Commit
•
bab86a2
1
Parent(s):
53f842e
Model save
Browse files- README.md +68 -0
- all_results.json +9 -0
- generation_config.json +7 -0
- runs/Aug05_22-38-20_poseidon/events.out.tfevents.1722897629.poseidon.1670779.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +576 -0
README.md
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- generator
|
| 10 |
+
model-index:
|
| 11 |
+
- name: tinyllama-1.1b-sum-sft-full_2gpus
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# tinyllama-1.1b-sum-sft-full_2gpus
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 2.0980
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 2e-05
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 1
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 2
|
| 47 |
+
- gradient_accumulation_steps: 16
|
| 48 |
+
- total_train_batch_size: 128
|
| 49 |
+
- total_eval_batch_size: 2
|
| 50 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
+
- lr_scheduler_type: cosine
|
| 52 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 53 |
+
- num_epochs: 2
|
| 54 |
+
|
| 55 |
+
### Training results
|
| 56 |
+
|
| 57 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 58 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 59 |
+
| 2.1046 | 0.9970 | 184 | 2.1051 |
|
| 60 |
+
| 2.0438 | 1.9939 | 368 | 2.0980 |
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
### Framework versions
|
| 64 |
+
|
| 65 |
+
- Transformers 4.43.3
|
| 66 |
+
- Pytorch 2.1.2+cu121
|
| 67 |
+
- Datasets 2.20.0
|
| 68 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9939045038943446,
|
| 3 |
+
"total_flos": 53334434119680.0,
|
| 4 |
+
"train_loss": 2.0994615062423376,
|
| 5 |
+
"train_runtime": 7293.2016,
|
| 6 |
+
"train_samples": 116722,
|
| 7 |
+
"train_samples_per_second": 6.477,
|
| 8 |
+
"train_steps_per_second": 0.05
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 1,
|
| 3 |
+
"eos_token_id": 2,
|
| 4 |
+
"max_length": 2048,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.43.3"
|
| 7 |
+
}
|
runs/Aug05_22-38-20_poseidon/events.out.tfevents.1722897629.poseidon.1670779.0
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:38621c12853eecee2baafa41823f74318431306aa61fd0de2bee3942ba1fded2
|
| 3 |
+
size 21558
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.9939045038943446,
|
| 3 |
+
"total_flos": 53334434119680.0,
|
| 4 |
+
"train_loss": 2.0994615062423376,
|
| 5 |
+
"train_runtime": 7293.2016,
|
| 6 |
+
"train_samples": 116722,
|
| 7 |
+
"train_samples_per_second": 6.477,
|
| 8 |
+
"train_steps_per_second": 0.05
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,576 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.9939045038943446,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 368,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.005418218760582459,
|
| 13 |
+
"grad_norm": 11.441351738340396,
|
| 14 |
+
"learning_rate": 5.405405405405406e-07,
|
| 15 |
+
"loss": 2.4665,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.027091093802912292,
|
| 20 |
+
"grad_norm": 11.567929424436132,
|
| 21 |
+
"learning_rate": 2.702702702702703e-06,
|
| 22 |
+
"loss": 2.4607,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.054182187605824585,
|
| 27 |
+
"grad_norm": 2.1647507226825287,
|
| 28 |
+
"learning_rate": 5.405405405405406e-06,
|
| 29 |
+
"loss": 2.3924,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.08127328140873688,
|
| 34 |
+
"grad_norm": 1.0652926230951467,
|
| 35 |
+
"learning_rate": 8.108108108108109e-06,
|
| 36 |
+
"loss": 2.2869,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.10836437521164917,
|
| 41 |
+
"grad_norm": 0.6956953231915263,
|
| 42 |
+
"learning_rate": 1.0810810810810812e-05,
|
| 43 |
+
"loss": 2.2241,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.13545546901456146,
|
| 48 |
+
"grad_norm": 0.6368662485384925,
|
| 49 |
+
"learning_rate": 1.3513513513513515e-05,
|
| 50 |
+
"loss": 2.1943,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16254656281747376,
