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 +591 -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: top_7_ranking_stackexchange
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# top_7_ranking_stackexchange
|
| 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: 0.8129
|
| 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: top_7_ranking_stackexchange
|
|
|
|
| 16 |
|
| 17 |
# top_7_ranking_stackexchange
|
| 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/top_7_ranking_stackexchange dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
- Loss: 0.8129
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9955423476968797,
|
| 3 |
+
"eval_loss": 0.8128942847251892,
|
| 4 |
+
"eval_runtime": 270.9601,
|
| 5 |
+
"eval_samples_per_second": 25.092,
|
| 6 |
+
"eval_steps_per_second": 0.395,
|
| 7 |
+
"total_flos": 1266118777896960.0,
|
| 8 |
+
"train_loss": 0.7958845669630343,
|
| 9 |
+
"train_runtime": 44860.7812,
|
| 10 |
+
"train_samples_per_second": 8.638,
|
| 11 |
+
"train_steps_per_second": 0.017
|
| 12 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9955423476968797,
|
| 3 |
+
"eval_loss": 0.8128942847251892,
|
| 4 |
+
"eval_runtime": 270.9601,
|
| 5 |
+
"eval_samples_per_second": 25.092,
|
| 6 |
+
"eval_steps_per_second": 0.395
|
| 7 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9955423476968797,
|
| 3 |
+
"total_flos": 1266118777896960.0,
|
| 4 |
+
"train_loss": 0.7958845669630343,
|
| 5 |
+
"train_runtime": 44860.7812,
|
| 6 |
+
"train_samples_per_second": 8.638,
|
| 7 |
+
"train_steps_per_second": 0.017
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,591 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9955423476968797,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 756,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0396235760277365,
|
| 13 |
+
"grad_norm": 27.41085149828123,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.0725,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.079247152055473,
|
| 20 |
+
"grad_norm": 21.426346851591315,
|
| 21 |
+
"learning_rate": 5e-06,
|
| 22 |
+
"loss": 0.9867,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.1188707280832095,
|
| 27 |
+
"grad_norm": 0.8214529838984242,
|
| 28 |
+
"learning_rate": 5e-06,
|
| 29 |
+
"loss": 0.9489,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.158494304110946,
|
| 34 |
+
"grad_norm": 0.8934541351618693,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 0.9168,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.1981178801386825,
|
| 41 |
+
"grad_norm": 0.6396922311734878,
|
| 42 |
+
"learning_rate": 5e-06,
|
| 43 |
+
"loss": 0.903,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.237741456166419,
|
| 48 |
+
"grad_norm": 0.8318834132473311,
|
| 49 |
+
"learning_rate": 5e-06,
|
| 50 |
+
"loss": 0.884,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.27736503219415554,
|
| 55 |
+
"grad_norm": 0.6283992782157446,
|
| 56 |
+
"learning_rate": 5e-06,
|
| 57 |
+
"loss": 0.8732,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.316988608221892,
|
| 62 |
+
"grad_norm": 0.6596849388425453,
|
| 63 |
+
"learning_rate": 5e-06,
|
| 64 |
+
"loss": 0.8701,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.35661218424962854,
|
| 69 |
+
"grad_norm": 0.6758187675410737,
|
| 70 |
+
"learning_rate": 5e-06,
|
| 71 |
+
"loss": 0.8641,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.396235760277365,
|
| 76 |
+
"grad_norm": 1.0513265622155463,
|
| 77 |
+
"learning_rate": 5e-06,
|
| 78 |
+
"loss": 0.8597,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.43585933630510154,
|
| 83 |
+
"grad_norm": 0.5790780273693242,
|
| 84 |
+
"learning_rate": 5e-06,
|
| 85 |
+
"loss": 0.8538,
|
| 86 |
+
"step": 110
