End of training
Browse files- README.md +2 -1
- all_results.json +12 -0
- eval_results.json +7 -0
- train_results.json +8 -0
- trainer_state.json +724 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: llama3.1
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_metamath
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_metamath
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- Loss: 0.6692
|
| 21 |
|
|
|
|
| 4 |
base_model: meta-llama/Meta-Llama-3.1-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_metamath
|
|
|
|
| 16 |
|
| 17 |
# oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_metamath
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_metamath dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.6692
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6691574454307556,
|
| 4 |
+
"eval_runtime": 30.2172,
|
| 5 |
+
"eval_samples_per_second": 279.807,
|
| 6 |
+
"eval_steps_per_second": 1.125,
|
| 7 |
+
"total_flos": 1577885085204480.0,
|
| 8 |
+
"train_loss": 0.6401269947141093,
|
| 9 |
+
"train_runtime": 5912.9311,
|
| 10 |
+
"train_samples_per_second": 81.505,
|
| 11 |
+
"train_steps_per_second": 0.159
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.6691574454307556,
|
| 4 |
+
"eval_runtime": 30.2172,
|
| 5 |
+
"eval_samples_per_second": 279.807,
|
| 6 |
+
"eval_steps_per_second": 1.125
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 1577885085204480.0,
|
| 4 |
+
"train_loss": 0.6401269947141093,
|
| 5 |
+
"train_runtime": 5912.9311,
|
| 6 |
+
"train_samples_per_second": 81.505,
|
| 7 |
+
"train_steps_per_second": 0.159
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,724 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 942,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03184713375796178,
|
| 13 |
+
"grad_norm": 5.6323702767298744,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.942,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.06369426751592357,
|
| 20 |
+
"grad_norm": 1.8772154794170284,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.8332,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.09554140127388536,
|
| 27 |
+
"grad_norm": 1.15240428378361,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.7857,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.12738853503184713,
|
| 34 |
+
"grad_norm": 0.9723964053330802,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.7718,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1592356687898089,
|
| 41 |
+
"grad_norm": 1.180485085299224,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.7492,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.1910828025477707,
|
| 48 |
+
"grad_norm": 1.047903477889757,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.7413,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2229299363057325,
|
| 55 |
+
"grad_norm": 0.8341131630541828,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.719,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.25477707006369427,
|
| 62 |
+
"grad_norm": 0.9122278937918772,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.7184,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.28662420382165604,
|
| 69 |
+
"grad_norm": 0.7073501886373434,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.7121,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.3184713375796178,
|
| 76 |
+
"grad_norm": 0.8281770199094491,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.7092,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.3503184713375796,
|
| 83 |
+
"grad_norm": 0.7210347968056159,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.7013,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.3821656050955414,
|
| 90 |
+
"grad_norm": 0.5738125544201067,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.7022,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4140127388535032,
|
| 97 |
+
"grad_norm": 1.2444329803886918,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.7044,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.445859872611465,
|
| 104 |
+
"grad_norm": 0.75470283252076,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.692,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.47770700636942676,
|
| 111 |
+
"grad_norm": 0.6449167354505037,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.7023,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.5095541401273885,
|
| 118 |
+
"grad_norm": 0.5910288139996942,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.6944,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.5414012738853503,
|
| 125 |
+
"grad_norm": 0.5604434405342383,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.6966,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.5732484076433121,
|
| 132 |
+
"grad_norm": 0.6654582315660812,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.6876,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.6050955414012739,
|
| 139 |
+
"grad_norm": 0.9166199094846909,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.6891,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.6369426751592356,
|
| 146 |
+
"grad_norm": 0.7178723052852772,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.6832,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.6687898089171974,
