End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +763 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ library_name: peft
|
|
| 4 |
license: llama3
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: material_sft_10epoch
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# material_sft_10epoch
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
license: llama3
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- lora
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: material_sft_10epoch
|
|
|
|
| 16 |
|
| 17 |
# material_sft_10epoch
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the material_data dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.927710843373493,
|
| 3 |
+
"total_flos": 144813601193984.0,
|
| 4 |
+
"train_loss": 0.8549524587334938,
|
| 5 |
+
"train_runtime": 9342.774,
|
| 6 |
+
"train_samples_per_second": 0.888,
|
| 7 |
+
"train_steps_per_second": 0.11
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 9.927710843373493,
|
| 3 |
+
"total_flos": 144813601193984.0,
|
| 4 |
+
"train_loss": 0.8549524587334938,
|
| 5 |
+
"train_runtime": 9342.774,
|
| 6 |
+
"train_samples_per_second": 0.888,
|
| 7 |
+
"train_steps_per_second": 0.11
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,763 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 9.927710843373493,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1030,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0963855421686747,
|
| 13 |
+
"grad_norm": 0.8919573686450439,
|
| 14 |
+
"learning_rate": 9.997674418116758e-05,
|
| 15 |
+
"loss": 1.9774,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.1927710843373494,
|
| 20 |
+
"grad_norm": 0.910704767308804,
|
| 21 |
+
"learning_rate": 9.990699835799469e-05,
|
| 22 |
+
"loss": 1.6692,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.2891566265060241,
|
| 27 |
+
"grad_norm": 0.812298320227036,
|
| 28 |
+
"learning_rate": 9.979082741033047e-05,
|
| 29 |
+
"loss": 1.5706,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.3855421686746988,
|
| 34 |
+
"grad_norm": 0.7732472432905145,
|
| 35 |
+
"learning_rate": 9.96283394041954e-05,
|
| 36 |
+
"loss": 1.5094,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4819277108433735,
|
| 41 |
+
"grad_norm": 0.8531022514130023,
|
| 42 |
+
"learning_rate": 9.941968549125481e-05,
|
| 43 |
+
"loss": 1.463,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.5783132530120482,
|
| 48 |
+
"grad_norm": 0.9116145183088319,
|
| 49 |
+
"learning_rate": 9.916505976821263e-05,
|
| 50 |
+
"loss": 1.4822,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.6746987951807228,
|
| 55 |
+
"grad_norm": 0.8879028360760914,
|
| 56 |
+
"learning_rate": 9.886469909625625e-05,
|
| 57 |
+
"loss": 1.4681,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.7710843373493976,
|
| 62 |
+
"grad_norm": 0.9147335792078393,
|
| 63 |
+
"learning_rate": 9.851888288072053e-05,
|
| 64 |
+
"loss": 1.3971,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.8674698795180723,
|
| 69 |
+
"grad_norm": 0.887118205770356,
|
| 70 |
+
"learning_rate": 9.81279328111758e-05,
|
| 71 |
+
"loss": 1.4472,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.963855421686747,
|
| 76 |
+
"grad_norm": 0.8531475377514153,
|
| 77 |
+
"learning_rate": 9.769221256218164e-05,
|
| 78 |
+
"loss": 1.4119,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 1.0602409638554218,
|
| 83 |
+
"grad_norm": 0.8430581950762995,
|
| 84 |
+
"learning_rate": 9.721212745498494e-05,
|
| 85 |
+
