Model save
Browse files- README.md +65 -0
- all_results.json +9 -0
- generation_config.json +7 -0
- model.safetensors +1 -1
- runs/Sep05_22-49-26_nova.cs.ucla.edu/events.out.tfevents.1725601953.nova.cs.ucla.edu.1919554.0 +2 -2
- train_results.json +9 -0
- trainer_state.json +801 -0
README.md
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
model-index:
|
| 9 |
+
- name: tinyllama-sft-wizard-processed-indicator-0.6-full
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# tinyllama-sft-wizard-processed-indicator-0.6-full
|
| 17 |
+
|
| 18 |
+
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 an unknown dataset.
|
| 19 |
+
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.7583
|
| 21 |
+
|
| 22 |
+
## Model description
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Intended uses & limitations
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training and evaluation data
|
| 31 |
+
|
| 32 |
+
More information needed
|
| 33 |
+
|
| 34 |
+
## Training procedure
|
| 35 |
+
|
| 36 |
+
### Training hyperparameters
|
| 37 |
+
|
| 38 |
+
The following hyperparameters were used during training:
|
| 39 |
+
- learning_rate: 2e-05
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
+
- eval_batch_size: 8
|
| 42 |
+
- seed: 42
|
| 43 |
+
- distributed_type: multi-GPU
|
| 44 |
+
- num_devices: 4
|
| 45 |
+
- gradient_accumulation_steps: 2
|
| 46 |
+
- total_train_batch_size: 128
|
| 47 |
+
- total_eval_batch_size: 32
|
| 48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
+
- lr_scheduler_type: cosine
|
| 50 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 51 |
+
- num_epochs: 1
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 57 |
+
| 0.7509 | 1.0 | 543 | 0.7583 |
|
| 58 |
+
|
| 59 |
+
|
| 60 |
+
### Framework versions
|
| 61 |
+
|
| 62 |
+
- Transformers 4.40.1
|
| 63 |
+
- Pytorch 2.4.0+cu121
|
| 64 |
+
- Datasets 2.20.0
|
| 65 |
+
- Tokenizers 0.19.1
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 49305877217280.0,
|
| 4 |
+
"train_loss": 0.7919497733616697,
|
| 5 |
+
"train_runtime": 3542.7729,
|
| 6 |
+
"train_samples": 69499,
|
| 7 |
+
"train_samples_per_second": 19.617,
|
| 8 |
+
"train_steps_per_second": 0.153
|
| 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": "4.40.1"
|
| 7 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2200136248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1bba5b08bec63a03fb2e79d01e1eb293bf7cb1950a7fcee2c9e0e4552d69d7f8
|
| 3 |
size 2200136248
|
runs/Sep05_22-49-26_nova.cs.ucla.edu/events.out.tfevents.1725601953.nova.cs.ucla.edu.1919554.0
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:aed645010c3be4ab738468c3ae65e8ed00dd8bfa6f88c9ede09e332d0666a318
|
| 3 |
+
size 28502
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 49305877217280.0,
|
| 4 |
+
"train_loss": 0.7919497733616697,
|
| 5 |
+
"train_runtime": 3542.7729,
|
| 6 |
+
"train_samples": 69499,
|
| 7 |
+
"train_samples_per_second": 19.617,
|
| 8 |
+
"train_steps_per_second": 0.153
|
| 9 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,801 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 543,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.001841620626151013,
|
| 13 |
+
"grad_norm": 9.486898645787276,
|
| 14 |
+
"learning_rate": 3.6363636363636366e-07,
|
| 15 |
+
"loss": 1.3331,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.009208103130755065,
|
| 20 |
+
"grad_norm": 9.648113107304198,
|
| 21 |
+
"learning_rate": 1.8181818181818183e-06,
|
| 22 |
+
"loss": 1.3395,
|