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.475482912332838,
|
| 90 |
+
"grad_norm": 0.5821582037832116,
|
| 91 |
+
"learning_rate": 5e-06,
|
| 92 |
+
"loss": 0.8493,
|
| 93 |
+
"step": 120
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.5151064883605745,
|
| 97 |
+
"grad_norm": 0.6354797019513801,
|
| 98 |
+
"learning_rate": 5e-06,
|
| 99 |
+
"loss": 0.8491,
|
| 100 |
+
"step": 130
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.5547300643883111,
|
| 104 |
+
"grad_norm": 0.74047379799972,
|
| 105 |
+
"learning_rate": 5e-06,
|
| 106 |
+
"loss": 0.8519,
|
| 107 |
+
"step": 140
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5943536404160475,
|
| 111 |
+
"grad_norm": 0.6926741472374109,
|
| 112 |
+
"learning_rate": 5e-06,
|
| 113 |
+
"loss": 0.8388,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.633977216443784,
|
| 118 |
+
"grad_norm": 0.5805929955993835,
|
| 119 |
+
"learning_rate": 5e-06,
|
| 120 |
+
"loss": 0.842,
|
| 121 |
+
"step": 160
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6736007924715206,
|
| 125 |
+
"grad_norm": 0.6028836834161021,
|
| 126 |
+
"learning_rate": 5e-06,
|
| 127 |
+
"loss": 0.8381,
|
| 128 |
+
"step": 170
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.7132243684992571,
|
| 132 |
+
"grad_norm": 0.5654340386019846,
|
| 133 |
+
"learning_rate": 5e-06,
|
| 134 |
+
"loss": 0.8341,
|
| 135 |
+
"step": 180
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7528479445269936,
|
| 139 |
+
"grad_norm": 0.5723158352099399,
|
| 140 |
+
"learning_rate": 5e-06,
|
| 141 |
+
"loss": 0.8375,
|
| 142 |
+
"step": 190
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.79247152055473,
|
| 146 |
+
"grad_norm": 0.5198688688930553,
|
| 147 |
+
"learning_rate": 5e-06,
|
| 148 |
+
"loss": 0.8381,
|
| 149 |
+
"step": 200
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.8320950965824666,
|
| 153 |
+
"grad_norm": 0.6050739761187648,
|
| 154 |
+
"learning_rate": 5e-06,
|
| 155 |
+
"loss": 0.8342,
|
| 156 |
+
"step": 210
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8717186726102031,
|
| 160 |
+
"grad_norm": 0.5397219218505803,
|
| 161 |
+
"learning_rate": 5e-06,
|
| 162 |
+
"loss": 0.8308,
|
| 163 |
+
"step": 220
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.9113422486379396,
|
| 167 |
+
"grad_norm": 0.5613324111744644,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.8302,
|
| 170 |
+
"step": 230
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.950965824665676,
|
| 174 |
+
"grad_norm": 0.5372566937252206,
|
| 175 |
+
"learning_rate": 5e-06,
|
| 176 |
+
"loss": 0.8272,
|
| 177 |
+
"step": 240
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9905894006934126,
|
| 181 |
+
"grad_norm": 0.4784741594645362,
|
| 182 |
+
"learning_rate": 5e-06,
|
| 183 |
+
"loss": 0.8269,
|
| 184 |
+
"step": 250
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9985141158989599,
|
| 188 |
+
"eval_loss": 0.8291837573051453,
|
| 189 |
+
"eval_runtime": 271.0608,
|
| 190 |
+
"eval_samples_per_second": 25.083,
|
| 191 |
+
"eval_steps_per_second": 0.395,
|
| 192 |
+
"step": 252
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.030212976721149,
|
| 196 |
+
"grad_norm": 0.87740197973562,
|
| 197 |
+
"learning_rate": 5e-06,
|
| 198 |
+
"loss": 0.8491,
|
| 199 |
+
"step": 260
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 1.0698365527488856,
|
| 203 |
+
"grad_norm": 0.5678119260366427,
|
| 204 |
+
"learning_rate": 5e-06,
|
| 205 |
+
"loss": 0.785,
|
| 206 |
+
"step": 270
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.1094601287766221,
|
| 210 |
+
"grad_norm": 0.6337004334606812,
|
| 211 |
+
"learning_rate": 5e-06,
|
| 212 |
+
"loss": 0.7887,
|
| 213 |
+
"step": 280
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.1490837048043585,