"loss": 1.3639,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.1566265060240963,
|
| 90 |
+
"grad_norm": 0.9779626124304455,
|
| 91 |
+
"learning_rate": 9.668812408047679e-05,
|
| 92 |
+
"loss": 1.3209,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 1.2530120481927711,
|
| 97 |
+
"grad_norm": 1.0822085428116495,
|
| 98 |
+
"learning_rate": 9.612068988375897e-05,
|
| 99 |
+
"loss": 1.3343,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 1.3493975903614457,
|
| 104 |
+
"grad_norm": 1.0414395683595772,
|
| 105 |
+
"learning_rate": 9.551035271070664e-05,
|
| 106 |
+
"loss": 1.2922,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.4457831325301205,
|
| 111 |
+
"grad_norm": 1.1344579456156207,
|
| 112 |
+
"learning_rate": 9.485768031694872e-05,
|
| 113 |
+
"loss": 1.3155,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.5421686746987953,
|
| 118 |
+
"grad_norm": 1.1349887667909784,
|
| 119 |
+
"learning_rate": 9.416327983972304e-05,
|
| 120 |
+
"loss": 1.2964,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.6385542168674698,
|
| 125 |
+
"grad_norm": 1.0901371692538764,
|
| 126 |
+
"learning_rate": 9.342779723309745e-05,
|
| 127 |
+
"loss": 1.3039,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.7349397590361446,
|
| 132 |
+
"grad_norm": 1.1237203962852838,
|
| 133 |
+
"learning_rate": 9.265191666708209e-05,
|
| 134 |
+
"loss": 1.3382,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.8313253012048194,
|
| 139 |
+
"grad_norm": 1.153171162807342,
|
| 140 |
+
"learning_rate": 9.18363598911921e-05,
|
| 141 |
+
"loss": 1.2993,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.927710843373494,
|
| 146 |
+
"grad_norm": 1.0603198764699773,
|
| 147 |
+
"learning_rate": 9.098188556305263e-05,
|
| 148 |
+
"loss": 1.2905,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 2.0240963855421685,
|
| 153 |
+
"grad_norm": 1.0860380934510327,
|
| 154 |
+
"learning_rate": 9.008928854267054e-05,
|
| 155 |
+
"loss": 1.2749,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 2.1204819277108435,
|
| 160 |
+
"grad_norm": 1.3046592302747626,
|
| 161 |
+
"learning_rate": 8.915939915302968e-05,
|
| 162 |
+
"loss": 1.1839,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 2.216867469879518,
|
| 167 |
+
"grad_norm": 1.2724868030271497,
|
| 168 |
+
"learning_rate": 8.819308240769724e-05,
|
| 169 |
+
"loss": 1.1675,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 2.3132530120481927,
|
| 174 |
+
"grad_norm": 1.4063722146992672,
|
| 175 |
+
"learning_rate": 8.71912372061598e-05,
|
| 176 |
+
"loss": 1.1765,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 2.4096385542168672,
|
| 181 |
+
"grad_norm": 1.4911158254860226,
|
| 182 |
+
"learning_rate": 8.615479549763756e-05,
|
| 183 |
+
"loss": 1.1846,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.5060240963855422,
|
| 188 |
+
"grad_norm": 1.4235766805578518,
|
| 189 |
+
"learning_rate": 8.508472141415467e-05,
|
| 190 |
+
"loss": 1.169,
|
| 191 |
+
"step": 260
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.602409638554217,
|
| 195 |
+
"grad_norm": 1.38772225064988,
|
| 196 |
+
"learning_rate": 8.398201037367201e-05,
|
| 197 |
+
"loss": 1.1542,
|
| 198 |
+
"step": 270
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.6987951807228914,
|
| 202 |
+
"grad_norm": 1.451662491739912,
|
| 203 |
+
"learning_rate": 8.284768815411692e-05,
|
| 204 |
+
"loss": 1.1561,
|
| 205 |
+
"step": 280
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.7951807228915664,
|
| 209 |
+
"grad_norm": 1.4370300928384818,
