End of training
Browse files- README.md +2 -1
- all_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +588 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -4,6 +4,7 @@ license: apache-2.0
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
|
|
|
| 7 |
- generated_from_trainer
|
| 8 |
model-index:
|
| 9 |
- name: fasttext_mixing_domains_top_1_code
|
|
@@ -15,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
|
| 16 |
# fasttext_mixing_domains_top_1_code
|
| 17 |
|
| 18 |
-
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on
|
| 19 |
|
| 20 |
## Model description
|
| 21 |
|
|
|
|
| 4 |
base_model: Qwen/Qwen2.5-7B-Instruct
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: fasttext_mixing_domains_top_1_code
|
|
|
|
| 16 |
|
| 17 |
# fasttext_mixing_domains_top_1_code
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/fasttext_mixing_domains_top_1_code dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9904153354632586,
|
| 3 |
+
"total_flos": 83614504427520.0,
|
| 4 |
+
"train_loss": 0.9489961503407894,
|
| 5 |
+
"train_runtime": 7848.0133,
|
| 6 |
+
"train_samples_per_second": 0.956,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 2.9904153354632586,
|
| 3 |
+
"total_flos": 83614504427520.0,
|
| 4 |
+
"train_loss": 0.9489961503407894,
|
| 5 |
+
"train_runtime": 7848.0133,
|
| 6 |
+
"train_samples_per_second": 0.956,
|
| 7 |
+
"train_steps_per_second": 0.01
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,588 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9904153354632586,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 78,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.038338658146964855,
|
| 13 |
+
"grad_norm": 6.963533401489258,
|
| 14 |
+
"learning_rate": 1.25e-06,
|
| 15 |
+
"loss": 1.2522,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.07667731629392971,
|
| 20 |
+
"grad_norm": 6.985895156860352,
|
| 21 |
+
"learning_rate": 2.5e-06,
|
| 22 |
+
"loss": 1.2678,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.11501597444089456,
|
| 27 |
+
"grad_norm": 7.023305416107178,
|
| 28 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 29 |
+
"loss": 1.273,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.15335463258785942,
|
| 34 |
+
"grad_norm": 6.416762351989746,
|
| 35 |
+
"learning_rate": 5e-06,
|
| 36 |
+
"loss": 1.2449,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.19169329073482427,
|
| 41 |
+
"grad_norm": 4.526856899261475,
|
| 42 |
+
"learning_rate": 6.25e-06,
|
| 43 |
+
"loss": 1.1674,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.23003194888178913,
|
| 48 |
+
"grad_norm": 3.004706621170044,
|
| 49 |
+
"learning_rate": 7.500000000000001e-06,
|
| 50 |
+
"loss": 1.1596,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.268370607028754,
|
| 55 |
+
"grad_norm": 5.936452865600586,
|
| 56 |
+
"learning_rate": 8.750000000000001e-06,
|
| 57 |
+
"loss": 1.1438,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.30670926517571884,
|
| 62 |
+
"grad_norm": 6.100061416625977,
|
| 63 |
+
"learning_rate": 1e-05,
|
| 64 |
+
"loss": 1.132,
|
| 65 |
+
"step": 8
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.3450479233226837,
|
| 69 |
+
"grad_norm": 6.210993766784668,
|
| 70 |
+
"learning_rate": 9.994965332706574e-06,
|
| 71 |
+
"loss": 1.1668,
|
| 72 |
+
"step": 9
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.38338658146964855,
|
| 76 |
+
"grad_norm": 5.787144184112549,
|
| 77 |
+
"learning_rate": 9.979871469976197e-06,
|
| 78 |
+
"loss": 1.0933,
|
| 79 |
+
"step": 10
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.4217252396166134,
|
| 83 |
+
"grad_norm": 3.9845287799835205,
|
| 84 |
+
"learning_rate": 9.954748808839675e-06,
|
| 85 |
+
"loss": 1.082,
|
| 86 |
+
"step": 11
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.46006389776357826,
|
| 90 |
+
"grad_norm": 2.1702077388763428,
|
| 91 |
+
"learning_rate": 9.91964794299315e-06,