|
| 217 |
+
"grad_norm": 0.6986139436792874,
|
| 218 |
+
"learning_rate": 5e-06,
|
| 219 |
+
"loss": 0.7862,
|
| 220 |
+
"step": 290
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.188707280832095,
|
| 224 |
+
"grad_norm": 0.5874593683473379,
|
| 225 |
+
"learning_rate": 5e-06,
|
| 226 |
+
"loss": 0.7793,
|
| 227 |
+
"step": 300
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.2283308568598317,
|
| 231 |
+
"grad_norm": 0.7975693973340302,
|
| 232 |
+
"learning_rate": 5e-06,
|
| 233 |
+
"loss": 0.7795,
|
| 234 |
+
"step": 310
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.267954432887568,
|
| 238 |
+
"grad_norm": 0.5846939921280547,
|
| 239 |
+
"learning_rate": 5e-06,
|
| 240 |
+
"loss": 0.7798,
|
| 241 |
+
"step": 320
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 1.3075780089153046,
|
| 245 |
+
"grad_norm": 0.7654979422005525,
|
| 246 |
+
"learning_rate": 5e-06,
|
| 247 |
+
"loss": 0.7832,
|
| 248 |
+
"step": 330
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.3472015849430412,
|
| 252 |
+
"grad_norm": 0.6496190339072363,
|
| 253 |
+
"learning_rate": 5e-06,
|
| 254 |
+
"loss": 0.7835,
|
| 255 |
+
"step": 340
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.3868251609707776,
|
| 259 |
+
"grad_norm": 0.7019021685342436,
|
| 260 |
+
"learning_rate": 5e-06,
|
| 261 |
+
"loss": 0.7841,
|
| 262 |
+
"step": 350
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 1.4264487369985142,
|
| 266 |
+
"grad_norm": 0.697904784471384,
|
| 267 |
+
"learning_rate": 5e-06,
|
| 268 |
+
"loss": 0.7809,
|
| 269 |
+
"step": 360
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.4660723130262507,
|
| 273 |
+
"grad_norm": 0.6140987998837893,
|
| 274 |
+
"learning_rate": 5e-06,
|
| 275 |
+
"loss": 0.7839,
|
| 276 |
+
"step": 370
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.505695889053987,
|
| 280 |
+
"grad_norm": 0.6176502513567036,
|
| 281 |
+
"learning_rate": 5e-06,
|
| 282 |
+
"loss": 0.78,
|
| 283 |
+
"step": 380
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.5453194650817235,
|
| 287 |
+
"grad_norm": 0.6195463728584585,
|
| 288 |
+
"learning_rate": 5e-06,
|
| 289 |
+
"loss": 0.7812,
|
| 290 |
+
"step": 390
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.5849430411094603,
|
| 294 |
+
"grad_norm": 0.5860977422231922,
|
| 295 |
+
"learning_rate": 5e-06,
|
| 296 |
+
"loss": 0.7855,
|
| 297 |
+
"step": 400
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.6245666171371966,
|
| 301 |
+
"grad_norm": 0.6058978073304615,
|
| 302 |
+
"learning_rate": 5e-06,
|
| 303 |
+
"loss": 0.7826,
|
| 304 |
+
"step": 410
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 1.664190193164933,
|
| 308 |
+
"grad_norm": 0.5726428056331896,
|
| 309 |
+
"learning_rate": 5e-06,
|
| 310 |
+
"loss": 0.7767,
|
| 311 |
+
"step": 420
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 1.7038137691926698,
|
| 315 |
+
"grad_norm": 0.6255990916494661,
|
| 316 |
+
"learning_rate": 5e-06,
|
| 317 |
+
"loss": 0.7776,
|
| 318 |
+
"step": 430
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.7434373452204062,
|
| 322 |
+
"grad_norm": 0.621833549178633,
|
| 323 |
+
"learning_rate": 5e-06,
|
| 324 |
+
"loss": 0.7786,
|
| 325 |
+
"step": 440
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.7830609212481425,
|
| 329 |
+
"grad_norm": 0.5435896897432534,
|
| 330 |
+
"learning_rate": 5e-06,
|
| 331 |
+
"loss": 0.7775,
|
| 332 |
+
"step": 450
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.8226844972758791,
|
| 336 |
+
"grad_norm": 0.7495004498554898,
|
| 337 |
+
"learning_rate": 5e-06,
|
| 338 |
+
"loss": 0.7759,
|
| 339 |
+
"step": 460
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.8623080733036157,
|
| 343 |
+
"grad_norm": 0.5987267949701414,