|
| 210 |
+
"learning_rate": 8.168280993917077e-05,
|
| 211 |
+
"loss": 1.1738,
|
| 212 |
+
"step": 290
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.891566265060241,
|
| 216 |
+
"grad_norm": 1.40886699437724,
|
| 217 |
+
"learning_rate": 8.048845933670273e-05,
|
| 218 |
+
"loss": 1.1636,
|
| 219 |
+
"step": 300
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.9879518072289155,
|
| 223 |
+
"grad_norm": 1.4108567826491814,
|
| 224 |
+
"learning_rate": 7.926574737076211e-05,
|
| 225 |
+
"loss": 1.1971,
|
| 226 |
+
"step": 310
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.0843373493975905,
|
| 230 |
+
"grad_norm": 1.7067948053286397,
|
| 231 |
+
"learning_rate": 7.801581144806752e-05,
|
| 232 |
+
"loss": 1.0335,
|
| 233 |
+
"step": 320
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 3.180722891566265,
|
| 237 |
+
"grad_norm": 1.6598822585089195,
|
| 238 |
+
"learning_rate": 7.673981429995372e-05,
|
| 239 |
+
"loss": 1.0365,
|
| 240 |
+
"step": 330
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 3.2771084337349397,
|
| 244 |
+
"grad_norm": 1.7326188759467145,
|
| 245 |
+
"learning_rate": 7.543894290076103e-05,
|
| 246 |
+
"loss": 1.0218,
|
| 247 |
+
"step": 340
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 3.3734939759036147,
|
| 251 |
+
"grad_norm": 1.7737673244546652,
|
| 252 |
+
"learning_rate": 7.411440736367281e-05,
|
| 253 |
+
"loss": 1.0187,
|
| 254 |
+
"step": 350
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 3.4698795180722892,
|
| 258 |
+
"grad_norm": 1.7613273642895082,
|
| 259 |
+
"learning_rate": 7.276743981502856e-05,
|
| 260 |
+
"loss": 1.0217,
|
| 261 |
+
"step": 360
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 3.566265060240964,
|
| 265 |
+
"grad_norm": 1.880423633009527,
|
| 266 |
+
"learning_rate": 7.139929324815965e-05,
|
| 267 |
+
"loss": 1.0378,
|
| 268 |
+
"step": 370
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 3.662650602409639,
|
| 272 |
+
"grad_norm": 1.9055198219521683,
|
| 273 |
+
"learning_rate": 7.00112403578139e-05,
|
| 274 |
+
"loss": 1.0406,
|
| 275 |
+
"step": 380
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.7590361445783134,
|
| 279 |
+
"grad_norm": 1.926797264762729,
|
| 280 |
+
"learning_rate": 6.860457235625322e-05,
|
| 281 |
+
"loss": 1.0331,
|
| 282 |
+
"step": 390
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.855421686746988,
|
| 286 |
+
"grad_norm": 1.9427994346863178,
|
| 287 |
+
"learning_rate": 6.718059777212567e-05,
|
| 288 |
+
"loss": 1.0354,
|
| 289 |
+
"step": 400
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 3.9518072289156625,
|
| 293 |
+
"grad_norm": 1.9647182978122792,
|
| 294 |
+
"learning_rate": 6.574064123322925e-05,
|
| 295 |
+
"loss": 1.0445,
|
| 296 |
+
"step": 410
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 4.048192771084337,
|
| 300 |
+
"grad_norm": 1.837995364067002,
|
| 301 |
+
"learning_rate": 6.42860422342998e-05,
|
| 302 |
+
"loss": 0.9521,
|
| 303 |
+
"step": 420
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 4.144578313253012,
|
| 307 |
+
"grad_norm": 2.148688266798288,
|
| 308 |
+
"learning_rate": 6.281815389096903e-05,
|
| 309 |
+
"loss": 0.8772,
|
| 310 |
+
"step": 430
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 4.240963855421687,
|
| 314 |
+
"grad_norm": 2.376205483254627,
|
| 315 |
+
"learning_rate": 6.133834168105206e-05,
|
| 316 |
+
"loss": 0.8616,
|
| 317 |
+
"step": 440
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 4.337349397590361,