| 23 |
+
"step": 5
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01841620626151013,
|
| 27 |
+
"grad_norm": 6.990867421428758,
|
| 28 |
+
"learning_rate": 3.6363636363636366e-06,
|
| 29 |
+
"loss": 1.2962,
|
| 30 |
+
"step": 10
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.027624309392265192,
|
| 34 |
+
"grad_norm": 3.458068927612039,
|
| 35 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 36 |
+
"loss": 1.0739,
|
| 37 |
+
"step": 15
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.03683241252302026,
|
| 41 |
+
"grad_norm": 1.2260366851944846,
|
| 42 |
+
"learning_rate": 7.272727272727273e-06,
|
| 43 |
+
"loss": 0.9505,
|
| 44 |
+
"step": 20
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.04604051565377532,
|
| 48 |
+
"grad_norm": 1.0221449554865838,
|
| 49 |
+
"learning_rate": 9.090909090909091e-06,
|
| 50 |
+
"loss": 0.9144,
|
| 51 |
+
"step": 25
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.055248618784530384,
|
| 55 |
+
"grad_norm": 0.8620729339974224,
|
| 56 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 57 |
+
"loss": 0.8733,
|
| 58 |
+
"step": 30
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06445672191528545,
|
| 62 |
+
"grad_norm": 0.851167156872127,
|
| 63 |
+
"learning_rate": 1.2727272727272728e-05,
|
| 64 |
+
"loss": 0.8785,
|
| 65 |
+
"step": 35
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.07366482504604052,
|
| 69 |
+
"grad_norm": 0.9108061969642942,
|
| 70 |
+
"learning_rate": 1.4545454545454546e-05,
|
| 71 |
+
"loss": 0.8671,
|
| 72 |
+
"step": 40
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08287292817679558,
|
| 76 |
+
"grad_norm": 0.9428707752739769,
|
| 77 |
+
"learning_rate": 1.6363636363636366e-05,
|
| 78 |
+
"loss": 0.8432,
|
| 79 |
+
"step": 45
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.09208103130755065,
|
| 83 |
+
"grad_norm": 0.799992233407414,
|
| 84 |
+
"learning_rate": 1.8181818181818182e-05,
|
| 85 |
+
"loss": 0.8391,
|
| 86 |
+
"step": 50
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.10128913443830571,
|
| 90 |
+
"grad_norm": 0.92988123755397,
|
| 91 |
+
"learning_rate": 2e-05,
|
| 92 |
+
"loss": 0.8069,
|
| 93 |
+
"step": 55
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.11049723756906077,
|
| 97 |
+
"grad_norm": 0.8806369480862966,
|
| 98 |
+
"learning_rate": 1.9994819965926346e-05,
|
| 99 |
+
"loss": 0.8461,
|
| 100 |
+
"step": 60
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.11970534069981584,
|
| 104 |
+
"grad_norm": 0.8429565875911434,
|
| 105 |
+
"learning_rate": 1.997928523025598e-05,
|
| 106 |
+
"loss": 0.8114,
|
| 107 |
+
"step": 65
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.1289134438305709,
|
| 111 |
+
"grad_norm": 2.6074141932570747,
|
| 112 |
+
"learning_rate": 1.9953411887080917e-05,
|
| 113 |
+
"loss": 0.8269,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.13812154696132597,
|
| 118 |
+
"grad_norm": 0.81068282261157,
|
| 119 |
+
"learning_rate": 1.9917226741361014e-05,
|
| 120 |
+
"loss": 0.8313,
|
| 121 |
+
"step": 75
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.14732965009208104,
|
| 125 |
+
"grad_norm": 0.8146705010362959,
|
| 126 |
+
"learning_rate": 1.987076728115383e-05,
|
| 127 |
+
"loss": 0.8233,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.15653775322283608,
|
| 132 |
+
"grad_norm": 0.8212502515723833,
|
| 133 |
+
"learning_rate": 1.9814081638776743e-05,
|
| 134 |
+
"loss": 0.8348,
|
| 135 |
+
"step": 85
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.16574585635359115,
