End of training
Browse files- README.md +2 -2
- trainer_state.json +12 -12
README.md
CHANGED
|
@@ -7,14 +7,14 @@ tags:
|
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
-
- name: chess-lora-adapter-llama-3.1-8b
|
| 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 |
-
# chess-lora-adapter-llama-3.1-8b
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
| 20 |
|
|
|
|
| 7 |
- sft
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
+
- name: chess-lora-adapter-shortened-llama-3.1-8b
|
| 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 |
+
# chess-lora-adapter-shortened-llama-3.1-8b
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
|
| 20 |
|
trainer_state.json
CHANGED
|
@@ -10,33 +10,33 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.922509225092251,
|
| 13 |
-
"grad_norm": 0.
|
| 14 |
"learning_rate": 3.4624846248462485e-05,
|
| 15 |
-
"loss": 0.
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.8450184501845017,
|
| 20 |
-
"grad_norm": 0.
|
| 21 |
"learning_rate": 1.924969249692497e-05,
|
| 22 |
-
"loss": 0.
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.767527675276753,
|
| 27 |
-
"grad_norm":
|
| 28 |
"learning_rate": 3.874538745387454e-06,
|
| 29 |
-
"loss": 0.
|
| 30 |
"step": 1500
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 3.0,
|
| 34 |
"step": 1626,
|
| 35 |
-
"total_flos":
|
| 36 |
-
"train_loss": 0.
|
| 37 |
-
"train_runtime":
|
| 38 |
-
"train_samples_per_second": 0.
|
| 39 |
-
"train_steps_per_second": 0.
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 500,
|
|
@@ -56,7 +56,7 @@
|
|
| 56 |
"attributes": {}
|
| 57 |
}
|
| 58 |
},
|
| 59 |
-
"total_flos":
|
| 60 |
"train_batch_size": 1,
|
| 61 |
"trial_name": null,
|
| 62 |
"trial_params": null
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 0.922509225092251,
|
| 13 |
+
"grad_norm": 0.7217928171157837,
|
| 14 |
"learning_rate": 3.4624846248462485e-05,
|
| 15 |
+
"loss": 0.6626,
|
| 16 |
"step": 500
|
| 17 |
},
|
| 18 |
{
|
| 19 |
"epoch": 1.8450184501845017,
|
| 20 |
+
"grad_norm": 0.7293610572814941,
|
| 21 |
"learning_rate": 1.924969249692497e-05,
|
| 22 |
+
"loss": 0.4814,
|
| 23 |
"step": 1000
|
| 24 |
},
|
| 25 |
{
|
| 26 |
"epoch": 2.767527675276753,
|
| 27 |
+
"grad_norm": 1.1111749410629272,
|
| 28 |
"learning_rate": 3.874538745387454e-06,
|
| 29 |
+
"loss": 0.3739,
|
| 30 |
"step": 1500
|
| 31 |
},
|
| 32 |
{
|
| 33 |
"epoch": 3.0,
|
| 34 |
"step": 1626,
|
| 35 |
+
"total_flos": 1.7396479642263552e+16,
|
| 36 |
+
"train_loss": 0.49204357611737126,
|
| 37 |
+
"train_runtime": 2840.3977,
|
| 38 |
+
"train_samples_per_second": 0.572,
|
| 39 |
+
"train_steps_per_second": 0.572
|
| 40 |
}
|
| 41 |
],
|
| 42 |
"logging_steps": 500,
|
|
|
|
| 56 |
"attributes": {}
|
| 57 |
}
|
| 58 |
},
|
| 59 |
+
"total_flos": 1.7396479642263552e+16,
|
| 60 |
"train_batch_size": 1,
|
| 61 |
"trial_name": null,
|
| 62 |
"trial_params": null
|