|
| 321 |
+
"grad_norm": 2.2364751098182527,
|
| 322 |
+
"learning_rate": 5.9847982174335316e-05,
|
| 323 |
+
"loss": 0.8602,
|
| 324 |
+
"step": 450
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 4.433734939759036,
|
| 328 |
+
"grad_norm": 2.240796410509819,
|
| 329 |
+
"learning_rate": 5.8348461752046116e-05,
|
| 330 |
+
"loss": 0.8754,
|
| 331 |
+
"step": 460
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 4.530120481927711,
|
| 335 |
+
"grad_norm": 2.2490246329419574,
|
| 336 |
+
"learning_rate": 5.6841175317195515e-05,
|
| 337 |
+
"loss": 0.8893,
|
| 338 |
+
"step": 470
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 4.626506024096385,
|
| 342 |
+
"grad_norm": 2.328620328311832,
|
| 343 |
+
"learning_rate": 5.532752499699381e-05,
|
| 344 |
+
"loss": 0.8905,
|
| 345 |
+
"step": 480
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 4.72289156626506,
|
| 349 |
+
"grad_norm": 2.4232879309790314,
|
| 350 |
+
"learning_rate": 5.380891883854591e-05,
|
| 351 |
+
"loss": 0.8761,
|
| 352 |
+
"step": 490
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 4.8192771084337345,
|
| 356 |
+
"grad_norm": 2.330347626994359,
|
| 357 |
+
"learning_rate": 5.228676949903973e-05,
|
| 358 |
+
"loss": 0.8947,
|
| 359 |
+
"step": 500
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 4.9156626506024095,
|
| 363 |
+
"grad_norm": 2.352453843969406,
|
| 364 |
+
"learning_rate": 5.07624929316463e-05,
|
| 365 |
+
"loss": 0.8807,
|
| 366 |
+
"step": 510
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 5.0120481927710845,
|
| 370 |
+
"grad_norm": 2.2677109085585476,
|
| 371 |
+
"learning_rate": 4.923750706835371e-05,
|
| 372 |
+
"loss": 0.877,
|
| 373 |
+
"step": 520
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 5.108433734939759,
|
| 377 |
+
"grad_norm": 2.929089690621969,
|
| 378 |
+
"learning_rate": 4.771323050096028e-05,
|
| 379 |
+
"loss": 0.6911,
|
| 380 |
+
"step": 530
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 5.204819277108434,
|
| 384 |
+
"grad_norm": 2.6683793778473053,
|
| 385 |
+
"learning_rate": 4.619108116145411e-05,
|
| 386 |
+
"loss": 0.7144,
|
| 387 |
+
"step": 540
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 5.301204819277109,
|
| 391 |
+
"grad_norm": 2.7047381812494806,
|
| 392 |
+
"learning_rate": 4.46724750030062e-05,
|
| 393 |
+
"loss": 0.725,
|
| 394 |
+
"step": 550
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 5.397590361445783,
|
| 398 |
+
"grad_norm": 2.851421639172732,
|
| 399 |
+
"learning_rate": 4.31588246828045e-05,
|
| 400 |
+
"loss": 0.7243,
|
| 401 |
+
"step": 560
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 5.493975903614458,
|
| 405 |
+
"grad_norm": 2.776878874955075,
|
| 406 |
+
"learning_rate": 4.16515382479539e-05,
|
| 407 |
+
"loss": 0.6986,
|
| 408 |
+
"step": 570
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 5.590361445783133,
|
| 412 |
+
"grad_norm": 2.9830553324496734,
|
| 413 |
+
"learning_rate": 4.015201782566471e-05,
|
| 414 |
+
"loss": 0.7311,
|
| 415 |
+
"step": 580
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 5.686746987951807,
|
| 419 |
+
"grad_norm": 2.8075065703920905,
|
| 420 |
+
"learning_rate": 3.866165831894796e-05,
|
| 421 |
+
"loss": 0.7511,
|
| 422 |
+
"step": 590
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.783132530120482,
|
| 426 |
+
"grad_norm": 3.060856835395072,
|
| 427 |
+
"learning_rate": 3.7181846109031005e-05,
|
| 428 |
+
"loss": 0.7277,
|
| 429 |
+
"step": 600