|
| 55 |
+
"grad_norm": 0.52626831061368,
|
| 56 |
+
"learning_rate": 1.6216216216216218e-05,
|
| 57 |
+
"loss": 2.1796,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18963765662038604,
|
| 62 |
+
"grad_norm": 0.5041342654725786,
|
| 63 |
+
"learning_rate": 1.891891891891892e-05,
|
| 64 |
+
"loss": 2.1739,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.21672875042329834,
|
| 69 |
+
"grad_norm": 0.531083346249148,
|
| 70 |
+
"learning_rate": 1.9995946530314384e-05,
|
| 71 |
+
"loss": 2.1573,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.24381984422621064,
|
| 76 |
+
"grad_norm": 0.4970950800288572,
|
| 77 |
+
"learning_rate": 1.9971187226043746e-05,
|
| 78 |
+
"loss": 2.1556,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2709109380291229,
|
| 83 |
+
"grad_norm": 0.4930331306794567,
|
| 84 |
+
"learning_rate": 1.9923976226947417e-05,
|
| 85 |
+
"loss": 2.1516,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.2980020318320352,
|
| 90 |
+
"grad_norm": 0.4792958893497388,
|
| 91 |
+
"learning_rate": 1.985441983600819e-05,
|
| 92 |
+
"loss": 2.1416,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3250931256349475,
|
| 97 |
+
"grad_norm": 0.4704908677461612,
|
| 98 |
+
"learning_rate": 1.9762674670369757e-05,
|
| 99 |
+
"loss": 2.1375,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.3521842194378598,
|
| 104 |
+
"grad_norm": 0.46530825034717316,
|
| 105 |
+
"learning_rate": 1.9648947308688594e-05,
|
| 106 |
+
"loss": 2.1328,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.37927531324077207,
|
| 111 |
+
"grad_norm": 0.47535573444890883,
|
| 112 |
+
"learning_rate": 1.9513493825989664e-05,
|
| 113 |
+
"loss": 2.1402,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.4063664070436844,
|
| 118 |
+
"grad_norm": 0.4759377502233077,
|
| 119 |
+
"learning_rate": 1.9356619217073252e-05,
|
| 120 |
+
"loss": 2.1332,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.4334575008465967,
|
| 125 |
+
"grad_norm": 0.4662210394921992,
|
| 126 |
+
"learning_rate": 1.917867670977126e-05,
|
| 127 |
+
"loss": 2.1335,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.460548594649509,
|
| 132 |
+
"grad_norm": 0.4757611076987449,
|
| 133 |
+
"learning_rate": 1.8980066969599216e-05,
|
| 134 |
+
"loss": 2.1258,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.4876396884524213,
|
| 139 |
+
"grad_norm": 0.45382312904649785,
|
| 140 |
+
"learning_rate": 1.8761237197594945e-05,
|
| 141 |
+
"loss": 2.1293,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.5147307822553335,
|
| 146 |
+
"grad_norm": 0.47488848221887603,
|
| 147 |
+
"learning_rate": 1.852268012337514e-05,
|
| 148 |
+
"loss": 2.1279,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.5418218760582458,
|
| 153 |
+
"grad_norm": 0.47098691848945873,
|
| 154 |
+
"learning_rate": 1.8264932895677195e-05,
|
| 155 |
+
"loss": 2.126,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5689129698611581,
|
| 160 |
+
"grad_norm": 0.47815599863300057,
|
| 161 |
+
"learning_rate": 1.798857587288445e-05,
|
| 162 |
+
"loss": 2.1249,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.5960040636640704,
|
| 167 |
+
"grad_norm": 0.45607203288859494,
|
| 168 |
+
"learning_rate": 1.769423131625808e-05,
|
| 169 |
+
"loss": 2.1182,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.6230951574669827,
|
| 174 |
+
"grad_norm": 0.4566297150188363,
|
| 175 |
+
"learning_rate": 1.738256198881809e-05,
|
| 176 |
+
"loss": 2.1182,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.650186251269895,
|
| 181 |
+
"grad_norm": 0.4563332108229212,
|
| 182 |
+
"learning_rate": 1.7054269663028232e-05,
|
| 183 |
+
"loss": 2.1158,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.6772773450728073,
|
| 188 |
+
"grad_norm": 0.4719747539449419,
|
| 189 |
+
"learning_rate": 1.6710093540645056e-05,
|
| 190 |
+
"loss": 2.1124,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.7043684388757196,
