Model save
Browse files- README.md +69 -0
- all_results.json +9 -0
- train_results.json +9 -0
- trainer_state.json +694 -0
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: llama3
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: meta-llama/Meta-Llama-3-8B
|
| 9 |
+
datasets:
|
| 10 |
+
- generator
|
| 11 |
+
model-index:
|
| 12 |
+
- name: downstream_0.1p_seed42_level1_rare
|
| 13 |
+
results: []
|
| 14 |
+
---
|
| 15 |
+
|
| 16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 17 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 18 |
+
|
| 19 |
+
# downstream_0.1p_seed42_level1_rare
|
| 20 |
+
|
| 21 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the generator dataset.
|
| 22 |
+
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.9927
|
| 24 |
+
|
| 25 |
+
## Model description
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Intended uses & limitations
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training and evaluation data
|
| 34 |
+
|
| 35 |
+
More information needed
|
| 36 |
+
|
| 37 |
+
## Training procedure
|
| 38 |
+
|
| 39 |
+
### Training hyperparameters
|
| 40 |
+
|
| 41 |
+
The following hyperparameters were used during training:
|
| 42 |
+
- learning_rate: 0.0002
|
| 43 |
+
- train_batch_size: 8
|
| 44 |
+
- eval_batch_size: 1
|
| 45 |
+
- seed: 42
|
| 46 |
+
- distributed_type: multi-GPU
|
| 47 |
+
- num_devices: 4
|
| 48 |
+
- gradient_accumulation_steps: 4
|
| 49 |
+
- total_train_batch_size: 128
|
| 50 |
+
- total_eval_batch_size: 4
|
| 51 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 52 |
+
- lr_scheduler_type: cosine
|
| 53 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 54 |
+
- num_epochs: 1
|
| 55 |
+
|
| 56 |
+
### Training results
|
| 57 |
+
|
| 58 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 59 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 60 |
+
| 1.0893 | 0.9984 | 456 | 0.9927 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- PEFT 0.11.1
|
| 66 |
+
- Transformers 4.43.4
|
| 67 |
+
- Pytorch 2.3.1+cu121
|
| 68 |
+
- Datasets 2.19.1
|
| 69 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9983579638752053,
|
| 3 |
+
"total_flos": 1.447234595979264e+16,
|
| 4 |
+
"train_loss": 1.1072515829613334,
|
| 5 |
+
"train_runtime": 17333.1907,
|
| 6 |
+
"train_samples": 100000,
|
| 7 |
+
"train_samples_per_second": 3.373,
|
| 8 |
+
"train_steps_per_second": 0.026
|
| 9 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.9983579638752053,
|
| 3 |
+
"total_flos": 1.447234595979264e+16,
|
| 4 |
+
"train_loss": 1.1072515829613334,
|
| 5 |
+
"train_runtime": 17333.1907,
|
| 6 |
+
"train_samples": 100000,
|
| 7 |
+
"train_samples_per_second": 3.373,
|
| 8 |
+
"train_steps_per_second": 0.026
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,694 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9983579638752053,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 456,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0021893814997263274,
|
| 13 |
+
"grad_norm": 1.099035580545203,
|
| 14 |
+
"learning_rate": 4.347826086956522e-06,
|
| 15 |
+
"loss": 1.3884,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.010946907498631636,
|
| 20 |
+
"grad_norm": 1.0633282817267398,
|
| 21 |
+
"learning_rate": 2.173913043478261e-05,
|
| 22 |
+
"loss": 1.3896,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.021893814997263273,
|
| 27 |
+
"grad_norm": 0.2753570266695847,
|
| 28 |
+
"learning_rate": 4.347826086956522e-05,
|
| 29 |
+
"loss": 1.3001,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03284072249589491,
|
| 34 |
+
"grad_norm": 0.23486140029795313,
|
| 35 |
+
"learning_rate": 6.521739130434783e-05,
|
| 36 |
+
"loss": 1.2641,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.043787629994526546,
