jennhu/olmo-7b-lora_simplewiki_baseline_simplewiki_baseline
Browse files- README.md +67 -0
- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- trainer_state.json +483 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: allenai/OLMo-7B-0724-hf
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
model-index:
|
| 8 |
+
- name: simplewiki_baseline
|
| 9 |
+
results: []
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 13 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 14 |
+
|
| 15 |
+
# simplewiki_baseline
|
| 16 |
+
|
| 17 |
+
This model is a fine-tuned version of [allenai/OLMo-7B-0724-hf](https://huggingface.co/allenai/OLMo-7B-0724-hf) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 2.3323
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 0.002
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 8
|
| 41 |
+
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 16
|
| 43 |
+
- total_train_batch_size: 256
|
| 44 |
+
- optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 45 |
+
- lr_scheduler_type: linear
|
| 46 |
+
- lr_scheduler_warmup_steps: 1
|
| 47 |
+
- num_epochs: 3
|
| 48 |
+
- mixed_precision_training: Native AMP
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 53 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 54 |
+
| 2.3175 | 0.5378 | 20 | 2.3252 |
|
| 55 |
+
| 2.3075 | 1.0538 | 40 | 2.2998 |
|
| 56 |
+
| 2.2741 | 1.5916 | 60 | 2.3083 |
|
| 57 |
+
| 2.2257 | 2.1076 | 80 | 2.3041 |
|
| 58 |
+
| 2.2605 | 2.6454 | 100 | 2.3115 |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- PEFT 0.14.0
|
| 64 |
+
- Transformers 4.49.0
|
| 65 |
+
- Pytorch 2.6.0
|
| 66 |
+
- Datasets 3.3.2
|
| 67 |
+
- Tokenizers 0.21.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "allenai/OLMo-7B-0724-hf",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"eva_config": null,
|
| 7 |
+
"exclude_modules": null,
|
| 8 |
+
"fan_in_fan_out": false,
|
| 9 |
+
"inference_mode": true,
|
| 10 |
+
"init_lora_weights": true,
|
| 11 |
+
"layer_replication": null,
|
| 12 |
+
"layers_pattern": null,
|
| 13 |
+
"layers_to_transform": null,
|
| 14 |
+
"loftq_config": {},
|
| 15 |
+
"lora_alpha": 16,
|
| 16 |
+
"lora_bias": false,
|
| 17 |
+
"lora_dropout": 0.1,
|
| 18 |
+
"megatron_config": null,
|
| 19 |
+
"megatron_core": "megatron.core",
|
| 20 |
+
"modules_to_save": null,
|
| 21 |
+
"peft_type": "LORA",
|
| 22 |
+
"r": 64,
|
| 23 |
+
"rank_pattern": {},
|
| 24 |
+
"revision": null,
|
| 25 |
+
"target_modules": [
|
| 26 |
+
"lm_head",
|
| 27 |
+
"up_proj",
|
| 28 |
+
"v_proj",
|
| 29 |
+
"q_proj",
|
| 30 |
+
"gate_proj",
|
| 31 |
+
"o_proj",
|
| 32 |
+
"down_proj",
|
| 33 |
+
"k_proj"
|
| 34 |
+
],
|
| 35 |
+
"task_type": "CAUSAL_LM",
|
| 36 |
+
"use_dora": false,
|
| 37 |
+
"use_rslora": false
|
| 38 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:403c2e359f3c18efc6d4531b1f787f1930cf4f25c9eaba8a101941af4c904ee9
|
| 3 |
+
size 1477800176
|
trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9411764705882355,
|
| 5 |
+
"eval_steps": 20,
|
| 6 |
+
"global_step": 111,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.05378151260504202,
|
| 13 |
+
"grad_norm": 0.012224463745951653,
|
| 14 |
+
"learning_rate": 0.001981818181818182,
|
| 15 |
+
"loss": 2.4733,
|
| 16 |
+
"step": 2
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.10756302521008404,
|
| 20 |
+
"grad_norm": 0.04710804298520088,
|
| 21 |
+
"learning_rate": 0.0019454545454545456,
|
| 22 |
+
"loss": 2.4443,
|
| 23 |
+
"step": 4
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16134453781512606,
|
| 27 |
+
"grad_norm": 0.09238269925117493,
