Model save
Browse files
README.md
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
library_name: peft
|
| 4 |
+
tags:
|
| 5 |
+
- trl
|
| 6 |
+
- sft
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
| 9 |
+
model-index:
|
| 10 |
+
- name: mistral5pEnt
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# mistral5pEnt
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the None dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: nan
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 0.0002
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 8
|
| 47 |
+
- total_train_batch_size: 256
|
| 48 |
+
- total_eval_batch_size: 4
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 1
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 58 |
+
| 0.7399 | 1.0 | 406 | nan |
|
| 59 |
+
|
| 60 |
+
|
| 61 |
+
### Framework versions
|
| 62 |
+
|
| 63 |
+
- PEFT 0.11.1
|
| 64 |
+
- Transformers 4.41.1
|
| 65 |
+
- Pytorch 2.2.2+cu121
|
| 66 |
+
- Datasets 2.19.1
|
| 67 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 8,
|
| 14 |
+
"lora_dropout": 0.05,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 6,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"k_proj",
|
| 24 |
+
"o_proj",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"q_proj",
|
| 27 |
+
"v_proj",
|
| 28 |
+
"down_proj",
|
| 29 |
+
"up_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:31b207d6aab65fa8c6d8864ec3feb0b5f2a6e2fd9ec0293ef44da2973bb24d7d
|
| 3 |
+
size 62973728
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 2.141142957716144e+18,
|
| 4 |
+
"train_loss": 0.7449051919829082,
|
| 5 |
+
"train_runtime": 67510.9339,
|
| 6 |
+
"train_samples": 103932,
|
| 7 |
+
"train_samples_per_second": 1.539,
|
| 8 |
+
"train_steps_per_second": 0.006
|
| 9 |
+
}
|
runs/Jun01_05-39-03_ip-172-31-69-60.ec2.internal/events.out.tfevents.1717220662.ip-172-31-69-60.ec2.internal.12840.0
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:bfe78d27aeea8f84fa21cc79db38d08db6b5025d9111ad453ac294f638593e93
|
| 3 |
+
size 22924
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 2.141142957716144e+18,
|
| 4 |
+
"train_loss": 0.7449051919829082,
|
| 5 |
+
"train_runtime": 67510.9339,
|
| 6 |
+
"train_samples": 103932,
|
| 7 |
+
"train_samples_per_second": 1.539,
|
| 8 |
+
"train_steps_per_second": 0.006
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,624 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 406,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0024630541871921183,
|
| 13 |
+
"grad_norm": 0.13162502646446228,
|
| 14 |
+
"learning_rate": 4.8780487804878055e-06,
|
| 15 |
+
"loss": 0.7597,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.012315270935960592,
|
| 20 |
+
"grad_norm": 0.13736732304096222,
|
| 21 |
+
"learning_rate": 2.4390243902439026e-05,
|
| 22 |
+
"loss": 0.7842,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.024630541871921183,
|
| 27 |
+
"grad_norm": 0.12169680744409561,
|
| 28 |
+
"learning_rate": 4.878048780487805e-05,
|
| 29 |
+
"loss": 0.7899,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.03694581280788178,
|
| 34 |
+
"grad_norm": 0.12660211324691772,
|
| 35 |
+
"learning_rate": 7.317073170731707e-05,
|
| 36 |
+
"loss": 0.7838,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.04926108374384237,
|
| 41 |
+
"grad_norm": 0.10873105376958847,
|
| 42 |
+
"learning_rate": 9.75609756097561e-05,
|
| 43 |
+
"loss": 0.7806,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.06157635467980296,
|
| 48 |
+
"grad_norm": 0.10080835968255997,
|
| 49 |
+
"learning_rate": 0.00012195121951219512,
|
| 50 |
+
"loss": 0.7563,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.07389162561576355,
|
| 55 |
+
"grad_norm": 0.10492738336324692,
|
| 56 |
+
"learning_rate": 0.00014634146341463414,
|
| 57 |
+
"loss": 0.7523,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.08620689655172414,
|
| 62 |
+
"grad_norm": 0.11805374175310135,
|
| 63 |
+
"learning_rate": 0.0001707317073170732,