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.879518072289157,
|
| 433 |
+
"grad_norm": 2.9964402401459407,
|
| 434 |
+
"learning_rate": 3.571395776570023e-05,
|
| 435 |
+
"loss": 0.7507,
|
| 436 |
+
"step": 610
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 5.975903614457831,
|
| 440 |
+
"grad_norm": 2.840908376303377,
|
| 441 |
+
"learning_rate": 3.4259358766770766e-05,
|
| 442 |
+
"loss": 0.7488,
|
| 443 |
+
"step": 620
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 6.072289156626506,
|
| 447 |
+
"grad_norm": 3.4568397677126326,
|
| 448 |
+
"learning_rate": 3.2819402227874365e-05,
|
| 449 |
+
"loss": 0.6285,
|
| 450 |
+
"step": 630
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 6.168674698795181,
|
| 454 |
+
"grad_norm": 3.1654598373448137,
|
| 455 |
+
"learning_rate": 3.1395427643746796e-05,
|
| 456 |
+
"loss": 0.5836,
|
| 457 |
+
"step": 640
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 6.265060240963855,
|
| 461 |
+
"grad_norm": 3.2675864044433585,
|
| 462 |
+
"learning_rate": 2.9988759642186097e-05,
|
| 463 |
+
"loss": 0.5849,
|
| 464 |
+
"step": 650
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 6.36144578313253,
|
| 468 |
+
"grad_norm": 3.2183821392920664,
|
| 469 |
+
"learning_rate": 2.860070675184036e-05,
|
| 470 |
+
"loss": 0.5949,
|
| 471 |
+
"step": 660
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 6.457831325301205,
|
| 475 |
+
"grad_norm": 3.0719394770792885,
|
| 476 |
+
"learning_rate": 2.7232560184971434e-05,
|
| 477 |
+
"loss": 0.5786,
|
| 478 |
+
"step": 670
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 6.554216867469879,
|
| 482 |
+
"grad_norm": 3.3384530164789523,
|
| 483 |
+
"learning_rate": 2.588559263632719e-05,
|
| 484 |
+
"loss": 0.5883,
|
| 485 |
+
"step": 680
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 6.650602409638554,
|
| 489 |
+
"grad_norm": 3.257889301524805,
|
| 490 |
+
"learning_rate": 2.456105709923897e-05,
|
| 491 |
+
"loss": 0.5929,
|
| 492 |
+
"step": 690
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 6.746987951807229,
|
| 496 |
+
"grad_norm": 3.3823887425006545,
|
| 497 |
+
"learning_rate": 2.3260185700046294e-05,
|
| 498 |
+
"loss": 0.594,
|
| 499 |
+
"step": 700
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 6.843373493975903,
|
| 503 |
+
"grad_norm": 3.435900725711256,
|
| 504 |
+
"learning_rate": 2.1984188551932512e-05,
|
| 505 |
+
"loss": 0.5924,
|
| 506 |
+
"step": 710
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 6.9397590361445785,
|
| 510 |
+
"grad_norm": 3.4675705465638473,
|
| 511 |
+
"learning_rate": 2.0734252629237894e-05,
|
| 512 |
+
"loss": 0.5927,
|
| 513 |
+
"step": 720
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 7.036144578313253,
|
| 517 |
+
"grad_norm": 2.905863499929125,
|
| 518 |
+
"learning_rate": 1.9511540663297285e-05,
|
| 519 |
+
"loss": 0.5441,
|
| 520 |
+
"step": 730
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 7.132530120481928,
|
| 524 |
+
"grad_norm": 3.525660740561049,
|
| 525 |
+
"learning_rate": 1.831719006082924e-05,
|
| 526 |
+
"loss": 0.4634,
|
| 527 |
+
"step": 740
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 7.228915662650603,
|
| 531 |
+
"grad_norm": 3.293264937231894,
|
| 532 |
+
"learning_rate": 1.7152311845883095e-05,
|
| 533 |
+
"loss": 0.4671,
|
| 534 |
+
"step": 750
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 7.325301204819277,
|
| 538 |
+
"grad_norm": 3.4643723238577904,
|
| 539 |
+
"learning_rate": 1.601798962632799e-05,
|
| 540 |
+
"loss": 0.476,
|
| 541 |