|
| 139 |
+
"grad_norm": 0.9178279389667914,
|
| 140 |
+
"learning_rate": 1.9747228540941555e-05,
|
| 141 |
+
"loss": 0.8146,
|
| 142 |
+
"step": 90
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.17495395948434622,
|
| 146 |
+
"grad_norm": 0.7885672960810044,
|
| 147 |
+
"learning_rate": 1.9670277247913205e-05,
|
| 148 |
+
"loss": 0.8296,
|
| 149 |
+
"step": 95
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.1841620626151013,
|
| 153 |
+
"grad_norm": 0.848764605997187,
|
| 154 |
+
"learning_rate": 1.958330748175568e-05,
|
| 155 |
+
"loss": 0.7949,
|
| 156 |
+
"step": 100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.19337016574585636,
|
| 160 |
+
"grad_norm": 0.7700219317674329,
|
| 161 |
+
"learning_rate": 1.948640934373939e-05,
|
| 162 |
+
"loss": 0.7866,
|
| 163 |
+
"step": 105
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.20257826887661143,
|
| 167 |
+
"grad_norm": 0.8315949857083919,
|
| 168 |
+
"learning_rate": 1.9379683220995657e-05,
|
| 169 |
+
"loss": 0.7962,
|
| 170 |
+
"step": 110
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.21178637200736647,
|
| 174 |
+
"grad_norm": 0.7752955445936617,
|
| 175 |
+
"learning_rate": 1.9263239682514953e-05,
|
| 176 |
+
"loss": 0.792,
|
| 177 |
+
"step": 115
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.22099447513812154,
|
| 181 |
+
"grad_norm": 0.8483319625591622,
|
| 182 |
+
"learning_rate": 1.9137199364596673e-05,
|
| 183 |
+
"loss": 0.7884,
|
| 184 |
+
"step": 120
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.2302025782688766,
|
| 188 |
+
"grad_norm": 0.8183776324168913,
|
| 189 |
+
"learning_rate": 1.9001692845869113e-05,
|
| 190 |
+
"loss": 0.801,
|
| 191 |
+
"step": 125
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.23941068139963168,
|
| 195 |
+
"grad_norm": 0.811447671431964,
|
| 196 |
+
"learning_rate": 1.8856860512009115e-05,
|
| 197 |
+
"loss": 0.7786,
|
| 198 |
+
"step": 130
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.24861878453038674,
|
| 202 |
+
"grad_norm": 0.8277281887592228,
|
| 203 |
+
"learning_rate": 1.8702852410301556e-05,
|
| 204 |
+
"loss": 0.8104,
|
| 205 |
+
"step": 135
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.2578268876611418,
|
| 209 |
+
"grad_norm": 0.8077180581855568,
|
| 210 |
+
"learning_rate": 1.853982809418932e-05,
|
| 211 |
+
"loss": 0.7828,
|
| 212 |
+
"step": 140
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.26703499079189685,
|
| 216 |
+
"grad_norm": 0.8329105731452281,
|
| 217 |
+
"learning_rate": 1.8367956457974872e-05,
|
| 218 |
+
"loss": 0.7894,
|
| 219 |
+
"step": 145
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.27624309392265195,
|
| 223 |
+
"grad_norm": 0.797486657559649,
|
| 224 |
+
"learning_rate": 1.8187415561844586e-05,
|
| 225 |
+
"loss": 0.7987,
|
| 226 |
+
"step": 150
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.285451197053407,
|
| 230 |
+
"grad_norm": 0.8537594990493205,
|
| 231 |
+
"learning_rate": 1.7998392447397197e-05,
|
| 232 |
+
"loss": 0.8036,
|
| 233 |
+
"step": 155
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.2946593001841621,
|
| 237 |
+
"grad_norm": 0.8180506794487967,
|
| 238 |
+
"learning_rate": 1.7801082943867406e-05,
|
| 239 |
+
"loss": 0.7932,
|
| 240 |
+
"step": 160
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.30386740331491713,
|
| 244 |
+
"grad_norm": 0.8084360565762896,
|
| 245 |
+
"learning_rate": 1.7595691465245484e-05,
|
| 246 |
+
"loss": 0.7835,
|
| 247 |
+