|
| 64 |
+
"loss": 0.7508,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.09852216748768473,
|
| 69 |
+
"grad_norm": 0.10792019963264465,
|
| 70 |
+
"learning_rate": 0.0001951219512195122,
|
| 71 |
+
"loss": 0.7493,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.11083743842364532,
|
| 76 |
+
"grad_norm": 0.1062043085694313,
|
| 77 |
+
"learning_rate": 0.0001999407400739705,
|
| 78 |
+
"loss": 0.7374,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.12315270935960591,
|
| 83 |
+
"grad_norm": 0.1073506623506546,
|
| 84 |
+
"learning_rate": 0.00019970011699250152,
|
| 85 |
+
"loss": 0.7742,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1354679802955665,
|
| 90 |
+
"grad_norm": 0.09551604837179184,
|
| 91 |
+
"learning_rate": 0.00019927487224577402,
|
| 92 |
+
"loss": 0.7462,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.1477832512315271,
|
| 97 |
+
"grad_norm": 0.09559881687164307,
|
| 98 |
+
"learning_rate": 0.0001986657932891657,
|
| 99 |
+
"loss": 0.7428,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.16009852216748768,
|
| 104 |
+
"grad_norm": 0.09791220724582672,
|
| 105 |
+
"learning_rate": 0.00019787400799669154,
|
| 106 |
+
"loss": 0.7474,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1724137931034483,
|
| 111 |
+
"grad_norm": 0.09669492393732071,
|
| 112 |
+
"learning_rate": 0.00019690098257244064,
|
| 113 |
+
"loss": 0.7544,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.18472906403940886,
|
| 118 |
+
"grad_norm": 0.10031192749738693,
|
| 119 |
+
"learning_rate": 0.00019574851883550395,
|
| 120 |
+
"loss": 0.7497,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.19704433497536947,
|
| 125 |
+
"grad_norm": 0.09971891343593597,
|
| 126 |
+
"learning_rate": 0.00019441875088341997,
|
| 127 |
+
"loss": 0.7436,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.20935960591133004,
|
| 132 |
+
"grad_norm": 0.09163269400596619,
|
| 133 |
+
"learning_rate": 0.00019291414114031743,
|
| 134 |
+
"loss": 0.7371,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.22167487684729065,
|
| 139 |
+
"grad_norm": 0.09539525210857391,
|
| 140 |
+
"learning_rate": 0.00019123747579707275,
|
| 141 |
+
"loss": 0.7586,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.23399014778325122,
|
| 146 |
+
"grad_norm": 0.0916183665394783,
|
| 147 |
+
"learning_rate": 0.0001893918596519257,
|
| 148 |
+
"loss": 0.763,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.24630541871921183,
|
| 153 |
+
"grad_norm": 0.10328999906778336,
|
| 154 |
+
"learning_rate": 0.00018738071036110808,
|
| 155 |
+
"loss": 0.7504,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.25862068965517243,
|
| 160 |
+
"grad_norm": 0.10348416864871979,
|
| 161 |
+
"learning_rate": 0.00018520775211013093,
|
| 162 |
+
"loss": 0.7501,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.270935960591133,
|
| 167 |
+
"grad_norm": 0.09487516433000565,
|
| 168 |
+
"learning_rate": 0.00018287700871745036,
|
| 169 |
+
"loss": 0.7644,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.2832512315270936,
|
| 174 |
+
"grad_norm": 0.105643130838871,
|
| 175 |
+
"learning_rate": 0.00018039279618328212,
|
| 176 |
+
"loss": 0.76,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.2955665024630542,
|
| 181 |
+
"grad_norm": 0.10078058391809464,
|
| 182 |
+
"learning_rate": 0.0001777597146973627,
|
| 183 |
+
"loss": 0.739,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.3078817733990148,
|
| 188 |
+
"grad_norm": 0.0928851068019867,
|
| 189 |
+
"learning_rate": 0.00017498264012045687,
|
| 190 |
+
"loss": 0.7442,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.32019704433497537,
|
| 195 |
+
"grad_norm": 0.09560341387987137,
|
| 196 |
+
"learning_rate": 0.00017206671495538612,
|
| 197 |
+
"loss": 0.7404,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.33251231527093594,
|
| 202 |
+
"grad_norm": 0.10253967344760895,
|
| 203 |
+
"learning_rate": 0.0001690173388242972,
|
| 204 |
+