|
| 28 |
+
"learning_rate": 0.0019090909090909091,
|
| 29 |
+
"loss": 2.3956,
|
| 30 |
+
"step": 6
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.21512605042016808,
|
| 34 |
+
"grad_norm": 0.17334744334220886,
|
| 35 |
+
"learning_rate": 0.0018727272727272729,
|
| 36 |
+
"loss": 2.4043,
|
| 37 |
+
"step": 8
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.2689075630252101,
|
| 41 |
+
"grad_norm": 0.11766365170478821,
|
| 42 |
+
"learning_rate": 0.0018363636363636364,
|
| 43 |
+
"loss": 2.385,
|
| 44 |
+
"step": 10
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.3226890756302521,
|
| 48 |
+
"grad_norm": 0.1385774314403534,
|
| 49 |
+
"learning_rate": 0.0018000000000000002,
|
| 50 |
+
"loss": 2.3933,
|
| 51 |
+
"step": 12
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.3764705882352941,
|
| 55 |
+
"grad_norm": 0.1210022047162056,
|
| 56 |
+
"learning_rate": 0.0017636363636363637,
|
| 57 |
+
"loss": 2.3733,
|
| 58 |
+
"step": 14
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.43025210084033616,
|
| 62 |
+
"grad_norm": 0.11510306596755981,
|
| 63 |
+
"learning_rate": 0.0017272727272727272,
|
| 64 |
+
"loss": 2.3297,
|
| 65 |
+
"step": 16
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.48403361344537815,
|
| 69 |
+
"grad_norm": 0.08369912207126617,
|
| 70 |
+
"learning_rate": 0.001690909090909091,
|
| 71 |
+
"loss": 2.351,
|
| 72 |
+
"step": 18
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.5378151260504201,
|
| 76 |
+
"grad_norm": 0.09298688918352127,
|
| 77 |
+
"learning_rate": 0.0016545454545454545,
|
| 78 |
+
"loss": 2.3175,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.5378151260504201,
|
| 83 |
+
"eval_loss": 2.3251912593841553,
|
| 84 |
+
"eval_runtime": 84.2914,
|
| 85 |
+
"eval_samples_per_second": 14.118,
|
| 86 |
+
"eval_steps_per_second": 1.768,
|
| 87 |
+
"step": 20
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.5915966386554622,
|
| 91 |
+
"grad_norm": 0.10441266000270844,
|
| 92 |
+
"learning_rate": 0.0016181818181818183,
|
| 93 |
+
"loss": 2.3643,
|
| 94 |
+
"step": 22
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.6453781512605042,
|
| 98 |
+
"grad_norm": 0.09343012422323227,
|
| 99 |
+
"learning_rate": 0.0015818181818181818,
|
| 100 |
+
"loss": 2.3391,
|
| 101 |
+
"step": 24
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6991596638655462,
|
| 105 |
+
"grad_norm": 0.09008985757827759,
|
| 106 |
+
"learning_rate": 0.0015454545454545454,
|
| 107 |
+
"loss": 2.2984,
|
| 108 |
+
"step": 26
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.7529411764705882,
|
| 112 |
+
"grad_norm": 0.08069847524166107,
|
| 113 |
+
"learning_rate": 0.0015090909090909091,
|
| 114 |
+
"loss": 2.3202,
|
| 115 |
+
"step": 28
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.8067226890756303,
|
| 119 |
+
"grad_norm": 0.08655106276273727,
|
| 120 |
+
"learning_rate": 0.0014727272727272727,
|
| 121 |
+
"loss": 2.3438,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.8605042016806723,
|
| 126 |
+
"grad_norm": 0.08203998953104019,
|
| 127 |
+
"learning_rate": 0.0014363636363636362,
|
| 128 |
+
"loss": 2.2862,
|
| 129 |
+
"step": 32
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.9142857142857143,
|
| 133 |
+
"grad_norm": 0.10055471211671829,
|
| 134 |
+
"learning_rate": 0.0014,
|
| 135 |
+
"loss": 2.3448,
|
| 136 |
+
"step": 34
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.9680672268907563,
|
| 140 |
+
"grad_norm": 0.08500978350639343,
|
| 141 |
+
"learning_rate": 0.0013636363636363635,
|
| 142 |
+
"loss": 2.3221,
|
| 143 |
+
"step": 36
