End of training
Browse files- README.md +78 -0
- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- args.txt +12 -0
- train_results.json +7 -0
- trainer_state.json +668 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama2
|
| 3 |
+
base_model: lmsys/vicuna-7b-v1.5
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: mc_cot_16
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# mc_cot_16
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [lmsys/vicuna-7b-v1.5](https://huggingface.co/lmsys/vicuna-7b-v1.5) on an unknown dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 3.0303
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 0.0001
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 42 |
+
- lr_scheduler_type: linear
|
| 43 |
+
- lr_scheduler_warmup_steps: 5
|
| 44 |
+
- num_epochs: 20
|
| 45 |
+
- mixed_precision_training: Native AMP
|
| 46 |
+
|
| 47 |
+
### Training results
|
| 48 |
+
|
| 49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 51 |
+
| 2.1538 | 1.0 | 4 | 2.1552 |
|
| 52 |
+
| 1.7905 | 2.0 | 8 | 1.9012 |
|
| 53 |
+
| 1.4229 | 3.0 | 12 | 1.7686 |
|
| 54 |
+
| 1.3834 | 4.0 | 16 | 1.7070 |
|
| 55 |
+
| 1.4421 | 5.0 | 20 | 1.7308 |
|
| 56 |
+
| 0.9003 | 6.0 | 24 | 1.7646 |
|
| 57 |
+
| 0.7013 | 7.0 | 28 | 1.9070 |
|
| 58 |
+
| 0.6291 | 8.0 | 32 | 2.0078 |
|
| 59 |
+
| 0.3314 | 9.0 | 36 | 2.2682 |
|
| 60 |
+
| 0.1554 | 10.0 | 40 | 2.3624 |
|
| 61 |
+
| 0.0814 | 11.0 | 44 | 2.6523 |
|
| 62 |
+
| 0.0499 | 12.0 | 48 | 2.7565 |
|
| 63 |
+
| 0.0216 | 13.0 | 52 | 2.8505 |
|
| 64 |
+
| 0.0197 | 14.0 | 56 | 2.9170 |
|
| 65 |
+
| 0.0174 | 15.0 | 60 | 2.9433 |
|
| 66 |
+
| 0.0174 | 16.0 | 64 | 2.9683 |
|
| 67 |
+
| 0.0145 | 17.0 | 68 | 2.9966 |
|
| 68 |
+
| 0.013 | 18.0 | 72 | 3.0193 |
|
| 69 |
+
| 0.0151 | 19.0 | 76 | 3.0277 |
|
| 70 |
+
| 0.0145 | 20.0 | 80 | 3.0303 |
|
| 71 |
+
|
| 72 |
+
|
| 73 |
+
### Framework versions
|
| 74 |
+
|
| 75 |
+
- Transformers 4.36.0.dev0
|
| 76 |
+
- Pytorch 2.1.0+cu121
|
| 77 |
+
- Datasets 2.13.1
|
| 78 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "lmsys/vicuna-7b-v1.5",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 64,
|
| 12 |
+
"lora_dropout": 0.1,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"o_proj",
|
| 20 |
+
"k_proj",
|
| 21 |
+
"q_proj",
|
| 22 |
+
"up_proj",
|
| 23 |
+
"down_proj",
|
| 24 |
+
"v_proj",
|
| 25 |
+
"gate_proj"
|
| 26 |
+
],
|
| 27 |
+
"task_type": "CAUSAL_LM"
|
| 28 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7df5842fa3ab0d31a93626608e53400f6d54d99decd6da41564e2ff212ab5c1
|
| 3 |
+
size 160069834
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ec05d360d6a52ad6dbd78a151e2524fefbc14cf4d37f79219e2476c2d718f4b4
|
| 3 |
+
size 159967880
|
all_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.6028558738762513,
|
| 4 |
+
"train_runtime": 922.3939,
|
| 5 |
+
"train_samples_per_second": 0.347,
|
| 6 |
+
"train_steps_per_second": 0.087
|
| 7 |
+
}
|
args.txt
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
base_model_name: lmsys/vicuna-7b-v1.5
|
| 2 |
+
batch_size: 4
|
| 3 |
+
cot: true
|
| 4 |
+
dataset_name: BENBENBENb/McTest640COT
|
| 5 |
+
epochs: 20
|
| 6 |
+
eval_strategy: epoch
|
| 7 |
+
learning_rate: 0.0001
|
| 8 |
+
logging_steps: 1
|
| 9 |
+
output_dir: brettbbb/mc_cot_16
|
| 10 |
+
seed: 42
|
| 11 |
+
train_size: 16
|
| 12 |
+
warmup_steps: 5
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 20.0,
|
| 3 |
+
"train_loss": 0.6028558738762513,
|
| 4 |
+
"train_runtime": 922.3939,
|
| 5 |
+
"train_samples_per_second": 0.347,
|
| 6 |
+
"train_steps_per_second": 0.087
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,668 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 80,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.25,