"loss": 0.737,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3448275862068966,
|
| 209 |
+
"grad_norm": 0.09540513157844543,
|
| 210 |
+
"learning_rate": 0.0001658401584698049,
|
| 211 |
+
"loss": 0.7467,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.35714285714285715,
|
| 216 |
+
"grad_norm": 0.09915637969970703,
|
| 217 |
+
"learning_rate": 0.00016254105729852464,
|
| 218 |
+
"loss": 0.7415,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.3694581280788177,
|
| 223 |
+
"grad_norm": 0.0903649777173996,
|
| 224 |
+
"learning_rate": 0.00015912614448635782,
|
| 225 |
+
"loss": 0.7529,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.3817733990147783,
|
| 230 |
+
"grad_norm": 0.09867067635059357,
|
| 231 |
+
"learning_rate": 0.00015560174366570446,
|
| 232 |
+
"loss": 0.7395,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.39408866995073893,
|
| 237 |
+
"grad_norm": 0.09925885498523712,
|
| 238 |
+
"learning_rate": 0.0001519743812155516,
|
| 239 |
+
"loss": 0.7535,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.4064039408866995,
|
| 244 |
+
"grad_norm": 0.09206779301166534,
|
| 245 |
+
"learning_rate": 0.00014825077417612186,
|
| 246 |
+
"loss": 0.7542,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4187192118226601,
|
| 251 |
+
"grad_norm": 0.09731363505125046,
|
| 252 |
+
"learning_rate": 0.00014443781781046136,
|
| 253 |
+
"loss": 0.7584,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.43103448275862066,
|
| 258 |
+
"grad_norm": 0.09406079351902008,
|
| 259 |
+
"learning_rate": 0.00014054257283599973,
|
| 260 |
+
"loss": 0.7193,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.4433497536945813,
|
| 265 |
+
"grad_norm": 0.0967475026845932,
|
| 266 |
+
"learning_rate": 0.00013657225234972695,
|
| 267 |
+
"loss": 0.7346,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.45566502463054187,
|
| 272 |
+
"grad_norm": 0.09659844636917114,
|
| 273 |
+
"learning_rate": 0.00013253420847119803,
|
| 274 |
+
"loss": 0.7356,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.46798029556650245,
|
| 279 |
+
"grad_norm": 0.09907151758670807,
|
| 280 |
+
"learning_rate": 0.0001284359187281004,
|
| 281 |
+
"loss": 0.7404,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.4802955665024631,
|
| 286 |
+
"grad_norm": 0.09383893758058548,
|
| 287 |
+
"learning_rate": 0.0001242849722095936,
|
| 288 |
+
"loss": 0.7282,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.49261083743842365,
|
| 293 |
+
"grad_norm": 0.09458262473344803,
|
| 294 |
+
"learning_rate": 0.00012008905551306356,
|
| 295 |
+
"loss": 0.7513,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.5049261083743842,
|
| 300 |
+
"grad_norm": 0.09368573129177094,
|
| 301 |
+
"learning_rate": 0.00011585593851031347,
|
| 302 |
+
"loss": 0.7376,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5172413793103449,
|
| 307 |
+
"grad_norm": 0.09154163300991058,
|
| 308 |
+
"learning_rate": 0.00011159345995955006,
|
| 309 |
+
"loss": 0.734,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5295566502463054,
|
| 314 |
+
"grad_norm": 0.09107346832752228,
|
| 315 |
+
"learning_rate": 0.00010730951298980776,
|
| 316 |
+
"loss": 0.7339,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.541871921182266,
|
| 321 |
+
"grad_norm": 0.09472489356994629,
|
| 322 |
+
"learning_rate": 0.00010301203048469083,
|
| 323 |
+
"loss": 0.7584,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.5541871921182266,
|
| 328 |
+
"grad_norm": 0.1033613383769989,
|
| 329 |
+
"learning_rate": 9.870897039249911e-05,
|
| 330 |
+
"loss": 0.7339,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.5665024630541872,
|
| 335 |
+
"grad_norm": 0.09532911330461502,
|
| 336 |
+
"learning_rate": 9.440830098993969e-05,
|
| 337 |
+
"loss": 0.737,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.5788177339901478,
|
| 342 |
+
"grad_norm": 0.09540988504886627,
|
| 343 |
+
"learning_rate": 9.011798612671286e-05,
|
| 344 |
+