|
| 344 |
+
"learning_rate": 5e-06,
|
| 345 |
+
"loss": 0.778,
|
| 346 |
+
"step": 470
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.901931649331352,
|
| 350 |
+
"grad_norm": 0.6388662201965061,
|
| 351 |
+
"learning_rate": 5e-06,
|
| 352 |
+
"loss": 0.7728,
|
| 353 |
+
"step": 480
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.9415552253590886,
|
| 357 |
+
"grad_norm": 0.5711439995135582,
|
| 358 |
+
"learning_rate": 5e-06,
|
| 359 |
+
"loss": 0.7817,
|
| 360 |
+
"step": 490
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.9811788013868252,
|
| 364 |
+
"grad_norm": 0.617975937550618,
|
| 365 |
+
"learning_rate": 5e-06,
|
| 366 |
+
"loss": 0.7778,
|
| 367 |
+
"step": 500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.9970282317979198,
|
| 371 |
+
"eval_loss": 0.8146935701370239,
|
| 372 |
+
"eval_runtime": 271.9619,
|
| 373 |
+
"eval_samples_per_second": 25.0,
|
| 374 |
+
"eval_steps_per_second": 0.393,
|
| 375 |
+
"step": 504
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 2.0208023774145616,
|
| 379 |
+
"grad_norm": 0.6930015338867856,
|
| 380 |
+
"learning_rate": 5e-06,
|
| 381 |
+
"loss": 0.8016,
|
| 382 |
+
"step": 510
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.060425953442298,
|
| 386 |
+
"grad_norm": 0.6358377946223995,
|
| 387 |
+
"learning_rate": 5e-06,
|
| 388 |
+
"loss": 0.7316,
|
| 389 |
+
"step": 520
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.1000495294700348,
|
| 393 |
+
"grad_norm": 0.8278609254484581,
|
| 394 |
+
"learning_rate": 5e-06,
|
| 395 |
+
"loss": 0.7265,
|
| 396 |
+
"step": 530
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 2.139673105497771,
|
| 400 |
+
"grad_norm": 0.6962674479421791,
|
| 401 |
+
"learning_rate": 5e-06,
|
| 402 |
+
"loss": 0.7311,
|
| 403 |
+
"step": 540
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 2.1792966815255075,
|
| 407 |
+
"grad_norm": 0.6727207101976576,
|
| 408 |
+
"learning_rate": 5e-06,
|
| 409 |
+
"loss": 0.7294,
|
| 410 |
+
"step": 550
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 2.2189202575532443,
|
| 414 |
+
"grad_norm": 0.5817825946787325,
|
| 415 |
+
"learning_rate": 5e-06,
|
| 416 |
+
"loss": 0.7307,
|
| 417 |
+
"step": 560
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.2585438335809807,
|
| 421 |
+
"grad_norm": 0.6436375631599169,
|
| 422 |
+
"learning_rate": 5e-06,
|
| 423 |
+
"loss": 0.7325,
|
| 424 |
+
"step": 570
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 2.298167409608717,
|
| 428 |
+
"grad_norm": 0.9292364267574976,
|
| 429 |
+
"learning_rate": 5e-06,
|
| 430 |
+
"loss": 0.7352,
|
| 431 |
+
"step": 580
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.337790985636454,
|
| 435 |
+
"grad_norm": 0.9489749212265489,
|
| 436 |
+
"learning_rate": 5e-06,
|
| 437 |
+
"loss": 0.7317,
|
| 438 |
+
"step": 590
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 2.37741456166419,
|
| 442 |
+
"grad_norm": 0.7240317017944226,
|
| 443 |
+
"learning_rate": 5e-06,
|
| 444 |
+
"loss": 0.7274,
|
| 445 |
+
"step": 600
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 2.4170381376919265,
|
| 449 |
+
"grad_norm": 0.6501433881507601,
|
| 450 |
+
"learning_rate": 5e-06,
|
| 451 |
+
"loss": 0.7301,
|
| 452 |
+
"step": 610
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 2.4566617137196634,
|
| 456 |
+
"grad_norm": 0.8099751855974757,
|
| 457 |
+
"learning_rate": 5e-06,
|
| 458 |
+
"loss": 0.734,
|
| 459 |
+
"step": 620
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.4962852897473997,
|
| 463 |
+
"grad_norm": 0.6496005537182832,
|
| 464 |
+
"learning_rate": 5e-06,
|
| 465 |
+
"loss": 0.7361,
|
| 466 |
+
"step": 630
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 2.535908865775136,
|
| 470 |