|
| 153 |
+
"grad_norm": 0.6541344411840553,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.6803,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.7006369426751592,
|
| 160 |
+
"grad_norm": 0.637825014720494,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.6768,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.732484076433121,
|
| 167 |
+
"grad_norm": 0.5549500561748851,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.6825,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.7643312101910829,
|
| 174 |
+
"grad_norm": 0.654612026735291,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.6806,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.7961783439490446,
|
| 181 |
+
"grad_norm": 0.5538249059296838,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.6848,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.8280254777070064,
|
| 188 |
+
"grad_norm": 0.5723698853730642,
|
| 189 |
+
"learning_rate": 5e-06,
|
| 190 |
+
"loss": 0.6842,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.8598726114649682,
|
| 195 |
+
"grad_norm": 0.5768848558596881,
|
| 196 |
+
"learning_rate": 5e-06,
|
| 197 |
+
"loss": 0.6826,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.89171974522293,
|
| 202 |
+
"grad_norm": 0.531302038623778,
|
| 203 |
+
"learning_rate": 5e-06,
|
| 204 |
+
"loss": 0.6812,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.9235668789808917,
|
| 209 |
+
"grad_norm": 0.543420146899659,
|
| 210 |
+
"learning_rate": 5e-06,
|
| 211 |
+
"loss": 0.6774,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.9554140127388535,
|
| 216 |
+
"grad_norm": 0.509668170466935,
|
| 217 |
+
"learning_rate": 5e-06,
|
| 218 |
+
"loss": 0.6757,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.9872611464968153,
|
| 223 |
+
"grad_norm": 0.5426815942872757,
|
| 224 |
+
"learning_rate": 5e-06,
|
| 225 |
+
"loss": 0.6774,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.0,
|
| 230 |
+
"eval_loss": 0.6760347485542297,
|
| 231 |
+
"eval_runtime": 30.8722,
|
| 232 |
+
"eval_samples_per_second": 273.871,
|
| 233 |
+
"eval_steps_per_second": 1.101,
|
| 234 |
+
"step": 314
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.019108280254777,
|
| 238 |
+
"grad_norm": 0.7477023983107832,
|
| 239 |
+
"learning_rate": 5e-06,
|
| 240 |
+
"loss": 0.6476,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.0509554140127388,
|
| 245 |
+
"grad_norm": 0.6149216256910138,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.6341,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.0828025477707006,
|
| 252 |
+
"grad_norm": 0.7013272885905804,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.6285,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.1146496815286624,
|
| 259 |
+
"grad_norm": 0.6645252684100534,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.6293,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.1464968152866242,
|
| 266 |
+
"grad_norm": 0.6691516868475139,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.624,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.178343949044586,
|
| 273 |
+
"grad_norm": 0.6277574945118575,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.628,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.2101910828025477,
|
| 280 |
+
"grad_norm": 0.5594126038913051,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.6293,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.2420382165605095,
|
| 287 |
+
"grad_norm": 0.6377404973712193,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.6272,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.2738853503184713,
|
| 294 |
+
"grad_norm": 0.5512534318917951,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.6314,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.305732484076433,
|
| 301 |
+
"grad_norm": 0.6708898369555326,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.6309,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.3375796178343948,
|
| 308 |
+
"grad_norm": 0.662681777058966,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.6322,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.3694267515923566,
|
| 315 |
+
"grad_norm": 0.5855564523983591,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.6293,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.4012738853503186,
|
| 322 |
+
"grad_norm": 0.7027168380973281,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.6231,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.4331210191082802,
|
| 329 |
+
"grad_norm": 0.5875190666099424,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.6308,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.4649681528662422,
|
| 336 |
+
"grad_norm": 0.5695855789396209,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.6316,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.4968152866242037,
|
| 343 |
+
"grad_norm": 0.5640229543248884,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.6216,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.5286624203821657,
|
| 350 |
+
"grad_norm": 0.5284708915831005,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.634,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.5605095541401273,
|
| 357 |
+