|
| 195 |
+
"grad_norm": 0.45233465694057096,
|
| 196 |
+
"learning_rate": 1.6350808588288964e-05,
|
| 197 |
+
"loss": 2.1173,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.731459532678632,
|
| 202 |
+
"grad_norm": 0.4494520104287378,
|
| 203 |
+
"learning_rate": 1.597722379248512e-05,
|
| 204 |
+
"loss": 2.1147,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.7585506264815441,
|
| 209 |
+
"grad_norm": 0.44217741153395734,
|
| 210 |
+
"learning_rate": 1.559018033810316e-05,
|
| 211 |
+
"loss": 2.1158,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.7856417202844564,
|
| 216 |
+
"grad_norm": 0.43568954148921973,
|
| 217 |
+
"learning_rate": 1.5190549714297303e-05,
|
| 218 |
+
"loss": 2.1155,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.8127328140873687,
|
| 223 |
+
"grad_norm": 0.45615630991925854,
|
| 224 |
+
"learning_rate": 1.4779231752211546e-05,
|
| 225 |
+
"loss": 2.1162,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.839823907890281,
|
| 230 |
+
"grad_norm": 0.4607530478729013,
|
| 231 |
+
"learning_rate": 1.4357152598868478e-05,
|
| 232 |
+
"loss": 2.117,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.8669150016931934,
|
| 237 |
+
"grad_norm": 0.43874353467346544,
|
| 238 |
+
"learning_rate": 1.3925262631803722e-05,
|
| 239 |
+
"loss": 2.1047,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.8940060954961057,
|
| 244 |
+
"grad_norm": 0.4577418545526205,
|
| 245 |
+
"learning_rate": 1.3484534319141592e-05,
|
| 246 |
+
"loss": 2.1103,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.921097189299018,
|
| 251 |
+
"grad_norm": 0.44202574956917495,
|
| 252 |
+
"learning_rate": 1.303596002993028e-05,
|
| 253 |
+
"loss": 2.1117,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.9481882831019303,
|
| 258 |
+
"grad_norm": 0.4461244150173344,
|
| 259 |
+
"learning_rate": 1.2580549799667034e-05,
|
| 260 |
+
"loss": 2.1141,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.9752793769048426,
|
| 265 |
+
"grad_norm": 0.45529168414311305,
|
| 266 |
+
"learning_rate": 1.2119329056044533e-05,
|
| 267 |
+
"loss": 2.1046,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.9969522519471724,
|
| 272 |
+
"eval_loss": 2.1050913333892822,
|
| 273 |
+
"eval_runtime": 76.5237,
|
| 274 |
+
"eval_samples_per_second": 17.054,
|
| 275 |
+
"eval_steps_per_second": 8.533,
|
| 276 |
+
"step": 184
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.0023704707077548,
|
| 280 |
+
"grad_norm": 0.4809974366908029,
|
| 281 |
+
"learning_rate": 1.165333631003928e-05,
|
| 282 |
+
"loss": 2.0998,
|
| 283 |
+
"step": 185
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.029461564510667,
|
| 287 |
+
"grad_norm": 0.48705866202596343,
|
| 288 |
+
"learning_rate": 1.1183620817540985e-05,
|
| 289 |
+
"loss": 2.0462,
|
| 290 |
+
"step": 190
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0565526583135794,
|
| 294 |
+
"grad_norm": 0.4868339560578216,
|
| 295 |
+
"learning_rate": 1.0711240216788036e-05,
|
| 296 |
+
"loss": 2.0529,
|
| 297 |
+
"step": 195
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.0836437521164917,
|
| 301 |
+
"grad_norm": 0.4620568487887428,
|
| 302 |
+
"learning_rate": 1.0237258146928849e-05,
|
| 303 |
+
"loss": 2.0494,
|
| 304 |
+
"step": 200
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.110734845919404,
|
| 308 |
+
"grad_norm": 0.4641633596897171,
|
| 309 |
+
"learning_rate": 9.762741853071153e-06,
|
| 310 |
+
"loss": 2.0467,
|
| 311 |
+
"step": 205
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.1378259397223163,
|
| 315 |
+
"grad_norm": 0.48677368374631885,
|
| 316 |
+
"learning_rate": 9.288759783211967e-06,
|
| 317 |
+
"loss": 2.0482,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.1649170335252286,
|
| 322 |
+
"grad_norm": 0.46534164607337153,
|
| 323 |
+
"learning_rate": 8.81637918245902e-06,
|
| 324 |
+
"loss": 2.0469,
|
| 325 |
+
"step": 215
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1920081273281409,
