.44,
|
| 400 |
+
"learning_rate": 0.00013197752427006679,
|
| 401 |
+
"loss": 2.2074,
|
| 402 |
+
"step": 315
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 2.48,
|
| 406 |
+
"learning_rate": 0.00012628452520832765,
|
| 407 |
+
"loss": 2.1916,
|
| 408 |
+
"step": 320
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.52,
|
| 412 |
+
"learning_rate": 0.00012065983318864011,
|
| 413 |
+
"loss": 2.2548,
|
| 414 |
+
"step": 325
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 2.56,
|
| 418 |
+
"learning_rate": 0.00011510866022483702,
|
| 419 |
+
"loss": 2.2211,
|
| 420 |
+
"step": 330
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.6,
|
| 424 |
+
"learning_rate": 0.00010963615020571705,
|
| 425 |
+
"loss": 2.1348,
|
| 426 |
+
"step": 335
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 2.63,
|
| 430 |
+
"learning_rate": 0.00010424737412855825,
|
| 431 |
+
"loss": 2.2425,
|
| 432 |
+
"step": 340
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.67,
|
| 436 |
+
"learning_rate": 9.894732540017415e-05,
|
| 437 |
+
"loss": 2.207,
|
| 438 |
+
"step": 345
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.71,
|
| 442 |
+
"learning_rate": 9.374091520986936e-05,
|
| 443 |
+
"loss": 2.1436,
|
| 444 |
+
"step": 350
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.75,
|
| 448 |
+
"learning_rate": 8.863296797857865e-05,
|
| 449 |
+
"loss": 2.1318,
|
| 450 |
+
"step": 355
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.79,
|
| 454 |
+
"learning_rate": 8.362821688840947e-05,
|
| 455 |
+
"loss": 2.193,
|
| 456 |
+
"step": 360
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.83,
|
| 460 |
+
"learning_rate": 7.873129949672862e-05,
|
| 461 |
+
"loss": 2.1751,
|
| 462 |
+
"step": 365
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.87,
|
| 466 |
+
"learning_rate": 7.394675343885826e-05,
|
| 467 |
+
"loss": 2.2015,
|
| 468 |
+
"step": 370
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.9,
|
| 472 |
+
"learning_rate": 6.927901222336221e-05,
|
| 473 |
+
"loss": 2.1469,
|
| 474 |
+
"step": 375
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.94,
|
| 478 |
+
"learning_rate": 6.473240112381944e-05,
|
| 479 |
+
"loss": 2.1919,
|
| 480 |
+
"step": 380
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.98,
|
| 484 |
+
"learning_rate": 6.0311133170892234e-05,
|
| 485 |
+
"loss": 2.2074,
|
| 486 |
+
"step": 385
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 3.0,
|
| 490 |
+
"eval_loss": 2.5594911575317383,
|
| 491 |
+
"eval_runtime": 57.8697,
|
| 492 |
+
"eval_samples_per_second": 32.971,
|
| 493 |
+
"eval_steps_per_second": 4.13,
|
| 494 |
+
"step": 387
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.02,
|
| 498 |
+
"learning_rate": 5.601930524840086e-05,
|
| 499 |
+
"loss": 2.1884,
|
| 500 |
+
"step": 390
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.06,
|
| 504 |
+
"learning_rate": 5.186089429702436e-05,
|
| 505 |
+
"loss": 2.0386,
|
| 506 |
+
"step": 395
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.1,
|
| 510 |
+
"learning_rate": 4.783975362914439e-05,
|
| 511 |
+
"loss": 2.0487,
|
| 512 |
+
"step": 400
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 3.14,
|
| 516 |
+
"learning_rate": 4.395960935824621e-05,
|
| 517 |
+
"loss": 1.8492,
|
| 518 |
+
"step": 405
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 3.18,
|
| 522 |
+
"learning_rate": 4.022405694618658e-05,
|
| 523 |
+
"loss": 2.0609,
|
| 524 |
+
"step": 410
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 3.22,
|
| 528 |
+
"learning_rate": 3.663655787152791e-05,
|
| 529 |
+
"loss": 1.9626,
|
| 530 |
+
"step": 415
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 3.26,
|
| 534 |
+
"learning_rate": 3.320043642202444e-05,
|
| 535 |
+
"loss": 1.9572,
|
| 536 |
+
"step": 420
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 3.29,
|
| 540 |
+
"learning_rate": 2.9918876614234493e-05,
|