|
| 41 |
+
"grad_norm": 0.17661059915753233,
|
| 42 |
+
"learning_rate": 8.695652173913044e-05,
|
| 43 |
+
"loss": 1.244,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.05473453749315818,
|
| 48 |
+
"grad_norm": 0.13588516740211107,
|
| 49 |
+
"learning_rate": 0.00010869565217391305,
|
| 50 |
+
"loss": 1.2062,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.06568144499178982,
|
| 55 |
+
"grad_norm": 0.09952038895662578,
|
| 56 |
+
"learning_rate": 0.00013043478260869567,
|
| 57 |
+
"loss": 1.2036,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.07662835249042145,
|
| 62 |
+
"grad_norm": 0.08662921860732123,
|
| 63 |
+
"learning_rate": 0.00015217391304347827,
|
| 64 |
+
"loss": 1.1697,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.08757525998905309,
|
| 69 |
+
"grad_norm": 0.08556102174203851,
|
| 70 |
+
"learning_rate": 0.00017391304347826088,
|
| 71 |
+
"loss": 1.168,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.09852216748768473,
|
| 76 |
+
"grad_norm": 0.08239874598331373,
|
| 77 |
+
"learning_rate": 0.0001956521739130435,
|
| 78 |
+
"loss": 1.1752,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.10946907498631636,
|
| 83 |
+
"grad_norm": 0.08011130479266197,
|
| 84 |
+
"learning_rate": 0.0001999530335191093,
|
| 85 |
+
"loss": 1.1317,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.120415982484948,
|
| 90 |
+
"grad_norm": 0.09091690871262173,
|
| 91 |
+
"learning_rate": 0.00019976230779866525,
|
| 92 |
+
"loss": 1.1235,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.13136288998357964,
|
| 97 |
+
"grad_norm": 0.10018228425429193,
|
| 98 |
+
"learning_rate": 0.000199425167134466,
|
| 99 |
+
"loss": 1.14,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1423097974822113,
|
| 104 |
+
"grad_norm": 0.08568976262387419,
|
| 105 |
+
"learning_rate": 0.00019894210632692745,
|
| 106 |
+
"loss": 1.1184,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1532567049808429,
|
| 111 |
+
"grad_norm": 0.09058910078299229,
|
| 112 |
+
"learning_rate": 0.00019831383433439797,
|
| 113 |
+
"loss": 1.1182,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.16420361247947454,
|
| 118 |
+
"grad_norm": 0.07075651635331383,
|
| 119 |
+
"learning_rate": 0.00019754127323266428,
|
| 120 |
+
"loss": 1.1107,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.17515051997810618,
|
| 125 |
+
"grad_norm": 0.08205972533630575,
|
| 126 |
+
"learning_rate": 0.00019662555686167808,
|
| 127 |
+
"loss": 1.1146,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.18609742747673783,
|
| 132 |
+
"grad_norm": 0.09822244044433728,
|
| 133 |
+
"learning_rate": 0.00019556802916148962,
|
| 134 |
+
"loss": 1.1206,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.19704433497536947,
|
| 139 |
+
"grad_norm": 0.08491467009411377,
|
| 140 |
+
"learning_rate": 0.00019437024219983028,
|
| 141 |
+
"loss": 1.1091,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.20799124247400108,
|
| 146 |
+
"grad_norm": 0.08166420957630437,
|
| 147 |
+
"learning_rate": 0.00019303395389423918,
|
| 148 |
+
"loss": 1.1115,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.21893814997263272,
|
| 153 |
+
"grad_norm": 0.08260201243872915,
|
| 154 |
+
"learning_rate": 0.00019156112543207673,
|
| 155 |
+
"loss": 1.1175,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.22988505747126436,
|
| 160 |
+
"grad_norm": 0.08255167959693703,
|
| 161 |
+
"learning_rate": 0.0001899539183922119,
|
| 162 |
+
"loss": 1.0968,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.240831964969896,
|
| 167 |
+
"grad_norm": 0.07836100445915845,
|
| 168 |
+
"learning_rate": 0.00018821469157260685,
|
| 169 |
+