"grad_norm": 0.6601370586932329,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.6211,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.5923566878980893,
|
| 364 |
+
"grad_norm": 0.5141465072879543,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.6263,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.6242038216560508,
|
| 371 |
+
"grad_norm": 0.7951970752704245,
|
| 372 |
+
"learning_rate": 5e-06,
|
| 373 |
+
"loss": 0.6283,
|
| 374 |
+
"step": 510
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.6560509554140128,
|
| 378 |
+
"grad_norm": 0.6915600915890423,
|
| 379 |
+
"learning_rate": 5e-06,
|
| 380 |
+
"loss": 0.6296,
|
| 381 |
+
"step": 520
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.6878980891719744,
|
| 385 |
+
"grad_norm": 0.5352783895102649,
|
| 386 |
+
"learning_rate": 5e-06,
|
| 387 |
+
"loss": 0.6243,
|
| 388 |
+
"step": 530
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.7197452229299364,
|
| 392 |
+
"grad_norm": 0.6389694940943629,
|
| 393 |
+
"learning_rate": 5e-06,
|
| 394 |
+
"loss": 0.6262,
|
| 395 |
+
"step": 540
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.7515923566878981,
|
| 399 |
+
"grad_norm": 0.638658826251017,
|
| 400 |
+
"learning_rate": 5e-06,
|
| 401 |
+
"loss": 0.6233,
|
| 402 |
+
"step": 550
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.78343949044586,
|
| 406 |
+
"grad_norm": 0.5164381003657269,
|
| 407 |
+
"learning_rate": 5e-06,
|
| 408 |
+
"loss": 0.6325,
|
| 409 |
+
"step": 560
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.8152866242038217,
|
| 413 |
+
"grad_norm": 0.5462044960453822,
|
| 414 |
+
"learning_rate": 5e-06,
|
| 415 |
+
"loss": 0.6262,
|
| 416 |
+
"step": 570
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.8471337579617835,
|
| 420 |
+
"grad_norm": 0.5320271319641363,
|
| 421 |
+
"learning_rate": 5e-06,
|
| 422 |
+
"loss": 0.6238,
|
| 423 |
+
"step": 580
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.8789808917197452,
|
| 427 |
+
"grad_norm": 0.6783189674697148,
|
| 428 |
+
"learning_rate": 5e-06,
|
| 429 |
+
"loss": 0.6195,
|
| 430 |
+
"step": 590
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.910828025477707,
|
| 434 |
+
"grad_norm": 0.6838086842362504,
|
| 435 |
+
"learning_rate": 5e-06,
|
| 436 |
+
"loss": 0.6242,
|
| 437 |
+
"step": 600
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.9426751592356688,
|
| 441 |
+
"grad_norm": 0.6094514581891239,
|
| 442 |
+
"learning_rate": 5e-06,
|
| 443 |
+
"loss": 0.6282,
|
| 444 |
+
"step": 610
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.9745222929936306,
|
| 448 |
+
"grad_norm": 0.627522298883166,
|
| 449 |
+
"learning_rate": 5e-06,
|
| 450 |
+
"loss": 0.6192,
|
| 451 |
+
"step": 620
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 2.0,
|
| 455 |
+
"eval_loss": 0.6656389832496643,
|
| 456 |
+
"eval_runtime": 31.0662,
|
| 457 |
+
"eval_samples_per_second": 272.161,
|
| 458 |
+
"eval_steps_per_second": 1.094,
|
| 459 |
+
"step": 628
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.0063694267515926,
|
| 463 |
+
"grad_norm": 0.9573075915273472,
|
| 464 |
+
"learning_rate": 5e-06,
|
| 465 |
+
"loss": 0.6157,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.038216560509554,
|
| 470 |
+
"grad_norm": 0.7301893995079715,
|
| 471 |
+
"learning_rate": 5e-06,
|
| 472 |
+
"loss": 0.5735,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.070063694267516,
|
| 477 |
+
"grad_norm": 0.7084282739053801,
|
| 478 |
+
"learning_rate": 5e-06,
|
| 479 |
+
"loss": 0.5778,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.1019108280254777,
|
| 484 |
+
"grad_norm": 0.6585976344607456,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.5784,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.1337579617834397,
|
| 491 |
+
"grad_norm": 0.6540062522321651,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.5751,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.1656050955414012,
|
| 498 |
+
"grad_norm": 0.5639591666878391,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.5766,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.1974522292993632,
|
| 505 |
+
"grad_norm": 0.8212954305221217,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.5798,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.229299363057325,
|
| 512 |
+
"grad_norm": 0.8109275454168715,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.5767,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.261146496815287,
|
| 519 |
+
"grad_norm": 0.6107672621726716,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.5773,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.2929936305732483,
|
| 526 |
+
"grad_norm": 0.6385570175836712,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.579,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.3248407643312103,
|
| 533 |
+
"grad_norm": 0.5907370356401401,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.5796,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.356687898089172,
|
| 540 |
+
"grad_norm": 0.5656820007312235,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.5748,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.388535031847134,
|
| 547 |
+