|
| 13 |
+
"learning_rate": 2e-05,
|
| 14 |
+
"loss": 2.2339,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.5,
|
| 19 |
+
"learning_rate": 4e-05,
|
| 20 |
+
"loss": 2.1977,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.75,
|
| 25 |
+
"learning_rate": 6e-05,
|
| 26 |
+
"loss": 2.3018,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"learning_rate": 8e-05,
|
| 32 |
+
"loss": 2.1538,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.0,
|
| 37 |
+
"eval_loss": 2.1552114486694336,
|
| 38 |
+
"eval_runtime": 32.1888,
|
| 39 |
+
"eval_samples_per_second": 3.728,
|
| 40 |
+
"eval_steps_per_second": 0.466,
|
| 41 |
+
"step": 4
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.25,
|
| 45 |
+
"learning_rate": 0.0001,
|
| 46 |
+
"loss": 2.0097,
|
| 47 |
+
"step": 5
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.5,
|
| 51 |
+
"learning_rate": 9.866666666666668e-05,
|
| 52 |
+
"loss": 1.9721,
|
| 53 |
+
"step": 6
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 1.75,
|
| 57 |
+
"learning_rate": 9.733333333333335e-05,
|
| 58 |
+
"loss": 2.0311,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 2.0,
|
| 63 |
+
"learning_rate": 9.6e-05,
|
| 64 |
+
"loss": 1.7905,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 2.0,
|
| 69 |
+
"eval_loss": 1.9012010097503662,
|
| 70 |
+
"eval_runtime": 32.3638,
|
| 71 |
+
"eval_samples_per_second": 3.708,
|
| 72 |
+
"eval_steps_per_second": 0.463,
|
| 73 |
+
"step": 8
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.25,
|
| 77 |
+
"learning_rate": 9.466666666666667e-05,
|
| 78 |
+
"loss": 1.9509,
|
| 79 |
+
"step": 9
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.5,
|
| 83 |
+
"learning_rate": 9.333333333333334e-05,
|
| 84 |
+
"loss": 1.8188,
|
| 85 |
+
"step": 10
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 2.75,
|
| 89 |
+
"learning_rate": 9.200000000000001e-05,
|
| 90 |
+
"loss": 1.537,
|
| 91 |
+
"step": 11
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 3.0,
|
| 95 |
+
"learning_rate": 9.066666666666667e-05,
|
| 96 |
+
"loss": 1.4229,
|
| 97 |
+
"step": 12
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 3.0,
|
| 101 |
+
"eval_loss": 1.7686142921447754,
|
| 102 |
+
"eval_runtime": 32.3865,
|
| 103 |
+
"eval_samples_per_second": 3.705,
|
| 104 |
+
"eval_steps_per_second": 0.463,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.25,
|
| 109 |
+
"learning_rate": 8.933333333333334e-05,
|
| 110 |
+
"loss": 1.4918,
|
| 111 |
+
"step": 13
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.5,
|
| 115 |
+
"learning_rate": 8.800000000000001e-05,
|
| 116 |
+
"loss": 1.4519,
|
| 117 |
+
"step": 14
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.75,
|
| 121 |
+
"learning_rate": 8.666666666666667e-05,
|
| 122 |
+
"loss": 1.5143,
|
| 123 |
+
"step": 15
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.0,
|
| 127 |
+
"learning_rate": 8.533333333333334e-05,
|
| 128 |
+
"loss": 1.3834,
|
| 129 |
+
"step": 16
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.0,
|
| 133 |
+
"eval_loss": 1.7070213556289673,
|
| 134 |
+
"eval_runtime": 32.3609,
|
| 135 |
+
"eval_samples_per_second": 3.708,
|
| 136 |
+
"eval_steps_per_second": 0.464,
|
| 137 |
+
"step": 16
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 4.25,
|
| 141 |
+
"learning_rate": 8.4e-05,
|
| 142 |
+
"loss": 1.1704,
|
| 143 |
+
"step": 17
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 4.5,
|
| 147 |
+
"learning_rate": 8.266666666666667e-05,
|
| 148 |
+
"loss": 1.4072,
|
| 149 |
+
"step": 18
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 4.75,
|
| 153 |
+