"loss": 1.0888,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.25177887246852765,
|
| 174 |
+
"grad_norm": 0.07207251942982666,
|
| 175 |
+
"learning_rate": 0.00018634599752845592,
|
| 176 |
+
"loss": 1.1074,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2627257799671593,
|
| 181 |
+
"grad_norm": 0.08720514170327426,
|
| 182 |
+
"learning_rate": 0.00018435057882595882,
|
| 183 |
+
"loss": 1.1052,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.27367268746579093,
|
| 188 |
+
"grad_norm": 0.0853293654672411,
|
| 189 |
+
"learning_rate": 0.0001822313640172265,
|
| 190 |
+
"loss": 1.0952,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.2846195949644226,
|
| 195 |
+
"grad_norm": 0.09875940431911555,
|
| 196 |
+
"learning_rate": 0.00017999146334222695,
|
| 197 |
+
"loss": 1.1227,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.2955665024630542,
|
| 202 |
+
"grad_norm": 0.07021884431606892,
|
| 203 |
+
"learning_rate": 0.00017763416416407952,
|
| 204 |
+
"loss": 1.0942,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3065134099616858,
|
| 209 |
+
"grad_norm": 0.06842699832201858,
|
| 210 |
+
"learning_rate": 0.00017516292614439585,
|
| 211 |
+
"loss": 1.0953,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.31746031746031744,
|
| 216 |
+
"grad_norm": 0.07208694079619522,
|
| 217 |
+
"learning_rate": 0.0001725813761657495,
|
| 218 |
+
"loss": 1.0967,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3284072249589491,
|
| 223 |
+
"grad_norm": 0.06921789319582454,
|
| 224 |
+
"learning_rate": 0.00016989330300872576,
|
| 225 |
+
"loss": 1.0801,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3393541324575807,
|
| 230 |
+
"grad_norm": 0.07271469189791151,
|
| 231 |
+
"learning_rate": 0.0001671026517913634,
|
| 232 |
+
"loss": 1.0833,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.35030103995621237,
|
| 237 |
+
"grad_norm": 0.06997352100806448,
|
| 238 |
+
"learning_rate": 0.00016421351817915024,
|
| 239 |
+
"loss": 1.0965,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.361247947454844,
|
| 244 |
+
"grad_norm": 0.07856963780328721,
|
| 245 |
+
"learning_rate": 0.00016123014237406913,
|
| 246 |
+
"loss": 1.1091,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.37219485495347565,
|
| 251 |
+
"grad_norm": 0.07209466893505154,
|
| 252 |
+
"learning_rate": 0.00015815690289151658,
|
| 253 |
+
"loss": 1.0899,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.3831417624521073,
|
| 258 |
+
"grad_norm": 0.07481315197731042,
|
| 259 |
+
"learning_rate": 0.00015499831013422803,
|
| 260 |
+
"loss": 1.1041,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.39408866995073893,
|
| 265 |
+
"grad_norm": 0.08084183121949147,
|
| 266 |
+
"learning_rate": 0.00015175899977263964,
|
| 267 |
+
"loss": 1.0955,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.4050355774493706,
|
| 272 |
+
"grad_norm": 0.0818129087053093,
|
| 273 |
+
"learning_rate": 0.0001484437259414027,
|
| 274 |
+
"loss": 1.1145,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.41598248494800216,
|
| 279 |
+
"grad_norm": 0.06950621743678526,
|
| 280 |
+
"learning_rate": 0.00014505735426203543,
|
| 281 |
+
"loss": 1.1149,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4269293924466338,
|
| 286 |
+
"grad_norm": 0.07548210193666667,
|
| 287 |
+
"learning_rate": 0.00014160485470195245,
|
| 288 |
+
"loss": 1.11,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.43787629994526545,
|
| 293 |
+
"grad_norm": 0.07058243846026176,
|
| 294 |
+
"learning_rate": 0.00013809129428035227,
|
| 295 |
+
"loss": 1.0846,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.4488232074438971,
|
| 300 |
+
"grad_norm": 0.07020891379155109,
|
| 301 |
+
"learning_rate": 0.00013452182963166794,
|
| 302 |