"loss": 0.7234,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.5911330049261084,
|
| 349 |
+
"grad_norm": 0.09416648745536804,
|
| 350 |
+
"learning_rate": 8.58459704782957e-05,
|
| 351 |
+
"loss": 0.7325,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.603448275862069,
|
| 356 |
+
"grad_norm": 0.09317279607057571,
|
| 357 |
+
"learning_rate": 8.160016483423199e-05,
|
| 358 |
+
"loss": 0.741,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.6157635467980296,
|
| 363 |
+
"grad_norm": 0.09846732765436172,
|
| 364 |
+
"learning_rate": 7.738843144917119e-05,
|
| 365 |
+
"loss": 0.7345,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6280788177339901,
|
| 370 |
+
"grad_norm": 0.0930534228682518,
|
| 371 |
+
"learning_rate": 7.321856948378259e-05,
|
| 372 |
+
"loss": 0.7464,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6403940886699507,
|
| 377 |
+
"grad_norm": 0.0964062288403511,
|
| 378 |
+
"learning_rate": 6.909830056250527e-05,
|
| 379 |
+
"loss": 0.7486,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.6527093596059114,
|
| 384 |
+
"grad_norm": 0.09874962270259857,
|
| 385 |
+
"learning_rate": 6.503525447487715e-05,
|
| 386 |
+
"loss": 0.7365,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.6650246305418719,
|
| 391 |
+
"grad_norm": 0.09022323042154312,
|
| 392 |
+
"learning_rate": 6.103695504692122e-05,
|
| 393 |
+
"loss": 0.7403,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.6773399014778325,
|
| 398 |
+
"grad_norm": 0.10088326781988144,
|
| 399 |
+
"learning_rate": 5.7110806208751655e-05,
|
| 400 |
+
"loss": 0.7391,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.6896551724137931,
|
| 405 |
+
"grad_norm": 0.09062828868627548,
|
| 406 |
+
"learning_rate": 5.326407828419979e-05,
|
| 407 |
+
"loss": 0.7475,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7019704433497537,
|
| 412 |
+
"grad_norm": 0.10531575977802277,
|
| 413 |
+
"learning_rate": 4.9503894527847964e-05,
|
| 414 |
+
"loss": 0.7406,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7142857142857143,
|
| 419 |
+
"grad_norm": 0.09364870190620422,
|
| 420 |
+
"learning_rate": 4.583721793440188e-05,
|
| 421 |
+
"loss": 0.7352,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7266009852216748,
|
| 426 |
+
"grad_norm": 0.1008005440235138,
|
| 427 |
+
"learning_rate": 4.227083834482728e-05,
|
| 428 |
+
"loss": 0.7564,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7389162561576355,
|
| 433 |
+
"grad_norm": 0.09413261711597443,
|
| 434 |
+
"learning_rate": 3.881135987312757e-05,
|
| 435 |
+
"loss": 0.7305,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.7512315270935961,
|
| 440 |
+
"grad_norm": 0.08913769572973251,
|
| 441 |
+
"learning_rate": 3.546518867704499e-05,
|
| 442 |
+
"loss": 0.7462,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.7635467980295566,
|
| 447 |
+
"grad_norm": 0.09481265395879745,
|
| 448 |
+
"learning_rate": 3.223852109533112e-05,
|
| 449 |
+
"loss": 0.7393,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.7758620689655172,
|
| 454 |
+
"grad_norm": 0.09792128205299377,
|
| 455 |
+
"learning_rate": 2.9137332173554043e-05,
|
| 456 |
+
"loss": 0.7319,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.7881773399014779,
|
| 461 |
+
"grad_norm": 0.09496279060840607,
|
| 462 |
+
"learning_rate": 2.616736459968936e-05,
|
| 463 |
+
"loss": 0.7403,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8004926108374384,
|
| 468 |
+
"grad_norm": 0.09277407079935074,
|
| 469 |
+
"learning_rate": 2.33341180699841e-05,
|
| 470 |
+
"loss": 0.7555,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.812807881773399,
|
| 475 |
+
"grad_norm": 0.09130670130252838,
|
| 476 |
+
"learning_rate": 2.0642839104785272e-05,
|
| 477 |
+
"loss": 0.7443,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8251231527093597,
|
| 482 |
+
"grad_norm": 0.09380558133125305,
|
| 483 |
+
"learning_rate": 1.8098511333192024e-05,
|
| 484 |
+
"loss": 0.7335,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.8374384236453202,