"learning_rate": 8.133333333333334e-05,
|
| 154 |
+
"loss": 1.0509,
|
| 155 |
+
"step": 19
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 5.0,
|
| 159 |
+
"learning_rate": 8e-05,
|
| 160 |
+
"loss": 1.4421,
|
| 161 |
+
"step": 20
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 5.0,
|
| 165 |
+
"eval_loss": 1.730824589729309,
|
| 166 |
+
"eval_runtime": 32.3413,
|
| 167 |
+
"eval_samples_per_second": 3.71,
|
| 168 |
+
"eval_steps_per_second": 0.464,
|
| 169 |
+
"step": 20
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 5.25,
|
| 173 |
+
"learning_rate": 7.866666666666666e-05,
|
| 174 |
+
"loss": 1.1629,
|
| 175 |
+
"step": 21
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 5.5,
|
| 179 |
+
"learning_rate": 7.733333333333333e-05,
|
| 180 |
+
"loss": 1.0278,
|
| 181 |
+
"step": 22
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 5.75,
|
| 185 |
+
"learning_rate": 7.6e-05,
|
| 186 |
+
"loss": 1.2421,
|
| 187 |
+
"step": 23
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 6.0,
|
| 191 |
+
"learning_rate": 7.466666666666667e-05,
|
| 192 |
+
"loss": 0.9003,
|
| 193 |
+
"step": 24
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 6.0,
|
| 197 |
+
"eval_loss": 1.764611005783081,
|
| 198 |
+
"eval_runtime": 32.3167,
|
| 199 |
+
"eval_samples_per_second": 3.713,
|
| 200 |
+
"eval_steps_per_second": 0.464,
|
| 201 |
+
"step": 24
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.25,
|
| 205 |
+
"learning_rate": 7.333333333333333e-05,
|
| 206 |
+
"loss": 0.9472,
|
| 207 |
+
"step": 25
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 6.5,
|
| 211 |
+
"learning_rate": 7.2e-05,
|
| 212 |
+
"loss": 0.8213,
|
| 213 |
+
"step": 26
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 6.75,
|
| 217 |
+
"learning_rate": 7.066666666666667e-05,
|
| 218 |
+
"loss": 0.9445,
|
| 219 |
+
"step": 27
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.0,
|
| 223 |
+
"learning_rate": 6.933333333333334e-05,
|
| 224 |
+
"loss": 0.7013,
|
| 225 |
+
"step": 28
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.0,
|
| 229 |
+
"eval_loss": 1.9069510698318481,
|
| 230 |
+
"eval_runtime": 32.3189,
|
| 231 |
+
"eval_samples_per_second": 3.713,
|
| 232 |
+
"eval_steps_per_second": 0.464,
|
| 233 |
+
"step": 28
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 7.25,
|
| 237 |
+
"learning_rate": 6.800000000000001e-05,
|
| 238 |
+
"loss": 0.6424,
|
| 239 |
+
"step": 29
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 7.5,
|
| 243 |
+
"learning_rate": 6.666666666666667e-05,
|
| 244 |
+
"loss": 0.6485,
|
| 245 |
+
"step": 30
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 7.75,
|
| 249 |
+
"learning_rate": 6.533333333333334e-05,
|
| 250 |
+
"loss": 0.5505,
|
| 251 |
+
"step": 31
|
| 252 |
+
},
|
| 253 |
+
{
|
| 254 |
+
"epoch": 8.0,
|
| 255 |
+
"learning_rate": 6.400000000000001e-05,
|
| 256 |
+
"loss": 0.6291,
|
| 257 |
+
"step": 32
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 8.0,
|
| 261 |
+
"eval_loss": 2.0077626705169678,
|
| 262 |
+
"eval_runtime": 32.3146,
|
| 263 |
+
"eval_samples_per_second": 3.713,
|
| 264 |
+
"eval_steps_per_second": 0.464,
|
| 265 |
+
"step": 32
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 8.25,
|
| 269 |
+
"learning_rate": 6.266666666666667e-05,
|
| 270 |
+
"loss": 0.3493,
|
| 271 |
+
"step": 33
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 8.5,
|
| 275 |
+
"learning_rate": 6.133333333333334e-05,
|
| 276 |
+
"loss": 0.53,
|
| 277 |
+
"step": 34
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 8.75,
|
| 281 |
+
"learning_rate": 6e-05,
|
| 282 |
+
"loss": 0.3821,
|
| 283 |
+
"step": 35
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 9.0,