+
"grad_norm": 0.5493051299286916,
|
| 471 |
+
"learning_rate": 5e-06,
|
| 472 |
+
"loss": 0.7327,
|
| 473 |
+
"step": 640
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.5755324418028724,
|
| 477 |
+
"grad_norm": 0.5890719222816667,
|
| 478 |
+
"learning_rate": 5e-06,
|
| 479 |
+
"loss": 0.7346,
|
| 480 |
+
"step": 650
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.6151560178306092,
|
| 484 |
+
"grad_norm": 0.5341897077649945,
|
| 485 |
+
"learning_rate": 5e-06,
|
| 486 |
+
"loss": 0.7314,
|
| 487 |
+
"step": 660
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 2.6547795938583456,
|
| 491 |
+
"grad_norm": 0.5921523513579053,
|
| 492 |
+
"learning_rate": 5e-06,
|
| 493 |
+
"loss": 0.7352,
|
| 494 |
+
"step": 670
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.6944031698860824,
|
| 498 |
+
"grad_norm": 0.5890344658716773,
|
| 499 |
+
"learning_rate": 5e-06,
|
| 500 |
+
"loss": 0.7328,
|
| 501 |
+
"step": 680
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.734026745913819,
|
| 505 |
+
"grad_norm": 0.5886927133745706,
|
| 506 |
+
"learning_rate": 5e-06,
|
| 507 |
+
"loss": 0.7353,
|
| 508 |
+
"step": 690
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 2.773650321941555,
|
| 512 |
+
"grad_norm": 0.7084337230865917,
|
| 513 |
+
"learning_rate": 5e-06,
|
| 514 |
+
"loss": 0.7359,
|
| 515 |
+
"step": 700
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 2.8132738979692915,
|
| 519 |
+
"grad_norm": 0.6320863625704357,
|
| 520 |
+
"learning_rate": 5e-06,
|
| 521 |
+
"loss": 0.7289,
|
| 522 |
+
"step": 710
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 2.8528974739970283,
|
| 526 |
+
"grad_norm": 0.6406803421798857,
|
| 527 |
+
"learning_rate": 5e-06,
|
| 528 |
+
"loss": 0.7321,
|
| 529 |
+
"step": 720
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.8925210500247647,
|
| 533 |
+
"grad_norm": 0.5985842168545841,
|
| 534 |
+
"learning_rate": 5e-06,
|
| 535 |
+
"loss": 0.7363,
|
| 536 |
+
"step": 730
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 2.9321446260525015,
|
| 540 |
+
"grad_norm": 0.5878885552435451,
|
| 541 |
+
"learning_rate": 5e-06,
|
| 542 |
+
"loss": 0.7317,
|
| 543 |
+
"step": 740
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.971768202080238,
|
| 547 |
+
"grad_norm": 0.7738327584141713,
|
| 548 |
+
"learning_rate": 5e-06,
|
| 549 |
+
"loss": 0.7327,
|
| 550 |
+
"step": 750
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 2.9955423476968797,
|
| 554 |
+
"eval_loss": 0.8128942847251892,
|
| 555 |
+
"eval_runtime": 272.1686,
|
| 556 |
+
"eval_samples_per_second": 24.981,
|
| 557 |
+
"eval_steps_per_second": 0.393,
|
| 558 |
+
"step": 756
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 2.9955423476968797,
|
| 562 |
+
"step": 756,
|
| 563 |
+
"total_flos": 1266118777896960.0,
|
| 564 |
+
"train_loss": 0.7958845669630343,
|
| 565 |
+
"train_runtime": 44860.7812,
|
| 566 |
+
"train_samples_per_second": 8.638,
|
| 567 |
+
"train_steps_per_second": 0.017
|
| 568 |
+
}
|
| 569 |
+
],
|
| 570 |
+
"logging_steps": 10,
|
| 571 |
+
"max_steps": 756,
|
| 572 |
+
"num_input_tokens_seen": 0,
|
| 573 |
+
"num_train_epochs": 3,
|
| 574 |
+
"save_steps": 500,
|
| 575 |
+
"stateful_callbacks": {
|
| 576 |
+
"TrainerControl": {
|
| 577 |
+
"args": {
|
| 578 |
+
"should_epoch_stop": false,
|
| 579 |
+
"should_evaluate": false,
|
| 580 |
+
"should_log": false,
|
| 581 |
+
"should_save": true,
|
| 582 |
+
"should_training_stop": true
|
| 583 |
+
},
|
| 584 |
+
"attributes": {}
|
| 585 |
+
}
|
| 586 |
+
},
|
| 587 |
+
"total_flos": 1266118777896960.0,
|
| 588 |
+
"train_batch_size": 8,
|
| 589 |
+
"trial_name": null,
|
| 590 |
+
"trial_params": null
|
| 591 |
+
}
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|