+
"step": 760
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 7.421686746987952,
|
| 545 |
+
"grad_norm": 3.188250058544125,
|
| 546 |
+
"learning_rate": 1.491527858584535e-05,
|
| 547 |
+
"loss": 0.4981,
|
| 548 |
+
"step": 770
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 7.518072289156627,
|
| 552 |
+
"grad_norm": 3.4201215516664516,
|
| 553 |
+
"learning_rate": 1.384520450236244e-05,
|
| 554 |
+
"loss": 0.4714,
|
| 555 |
+
"step": 780
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 7.614457831325301,
|
| 559 |
+
"grad_norm": 3.2016173663444145,
|
| 560 |
+
"learning_rate": 1.2808762793840201e-05,
|
| 561 |
+
"loss": 0.4878,
|
| 562 |
+
"step": 790
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 7.710843373493976,
|
| 566 |
+
"grad_norm": 3.513424701410591,
|
| 567 |
+
"learning_rate": 1.1806917592302762e-05,
|
| 568 |
+
"loss": 0.4914,
|
| 569 |
+
"step": 800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 7.807228915662651,
|
| 573 |
+
"grad_norm": 3.4642537282355543,
|
| 574 |
+
"learning_rate": 1.0840600846970334e-05,
|
| 575 |
+
"loss": 0.4742,
|
| 576 |
+
"step": 810
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 7.903614457831325,
|
| 580 |
+
"grad_norm": 3.4479929396821443,
|
| 581 |
+
"learning_rate": 9.91071145732948e-06,
|
| 582 |
+
"loss": 0.4749,
|
| 583 |
+
"step": 820
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 8.0,
|
| 587 |
+
"grad_norm": 3.417147882208991,
|
| 588 |
+
"learning_rate": 9.018114436947373e-06,
|
| 589 |
+
"loss": 0.4918,
|
| 590 |
+
"step": 830
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 8.096385542168674,
|
| 594 |
+
"grad_norm": 3.152072043029231,
|
| 595 |
+
"learning_rate": 8.163640108807896e-06,
|
| 596 |
+
"loss": 0.4106,
|
| 597 |
+
"step": 840
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 8.19277108433735,
|
| 601 |
+
"grad_norm": 3.5086623296717816,
|
| 602 |
+
"learning_rate": 7.348083332917926e-06,
|
| 603 |
+
"loss": 0.4141,
|
| 604 |
+
"step": 850
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 8.289156626506024,
|
| 608 |
+
"grad_norm": 3.727099779414922,
|
| 609 |
+
"learning_rate": 6.572202766902569e-06,
|
| 610 |
+
"loss": 0.4287,
|
| 611 |
+
"step": 860
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 8.385542168674698,
|
| 615 |
+
"grad_norm": 3.356502113157289,
|
| 616 |
+
"learning_rate": 5.83672016027697e-06,
|
| 617 |
+
"loss": 0.3974,
|
| 618 |
+
"step": 870
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 8.481927710843374,
|
| 622 |
+
"grad_norm": 3.5114290988775427,
|
| 623 |
+
"learning_rate": 5.1423196830513e-06,
|
| 624 |
+
"loss": 0.4111,
|
| 625 |
+
"step": 880
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 8.578313253012048,
|
| 629 |
+
"grad_norm": 3.3470018501511447,
|
| 630 |
+
"learning_rate": 4.489647289293369e-06,
|
| 631 |
+
"loss": 0.4165,
|
| 632 |
+
"step": 890
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 8.674698795180722,
|
| 636 |
+
"grad_norm": 3.1455647605463666,
|
| 637 |
+
"learning_rate": 3.879310116241042e-06,
|
| 638 |
+
"loss": 0.4156,
|
| 639 |
+
"step": 900
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 8.771084337349398,
|
| 643 |
+
"grad_norm": 3.4300111085823124,
|
| 644 |
+
"learning_rate": 3.3118759195232275e-06,
|
| 645 |
+
"loss": 0.3935,
|
| 646 |
+
"step": 910
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 8.867469879518072,
|
| 650 |
+
"grad_norm": 3.2501800712068825,
|
| 651 |
+
"learning_rate": 2.787872545015069e-06,
|
| 652 |
+