|
| 287 |
+
"learning_rate": 5.866666666666667e-05,
|
| 288 |
+
"loss": 0.3314,
|
| 289 |
+
"step": 36
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 9.0,
|
| 293 |
+
"eval_loss": 2.268174886703491,
|
| 294 |
+
"eval_runtime": 32.301,
|
| 295 |
+
"eval_samples_per_second": 3.715,
|
| 296 |
+
"eval_steps_per_second": 0.464,
|
| 297 |
+
"step": 36
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 9.25,
|
| 301 |
+
"learning_rate": 5.7333333333333336e-05,
|
| 302 |
+
"loss": 0.3121,
|
| 303 |
+
"step": 37
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 9.5,
|
| 307 |
+
"learning_rate": 5.6000000000000006e-05,
|
| 308 |
+
"loss": 0.1531,
|
| 309 |
+
"step": 38
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 9.75,
|
| 313 |
+
"learning_rate": 5.466666666666666e-05,
|
| 314 |
+
"loss": 0.2633,
|
| 315 |
+
"step": 39
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 10.0,
|
| 319 |
+
"learning_rate": 5.333333333333333e-05,
|
| 320 |
+
"loss": 0.1554,
|
| 321 |
+
"step": 40
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 10.0,
|
| 325 |
+
"eval_loss": 2.3624258041381836,
|
| 326 |
+
"eval_runtime": 32.3025,
|
| 327 |
+
"eval_samples_per_second": 3.715,
|
| 328 |
+
"eval_steps_per_second": 0.464,
|
| 329 |
+
"step": 40
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 10.25,
|
| 333 |
+
"learning_rate": 5.2000000000000004e-05,
|
| 334 |
+
"loss": 0.0969,
|
| 335 |
+
"step": 41
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 10.5,
|
| 339 |
+
"learning_rate": 5.0666666666666674e-05,
|
| 340 |
+
"loss": 0.1729,
|
| 341 |
+
"step": 42
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 10.75,
|
| 345 |
+
"learning_rate": 4.933333333333334e-05,
|
| 346 |
+
"loss": 0.1003,
|
| 347 |
+
"step": 43
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 11.0,
|
| 351 |
+
"learning_rate": 4.8e-05,
|
| 352 |
+
"loss": 0.0814,
|
| 353 |
+
"step": 44
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 11.0,
|
| 357 |
+
"eval_loss": 2.6522703170776367,
|
| 358 |
+
"eval_runtime": 32.3054,
|
| 359 |
+
"eval_samples_per_second": 3.715,
|
| 360 |
+
"eval_steps_per_second": 0.464,
|
| 361 |
+
"step": 44
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 11.25,
|
| 365 |
+
"learning_rate": 4.666666666666667e-05,
|
| 366 |
+
"loss": 0.0623,
|
| 367 |
+
"step": 45
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 11.5,
|
| 371 |
+
"learning_rate": 4.5333333333333335e-05,
|
| 372 |
+
"loss": 0.0566,
|
| 373 |
+
"step": 46
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 11.75,
|
| 377 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 378 |
+
"loss": 0.0357,
|
| 379 |
+
"step": 47
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 12.0,
|
| 383 |
+
"learning_rate": 4.266666666666667e-05,
|
| 384 |
+
"loss": 0.0499,
|
| 385 |
+
"step": 48
|
| 386 |
+
},
|
| 387 |
+
{
|
| 388 |
+
"epoch": 12.0,
|
| 389 |
+
"eval_loss": 2.7565455436706543,
|
| 390 |
+
"eval_runtime": 32.2967,
|
| 391 |
+
"eval_samples_per_second": 3.716,
|
| 392 |
+
"eval_steps_per_second": 0.464,
|
| 393 |
+
"step": 48
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 12.25,
|
| 397 |
+
"learning_rate": 4.133333333333333e-05,
|
| 398 |
+
"loss": 0.0298,
|
| 399 |
+
"step": 49
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 12.5,
|
| 403 |
+
"learning_rate": 4e-05,
|
| 404 |
+
"loss": 0.036,
|
| 405 |
+
"step": 50
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 12.75,
|
| 409 |
+
"learning_rate": 3.866666666666667e-05,
|
| 410 |
+
"loss": 0.0269,
|
| 411 |
+
"step": 51
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 13.0,
|
| 415 |
+
"learning_rate": 3.733333333333334e-05,
|
| 416 |