"step": 165
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.31307550644567217,
|
| 251 |
+
"grad_norm": 0.8626100032968109,
|
| 252 |
+
"learning_rate": 1.7382430798502977e-05,
|
| 253 |
+
"loss": 0.7946,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.32228360957642727,
|
| 258 |
+
"grad_norm": 0.8294498359295781,
|
| 259 |
+
"learning_rate": 1.7161521883143936e-05,
|
| 260 |
+
"loss": 0.7854,
|
| 261 |
+
"step": 175
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.3314917127071823,
|
| 265 |
+
"grad_norm": 0.7709771325792745,
|
| 266 |
+
"learning_rate": 1.693319358231011e-05,
|
| 267 |
+
"loss": 0.8142,
|
| 268 |
+
"step": 180
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.3406998158379374,
|
| 272 |
+
"grad_norm": 0.7818326227818909,
|
| 273 |
+
"learning_rate": 1.6697682445677158e-05,
|
| 274 |
+
"loss": 0.7954,
|
| 275 |
+
"step": 185
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.34990791896869244,
|
| 279 |
+
"grad_norm": 0.8179375717027894,
|
| 280 |
+
"learning_rate": 1.6455232464387587e-05,
|
| 281 |
+
"loss": 0.7884,
|
| 282 |
+
"step": 190
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.35911602209944754,
|
| 286 |
+
"grad_norm": 0.7920896471000997,
|
| 287 |
+
"learning_rate": 1.6206094818274228e-05,
|
| 288 |
+
"loss": 0.7718,
|
| 289 |
+
"step": 195
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3683241252302026,
|
| 293 |
+
"grad_norm": 0.7893170590987618,
|
| 294 |
+
"learning_rate": 1.595052761563627e-05,
|
| 295 |
+
"loss": 0.7689,
|
| 296 |
+
"step": 200
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3775322283609576,
|
| 300 |
+
"grad_norm": 0.7657795923746319,
|
| 301 |
+
"learning_rate": 1.5688795625837274e-05,
|
| 302 |
+
"loss": 0.7881,
|
| 303 |
+
"step": 205
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.3867403314917127,
|
| 307 |
+
"grad_norm": 0.8393984134836868,
|
| 308 |
+
"learning_rate": 1.542117000500229e-05,
|
| 309 |
+
"loss": 0.7788,
|
| 310 |
+
"step": 210
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.39594843462246776,
|
| 314 |
+
"grad_norm": 0.8118764962105299,
|
| 315 |
+
"learning_rate": 1.5147928015098309e-05,
|
| 316 |
+
"loss": 0.7505,
|
| 317 |
+
"step": 215
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.40515653775322286,
|
| 321 |
+
"grad_norm": 0.7991535490667581,
|
| 322 |
+
"learning_rate": 1.4869352736688938e-05,
|
| 323 |
+
"loss": 0.7957,
|
| 324 |
+
"step": 220
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.4143646408839779,
|
| 328 |
+
"grad_norm": 0.8314136999499325,
|
| 329 |
+
"learning_rate": 1.458573277566103e-05,
|
| 330 |
+
"loss": 0.7912,
|
| 331 |
+
"step": 225
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.42357274401473294,
|
| 335 |
+
"grad_norm": 0.8256559921181463,
|
| 336 |
+
"learning_rate": 1.4297361964227004e-05,
|
| 337 |
+
"loss": 0.7764,
|
| 338 |
+
"step": 230
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.43278084714548803,
|
| 342 |
+
"grad_norm": 0.8766553756889243,
|
| 343 |
+
"learning_rate": 1.4004539056512667e-05,
|
| 344 |
+
"loss": 0.7755,
|
| 345 |
+
"step": 235
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.4419889502762431,
|
| 349 |
+
"grad_norm": 0.833181681270549,
|
| 350 |
+
"learning_rate": 1.3707567419045926e-05,
|
| 351 |
+
"loss": 0.7767,
|
| 352 |
+
"step": 240
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.45119705340699817,
|
| 356 |
+
"grad_norm": 0.7499469252603318,
|
| 357 |
+
"learning_rate": 1.3406754716466978e-05,
|
| 358 |