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.0,
|
| 147 |
+
"grad_norm": 0.16502036154270172,
|
| 148 |
+
"learning_rate": 0.0013272727272727275,
|
| 149 |
+
"loss": 2.3438,
|
| 150 |
+
"step": 38
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.053781512605042,
|
| 154 |
+
"grad_norm": 0.08134379237890244,
|
| 155 |
+
"learning_rate": 0.001290909090909091,
|
| 156 |
+
"loss": 2.3075,
|
| 157 |
+
"step": 40
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.053781512605042,
|
| 161 |
+
"eval_loss": 2.299827814102173,
|
| 162 |
+
"eval_runtime": 84.1245,
|
| 163 |
+
"eval_samples_per_second": 14.146,
|
| 164 |
+
"eval_steps_per_second": 1.771,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.107563025210084,
|
| 169 |
+
"grad_norm": 0.09189953655004501,
|
| 170 |
+
"learning_rate": 0.0012545454545454546,
|
| 171 |
+
"loss": 2.2457,
|
| 172 |
+
"step": 42
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.1613445378151261,
|
| 176 |
+
"grad_norm": 0.09041959792375565,
|
| 177 |
+
"learning_rate": 0.0012181818181818183,
|
| 178 |
+
"loss": 2.2977,
|
| 179 |
+
"step": 44
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.2151260504201682,
|
| 183 |
+
"grad_norm": 0.08456366509199142,
|
| 184 |
+
"learning_rate": 0.0011818181818181819,
|
| 185 |
+
"loss": 2.2843,
|
| 186 |
+
"step": 46
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.26890756302521,
|
| 190 |
+
"grad_norm": 0.08097781240940094,
|
| 191 |
+
"learning_rate": 0.0011454545454545454,
|
| 192 |
+
"loss": 2.2328,
|
| 193 |
+
"step": 48
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.322689075630252,
|
| 197 |
+
"grad_norm": 0.10243827849626541,
|
| 198 |
+
"learning_rate": 0.0011090909090909092,
|
| 199 |
+
"loss": 2.254,
|
| 200 |
+
"step": 50
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.3764705882352941,
|
| 204 |
+
"grad_norm": 0.09242815524339676,
|
| 205 |
+
"learning_rate": 0.0010727272727272727,
|
| 206 |
+
"loss": 2.3295,
|
| 207 |
+
"step": 52
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.4302521008403362,
|
| 211 |
+
"grad_norm": 0.09403648227453232,
|
| 212 |
+
"learning_rate": 0.0010363636363636365,
|
| 213 |
+
"loss": 2.2749,
|
| 214 |
+
"step": 54
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.4840336134453782,
|
| 218 |
+
"grad_norm": 0.09187959879636765,
|
| 219 |
+
"learning_rate": 0.001,
|
| 220 |
+
"loss": 2.2606,
|
| 221 |
+
"step": 56
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.53781512605042,
|
| 225 |
+
"grad_norm": 0.09116198122501373,
|
| 226 |
+
"learning_rate": 0.0009636363636363637,
|
| 227 |
+
"loss": 2.2676,
|
| 228 |
+
"step": 58
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.5915966386554623,
|
| 232 |
+
"grad_norm": 0.08270075172185898,
|
| 233 |
+
"learning_rate": 0.0009272727272727273,
|
| 234 |
+
"loss": 2.2741,
|
| 235 |
+
"step": 60
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.5915966386554623,
|
| 239 |
+
"eval_loss": 2.3082737922668457,
|
| 240 |
+
"eval_runtime": 84.2709,
|
| 241 |
+
"eval_samples_per_second": 14.121,
|
| 242 |
+
"eval_steps_per_second": 1.768,
|
| 243 |
+
"step": 60
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.6453781512605041,
|
| 247 |
+
"grad_norm": 0.09275200217962265,
|
| 248 |
+
"learning_rate": 0.0008909090909090909,
|
| 249 |
+
"loss": 2.2582,
|
| 250 |
+
"step": 62
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 1.6991596638655462,
|
| 254 |
+
"grad_norm": 0.09241969138383865,
|
| 255 |
+
"learning_rate": 0.0008545454545454545,
|
| 256 |
+
"loss": 2.2554,
|
| 257 |
+
"step": 64