+
"loss": 0.0216,
|
| 417 |
+
"step": 52
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 13.0,
|
| 421 |
+
"eval_loss": 2.8505098819732666,
|
| 422 |
+
"eval_runtime": 32.3048,
|
| 423 |
+
"eval_samples_per_second": 3.715,
|
| 424 |
+
"eval_steps_per_second": 0.464,
|
| 425 |
+
"step": 52
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 13.25,
|
| 429 |
+
"learning_rate": 3.6e-05,
|
| 430 |
+
"loss": 0.0184,
|
| 431 |
+
"step": 53
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 13.5,
|
| 435 |
+
"learning_rate": 3.466666666666667e-05,
|
| 436 |
+
"loss": 0.0254,
|
| 437 |
+
"step": 54
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 13.75,
|
| 441 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 442 |
+
"loss": 0.022,
|
| 443 |
+
"step": 55
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 14.0,
|
| 447 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 448 |
+
"loss": 0.0197,
|
| 449 |
+
"step": 56
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 14.0,
|
| 453 |
+
"eval_loss": 2.9169647693634033,
|
| 454 |
+
"eval_runtime": 32.2965,
|
| 455 |
+
"eval_samples_per_second": 3.716,
|
| 456 |
+
"eval_steps_per_second": 0.464,
|
| 457 |
+
"step": 56
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 14.25,
|
| 461 |
+
"learning_rate": 3.066666666666667e-05,
|
| 462 |
+
"loss": 0.0173,
|
| 463 |
+
"step": 57
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 14.5,
|
| 467 |
+
"learning_rate": 2.9333333333333336e-05,
|
| 468 |
+
"loss": 0.0153,
|
| 469 |
+
"step": 58
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 14.75,
|
| 473 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 474 |
+
"loss": 0.016,
|
| 475 |
+
"step": 59
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 15.0,
|
| 479 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 480 |
+
"loss": 0.0174,
|
| 481 |
+
"step": 60
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 15.0,
|
| 485 |
+
"eval_loss": 2.943286657333374,
|
| 486 |
+
"eval_runtime": 32.2924,
|
| 487 |
+
"eval_samples_per_second": 3.716,
|
| 488 |
+
"eval_steps_per_second": 0.465,
|
| 489 |
+
"step": 60
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 15.25,
|
| 493 |
+
"learning_rate": 2.5333333333333337e-05,
|
| 494 |
+
"loss": 0.0136,
|
| 495 |
+
"step": 61
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 15.5,
|
| 499 |
+
"learning_rate": 2.4e-05,
|
| 500 |
+
"loss": 0.017,
|
| 501 |
+
"step": 62
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 15.75,
|
| 505 |
+
"learning_rate": 2.2666666666666668e-05,
|
| 506 |
+
"loss": 0.0146,
|
| 507 |
+
"step": 63
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 16.0,
|
| 511 |
+
"learning_rate": 2.1333333333333335e-05,
|
| 512 |
+
"loss": 0.0174,
|
| 513 |
+
"step": 64
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 16.0,
|
| 517 |
+
"eval_loss": 2.968252420425415,
|
| 518 |
+
"eval_runtime": 32.2957,
|
| 519 |
+
"eval_samples_per_second": 3.716,
|
| 520 |
+
"eval_steps_per_second": 0.464,
|
| 521 |
+
"step": 64
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 16.25,
|
| 525 |
+
"learning_rate": 2e-05,
|
| 526 |
+
"loss": 0.0147,
|
| 527 |
+
"step": 65
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 16.5,
|
| 531 |
+
"learning_rate": 1.866666666666667e-05,
|
| 532 |
+
"loss": 0.014,
|
| 533 |
+
"step": 66
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 16.75,
|
| 537 |
+
"learning_rate": 1.7333333333333336e-05,
|
| 538 |
+
"loss": 0.0145,
|
| 539 |
+
"step": 67
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 17.0,
|
| 543 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 544 |
+
"loss": 0.0145,
|
| 545 |
+
"step": 68