+
"loss": 1.0848,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.45977011494252873,
|
| 307 |
+
"grad_norm": 0.06835760784196979,
|
| 308 |
+
"learning_rate": 0.00013090169943749476,
|
| 309 |
+
"loss": 1.0851,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.47071702244116037,
|
| 314 |
+
"grad_norm": 0.07605646093102703,
|
| 315 |
+
"learning_rate": 0.00012723621673810275,
|
| 316 |
+
"loss": 1.1047,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.481663929939792,
|
| 321 |
+
"grad_norm": 0.0705995475810648,
|
| 322 |
+
"learning_rate": 0.0001235307611348174,
|
| 323 |
+
"loss": 1.0808,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.49261083743842365,
|
| 328 |
+
"grad_norm": 0.07066082603796292,
|
| 329 |
+
"learning_rate": 0.00011979077089471287,
|
| 330 |
+
"loss": 1.0823,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5035577449370553,
|
| 335 |
+
"grad_norm": 0.06843040733212367,
|
| 336 |
+
"learning_rate": 0.0001160217349692051,
|
| 337 |
+
"loss": 1.093,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5145046524356869,
|
| 342 |
+
"grad_norm": 0.07581398076733512,
|
| 343 |
+
"learning_rate": 0.00011222918493825876,
|
| 344 |
+
"loss": 1.0799,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5254515599343186,
|
| 349 |
+
"grad_norm": 0.06701479053423436,
|
| 350 |
+
"learning_rate": 0.00010841868689203071,
|
| 351 |
+
"loss": 1.0984,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.5363984674329502,
|
| 356 |
+
"grad_norm": 0.06919851726403416,
|
| 357 |
+
"learning_rate": 0.00010459583326186533,
|
| 358 |
+
"loss": 1.0919,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.5473453749315819,
|
| 363 |
+
"grad_norm": 0.07632131476135244,
|
| 364 |
+
"learning_rate": 0.00010076623461263018,
|
| 365 |
+
"loss": 1.0801,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.5582922824302134,
|
| 370 |
+
"grad_norm": 0.0661733510360967,
|
| 371 |
+
"learning_rate": 9.693551140843847e-05,
|
| 372 |
+
"loss": 1.0824,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.5692391899288451,
|
| 377 |
+
"grad_norm": 0.06851059826679573,
|
| 378 |
+
"learning_rate": 9.310928576384293e-05,
|
| 379 |
+
"loss": 1.0956,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.5801860974274767,
|
| 384 |
+
"grad_norm": 0.07225957964642454,
|
| 385 |
+
"learning_rate": 8.929317319260726e-05,
|
| 386 |
+
"loss": 1.0818,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.5911330049261084,
|
| 391 |
+
"grad_norm": 0.07526177174581719,
|
| 392 |
+
"learning_rate": 8.549277436616551e-05,
|
| 393 |
+
"loss": 1.0876,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.60207991242474,
|
| 398 |
+
"grad_norm": 0.0688828763506549,
|
| 399 |
+
"learning_rate": 8.171366689386432e-05,
|
| 400 |
+
"loss": 1.0834,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6130268199233716,
|
| 405 |
+
"grad_norm": 0.07233185605708406,
|
| 406 |
+
"learning_rate": 7.796139713705213e-05,
|
| 407 |
+
"loss": 1.0904,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.6239737274220033,
|
| 412 |
+
"grad_norm": 0.07238689140745656,
|
| 413 |
+
"learning_rate": 7.424147206902891e-05,
|
| 414 |
+
"loss": 1.078,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.6349206349206349,
|
| 419 |
+
"grad_norm": 0.07045252374699128,
|
| 420 |
+
"learning_rate": 7.055935119280369e-05,
|
| 421 |
+
"loss": 1.0746,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.6458675424192666,
|
| 426 |
+
"grad_norm": 0.06885925177718841,
|
| 427 |
+
"learning_rate": 6.692043852852079e-05,
|
| 428 |
+
"loss": 1.0914,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.6568144499178982,
|
| 433 |
+
"grad_norm": 0.0714964117404916,
|
| 434 |
+
"learning_rate": 6.333007468231521e-05,