+
"loss": 0.7632,
|
| 359 |
+
"step": 245
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.4604051565377532,
|
| 363 |
+
"grad_norm": 0.79015324314155,
|
| 364 |
+
"learning_rate": 1.3102412592785654e-05,
|
| 365 |
+
"loss": 0.7621,
|
| 366 |
+
"step": 250
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.4696132596685083,
|
| 370 |
+
"grad_norm": 0.7575412875758781,
|
| 371 |
+
"learning_rate": 1.2794856348516095e-05,
|
| 372 |
+
"loss": 0.7623,
|
| 373 |
+
"step": 255
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.47882136279926335,
|
| 377 |
+
"grad_norm": 0.8681572551776058,
|
| 378 |
+
"learning_rate": 1.248440461402328e-05,
|
| 379 |
+
"loss": 0.782,
|
| 380 |
+
"step": 260
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.4880294659300184,
|
| 384 |
+
"grad_norm": 0.8073679206498725,
|
| 385 |
+
"learning_rate": 1.2171379019419786e-05,
|
| 386 |
+
"loss": 0.7705,
|
| 387 |
+
"step": 265
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.4972375690607735,
|
| 391 |
+
"grad_norm": 0.7841235830752601,
|
| 392 |
+
"learning_rate": 1.1856103861354809e-05,
|
| 393 |
+
"loss": 0.7583,
|
| 394 |
+
"step": 270
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5064456721915286,
|
| 398 |
+
"grad_norm": 0.8108587176276811,
|
| 399 |
+
"learning_rate": 1.153890576704062e-05,
|
| 400 |
+
"loss": 0.765,
|
| 401 |
+
"step": 275
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.5156537753222836,
|
| 405 |
+
"grad_norm": 0.8126438543382127,
|
| 406 |
+
"learning_rate": 1.1220113355864549e-05,
|
| 407 |
+
"loss": 0.7525,
|
| 408 |
+
"step": 280
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.5248618784530387,
|
| 412 |
+
"grad_norm": 0.7777072836945255,
|
| 413 |
+
"learning_rate": 1.0900056898937055e-05,
|
| 414 |
+
"loss": 0.7544,
|
| 415 |
+
"step": 285
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.5340699815837937,
|
| 419 |
+
"grad_norm": 0.7965361718611623,
|
| 420 |
+
"learning_rate": 1.0579067976928614e-05,
|
| 421 |
+
"loss": 0.773,
|
| 422 |
+
"step": 290
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.5432780847145487,
|
| 426 |
+
"grad_norm": 0.8193189022177652,
|
| 427 |
+
"learning_rate": 1.0257479136549889e-05,
|
| 428 |
+
"loss": 0.7675,
|
| 429 |
+
"step": 295
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.5524861878453039,
|
| 433 |
+
"grad_norm": 0.8067397329296685,
|
| 434 |
+
"learning_rate": 9.935623546031043e-06,
|
| 435 |
+
"loss": 0.7762,
|
| 436 |
+
"step": 300
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.5616942909760589,
|
| 440 |
+
"grad_norm": 0.7907814478229841,
|
| 441 |
+
"learning_rate": 9.613834649957216e-06,
|
| 442 |
+
"loss": 0.7638,
|
| 443 |
+
"step": 305
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.570902394106814,
|
| 447 |
+
"grad_norm": 0.7491658704683205,
|
| 448 |
+
"learning_rate": 9.292445823817647e-06,
|
| 449 |
+
"loss": 0.7573,
|
| 450 |
+
"step": 310
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.580110497237569,
|
| 454 |
+
"grad_norm": 0.7616414768278772,
|
| 455 |
+
"learning_rate": 8.971790028626395e-06,
|
| 456 |
+
"loss": 0.7536,
|
| 457 |
+
"step": 315
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5893186003683242,
|
| 461 |
+
"grad_norm": 0.8064255556517879,
|
| 462 |
+
"learning_rate": 8.652199465972462e-06,
|
| 463 |
+
"loss": 0.7772,
|
| 464 |
+
"step": 320
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.5985267034990792,
|
| 468 |
+
"grad_norm": 0.8002742479547474,
|
| 469 |
+