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 17.0,
|
| 549 |
+
"eval_loss": 2.9966158866882324,
|
| 550 |
+
"eval_runtime": 32.3008,
|
| 551 |
+
"eval_samples_per_second": 3.715,
|
| 552 |
+
"eval_steps_per_second": 0.464,
|
| 553 |
+
"step": 68
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 17.25,
|
| 557 |
+
"learning_rate": 1.4666666666666668e-05,
|
| 558 |
+
"loss": 0.0139,
|
| 559 |
+
"step": 69
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 17.5,
|
| 563 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 564 |
+
"loss": 0.0121,
|
| 565 |
+
"step": 70
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 17.75,
|
| 569 |
+
"learning_rate": 1.2e-05,
|
| 570 |
+
"loss": 0.0139,
|
| 571 |
+
"step": 71
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 18.0,
|
| 575 |
+
"learning_rate": 1.0666666666666667e-05,
|
| 576 |
+
"loss": 0.013,
|
| 577 |
+
"step": 72
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 18.0,
|
| 581 |
+
"eval_loss": 3.0193371772766113,
|
| 582 |
+
"eval_runtime": 32.2982,
|
| 583 |
+
"eval_samples_per_second": 3.715,
|
| 584 |
+
"eval_steps_per_second": 0.464,
|
| 585 |
+
"step": 72
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 18.25,
|
| 589 |
+
"learning_rate": 9.333333333333334e-06,
|
| 590 |
+
"loss": 0.0132,
|
| 591 |
+
"step": 73
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 18.5,
|
| 595 |
+
"learning_rate": 8.000000000000001e-06,
|
| 596 |
+
"loss": 0.0127,
|
| 597 |
+
"step": 74
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 18.75,
|
| 601 |
+
"learning_rate": 6.666666666666667e-06,
|
| 602 |
+
"loss": 0.0134,
|
| 603 |
+
"step": 75
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 19.0,
|
| 607 |
+
"learning_rate": 5.333333333333334e-06,
|
| 608 |
+
"loss": 0.0151,
|
| 609 |
+
"step": 76
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 19.0,
|
| 613 |
+
"eval_loss": 3.027658700942993,
|
| 614 |
+
"eval_runtime": 32.2971,
|
| 615 |
+
"eval_samples_per_second": 3.716,
|
| 616 |
+
"eval_steps_per_second": 0.464,
|
| 617 |
+
"step": 76
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 19.25,
|
| 621 |
+
"learning_rate": 4.000000000000001e-06,
|
| 622 |
+
"loss": 0.0126,
|
| 623 |
+
"step": 77
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 19.5,
|
| 627 |
+
"learning_rate": 2.666666666666667e-06,
|
| 628 |
+
"loss": 0.014,
|
| 629 |
+
"step": 78
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 19.75,
|
| 633 |
+
"learning_rate": 1.3333333333333334e-06,
|
| 634 |
+
"loss": 0.0113,
|
| 635 |
+
"step": 79
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 20.0,
|
| 639 |
+
"learning_rate": 0.0,
|
| 640 |
+
"loss": 0.0145,
|
| 641 |
+
"step": 80
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 20.0,
|
| 645 |
+
"eval_loss": 3.0302772521972656,
|
| 646 |
+
"eval_runtime": 32.2941,
|
| 647 |
+
"eval_samples_per_second": 3.716,
|
| 648 |
+
"eval_steps_per_second": 0.464,
|
| 649 |
+
"step": 80
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 20.0,
|
| 653 |
+
"step": 80,
|
| 654 |
+
"total_flos": 8972287420661760.0,
|
| 655 |
+
"train_loss": 0.6028558738762513,
|
| 656 |
+
"train_runtime": 922.3939,
|
| 657 |
+
"train_samples_per_second": 0.347,
|
| 658 |
+
"train_steps_per_second": 0.087
|
| 659 |
+
}
|
| 660 |
+
],
|
| 661 |
+
"logging_steps": 1,
|
| 662 |
+
"max_steps": 80,
|
| 663 |
+
"num_train_epochs": 20,
|
| 664 |
+
"save_steps": 500,
|
| 665 |
+
"total_flos": 8972287420661760.0,
|
| 666 |
+
"trial_name": null,
|
| 667 |
+
"trial_params": null
|
| 668 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50b0fda92390d96fa1802370f8c9e81c35e9b4ff74e74c9689a50be3e815c264
|
| 3 |
+
size 4600
|