|
| 435 |
+
"loss": 1.0829,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.6677613574165299,
|
| 440 |
+
"grad_norm": 0.0670654539976087,
|
| 441 |
+
"learning_rate": 5.9793529008236625e-05,
|
| 442 |
+
"loss": 1.0756,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.6787082649151615,
|
| 447 |
+
"grad_norm": 0.06833244959359351,
|
| 448 |
+
"learning_rate": 5.63159918747457e-05,
|
| 449 |
+
"loss": 1.0779,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.6896551724137931,
|
| 454 |
+
"grad_norm": 0.07144684011257411,
|
| 455 |
+
"learning_rate": 5.29025670471325e-05,
|
| 456 |
+
"loss": 1.0983,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7006020799124247,
|
| 461 |
+
"grad_norm": 0.07142805023654634,
|
| 462 |
+
"learning_rate": 4.955826419703735e-05,
|
| 463 |
+
"loss": 1.0867,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.7115489874110563,
|
| 468 |
+
"grad_norm": 0.07674467638840121,
|
| 469 |
+
"learning_rate": 4.628799155006669e-05,
|
| 470 |
+
"loss": 1.0651,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.722495894909688,
|
| 475 |
+
"grad_norm": 0.06634612204586297,
|
| 476 |
+
"learning_rate": 4.30965486822953e-05,
|
| 477 |
+
"loss": 1.0938,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.7334428024083196,
|
| 482 |
+
"grad_norm": 0.06579811491660853,
|
| 483 |
+
"learning_rate": 3.9988619476226355e-05,
|
| 484 |
+
"loss": 1.0781,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.7443897099069513,
|
| 489 |
+
"grad_norm": 0.06839286253175804,
|
| 490 |
+
"learning_rate": 3.69687652465482e-05,
|
| 491 |
+
"loss": 1.0807,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.7553366174055829,
|
| 496 |
+
"grad_norm": 0.06644270765658328,
|
| 497 |
+
"learning_rate": 3.4041418045775895e-05,
|
| 498 |
+
"loss": 1.074,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.7662835249042146,
|
| 503 |
+
"grad_norm": 0.06772025228639957,
|
| 504 |
+
"learning_rate": 3.121087415960304e-05,
|
| 505 |
+
"loss": 1.0762,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.7772304324028462,
|
| 510 |
+
"grad_norm": 0.06615084228702964,
|
| 511 |
+
"learning_rate": 2.848128780150995e-05,
|
| 512 |
+
"loss": 1.0779,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.7881773399014779,
|
| 517 |
+
"grad_norm": 0.0706561964889078,
|
| 518 |
+
"learning_rate": 2.5856665015882685e-05,
|
| 519 |
+
"loss": 1.0904,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.7991242474001095,
|
| 524 |
+
"grad_norm": 0.06748598590158515,
|
| 525 |
+
"learning_rate": 2.334085779859041e-05,
|
| 526 |
+
"loss": 1.0654,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.8100711548987412,
|
| 531 |
+
"grad_norm": 0.06669809967764875,
|
| 532 |
+
"learning_rate": 2.0937558443650206e-05,
|
| 533 |
+
"loss": 1.0835,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.8210180623973727,
|
| 538 |
+
"grad_norm": 0.06776479655939238,
|
| 539 |
+
"learning_rate": 1.8650294124276556e-05,
|
| 540 |
+
"loss": 1.0836,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.8319649698960043,
|
| 545 |
+
"grad_norm": 0.06672866236853266,
|
| 546 |
+
"learning_rate": 1.6482421716268215e-05,
|
| 547 |
+
"loss": 1.0909,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.842911877394636,
|
| 552 |
+
"grad_norm": 0.0670546035798045,
|
| 553 |
+
"learning_rate": 1.4437122871329955e-05,
|
| 554 |
+
"loss": 1.0984,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.8538587848932676,
|
| 559 |
+
"grad_norm": 0.06639094648741257,
|
| 560 |
+
"learning_rate": 1.2517399347560167e-05,
|
| 561 |
+
"loss": 1.1008,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.8648056923918993,
|
| 566 |
+
"grad_norm": 0.06852807789172832,
|
| 567 |
+