|
| 489 |
+
"grad_norm": 0.09957650303840637,
|
| 490 |
+
"learning_rate": 1.570584626452173e-05,
|
| 491 |
+
"loss": 0.7601,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.8497536945812808,
|
| 496 |
+
"grad_norm": 0.09125210344791412,
|
| 497 |
+
"learning_rate": 1.3469274563679402e-05,
|
| 498 |
+
"loss": 0.7457,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.8620689655172413,
|
| 503 |
+
"grad_norm": 0.09114491194486618,
|
| 504 |
+
"learning_rate": 1.1392937846586215e-05,
|
| 505 |
+
"loss": 0.7409,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.874384236453202,
|
| 510 |
+
"grad_norm": 0.09509284049272537,
|
| 511 |
+
"learning_rate": 9.48068101086026e-06,
|
| 512 |
+
"loss": 0.7192,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.8866995073891626,
|
| 517 |
+
"grad_norm": 0.09615782648324966,
|
| 518 |
+
"learning_rate": 7.736045115951251e-06,
|
| 519 |
+
"loss": 0.7328,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.8990147783251231,
|
| 524 |
+
"grad_norm": 0.0975566878914833,
|
| 525 |
+
"learning_rate": 6.16226082591359e-06,
|
| 526 |
+
"loss": 0.7294,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9113300492610837,
|
| 531 |
+
"grad_norm": 0.09337764233350754,
|
| 532 |
+
"learning_rate": 4.762242426960262e-06,
|
| 533 |
+
"loss": 0.7285,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9236453201970444,
|
| 538 |
+
"grad_norm": 0.08856361359357834,
|
| 539 |
+
"learning_rate": 3.5385824308756587e-06,
|
| 540 |
+
"loss": 0.7406,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.9359605911330049,
|
| 545 |
+
"grad_norm": 0.0950755774974823,
|
| 546 |
+
"learning_rate": 2.493546774280531e-06,
|
| 547 |
+
"loss": 0.7322,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.9482758620689655,
|
| 552 |
+
"grad_norm": 0.09195266664028168,
|
| 553 |
+
"learning_rate": 1.6290706226390285e-06,
|
| 554 |
+
"loss": 0.7347,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.9605911330049262,
|
| 559 |
+
"grad_norm": 0.09885134547948837,
|
| 560 |
+
"learning_rate": 9.46754786777726e-07,
|
| 561 |
+
"loss": 0.7334,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.9729064039408867,
|
| 566 |
+
"grad_norm": 0.08973979949951172,
|
| 567 |
+
"learning_rate": 4.4786275855247527e-07,
|
| 568 |
+
"loss": 0.7481,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.9852216748768473,
|
| 573 |
+
"grad_norm": 0.08960015326738358,
|
| 574 |
+
"learning_rate": 1.333183711524133e-07,
|
| 575 |
+
"loss": 0.7376,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.9975369458128078,
|
| 580 |
+
"grad_norm": 0.09271183609962463,
|
| 581 |
+
"learning_rate": 3.7040883734462683e-09,
|
| 582 |
+
"loss": 0.7399,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.0,
|
| 587 |
+
"eval_loss": NaN,
|
| 588 |
+
"eval_runtime": 934.5149,
|
| 589 |
+
"eval_samples_per_second": 1.236,
|
| 590 |
+
"eval_steps_per_second": 0.309,
|
| 591 |
+
"step": 406
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0,
|
| 595 |
+
"step": 406,
|
| 596 |
+
"total_flos": 2.141142957716144e+18,
|
| 597 |
+
"train_loss": 0.7449051919829082,
|
| 598 |
+
"train_runtime": 67510.9339,
|
| 599 |
+
"train_samples_per_second": 1.539,
|
| 600 |
+
"train_steps_per_second": 0.006
|
| 601 |
+
}
|
| 602 |
+
],
|
| 603 |
+
"logging_steps": 5,
|
| 604 |
+
"max_steps": 406,
|
| 605 |
+
"num_input_tokens_seen": 0,
|
| 606 |
+
"num_train_epochs": 1,
|
| 607 |
+
"save_steps": 100,
|
| 608 |
+
"stateful_callbacks": {
|
| 609 |
+
"TrainerControl": {
|
| 610 |
+
"args": {
|
| 611 |
+
"should_epoch_stop": false,
|
| 612 |
+
"should_evaluate": false,
|
| 613 |
+
"should_log": false,
|
| 614 |
+
"should_save": true,
|
| 615 |
+
"should_training_stop": false
|
| 616 |
+
},
|
| 617 |
+
"attributes": {}
|
| 618 |
+
}
|
| 619 |
+
},
|
| 620 |
+
"total_flos": 2.141142957716144e+18,
|
| 621 |
+
"train_batch_size": 8,
|
| 622 |
+
"trial_name": null,
|
| 623 |
+
"trial_params": null
|
| 624 |
+
}
|