|
| 92 |
+
"loss": 1.0384,
|
| 93 |
+
"step": 12
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.4984025559105431,
|
| 97 |
+
"grad_norm": 2.0777156352996826,
|
| 98 |
+
"learning_rate": 9.874639560909118e-06,
|
| 99 |
+
"loss": 1.0273,
|
| 100 |
+
"step": 13
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.536741214057508,
|
| 104 |
+
"grad_norm": 1.8550976514816284,
|
| 105 |
+
"learning_rate": 9.819814303479268e-06,
|
| 106 |
+
"loss": 0.9826,
|
| 107 |
+
"step": 14
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.5750798722044729,
|
| 111 |
+
"grad_norm": 1.7968131303787231,
|
| 112 |
+
"learning_rate": 9.755282581475769e-06,
|
| 113 |
+
"loss": 1.0165,
|
| 114 |
+
"step": 15
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.6134185303514377,
|
| 118 |
+
"grad_norm": 1.2006772756576538,
|
| 119 |
+
"learning_rate": 9.681174353198687e-06,
|
| 120 |
+
"loss": 0.9806,
|
| 121 |
+
"step": 16
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.6517571884984026,
|
| 125 |
+
"grad_norm": 1.3176575899124146,
|
| 126 |
+
"learning_rate": 9.597638862757255e-06,
|
| 127 |
+
"loss": 0.9406,
|
| 128 |
+
"step": 17
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.6900958466453674,
|
| 132 |
+
"grad_norm": 1.2367537021636963,
|
| 133 |
+
"learning_rate": 9.504844339512096e-06,
|
| 134 |
+
"loss": 0.997,
|
| 135 |
+
"step": 18
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.7284345047923323,
|
| 139 |
+
"grad_norm": 1.1063867807388306,
|
| 140 |
+
"learning_rate": 9.40297765928369e-06,
|
| 141 |
+
"loss": 0.9377,
|
| 142 |
+
"step": 19
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.7667731629392971,
|
| 146 |
+
"grad_norm": 1.058079719543457,
|
| 147 |
+
"learning_rate": 9.292243968009332e-06,
|
| 148 |
+
"loss": 0.974,
|
| 149 |
+
"step": 20
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.805111821086262,
|
| 153 |
+
"grad_norm": 0.9872468709945679,
|
| 154 |
+
"learning_rate": 9.172866268606514e-06,
|
| 155 |
+
"loss": 0.9445,
|
| 156 |
+
"step": 21
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.8434504792332268,
|
| 160 |
+
"grad_norm": 1.0114097595214844,
|
| 161 |
+
"learning_rate": 9.045084971874738e-06,
|
| 162 |
+
"loss": 0.9457,
|
| 163 |
+
"step": 22
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.8817891373801917,
|
| 167 |
+
"grad_norm": 1.0542124509811401,
|
| 168 |
+
"learning_rate": 8.90915741234015e-06,
|
| 169 |
+
"loss": 0.948,
|
| 170 |
+
"step": 23
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.9201277955271565,
|
| 174 |
+
"grad_norm": 0.8742199540138245,
|
| 175 |
+
"learning_rate": 8.765357330018056e-06,
|
| 176 |
+
"loss": 0.9326,
|
| 177 |
+
"step": 24
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9584664536741214,
|
| 181 |
+
"grad_norm": 0.8770824670791626,
|
| 182 |
+
"learning_rate": 8.613974319136959e-06,
|
| 183 |
+
"loss": 0.9123,
|
| 184 |
+
"step": 25
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.9968051118210862,
|
| 188 |
+
"grad_norm": 0.875529408454895,
|
| 189 |
+
"learning_rate": 8.455313244934324e-06,
|
| 190 |
+
"loss": 0.9606,
|
| 191 |
+
"step": 26
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.035143769968051,
|
| 195 |
+
"grad_norm": 2.2319250106811523,
|
| 196 |
+
"learning_rate": 8.289693629698564e-06,
|
| 197 |
+
"loss": 1.805,
|
| 198 |
+
"step": 27
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.073482428115016,
|
| 202 |
+
"grad_norm": 0.9425653219223022,
|
| 203 |
+
"learning_rate": 8.117449009293668e-06,
|
| 204 |
+
"loss": 0.9238,
|
| 205 |
+
"step": 28
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 1.1118210862619808,
|
| 209 |
+
"grad_norm": 0.89967942237854,
|
| 210 |
+
"learning_rate": 7.938926261462366e-06,
|
| 211 |
+
"loss": 0.8597,
|
| 212 |
+
"step": 29
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.1501597444089458,
|
| 216 |
+
"grad_norm": 0.8135074377059937,
|
| 217 |