| 541 |
+
"loss": 1.9518,
|
| 542 |
+
"step": 425
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 3.33,
|
| 546 |
+
"learning_rate": 2.679491924311226e-05,
|
| 547 |
+
"loss": 2.0956,
|
| 548 |
+
"step": 430
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.37,
|
| 552 |
+
"learning_rate": 2.3831459064312743e-05,
|
| 553 |
+
"loss": 1.997,
|
| 554 |
+
"step": 435
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.41,
|
| 558 |
+
"learning_rate": 2.1031242111821635e-05,
|
| 559 |
+
"loss": 1.965,
|
| 560 |
+
"step": 440
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 3.45,
|
| 564 |
+
"learning_rate": 1.8396863153395216e-05,
|
| 565 |
+
"loss": 2.0042,
|
| 566 |
+
"step": 445
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 3.49,
|
| 570 |
+
"learning_rate": 1.593076328616814e-05,
|
| 571 |
+
"loss": 2.009,
|
| 572 |
+
"step": 450
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 3.53,
|
| 576 |
+
"learning_rate": 1.3635227674657147e-05,
|
| 577 |
+
"loss": 1.9708,
|
| 578 |
+
"step": 455
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.56,
|
| 582 |
+
"learning_rate": 1.1512383433257112e-05,
|
| 583 |
+
"loss": 1.9904,
|
| 584 |
+
"step": 460
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.6,
|
| 588 |
+
"learning_rate": 9.564197655190609e-06,
|
| 589 |
+
"loss": 1.9272,
|
| 590 |
+
"step": 465
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 3.64,
|
| 594 |
+
"learning_rate": 7.792475589738679e-06,
|
| 595 |
+
"loss": 1.9683,
|
| 596 |
+
"step": 470
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 3.68,
|
| 600 |
+
"learning_rate": 6.198858969440747e-06,
|
| 601 |
+
"loss": 1.9925,
|
| 602 |
+
"step": 475
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 3.72,
|
| 606 |
+
"learning_rate": 4.784824488814588e-06,
|
| 607 |
+
"loss": 1.969,
|
| 608 |
+
"step": 480
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.76,
|
| 612 |
+
"learning_rate": 3.5516824360052546e-06,
|
| 613 |
+
"loss": 1.9914,
|
| 614 |
+
"step": 485
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.8,
|
| 618 |
+
"learning_rate": 2.500575478631717e-06,
|
| 619 |
+
"loss": 1.867,
|
| 620 |
+
"step": 490
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 3.84,
|
| 624 |
+
"learning_rate": 1.6324776049554401e-06,
|
| 625 |
+
"loss": 2.0106,
|
| 626 |
+
"step": 495
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 3.87,
|
| 630 |
+
"learning_rate": 9.481932213528443e-07,
|
| 631 |
+
"loss": 1.9669,
|
| 632 |
+
"step": 500
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 3.91,
|
| 636 |
+
"learning_rate": 4.483564069273527e-07,
|
| 637 |
+
"loss": 1.9383,
|
| 638 |
+
"step": 505
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.95,
|
| 642 |
+
"learning_rate": 1.334303259521219e-07,
|
| 643 |
+
"loss": 1.9087,
|
| 644 |
+
"step": 510
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.99,
|
| 648 |
+
"learning_rate": 3.7067986876637704e-09,
|
| 649 |
+
"loss": 2.0145,
|
| 650 |
+
"step": 515
|
| 651 |
+
},
|
| 652 |
+
{
|
| 653 |
+
"epoch": 4.0,
|
| 654 |
+
"eval_loss": 2.555163860321045,
|
| 655 |
+
"eval_runtime": 57.8174,
|
| 656 |
+
"eval_samples_per_second": 33.0,
|
| 657 |
+
"eval_steps_per_second": 4.134,
|
| 658 |
+
"step": 516
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 4.0,
|
| 662 |
+
"step": 516,
|
| 663 |
+
"total_flos": 3.457207135056691e+16,
|
| 664 |
+
"train_loss": 2.476019163464391,
|
| 665 |
+
"train_runtime": 8176.7734,
|
| 666 |
+
"train_samples_per_second": 8.095,
|
| 667 |
+
"train_steps_per_second": 0.063
|
| 668 |
+
}
|
| 669 |
+
],
|
| 670 |
+
"max_steps": 516,
|
| 671 |
+
"num_train_epochs": 4,
|
| 672 |
+
"total_flos": 3.457207135056691e+16,
|
| 673 |
+
"trial_name": null,
|
| 674 |
+
"trial_params": null
|
| 675 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21fbbbf04ae745232f6880bd08d7f6a6b9f98649b60fa6c36ca6e3e2e060daf2
|
| 3 |
+
size 4335
|