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 1.7529411764705882,
|
| 261 |
+
"grad_norm": 0.08338718116283417,
|
| 262 |
+
"learning_rate": 0.0008181818181818183,
|
| 263 |
+
"loss": 2.2244,
|
| 264 |
+
"step": 66
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.8067226890756303,
|
| 268 |
+
"grad_norm": 0.09568168222904205,
|
| 269 |
+
"learning_rate": 0.0007818181818181819,
|
| 270 |
+
"loss": 2.2719,
|
| 271 |
+
"step": 68
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 1.8605042016806723,
|
| 275 |
+
"grad_norm": 0.0905410498380661,
|
| 276 |
+
"learning_rate": 0.0007454545454545455,
|
| 277 |
+
"loss": 2.2505,
|
| 278 |
+
"step": 70
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.9142857142857141,
|
| 282 |
+
"grad_norm": 0.08841802924871445,
|
| 283 |
+
"learning_rate": 0.0007090909090909091,
|
| 284 |
+
"loss": 2.3005,
|
| 285 |
+
"step": 72
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.9680672268907564,
|
| 289 |
+
"grad_norm": 0.09013470262289047,
|
| 290 |
+
"learning_rate": 0.0006727272727272728,
|
| 291 |
+
"loss": 2.2682,
|
| 292 |
+
"step": 74
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.0,
|
| 296 |
+
"grad_norm": 0.19737772643566132,
|
| 297 |
+
"learning_rate": 0.0006363636363636364,
|
| 298 |
+
"loss": 2.3476,
|
| 299 |
+
"step": 76
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.053781512605042,
|
| 303 |
+
"grad_norm": 0.0839110016822815,
|
| 304 |
+
"learning_rate": 0.0006,
|
| 305 |
+
"loss": 2.2338,
|
| 306 |
+
"step": 78
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.107563025210084,
|
| 310 |
+
"grad_norm": 0.10582801699638367,
|
| 311 |
+
"learning_rate": 0.0005636363636363636,
|
| 312 |
+
"loss": 2.2257,
|
| 313 |
+
"step": 80
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.107563025210084,
|
| 317 |
+
"eval_loss": 2.304074764251709,
|
| 318 |
+
"eval_runtime": 84.3347,
|
| 319 |
+
"eval_samples_per_second": 14.11,
|
| 320 |
+
"eval_steps_per_second": 1.767,
|
| 321 |
+
"step": 80
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.161344537815126,
|
| 325 |
+
"grad_norm": 0.09145358949899673,
|
| 326 |
+
"learning_rate": 0.0005272727272727272,
|
| 327 |
+
"loss": 2.2488,
|
| 328 |
+
"step": 82
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 2.215126050420168,
|
| 332 |
+
"grad_norm": 0.08459240943193436,
|
| 333 |
+
"learning_rate": 0.0004909090909090909,
|
| 334 |
+
"loss": 2.2518,
|
| 335 |
+
"step": 84
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 2.26890756302521,
|
| 339 |
+
"grad_norm": 0.09590018540620804,
|
| 340 |
+
"learning_rate": 0.00045454545454545455,
|
| 341 |
+
"loss": 2.2324,
|
| 342 |
+
"step": 86
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.3226890756302523,
|
| 346 |
+
"grad_norm": 0.10032965242862701,
|
| 347 |
+
"learning_rate": 0.00041818181818181814,
|
| 348 |
+
"loss": 2.2099,
|
| 349 |
+
"step": 88
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 2.376470588235294,
|
| 353 |
+
"grad_norm": 0.09092257171869278,
|
| 354 |
+
"learning_rate": 0.00038181818181818184,
|
| 355 |
+
"loss": 2.2077,
|
| 356 |
+
"step": 90
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.4302521008403364,
|
| 360 |
+
"grad_norm": 0.10066290944814682,
|
| 361 |
+
"learning_rate": 0.00034545454545454544,
|
| 362 |
+
"loss": 2.2629,
|
| 363 |
+
"step": 92
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 2.484033613445378,
|
| 367 |
+
"grad_norm": 0.0973694771528244,
|
| 368 |
+
"learning_rate": 0.0003090909090909091,
|
| 369 |
+
"loss": 2.2292,
|
| 370 |
+
"step": 94
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 2.53781512605042,
