MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-4
Browse files- README.md +2 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +420 -0
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-4
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
|
|
|
|
|
|
| 18 |
|
| 19 |
## Model description
|
| 20 |
|
|
|
|
| 15 |
# gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-4
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
|
| 18 |
+
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 1.9914
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.991428017616272,
|
| 4 |
+
"eval_runtime": 53.9435,
|
| 5 |
+
"eval_samples_per_second": 22.208,
|
| 6 |
+
"eval_steps_per_second": 2.781,
|
| 7 |
+
"perplexity": 7.325987935990124,
|
| 8 |
+
"total_flos": 9.859643179008e+16,
|
| 9 |
+
"train_loss": 2.0996591644456246,
|
| 10 |
+
"train_runtime": 1436.8604,
|
| 11 |
+
"train_samples_per_second": 7.534,
|
| 12 |
+
"train_steps_per_second": 3.767
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.991428017616272,
|
| 4 |
+
"eval_runtime": 53.9435,
|
| 5 |
+
"eval_samples_per_second": 22.208,
|
| 6 |
+
"eval_steps_per_second": 2.781,
|
| 7 |
+
"perplexity": 7.325987935990124
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 9.859643179008e+16,
|
| 4 |
+
"train_loss": 2.0996591644456246,
|
| 5 |
+
"train_runtime": 1436.8604,
|
| 6 |
+
"train_samples_per_second": 7.534,
|
| 7 |
+
"train_steps_per_second": 3.767
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,420 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 5413,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.018474043968224645,
|
| 13 |
+
"grad_norm": 0.16043339669704437,
|
| 14 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
+
"loss": 2.4188,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03694808793644929,
|
| 20 |
+
"grad_norm": 0.24347032606601715,
|
| 21 |
+
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 2.426,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.05542213190467393,
|
| 27 |
+
"grad_norm": 0.18731114268302917,
|
| 28 |
+
"learning_rate": 6e-06,
|
| 29 |
+
"loss": 2.3901,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.07389617587289858,
|
| 34 |
+
"grad_norm": 0.28469762206077576,
|
| 35 |
+
"learning_rate": 8.000000000000001e-06,
|
| 36 |
+
"loss": 2.4127,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.09237021984112322,
|
| 41 |
+
"grad_norm": 0.38004377484321594,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 2.3162,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11084426380934786,
|
| 48 |
+
"grad_norm": 0.416911244392395,
|
| 49 |
+
"learning_rate": 1.2e-05,
|
| 50 |
+
"loss": 2.2961,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1293183077775725,
|
| 55 |
+
"grad_norm": 0.5000600814819336,
|
| 56 |
+
"learning_rate": 1.4e-05,
|
| 57 |
+
"loss": 2.2668,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.14779235174579716,
|
| 62 |
+
"grad_norm": 0.5812170505523682,
|
| 63 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 64 |
+
"loss": 2.2452,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1662663957140218,
|
| 69 |
+
"grad_norm": 0.6577287912368774,
|
| 70 |
+
"learning_rate": 1.8e-05,
|
| 71 |
+
"loss": 2.2119,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.18474043968224643,
|
| 76 |
+
"grad_norm": 0.5899447798728943,
|
| 77 |
+
"learning_rate": 2e-05,
|
| 78 |
+
"loss": 2.2027,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.2032144836504711,
|
| 83 |
+
"grad_norm": 0.649770200252533,
|
| 84 |
+
"learning_rate": 1.9974670975035436e-05,
|
| 85 |
+
"loss": 2.1942,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.22168852761869573,
|
| 90 |
+
"grad_norm": 0.6893395185470581,
|
| 91 |
+
"learning_rate": 1.9898812212042866e-05,
|
| 92 |
+
"loss": 2.1692,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.24016257158692036,
|
| 97 |
+
"grad_norm": 0.6736598610877991,
|
| 98 |
+
"learning_rate": 1.9772807996722613e-05,
|
| 99 |
+
"loss": 2.1466,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.258636615555145,
|
| 104 |
+
"grad_norm": 0.7326681017875671,
|
| 105 |
+
"learning_rate": 1.9597296641857785e-05,
|
| 106 |
+
"loss": 2.1331,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.27711065952336966,
|
| 111 |
+
"grad_norm": 0.6430918574333191,
|
| 112 |
+
"learning_rate": 1.937316725374616e-05,
|
| 113 |
+
"loss": 2.1098,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2955847034915943,
|
| 118 |
+
"grad_norm": 0.7850959300994873,
|
| 119 |
+
"learning_rate": 1.9101555228161095e-05,
|
| 120 |
+
"loss": 2.1525,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.31405874745981893,
|
| 125 |
+
"grad_norm": 0.8825465440750122,
|
| 126 |
+
"learning_rate": 1.8783836498657935e-05,
|
| 127 |
+
"loss": 2.0498,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.3325327914280436,
|
| 132 |
+
"grad_norm": 0.6566112637519836,
|
| 133 |
+
"learning_rate": 1.842162056636294e-05,
|
| 134 |
+
"loss": 2.1045,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.35100683539626826,