"learning_rate": 8.334005233856681e-06,
|
| 470 |
+
"loss": 0.797,
|
| 471 |
+
"step": 325
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.6077348066298343,
|
| 475 |
+
"grad_norm": 0.7711512481084595,
|
| 476 |
+
"learning_rate": 8.017536983671929e-06,
|
| 477 |
+
"loss": 0.7492,
|
| 478 |
+
"step": 330
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6169429097605893,
|
| 482 |
+
"grad_norm": 0.877795536912771,
|
| 483 |
+
"learning_rate": 7.703122578682047e-06,
|
| 484 |
+
"loss": 0.7664,
|
| 485 |
+
"step": 335
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.6261510128913443,
|
| 489 |
+
"grad_norm": 0.7877424655087469,
|
| 490 |
+
"learning_rate": 7.391087754353252e-06,
|
| 491 |
+
"loss": 0.7521,
|
| 492 |
+
"step": 340
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.6353591160220995,
|
| 496 |
+
"grad_norm": 0.7447106165793183,
|
| 497 |
+
"learning_rate": 7.081755780889978e-06,
|
| 498 |
+
"loss": 0.7576,
|
| 499 |
+
"step": 345
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.6445672191528545,
|
| 503 |
+
"grad_norm": 0.755847533013407,
|
| 504 |
+
"learning_rate": 6.7754471283247594e-06,
|
| 505 |
+
"loss": 0.7575,
|
| 506 |
+
"step": 350
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6537753222836096,
|
| 510 |
+
"grad_norm": 0.8049779605578884,
|
| 511 |
+
"learning_rate": 6.472479134509052e-06,
|
| 512 |
+
"loss": 0.7527,
|
| 513 |
+
"step": 355
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6629834254143646,
|
| 517 |
+
"grad_norm": 0.7303729256503527,
|
| 518 |
+
"learning_rate": 6.173165676349103e-06,
|
| 519 |
+
"loss": 0.751,
|
| 520 |
+
"step": 360
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.6721915285451197,
|
| 524 |
+
"grad_norm": 0.7685648396444108,
|
| 525 |
+
"learning_rate": 5.8778168446273045e-06,
|
| 526 |
+
"loss": 0.7578,
|
| 527 |
+
"step": 365
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.6813996316758748,
|
| 531 |
+
"grad_norm": 0.8106456096464736,
|
| 532 |
+
"learning_rate": 5.586738622746042e-06,
|
| 533 |
+
"loss": 0.7552,
|
| 534 |
+
"step": 370
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.6906077348066298,
|
| 538 |
+
"grad_norm": 0.820301021151535,
|
| 539 |
+
"learning_rate": 5.300232569726805e-06,
|
| 540 |
+
"loss": 0.7532,
|
| 541 |
+
"step": 375
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 0.6998158379373849,
|
| 545 |
+
"grad_norm": 0.7482967036736521,
|
| 546 |
+
"learning_rate": 5.0185955077929774e-06,
|
| 547 |
+
"loss": 0.74,
|
| 548 |
+
"step": 380
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 0.7090239410681399,
|
| 552 |
+
"grad_norm": 0.7662545231902685,
|
| 553 |
+
"learning_rate": 4.742119214860009e-06,
|
| 554 |
+
"loss": 0.7506,
|
| 555 |
+
"step": 385
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.7182320441988951,
|
| 559 |
+
"grad_norm": 0.8228369078010023,
|
| 560 |
+
"learning_rate": 4.471090122251496e-06,
|
| 561 |
+
"loss": 0.7683,
|
| 562 |
+
"step": 390
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.7274401473296501,
|
| 566 |
+
"grad_norm": 0.815178887743864,
|
| 567 |
+
"learning_rate": 4.205789017954364e-06,
|
| 568 |
+
"loss": 0.7593,
|
| 569 |
+
"step": 395
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.7366482504604052,
|
| 573 |
+
"grad_norm": 0.784624202462136,
|
| 574 |
+
"learning_rate": 3.946490755720621e-06,
|
| 575 |
+
"loss": 0.737,
|
| 576 |
+
"step": 400
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.7458563535911602,
|
| 580 |
+
"grad_norm": 0.746907024064999,