|
| 329 |
+
"grad_norm": 0.46946874812594946,
|
| 330 |
+
"learning_rate": 8.346663689960724e-06,
|
| 331 |
+
"loss": 2.0445,
|
| 332 |
+
"step": 220
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2190992211310532,
|
| 336 |
+
"grad_norm": 0.4663999382035462,
|
| 337 |
+
"learning_rate": 7.880670943955467e-06,
|
| 338 |
+
"loss": 2.0481,
|
| 339 |
+
"step": 225
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.2461903149339655,
|
| 343 |
+
"grad_norm": 0.4457099195715021,
|
| 344 |
+
"learning_rate": 7.419450200332965e-06,
|
| 345 |
+
"loss": 2.0529,
|
| 346 |
+
"step": 230
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2732814087368778,
|
| 350 |
+
"grad_norm": 0.46304032166442355,
|
| 351 |
+
"learning_rate": 6.964039970069722e-06,
|
| 352 |
+
"loss": 2.0467,
|
| 353 |
+
"step": 235
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.30037250253979,
|
| 357 |
+
"grad_norm": 0.4449406613479281,
|
| 358 |
+
"learning_rate": 6.515465680858412e-06,
|
| 359 |
+
"loss": 2.0486,
|
| 360 |
+
"step": 240
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3274635963427024,
|
| 364 |
+
"grad_norm": 0.4389522489189322,
|
| 365 |
+
"learning_rate": 6.074737368196279e-06,
|
| 366 |
+
"loss": 2.0516,
|
| 367 |
+
"step": 245
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3545546901456147,
|
| 371 |
+
"grad_norm": 0.43429376447812934,
|
| 372 |
+
"learning_rate": 5.642847401131526e-06,
|
| 373 |
+
"loss": 2.0398,
|
| 374 |
+
"step": 250
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.381645783948527,
|
| 378 |
+
"grad_norm": 0.42907764023330297,
|
| 379 |
+
"learning_rate": 5.220768247788458e-06,
|
| 380 |
+
"loss": 2.0469,
|
| 381 |
+
"step": 255
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.4087368777514393,
|
| 385 |
+
"grad_norm": 0.43261082208262897,
|
| 386 |
+
"learning_rate": 4.809450285702697e-06,
|
| 387 |
+
"loss": 2.049,
|
| 388 |
+
"step": 260
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.4358279715543514,
|
| 392 |
+
"grad_norm": 0.4495153435008709,
|
| 393 |
+
"learning_rate": 4.409819661896839e-06,
|
| 394 |
+
"loss": 2.0453,
|
| 395 |
+
"step": 265
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.462919065357264,
|
| 399 |
+
"grad_norm": 0.44801407055899056,
|
| 400 |
+
"learning_rate": 4.022776207514885e-06,
|
| 401 |
+
"loss": 2.0401,
|
| 402 |
+
"step": 270
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.490010159160176,
|
| 406 |
+
"grad_norm": 0.43760507616111505,
|
| 407 |
+
"learning_rate": 3.6491914117110405e-06,
|
| 408 |
+
"loss": 2.047,
|
| 409 |
+
"step": 275
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.5171012529630885,
|
| 413 |
+
"grad_norm": 0.4323485633364769,
|
| 414 |
+
"learning_rate": 3.2899064593549477e-06,
|
| 415 |
+
"loss": 2.0445,
|
| 416 |
+
"step": 280
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.5441923467660006,
|
| 420 |
+
"grad_norm": 0.44598125572196134,
|
| 421 |
+
"learning_rate": 2.945730336971767e-06,
|
| 422 |
+
"loss": 2.0405,
|
| 423 |
+
"step": 285
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.5712834405689131,
|
| 427 |
+
"grad_norm": 0.44045190794321376,
|
| 428 |
+
"learning_rate": 2.6174380111819144e-06,
|
| 429 |
+
"loss": 2.0449,
|
| 430 |
+
"step": 290
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.5983745343718252,
|
| 434 |
+
"grad_norm": 0.4315376791223261,
|
| 435 |
+
"learning_rate": 2.3057686837419246e-06,
|
| 436 |
+
"loss": 2.0455,
|
| 437 |
+
"step": 295
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.6254656281747377,
|
| 441 |
+
"grad_norm": 0.4141056168787056,
|
| 442 |
+
"learning_rate": 2.011424127115552e-06,
|
| 443 |
+
"loss": 2.0429,
|
| 444 |
+
"step": 300
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.6525567219776498,
|
| 448 |
+
"grad_norm": 0.42561322896204196,
|
| 449 |
+
"learning_rate": 1.7350671043228072e-06,
|
| 450 |
+
"loss": 2.0473,
|
| 451 |
+
"step": 305