+
"learning_rate": 7.754484907260513e-06,
|
| 218 |
+
"loss": 0.8425,
|
| 219 |
+
"step": 30
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.1884984025559104,
|
| 223 |
+
"grad_norm": 1.1999098062515259,
|
| 224 |
+
"learning_rate": 7.564496387029532e-06,
|
| 225 |
+
"loss": 0.9266,
|
| 226 |
+
"step": 31
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.2268370607028753,
|
| 230 |
+
"grad_norm": 1.0764687061309814,
|
| 231 |
+
"learning_rate": 7.369343312364994e-06,
|
| 232 |
+
"loss": 0.9045,
|
| 233 |
+
"step": 32
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.2651757188498403,
|
| 237 |
+
"grad_norm": 0.8604357838630676,
|
| 238 |
+
"learning_rate": 7.169418695587791e-06,
|
| 239 |
+
"loss": 0.9039,
|
| 240 |
+
"step": 33
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.3035143769968052,
|
| 244 |
+
"grad_norm": 0.7828784584999084,
|
| 245 |
+
"learning_rate": 6.965125158269619e-06,
|
| 246 |
+
"loss": 0.8709,
|
| 247 |
+
"step": 34
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 1.34185303514377,
|
| 251 |
+
"grad_norm": 0.8666354417800903,
|
| 252 |
+
"learning_rate": 6.7568741204067145e-06,
|
| 253 |
+
"loss": 0.8737,
|
| 254 |
+
"step": 35
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.3801916932907348,
|
| 258 |
+
"grad_norm": 0.8065346479415894,
|
| 259 |
+
"learning_rate": 6.545084971874738e-06,
|
| 260 |
+
"loss": 0.8212,
|
| 261 |
+
"step": 36
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.4185303514376997,
|
| 265 |
+
"grad_norm": 0.8298048377037048,
|
| 266 |
+
"learning_rate": 6.330184227833376e-06,
|
| 267 |
+
"loss": 0.8911,
|
| 268 |
+
"step": 37
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 1.4568690095846646,
|
| 272 |
+
"grad_norm": 0.7558190226554871,
|
| 273 |
+
"learning_rate": 6.112604669781572e-06,
|
| 274 |
+
"loss": 0.8792,
|
| 275 |
+
"step": 38
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 1.4952076677316293,
|
| 279 |
+
"grad_norm": 0.7565321326255798,
|
| 280 |
+
"learning_rate": 5.892784473993184e-06,
|
| 281 |
+
"loss": 0.898,
|
| 282 |
+
"step": 39
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.5335463258785942,
|
| 286 |
+
"grad_norm": 0.696410596370697,
|
| 287 |
+
"learning_rate": 5.671166329088278e-06,
|
| 288 |
+
"loss": 0.8933,
|
| 289 |
+
"step": 40
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 1.571884984025559,
|
| 293 |
+
"grad_norm": 0.6744368672370911,
|
| 294 |
+
"learning_rate": 5.448196544517168e-06,
|
| 295 |
+
"loss": 0.8078,
|
| 296 |
+
"step": 41
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.610223642172524,
|
| 300 |
+
"grad_norm": 0.8514912128448486,
|
| 301 |
+
"learning_rate": 5.224324151752575e-06,
|
| 302 |
+
"loss": 0.9273,
|
| 303 |
+
"step": 42
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.648562300319489,
|
| 307 |
+
"grad_norm": 0.634422779083252,
|
| 308 |
+
"learning_rate": 5e-06,
|
| 309 |
+
"loss": 0.8608,
|
| 310 |
+
"step": 43
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.6869009584664538,
|
| 314 |
+
"grad_norm": 0.5979927182197571,
|
| 315 |
+
"learning_rate": 4.775675848247427e-06,
|
| 316 |
+
"loss": 0.8584,
|
| 317 |
+
"step": 44
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 1.7252396166134185,
|
| 321 |
+
"grad_norm": 0.7261207103729248,
|
| 322 |
+
"learning_rate": 4.551803455482833e-06,
|
| 323 |
+
"loss": 0.867,
|
| 324 |
+
"step": 45
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.7635782747603834,
|
| 328 |
+
"grad_norm": 0.659273624420166,
|
| 329 |
+
"learning_rate": 4.3288336709117246e-06,
|
| 330 |
+
"loss": 0.9153,
|
| 331 |
+
"step": 46
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 1.8019169329073481,
|
| 335 |
+
"grad_norm": 0.5927888751029968,
|
| 336 |
+
"learning_rate": 4.107215526006818e-06,
|
| 337 |
+
"loss": 0.8913,
|
| 338 |
+
"step": 47
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.840255591054313,
|
| 342 |