|
| 581 |
+
"learning_rate": 3.6934639703169905e-06,
|
| 582 |
+
"loss": 0.7688,
|
| 583 |
+
"step": 405
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 0.7550644567219152,
|
| 587 |
+
"grad_norm": 0.7543025440325943,
|
| 588 |
+
"learning_rate": 3.4469707992174607e-06,
|
| 589 |
+
"loss": 0.7549,
|
| 590 |
+
"step": 410
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.7642725598526704,
|
| 594 |
+
"grad_norm": 0.7752230336855982,
|
| 595 |
+
"learning_rate": 3.207266611027069e-06,
|
| 596 |
+
"loss": 0.753,
|
| 597 |
+
"step": 415
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.7734806629834254,
|
| 601 |
+
"grad_norm": 0.7518906525746277,
|
| 602 |
+
"learning_rate": 2.97459974091831e-06,
|
| 603 |
+
"loss": 0.7282,
|
| 604 |
+
"step": 420
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 0.7826887661141805,
|
| 608 |
+
"grad_norm": 0.7680193007274547,
|
| 609 |
+
"learning_rate": 2.7492112333541744e-06,
|
| 610 |
+
"loss": 0.7627,
|
| 611 |
+
"step": 425
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.7918968692449355,
|
| 615 |
+
"grad_norm": 0.7566643318267062,
|
| 616 |
+
"learning_rate": 2.531334592364457e-06,
|
| 617 |
+
"loss": 0.751,
|
| 618 |
+
"step": 430
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.8011049723756906,
|
| 622 |
+
"grad_norm": 0.7844855003556812,
|
| 623 |
+
"learning_rate": 2.3211955396340003e-06,
|
| 624 |
+
"loss": 0.7418,
|
| 625 |
+
"step": 435
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.8103130755064457,
|
| 629 |
+
"grad_norm": 0.803025429826923,
|
| 630 |
+
"learning_rate": 2.1190117806534714e-06,
|
| 631 |
+
"loss": 0.7592,
|
| 632 |
+
"step": 440
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.8195211786372008,
|
| 636 |
+
"grad_norm": 0.7378091665334658,
|
| 637 |
+
"learning_rate": 1.924992779174999e-06,
|
| 638 |
+
"loss": 0.751,
|
| 639 |
+
"step": 445
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.8287292817679558,
|
| 643 |
+
"grad_norm": 0.7457306258807127,
|
| 644 |
+
"learning_rate": 1.7393395402063085e-06,
|
| 645 |
+
"loss": 0.7453,
|
| 646 |
+
"step": 450
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8379373848987108,
|
| 650 |
+
"grad_norm": 0.8022714604664063,
|
| 651 |
+
"learning_rate": 1.5622444017681438e-06,
|
| 652 |
+
"loss": 0.7754,
|
| 653 |
+
"step": 455
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.8471454880294659,
|
| 657 |
+
"grad_norm": 0.776511111974054,
|
| 658 |
+
"learning_rate": 1.3938908356307846e-06,
|
| 659 |
+
"loss": 0.7521,
|
| 660 |
+
"step": 460
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.856353591160221,
|
| 664 |
+
"grad_norm": 0.813230099626258,
|
| 665 |
+
"learning_rate": 1.2344532572360325e-06,
|
| 666 |
+
"loss": 0.7613,
|
| 667 |
+
"step": 465
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 0.8655616942909761,
|
| 671 |
+
"grad_norm": 0.7447985437221388,
|
| 672 |
+
"learning_rate": 1.0840968450016276e-06,
|
| 673 |
+
"loss": 0.7536,
|
| 674 |
+
"step": 470
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8747697974217311,
|
| 678 |
+
"grad_norm": 0.7650288847018589,
|
| 679 |
+
"learning_rate": 9.42977369195286e-07,
|
| 680 |
+
"loss": 0.7384,
|
| 681 |
+
"step": 475
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.8839779005524862,
|
| 685 |
+
"grad_norm": 0.7256984697699458,
|
| 686 |
+
"learning_rate": 8.112410305556307e-07,
|
| 687 |
+
"loss": 0.7667,
|
| 688 |
+
"step": 480
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 0.8931860036832413,