"loss": 0.4103,
|
| 653 |
+
"step": 920
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 8.963855421686747,
|
| 657 |
+
"grad_norm": 3.2829723029519666,
|
| 658 |
+
"learning_rate": 2.307787437818365e-06,
|
| 659 |
+
"loss": 0.4131,
|
| 660 |
+
"step": 930
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 9.060240963855422,
|
| 664 |
+
"grad_norm": 3.145951812862308,
|
| 665 |
+
"learning_rate": 1.8720671888242059e-06,
|
| 666 |
+
"loss": 0.3828,
|
| 667 |
+
"step": 940
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 9.156626506024097,
|
| 671 |
+
"grad_norm": 3.1956957268186112,
|
| 672 |
+
"learning_rate": 1.4811171192794627e-06,
|
| 673 |
+
"loss": 0.365,
|
| 674 |
+
"step": 950
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 9.25301204819277,
|
| 678 |
+
"grad_norm": 3.024863424355031,
|
| 679 |
+
"learning_rate": 1.1353009037437523e-06,
|
| 680 |
+
"loss": 0.3736,
|
| 681 |
+
"step": 960
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 9.349397590361447,
|
| 685 |
+
"grad_norm": 3.4426367987042106,
|
| 686 |
+
"learning_rate": 8.349402317873789e-07,
|
| 687 |
+
"loss": 0.378,
|
| 688 |
+
"step": 970
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 9.44578313253012,
|
| 692 |
+
"grad_norm": 3.3566957382084515,
|
| 693 |
+
"learning_rate": 5.803145087451945e-07,
|
| 694 |
+
"loss": 0.4013,
|
| 695 |
+
"step": 980
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 9.542168674698795,
|
| 699 |
+
"grad_norm": 3.616442803141579,
|
| 700 |
+
"learning_rate": 3.716605958046071e-07,
|
| 701 |
+
"loss": 0.386,
|
| 702 |
+
"step": 990
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 9.638554216867469,
|
| 706 |
+
"grad_norm": 3.1110352724634835,
|
| 707 |
+
"learning_rate": 2.0917258966953733e-07,
|
| 708 |
+
"loss": 0.3862,
|
| 709 |
+
"step": 1000
|
| 710 |
+
},
|
| 711 |
+
{
|
| 712 |
+
"epoch": 9.734939759036145,
|
| 713 |
+
"grad_norm": 3.3766596212586504,
|
| 714 |
+
"learning_rate": 9.300164200530814e-08,
|
| 715 |
+
"loss": 0.3808,
|
| 716 |
+
"step": 1010
|
| 717 |
+
},
|
| 718 |
+
{
|
| 719 |
+
"epoch": 9.831325301204819,
|
| 720 |
+
"grad_norm": 3.202391216065192,
|
| 721 |
+
"learning_rate": 2.3255818832423894e-08,
|
| 722 |
+
"loss": 0.3844,
|
| 723 |
+
"step": 1020
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 9.927710843373493,
|
| 727 |
+
"grad_norm": 3.3375553267537876,
|
| 728 |
+
"learning_rate": 0.0,
|
| 729 |
+
"loss": 0.367,
|
| 730 |
+
"step": 1030
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 9.927710843373493,
|
| 734 |
+
"step": 1030,
|
| 735 |
+
"total_flos": 144813601193984.0,
|
| 736 |
+
"train_loss": 0.8549524587334938,
|
| 737 |
+
"train_runtime": 9342.774,
|
| 738 |
+
"train_samples_per_second": 0.888,
|
| 739 |
+
"train_steps_per_second": 0.11
|
| 740 |
+
}
|
| 741 |
+
],
|
| 742 |
+
"logging_steps": 10,
|
| 743 |
+
"max_steps": 1030,
|
| 744 |
+
"num_input_tokens_seen": 0,
|
| 745 |
+
"num_train_epochs": 10,
|
| 746 |
+
"save_steps": 500,
|
| 747 |
+
"stateful_callbacks": {
|
| 748 |
+
"TrainerControl": {
|
| 749 |
+
"args": {
|
| 750 |
+
"should_epoch_stop": false,
|
| 751 |
+
"should_evaluate": false,
|
| 752 |
+
"should_log": false,
|
| 753 |
+
"should_save": true,
|
| 754 |
+
"should_training_stop": true
|
| 755 |
+
},
|
| 756 |
+
"attributes": {}
|
| 757 |
+
}
|
| 758 |
+
},
|
| 759 |
+
"total_flos": 144813601193984.0,
|
| 760 |
+
"train_batch_size": 1,
|
| 761 |
+
"trial_name": null,
|
| 762 |
+
"trial_params": null
|
| 763 |
+
}
|
training_loss.png
ADDED
|