+
"grad_norm": 0.6192860007286072,
|
| 343 |
+
"learning_rate": 3.887395330218429e-06,
|
| 344 |
+
"loss": 0.9051,
|
| 345 |
+
"step": 48
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.878594249201278,
|
| 349 |
+
"grad_norm": 0.5434866547584534,
|
| 350 |
+
"learning_rate": 3.669815772166625e-06,
|
| 351 |
+
"loss": 0.7876,
|
| 352 |
+
"step": 49
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 1.9169329073482428,
|
| 356 |
+
"grad_norm": 0.6223477721214294,
|
| 357 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 358 |
+
"loss": 0.9688,
|
| 359 |
+
"step": 50
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.9552715654952078,
|
| 363 |
+
"grad_norm": 0.4924392104148865,
|
| 364 |
+
"learning_rate": 3.2431258795932863e-06,
|
| 365 |
+
"loss": 0.8987,
|
| 366 |
+
"step": 51
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.9936102236421727,
|
| 370 |
+
"grad_norm": 0.5333181023597717,
|
| 371 |
+
"learning_rate": 3.0348748417303826e-06,
|
| 372 |
+
"loss": 0.8741,
|
| 373 |
+
"step": 52
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 2.0319488817891376,
|
| 377 |
+
"grad_norm": 1.4406224489212036,
|
| 378 |
+
"learning_rate": 2.83058130441221e-06,
|
| 379 |
+
"loss": 1.6146,
|
| 380 |
+
"step": 53
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 2.070287539936102,
|
| 384 |
+
"grad_norm": 0.5448528528213501,
|
| 385 |
+
"learning_rate": 2.6306566876350072e-06,
|
| 386 |
+
"loss": 0.8606,
|
| 387 |
+
"step": 54
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 2.108626198083067,
|
| 391 |
+
"grad_norm": 0.5303082466125488,
|
| 392 |
+
"learning_rate": 2.43550361297047e-06,
|
| 393 |
+
"loss": 0.8851,
|
| 394 |
+
"step": 55
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.146964856230032,
|
| 398 |
+
"grad_norm": 0.5754915475845337,
|
| 399 |
+
"learning_rate": 2.245515092739488e-06,
|
| 400 |
+
"loss": 0.8336,
|
| 401 |
+
"step": 56
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 2.1853035143769968,
|
| 405 |
+
"grad_norm": 0.4765103757381439,
|
| 406 |
+
"learning_rate": 2.061073738537635e-06,
|
| 407 |
+
"loss": 0.8015,
|
| 408 |
+
"step": 57
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 2.2236421725239617,
|
| 412 |
+
"grad_norm": 0.5756860971450806,
|
| 413 |
+
"learning_rate": 1.8825509907063328e-06,
|
| 414 |
+
"loss": 0.8836,
|
| 415 |
+
"step": 58
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 2.2619808306709266,
|
| 419 |
+
"grad_norm": 0.5327685475349426,
|
| 420 |
+
"learning_rate": 1.7103063703014372e-06,
|
| 421 |
+
"loss": 0.8488,
|
| 422 |
+
"step": 59
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 2.3003194888178915,
|
| 426 |
+
"grad_norm": 0.5584383606910706,
|
| 427 |
+
"learning_rate": 1.544686755065677e-06,
|
| 428 |
+
"loss": 0.8346,
|
| 429 |
+
"step": 60
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.3386581469648564,
|
| 433 |
+
"grad_norm": 0.5516854524612427,
|
| 434 |
+
"learning_rate": 1.3860256808630429e-06,
|
| 435 |
+
"loss": 0.8489,
|
| 436 |
+
"step": 61
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 2.376996805111821,
|
| 440 |
+
"grad_norm": 0.43996500968933105,
|
| 441 |
+
"learning_rate": 1.234642669981946e-06,
|
| 442 |
+
"loss": 0.8612,
|
| 443 |
+
"step": 62
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.415335463258786,
|
| 447 |
+
"grad_norm": 0.4551750719547272,
|
| 448 |
+
"learning_rate": 1.0908425876598512e-06,
|
| 449 |
+
"loss": 0.8517,
|
| 450 |
+
"step": 63
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 2.4536741214057507,
|
| 454 |
+
"grad_norm": 0.4995584785938263,
|
| 455 |
+
"learning_rate": 9.549150281252633e-07,
|
| 456 |
+
"loss": 0.7894,
|
| 457 |
+
"step": 64
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 2.4920127795527156,
|
| 461 |
+
"grad_norm": 0.5211077928543091,
|
| 462 |
+
"learning_rate": 8.271337313934869e-07,
|
| 463 |
+
"loss": 0.8612,
|
| 464 |
+
"step": 65