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.679647815780562,
|
| 455 |
+
"grad_norm": 0.4318633569152662,
|
| 456 |
+
"learning_rate": 1.4773198766248642e-06,
|
| 457 |
+
"loss": 2.0471,
|
| 458 |
+
"step": 310
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.7067389095834744,
|
| 462 |
+
"grad_norm": 0.42654823899186717,
|
| 463 |
+
"learning_rate": 1.2387628024050557e-06,
|
| 464 |
+
"loss": 2.0502,
|
| 465 |
+
"step": 315
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.7338300033863867,
|
| 469 |
+
"grad_norm": 0.4318585206830447,
|
| 470 |
+
"learning_rate": 1.0199330304007858e-06,
|
| 471 |
+
"loss": 2.0374,
|
| 472 |
+
"step": 320
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.760921097189299,
|
| 476 |
+
"grad_norm": 0.42587188797302283,
|
| 477 |
+
"learning_rate": 8.213232902287438e-07,
|
| 478 |
+
"loss": 2.0508,
|
| 479 |
+
"step": 325
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.7880121909922113,
|
| 483 |
+
"grad_norm": 0.42658756639019496,
|
| 484 |
+
"learning_rate": 6.433807829267491e-07,
|
| 485 |
+
"loss": 2.0458,
|
| 486 |
+
"step": 330
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.8151032847951236,
|
| 490 |
+
"grad_norm": 0.4254891411016103,
|
| 491 |
+
"learning_rate": 4.865061740103361e-07,
|
| 492 |
+
"loss": 2.0538,
|
| 493 |
+
"step": 335
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.842194378598036,
|
| 497 |
+
"grad_norm": 0.43121146874552274,
|
| 498 |
+
"learning_rate": 3.510526913114065e-07,
|
| 499 |
+
"loss": 2.0437,
|
| 500 |
+
"step": 340
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.8692854724009482,
|
| 504 |
+
"grad_norm": 0.4148670481064235,
|
| 505 |
+
"learning_rate": 2.3732532963024468e-07,
|
| 506 |
+
"loss": 2.0366,
|
| 507 |
+
"step": 345
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.8963765662038605,
|
| 511 |
+
"grad_norm": 0.4240449705158572,
|
| 512 |
+
"learning_rate": 1.4558016399181086e-07,
|
| 513 |
+
"loss": 2.0462,
|
| 514 |
+
"step": 350
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.9234676600067728,
|
| 518 |
+
"grad_norm": 0.41343102256412484,
|
| 519 |
+
"learning_rate": 7.602377305258479e-08,
|
| 520 |
+
"loss": 2.0485,
|
| 521 |
+
"step": 355
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.950558753809685,
|
| 525 |
+
"grad_norm": 0.4219092082642883,
|
| 526 |
+
"learning_rate": 2.8812773956256034e-08,
|
| 527 |
+
"loss": 2.0398,
|
| 528 |
+
"step": 360
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.9776498476125974,
|
| 532 |
+
"grad_norm": 0.4203661391482514,
|
| 533 |
+
"learning_rate": 4.053469685617595e-09,
|
| 534 |
+
"loss": 2.0438,
|
| 535 |
+
"step": 365
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.9939045038943446,
|
| 539 |
+
"eval_loss": 2.097979784011841,
|
| 540 |
+
"eval_runtime": 77.4795,
|
| 541 |
+
"eval_samples_per_second": 16.843,
|
| 542 |
+
"eval_steps_per_second": 8.428,
|
| 543 |
+
"step": 368
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.9939045038943446,
|
| 547 |
+
"step": 368,
|
| 548 |
+
"total_flos": 53334434119680.0,
|
| 549 |
+
"train_loss": 2.0994615062423376,
|
| 550 |
+
"train_runtime": 7293.2016,
|
| 551 |
+
"train_samples_per_second": 6.477,
|
| 552 |
+
"train_steps_per_second": 0.05
|
| 553 |
+
}
|
| 554 |
+
],
|
| 555 |
+
"logging_steps": 5,
|
| 556 |
+
"max_steps": 368,
|
| 557 |
+
"num_input_tokens_seen": 0,
|
| 558 |
+
"num_train_epochs": 2,
|
| 559 |
+
"save_steps": 100,
|
| 560 |
+
"stateful_callbacks": {
|
| 561 |
+
"TrainerControl": {
|
| 562 |
+
"args": {
|
| 563 |
+
"should_epoch_stop": false,
|
| 564 |
+
"should_evaluate": false,
|
| 565 |
+
"should_log": false,
|
| 566 |
+
"should_save": true,
|
| 567 |
+
"should_training_stop": true
|
| 568 |
+
},
|
| 569 |
+
"attributes": {}
|
| 570 |
+
}
|
| 571 |
+
},
|
| 572 |
+
"total_flos": 53334434119680.0,
|
| 573 |
+
"train_batch_size": 4,
|
| 574 |
+
"trial_name": null,
|
| 575 |
+
"trial_params": null
|
| 576 |
+
}
|