"learning_rate": 1.0726068603956741e-05,
|
| 568 |
+
"loss": 1.0783,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.8757525998905309,
|
| 573 |
+
"grad_norm": 0.06914284979355585,
|
| 574 |
+
"learning_rate": 9.065759665407515e-06,
|
| 575 |
+
"loss": 1.0828,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.8866995073891626,
|
| 580 |
+
"grad_norm": 0.06687442460085294,
|
| 581 |
+
"learning_rate": 7.538909264233751e-06,
|
| 582 |
+
"loss": 1.0845,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.8976464148877942,
|
| 587 |
+
"grad_norm": 0.07046699389113141,
|
| 588 |
+
"learning_rate": 6.147758263949321e-06,
|
| 589 |
+
"loss": 1.0784,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.9085933223864259,
|
| 594 |
+
"grad_norm": 0.06774076270250588,
|
| 595 |
+
"learning_rate": 4.8943483704846475e-06,
|
| 596 |
+
"loss": 1.0914,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.9195402298850575,
|
| 601 |
+
"grad_norm": 0.06693453050067996,
|
| 602 |
+
"learning_rate": 3.7805191357015657e-06,
|
| 603 |
+
"loss": 1.0986,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.9304871373836892,
|
| 608 |
+
"grad_norm": 0.06389085654103847,
|
| 609 |
+
"learning_rate": 2.8079052575973765e-06,
|
| 610 |
+
"loss": 1.087,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.9414340448823207,
|
| 615 |
+
"grad_norm": 0.06811361952720432,
|
| 616 |
+
"learning_rate": 1.9779341811600794e-06,
|
| 617 |
+
"loss": 1.07,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.9523809523809523,
|
| 622 |
+
"grad_norm": 0.06592264001597521,
|
| 623 |
+
"learning_rate": 1.2918240033960027e-06,
|
| 624 |
+
"loss": 1.0825,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.963327859879584,
|
| 629 |
+
"grad_norm": 0.06657689313692897,
|
| 630 |
+
"learning_rate": 7.505816856045012e-07,
|
| 631 |
+
"loss": 1.0843,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.9742747673782156,
|
| 636 |
+
"grad_norm": 0.06488852108049653,
|
| 637 |
+
"learning_rate": 3.5500157552337264e-07,
|
| 638 |
+
"loss": 1.0923,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.9852216748768473,
|
| 643 |
+
"grad_norm": 0.06657099771817772,
|
| 644 |
+
"learning_rate": 1.0566424151401411e-07,
|
| 645 |
+
"loss": 1.0882,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.9961685823754789,
|
| 650 |
+
"grad_norm": 0.06558284673944498,
|
| 651 |
+
"learning_rate": 2.935620497301894e-09,
|
| 652 |
+
"loss": 1.0893,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.9983579638752053,
|
| 657 |
+
"eval_loss": 0.9926520586013794,
|
| 658 |
+
"eval_runtime": 2.1266,
|
| 659 |
+
"eval_samples_per_second": 3.292,
|
| 660 |
+
"eval_steps_per_second": 0.94,
|
| 661 |
+
"step": 456
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.9983579638752053,
|
| 665 |
+
"step": 456,
|
| 666 |
+
"total_flos": 1.447234595979264e+16,
|
| 667 |
+
"train_loss": 1.1072515829613334,
|
| 668 |
+
"train_runtime": 17333.1907,
|
| 669 |
+
"train_samples_per_second": 3.373,
|
| 670 |
+
"train_steps_per_second": 0.026
|
| 671 |
+
}
|
| 672 |
+
],
|
| 673 |
+
"logging_steps": 5,
|
| 674 |
+
"max_steps": 456,
|
| 675 |
+
"num_input_tokens_seen": 0,
|
| 676 |
+
"num_train_epochs": 1,
|
| 677 |
+
"save_steps": 100,
|
| 678 |
+
"stateful_callbacks": {
|
| 679 |
+
"TrainerControl": {
|
| 680 |
+
"args": {
|
| 681 |
+
"should_epoch_stop": false,
|
| 682 |
+
"should_evaluate": false,
|
| 683 |
+
"should_log": false,
|
| 684 |
+
"should_save": true,
|
| 685 |
+
"should_training_stop": true
|
| 686 |
+
},
|
| 687 |
+
"attributes": {}
|
| 688 |
+
}
|
| 689 |
+
},
|
| 690 |
+
"total_flos": 1.447234595979264e+16,
|
| 691 |
+
"train_batch_size": 8,
|
| 692 |
+
"trial_name": null,
|
| 693 |
+
"trial_params": null
|
| 694 |
+
}
|