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.5303514376996805,
|
| 468 |
+
"grad_norm": 0.4741087853908539,
|
| 469 |
+
"learning_rate": 7.077560319906696e-07,
|
| 470 |
+
"loss": 0.7943,
|
| 471 |
+
"step": 66
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.5686900958466454,
|
| 475 |
+
"grad_norm": 0.5456284284591675,
|
| 476 |
+
"learning_rate": 5.9702234071631e-07,
|
| 477 |
+
"loss": 0.8837,
|
| 478 |
+
"step": 67
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 2.6070287539936103,
|
| 482 |
+
"grad_norm": 0.4274314045906067,
|
| 483 |
+
"learning_rate": 4.951556604879049e-07,
|
| 484 |
+
"loss": 0.7933,
|
| 485 |
+
"step": 68
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 2.6453674121405752,
|
| 489 |
+
"grad_norm": 0.4134873151779175,
|
| 490 |
+
"learning_rate": 4.0236113724274716e-07,
|
| 491 |
+
"loss": 0.7844,
|
| 492 |
+
"step": 69
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 2.68370607028754,
|
| 496 |
+
"grad_norm": 0.5081937909126282,
|
| 497 |
+
"learning_rate": 3.18825646801314e-07,
|
| 498 |
+
"loss": 0.9437,
|
| 499 |
+
"step": 70
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.722044728434505,
|
| 503 |
+
"grad_norm": 0.40975120663642883,
|
| 504 |
+
"learning_rate": 2.447174185242324e-07,
|
| 505 |
+
"loss": 0.8216,
|
| 506 |
+
"step": 71
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 2.7603833865814695,
|
| 510 |
+
"grad_norm": 0.5075166821479797,
|
| 511 |
+
"learning_rate": 1.801856965207338e-07,
|
| 512 |
+
"loss": 0.8,
|
| 513 |
+
"step": 72
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.7987220447284344,
|
| 517 |
+
"grad_norm": 0.44598546624183655,
|
| 518 |
+
"learning_rate": 1.253604390908819e-07,
|
| 519 |
+
"loss": 0.7936,
|
| 520 |
+
"step": 73
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 2.8370607028753994,
|
| 524 |
+
"grad_norm": 0.44412437081336975,
|
| 525 |
+
"learning_rate": 8.035205700685167e-08,
|
| 526 |
+
"loss": 0.8873,
|
| 527 |
+
"step": 74
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 2.8753993610223643,
|
| 531 |
+
"grad_norm": 0.446247398853302,
|
| 532 |
+
"learning_rate": 4.52511911603265e-08,
|
| 533 |
+
"loss": 0.8038,
|
| 534 |
+
"step": 75
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 2.913738019169329,
|
| 538 |
+
"grad_norm": 0.412568062543869,
|
| 539 |
+
"learning_rate": 2.012853002380466e-08,
|
| 540 |
+
"loss": 0.8549,
|
| 541 |
+
"step": 76
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 2.952076677316294,
|
| 545 |
+
"grad_norm": 0.43607237935066223,
|
| 546 |
+
"learning_rate": 5.034667293427053e-09,
|
| 547 |
+
"loss": 0.8204,
|
| 548 |
+
"step": 77
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.9904153354632586,
|
| 552 |
+
"grad_norm": 0.4113236963748932,
|
| 553 |
+
"learning_rate": 0.0,
|
| 554 |
+
"loss": 0.8888,
|
| 555 |
+
"step": 78
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.9904153354632586,
|
| 559 |
+
"step": 78,
|
| 560 |
+
"total_flos": 83614504427520.0,
|
| 561 |
+
"train_loss": 0.9489961503407894,
|
| 562 |
+
"train_runtime": 7848.0133,
|
| 563 |
+
"train_samples_per_second": 0.956,
|
| 564 |
+
"train_steps_per_second": 0.01
|
| 565 |
+
}
|
| 566 |
+
],
|
| 567 |
+
"logging_steps": 1.0,
|
| 568 |
+
"max_steps": 78,
|
| 569 |
+
"num_input_tokens_seen": 0,
|
| 570 |
+
"num_train_epochs": 3,
|
| 571 |
+
"save_steps": 500,
|
| 572 |
+
"stateful_callbacks": {
|
| 573 |
+
"TrainerControl": {
|
| 574 |
+
"args": {
|
| 575 |
+
"should_epoch_stop": false,
|
| 576 |
+
"should_evaluate": false,
|
| 577 |
+
"should_log": false,
|
| 578 |
+
"should_save": true,
|
| 579 |
+
"should_training_stop": true
|
| 580 |
+
},
|
| 581 |
+
"attributes": {}
|
| 582 |
+
}
|
| 583 |
+
},
|
| 584 |
+
"total_flos": 83614504427520.0,
|
| 585 |
+
"train_batch_size": 1,
|
| 586 |
+
"trial_name": null,
|
| 587 |
+
"trial_params": null
|
| 588 |
+
}
|
training_loss.png
ADDED
|