|
| 374 |
+
"grad_norm": 0.09254106879234314,
|
| 375 |
+
"learning_rate": 0.00027272727272727274,
|
| 376 |
+
"loss": 2.1923,
|
| 377 |
+
"step": 96
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.5915966386554623,
|
| 381 |
+
"grad_norm": 0.10056042671203613,
|
| 382 |
+
"learning_rate": 0.00023636363636363636,
|
| 383 |
+
"loss": 2.2445,
|
| 384 |
+
"step": 98
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 2.645378151260504,
|
| 388 |
+
"grad_norm": 0.09601625055074692,
|
| 389 |
+
"learning_rate": 0.0002,
|
| 390 |
+
"loss": 2.2605,
|
| 391 |
+
"step": 100
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 2.645378151260504,
|
| 395 |
+
"eval_loss": 2.3115394115448,
|
| 396 |
+
"eval_runtime": 84.2807,
|
| 397 |
+
"eval_samples_per_second": 14.119,
|
| 398 |
+
"eval_steps_per_second": 1.768,
|
| 399 |
+
"step": 100
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.6991596638655464,
|
| 403 |
+
"grad_norm": 0.09498832374811172,
|
| 404 |
+
"learning_rate": 0.00016363636363636363,
|
| 405 |
+
"loss": 2.215,
|
| 406 |
+
"step": 102
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 2.7529411764705882,
|
| 410 |
+
"grad_norm": 0.09191343188285828,
|
| 411 |
+
"learning_rate": 0.00012727272727272725,
|
| 412 |
+
"loss": 2.2116,
|
| 413 |
+
"step": 104
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.80672268907563,
|
| 417 |
+
"grad_norm": 0.10717286169528961,
|
| 418 |
+
"learning_rate": 9.090909090909092e-05,
|
| 419 |
+
"loss": 2.2435,
|
| 420 |
+
"step": 106
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 2.8605042016806723,
|
| 424 |
+
"grad_norm": 0.09715902805328369,
|
| 425 |
+
"learning_rate": 5.4545454545454546e-05,
|
| 426 |
+
"loss": 2.2196,
|
| 427 |
+
"step": 108
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 2.914285714285714,
|
| 431 |
+
"grad_norm": 0.10500436276197433,
|
| 432 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 433 |
+
"loss": 2.2351,
|
| 434 |
+
"step": 110
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.9411764705882355,
|
| 438 |
+
"step": 111,
|
| 439 |
+
"total_flos": 8.1776874848256e+17,
|
| 440 |
+
"train_loss": 2.2894913076280474,
|
| 441 |
+
"train_runtime": 2825.7191,
|
| 442 |
+
"train_samples_per_second": 10.107,
|
| 443 |
+
"train_steps_per_second": 0.039
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.9411764705882355,
|
| 447 |
+
"eval_loss": 2.311664342880249,
|
| 448 |
+
"eval_runtime": 84.4111,
|
| 449 |
+
"eval_samples_per_second": 14.098,
|
| 450 |
+
"eval_steps_per_second": 1.765,
|
| 451 |
+
"step": 111
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.9411764705882355,
|
| 455 |
+
"eval_loss": 2.3323311805725098,
|
| 456 |
+
"eval_runtime": 84.1513,
|
| 457 |
+
"eval_samples_per_second": 14.141,
|
| 458 |
+
"eval_steps_per_second": 1.771,
|
| 459 |
+
"step": 111
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 2,
|
| 463 |
+
"max_steps": 111,
|
| 464 |
+
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 3,
|
| 466 |
+
"save_steps": 500,
|
| 467 |
+
"stateful_callbacks": {
|
| 468 |
+
"TrainerControl": {
|
| 469 |
+
"args": {
|
| 470 |
+
"should_epoch_stop": false,
|
| 471 |
+
"should_evaluate": false,
|
| 472 |
+
"should_log": false,
|
| 473 |
+
"should_save": true,
|
| 474 |
+
"should_training_stop": true
|
| 475 |
+
},
|
| 476 |
+
"attributes": {}
|
| 477 |
+
}
|
| 478 |
+
},
|
| 479 |
+
"total_flos": 8.1776874848256e+17,
|
| 480 |
+
"train_batch_size": 16,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4a1052c16d91be09a7b1f09514179cb0cb614fe81af5279d9a8cd2d7333c145
|
| 3 |
+
size 5496
|