End of training
Browse files- README.md +3 -2
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +84 -0
README.md
CHANGED
|
@@ -3,8 +3,9 @@ base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
|
| 3 |
library_name: peft
|
| 4 |
license: llama3.1
|
| 5 |
tags:
|
| 6 |
-
- unsloth
|
| 7 |
- llama-factory
|
|
|
|
|
|
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: new-llamafactory-llama-3-8b
|
|
@@ -16,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# new-llamafactory-llama-3-8b
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 3 |
library_name: peft
|
| 4 |
license: llama3.1
|
| 5 |
tags:
|
|
|
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
+
- unsloth
|
| 9 |
- generated_from_trainer
|
| 10 |
model-index:
|
| 11 |
- name: new-llamafactory-llama-3-8b
|
|
|
|
| 17 |
|
| 18 |
# new-llamafactory-llama-3-8b
|
| 19 |
|
| 20 |
+
This model is a fine-tuned version of [unsloth/llama-3-8b-Instruct-bnb-4bit](https://huggingface.co/unsloth/llama-3-8b-Instruct-bnb-4bit) on the formatted_data dataset.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.992,
|
| 3 |
+
"total_flos": 1.6166347506450432e+16,
|
| 4 |
+
"train_loss": 0.15166758986250048,
|
| 5 |
+
"train_runtime": 892.7422,
|
| 6 |
+
"train_samples_per_second": 0.56,
|
| 7 |
+
"train_steps_per_second": 0.069
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.992,
|
| 3 |
+
"total_flos": 1.6166347506450432e+16,
|
| 4 |
+
"train_loss": 0.15166758986250048,
|
| 5 |
+
"train_runtime": 892.7422,
|
| 6 |
+
"train_samples_per_second": 0.56,
|
| 7 |
+
"train_steps_per_second": 0.069
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.992,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 62,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.16,
|
| 13 |
+
"grad_norm": 1.7386187314987183,
|
| 14 |
+
"learning_rate": 1.9853538358476933e-05,
|
| 15 |
+
"loss": 0.2613,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.32,
|
| 20 |
+
"grad_norm": 2.1634316444396973,
|
| 21 |
+
"learning_rate": 1.736741137876405e-05,
|
| 22 |
+
"loss": 0.216,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.48,
|
| 27 |
+
"grad_norm": 2.8627727031707764,
|
| 28 |
+
"learning_rate": 1.2542183341934873e-05,
|
| 29 |
+
"loss": 0.1431,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.64,
|
| 34 |
+
"grad_norm": 2.0235531330108643,
|
| 35 |
+
"learning_rate": 6.909830056250527e-06,
|
| 36 |
+
"loss": 0.088,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.8,
|
| 41 |
+
"grad_norm": 1.9142417907714844,
|
| 42 |
+
"learning_rate": 2.2585838936091753e-06,
|
| 43 |
+
"loss": 0.107,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.96,
|
| 48 |
+
"grad_norm": 1.0446289777755737,
|
| 49 |
+
"learning_rate": 6.51826465144978e-08,
|
| 50 |
+
"loss": 0.118,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.992,
|
| 55 |
+
"step": 62,
|
| 56 |
+
"total_flos": 1.6166347506450432e+16,
|
| 57 |
+
"train_loss": 0.15166758986250048,
|
| 58 |
+
"train_runtime": 892.7422,
|
| 59 |
+
"train_samples_per_second": 0.56,
|
| 60 |
+
"train_steps_per_second": 0.069
|
| 61 |
+
}
|
| 62 |
+
],
|
| 63 |
+
"logging_steps": 10,
|
| 64 |
+
"max_steps": 62,
|
| 65 |
+
"num_input_tokens_seen": 0,
|
| 66 |
+
"num_train_epochs": 1,
|
| 67 |
+
"save_steps": 1000,
|
| 68 |
+
"stateful_callbacks": {
|
| 69 |
+
"TrainerControl": {
|
| 70 |
+
"args": {
|
| 71 |
+
"should_epoch_stop": false,
|
| 72 |
+
"should_evaluate": false,
|
| 73 |
+
"should_log": false,
|
| 74 |
+
"should_save": false,
|
| 75 |
+
"should_training_stop": false
|
| 76 |
+
},
|
| 77 |
+
"attributes": {}
|
| 78 |
+
}
|
| 79 |
+
},
|
| 80 |
+
"total_flos": 1.6166347506450432e+16,
|
| 81 |
+
"train_batch_size": 2,
|
| 82 |
+
"trial_name": null,
|
| 83 |
+
"trial_params": null
|
| 84 |
+
}
|