|
| 692 |
+
"grad_norm": 0.7357960253082361,
|
| 693 |
+
"learning_rate": 6.890243088272453e-07,
|
| 694 |
+
"loss": 0.7622,
|
| 695 |
+
"step": 485
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.9023941068139963,
|
| 699 |
+
"grad_norm": 0.7811263789047292,
|
| 700 |
+
"learning_rate": 5.764538213667103e-07,
|
| 701 |
+
"loss": 0.7452,
|
| 702 |
+
"step": 490
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.9116022099447514,
|
| 706 |
+
"grad_norm": 0.739936412399576,
|
| 707 |
+
"learning_rate": 4.73646191966175e-07,
|
| 708 |
+
"loss": 0.7562,
|
| 709 |
+
"step": 495
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 0.9208103130755064,
|
| 713 |
+
"grad_norm": 0.723301898239526,
|
| 714 |
+
"learning_rate": 3.8070793003030296e-07,
|
| 715 |
+
"loss": 0.7391,
|
| 716 |
+
"step": 500
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 0.9300184162062615,
|
| 720 |
+
"grad_norm": 0.7573677757358993,
|
| 721 |
+
"learning_rate": 2.9773532023180897e-07,
|
| 722 |
+
"loss": 0.7652,
|
| 723 |
+
"step": 505
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9392265193370166,
|
| 727 |
+
"grad_norm": 0.8052929969157859,
|
| 728 |
+
"learning_rate": 2.248143227598809e-07,
|
| 729 |
+
"loss": 0.7637,
|
| 730 |
+
"step": 510
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9484346224677717,
|
| 734 |
+
"grad_norm": 0.764474777249725,
|
| 735 |
+
"learning_rate": 1.6202048426483652e-07,
|
| 736 |
+
"loss": 0.7541,
|
| 737 |
+
"step": 515
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.9576427255985267,
|
| 741 |
+
"grad_norm": 0.7342491064890043,
|
| 742 |
+
"learning_rate": 1.094188595912804e-07,
|
| 743 |
+
"loss": 0.7498,
|
| 744 |
+
"step": 520
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.9668508287292817,
|
| 748 |
+
"grad_norm": 0.7649422354591825,
|
| 749 |
+
"learning_rate": 6.706394438083962e-08,
|
| 750 |
+
"loss": 0.7451,
|
| 751 |
+
"step": 525
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 0.9760589318600368,
|
| 755 |
+
"grad_norm": 0.7902374858951695,
|
| 756 |
+
"learning_rate": 3.4999618614309784e-08,
|
| 757 |
+
"loss": 0.7636,
|
| 758 |
+
"step": 530
|
| 759 |
+
},
|
| 760 |
+
{
|
| 761 |
+
"epoch": 0.9852670349907919,
|
| 762 |
+
"grad_norm": 0.790427562884146,
|
| 763 |
+
"learning_rate": 1.325910115169471e-08,
|
| 764 |
+
"loss": 0.7452,
|
| 765 |
+
"step": 535
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.994475138121547,
|
| 769 |
+
"grad_norm": 0.7278103543057389,
|
| 770 |
+
"learning_rate": 1.8649153172423106e-09,
|
| 771 |
+
"loss": 0.7509,
|
| 772 |
+
"step": 540
|
| 773 |
+
},
|
| 774 |
+
{
|
| 775 |
+
"epoch": 1.0,
|
| 776 |
+
"eval_loss": 0.7582516074180603,
|
| 777 |
+
"eval_runtime": 7.3708,
|
| 778 |
+
"eval_samples_per_second": 67.835,
|
| 779 |
+
"eval_steps_per_second": 2.171,
|
| 780 |
+
"step": 543
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.0,
|
| 784 |
+
"step": 543,
|
| 785 |
+
"total_flos": 49305877217280.0,
|
| 786 |
+
"train_loss": 0.7919497733616697,
|
| 787 |
+
"train_runtime": 3542.7729,
|
| 788 |
+
"train_samples_per_second": 19.617,
|
| 789 |
+
"train_steps_per_second": 0.153
|
| 790 |
+
}
|
| 791 |
+
],
|
| 792 |
+
"logging_steps": 5,
|
| 793 |
+
"max_steps": 543,
|
| 794 |
+
"num_input_tokens_seen": 0,
|
| 795 |
+
"num_train_epochs": 1,
|
| 796 |
+
"save_steps": 100,
|
| 797 |
+
"total_flos": 49305877217280.0,
|
| 798 |
+
"train_batch_size": 16,
|
| 799 |
+
"trial_name": null,
|
| 800 |
+
"trial_params": null
|
| 801 |
+
}
|