"grad_norm": 0.5760709804095724,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.5834,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.4203821656050954,
|
| 554 |
+
"grad_norm": 0.6305043111751713,
|
| 555 |
+
"learning_rate": 5e-06,
|
| 556 |
+
"loss": 0.5758,
|
| 557 |
+
"step": 760
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 2.4522292993630574,
|
| 561 |
+
"grad_norm": 0.5901331102554143,
|
| 562 |
+
"learning_rate": 5e-06,
|
| 563 |
+
"loss": 0.5856,
|
| 564 |
+
"step": 770
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 2.484076433121019,
|
| 568 |
+
"grad_norm": 0.6608011253619817,
|
| 569 |
+
"learning_rate": 5e-06,
|
| 570 |
+
"loss": 0.5786,
|
| 571 |
+
"step": 780
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.515923566878981,
|
| 575 |
+
"grad_norm": 0.6413426727699342,
|
| 576 |
+
"learning_rate": 5e-06,
|
| 577 |
+
"loss": 0.577,
|
| 578 |
+
"step": 790
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.5477707006369426,
|
| 582 |
+
"grad_norm": 0.5719942317033819,
|
| 583 |
+
"learning_rate": 5e-06,
|
| 584 |
+
"loss": 0.581,
|
| 585 |
+
"step": 800
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.5796178343949046,
|
| 589 |
+
"grad_norm": 0.5846298214850376,
|
| 590 |
+
"learning_rate": 5e-06,
|
| 591 |
+
"loss": 0.5809,
|
| 592 |
+
"step": 810
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 2.611464968152866,
|
| 596 |
+
"grad_norm": 0.6682316534474163,
|
| 597 |
+
"learning_rate": 5e-06,
|
| 598 |
+
"loss": 0.5845,
|
| 599 |
+
"step": 820
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 2.643312101910828,
|
| 603 |
+
"grad_norm": 0.5948936776108811,
|
| 604 |
+
"learning_rate": 5e-06,
|
| 605 |
+
"loss": 0.5837,
|
| 606 |
+
"step": 830
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 2.6751592356687897,
|
| 610 |
+
"grad_norm": 0.8151554129031496,
|
| 611 |
+
"learning_rate": 5e-06,
|
| 612 |
+
"loss": 0.5871,
|
| 613 |
+
"step": 840
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 2.7070063694267517,
|
| 617 |
+
"grad_norm": 0.5916261196390682,
|
| 618 |
+
"learning_rate": 5e-06,
|
| 619 |
+
"loss": 0.5797,
|
| 620 |
+
"step": 850
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 2.738853503184713,
|
| 624 |
+
"grad_norm": 0.6442969800604952,
|
| 625 |
+
"learning_rate": 5e-06,
|
| 626 |
+
"loss": 0.5814,
|
| 627 |
+
"step": 860
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.770700636942675,
|
| 631 |
+
"grad_norm": 0.6420974104025357,
|
| 632 |
+
"learning_rate": 5e-06,
|
| 633 |
+
"loss": 0.585,
|
| 634 |
+
"step": 870
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.802547770700637,
|
| 638 |
+
"grad_norm": 0.6318903979436119,
|
| 639 |
+
"learning_rate": 5e-06,
|
| 640 |
+
"loss": 0.5813,
|
| 641 |
+
"step": 880
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.8343949044585988,
|
| 645 |
+
"grad_norm": 0.6105841622731739,
|
| 646 |
+
"learning_rate": 5e-06,
|
| 647 |
+
"loss": 0.5823,
|
| 648 |
+
"step": 890
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.8662420382165603,
|
| 652 |
+
"grad_norm": 0.5727955806455897,
|
| 653 |
+
"learning_rate": 5e-06,
|
| 654 |
+
"loss": 0.5799,
|
| 655 |
+
"step": 900
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.8980891719745223,
|
| 659 |
+
"grad_norm": 0.5970248698087671,
|
| 660 |
+
"learning_rate": 5e-06,
|
| 661 |
+
"loss": 0.583,
|
| 662 |
+
"step": 910
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.9299363057324843,
|
| 666 |
+
"grad_norm": 0.6176747095322584,
|
| 667 |
+
"learning_rate": 5e-06,
|
| 668 |
+
"loss": 0.5816,
|
| 669 |
+
"step": 920
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.961783439490446,
|
| 673 |
+
"grad_norm": 0.550436105577002,
|
| 674 |
+
"learning_rate": 5e-06,
|
| 675 |
+
"loss": 0.585,
|
| 676 |
+
"step": 930
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.9936305732484074,
|
| 680 |
+
"grad_norm": 0.6334063259900834,
|
| 681 |
+
"learning_rate": 5e-06,
|
| 682 |
+
"loss": 0.5826,
|
| 683 |
+
"step": 940
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.0,
|
| 687 |
+
"eval_loss": 0.6691574454307556,
|
| 688 |
+
"eval_runtime": 30.8039,
|
| 689 |
+
"eval_samples_per_second": 274.478,
|
| 690 |
+
"eval_steps_per_second": 1.104,
|
| 691 |
+
"step": 942
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 3.0,
|
| 695 |
+
"step": 942,
|
| 696 |
+
"total_flos": 1577885085204480.0,
|
| 697 |
+
"train_loss": 0.6401269947141093,
|
| 698 |
+
"train_runtime": 5912.9311,
|
| 699 |
+
"train_samples_per_second": 81.505,
|
| 700 |
+
"train_steps_per_second": 0.159
|
| 701 |
+
}
|
| 702 |
+
],
|
| 703 |
+
"logging_steps": 10,
|
| 704 |
+
"max_steps": 942,
|
| 705 |
+
"num_input_tokens_seen": 0,
|
| 706 |
+
"num_train_epochs": 3,
|
| 707 |
+
"save_steps": 500,
|
| 708 |
+
"stateful_callbacks": {
|
| 709 |
+
"TrainerControl": {
|
| 710 |
+
"args": {
|
| 711 |
+
"should_epoch_stop": false,
|
| 712 |
+
"should_evaluate": false,
|
| 713 |
+
"should_log": false,
|
| 714 |
+
"should_save": true,
|
| 715 |
+
"should_training_stop": true
|
| 716 |
+
},
|
| 717 |
+
"attributes": {}
|
| 718 |
+
}
|
| 719 |
+
},
|
| 720 |
+
"total_flos": 1577885085204480.0,
|
| 721 |
+
"train_batch_size": 16,
|
| 722 |
+
"trial_name": null,
|
| 723 |
+
"trial_params": null
|
| 724 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|