|
| 139 |
+
"grad_norm": 1.326594352722168,
|
| 140 |
+
"learning_rate": 1.8016742346554438e-05,
|
| 141 |
+
"loss": 2.052,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.36948087936449286,
|
| 146 |
+
"grad_norm": 0.833807110786438,
|
| 147 |
+
"learning_rate": 1.757125287333986e-05,
|
| 148 |
+
"loss": 2.1336,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3879549233327175,
|
| 153 |
+
"grad_norm": 0.9102203845977783,
|
| 154 |
+
"learning_rate": 1.7087408909516908e-05,
|
| 155 |
+
"loss": 2.0542,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.4064289673009422,
|
| 160 |
+
"grad_norm": 0.7581120133399963,
|
| 161 |
+
"learning_rate": 1.6567661514253307e-05,
|
| 162 |
+
"loss": 2.0792,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.4249030112691668,
|
| 167 |
+
"grad_norm": 0.8886149525642395,
|
| 168 |
+
"learning_rate": 1.6014643626499038e-05,
|
| 169 |
+
"loss": 2.0729,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.44337705523739146,
|
| 174 |
+
"grad_norm": 1.0382766723632812,
|
| 175 |
+
"learning_rate": 1.543115672703105e-05,
|
| 176 |
+
"loss": 2.0693,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4618510992056161,
|
| 181 |
+
"grad_norm": 0.6785975694656372,
|
| 182 |
+
"learning_rate": 1.482015664669798e-05,
|
| 183 |
+
"loss": 2.0846,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.48032514317384073,
|
| 188 |
+
"grad_norm": 0.8943729996681213,
|
| 189 |
+
"learning_rate": 1.4184738592757442e-05,
|
| 190 |
+
"loss": 2.0731,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.4987991871420654,
|
| 195 |
+
"grad_norm": 0.8952649831771851,
|
| 196 |
+
"learning_rate": 1.352812146915967e-05,
|
| 197 |
+
"loss": 2.0078,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.51727323111029,
|
| 202 |
+
"grad_norm": 0.9793375730514526,
|
| 203 |
+
"learning_rate": 1.2853631570207828e-05,
|
| 204 |
+
"loss": 2.0606,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.5357472750785147,
|
| 209 |
+
"grad_norm": 0.9555624127388,
|
| 210 |
+
"learning_rate": 1.2164685730199688e-05,
|
| 211 |
+
"loss": 2.0384,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.5542213190467393,
|
| 216 |
+
"grad_norm": 0.8237419724464417,
|
| 217 |
+
"learning_rate": 1.1464774014411416e-05,
|
| 218 |
+
"loss": 2.0578,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.5726953630149639,
|
| 223 |
+
"grad_norm": 1.0005195140838623,
|
| 224 |
+
"learning_rate": 1.0757442039107453e-05,
|
| 225 |
+
"loss": 2.033,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5911694069831886,
|
| 230 |
+
"grad_norm": 1.155673623085022,
|
| 231 |
+
"learning_rate": 1.0046273010139933e-05,
|
| 232 |
+
"loss": 2.0838,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.6096434509514133,
|
| 237 |
+
"grad_norm": 0.974641740322113,
|
| 238 |
+
"learning_rate": 9.334869571126606e-06,
|
| 239 |
+
"loss": 1.9982,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.6281174949196379,
|
| 244 |
+
"grad_norm": 0.9602746367454529,
|
| 245 |
+
"learning_rate": 8.626835553160812e-06,
|
| 246 |
+
"loss": 1.9969,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.6465915388878626,
|
| 251 |
+
"grad_norm": 1.0560555458068848,
|
| 252 |
+
"learning_rate": 7.925757718505905e-06,
|
| 253 |
+
"loss": 2.0479,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.6650655828560872,
|
| 258 |
+
"grad_norm": 1.1622087955474854,
|
| 259 |
+
"learning_rate": 7.235187590757096e-06,
|
| 260 |
+
"loss": 2.0234,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.6835396268243118,
|
| 265 |
+
"grad_norm": 1.1424589157104492,
|
| 266 |
+
"learning_rate": 6.558623463515508e-06,
|
| 267 |
+
"loss": 2.0209,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.7020136707925365,
|
| 272 |
+
"grad_norm": 1.2108582258224487,
|
| 273 |
+
"learning_rate": 5.89949267871493e-06,
|
| 274 |
+
"loss": 2.0022,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7204877147607611,
|
| 279 |
+
"grad_norm": 1.145391583442688,
|
| 280 |
+
"learning_rate": 5.261134264376e-06,
|
| 281 |
+
"loss": 2.0385,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7389617587289857,
|
| 286 |
+
"grad_norm": 1.037288784980774,
|
| 287 |
+
"learning_rate": 4.646782019741341e-06,
|
| 288 |
+
"loss": 2.0347,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7574358026972104,
|
| 293 |
+
"grad_norm": 0.7393826246261597,
|
| 294 |
+
"learning_rate": 4.05954813347923e-06,
|
| 295 |
+
"loss": 2.0283,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.775909846665435,
|
| 300 |
+
"grad_norm": 0.8227554559707642,
|
| 301 |
+
"learning_rate": 3.5024074179427013e-06,
|
| 302 |
+
"loss": 1.9719,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7943838906336597,
|
| 307 |
+
"grad_norm": 1.2980815172195435,
|
| 308 |
+
"learning_rate": 2.9781822393502733e-06,
|
| 309 |
+
"loss": 2.0397,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.8128579346018844,
|
| 314 |
+
"grad_norm": 1.4079487323760986,
|
| 315 |
+
"learning_rate": 2.489528220229076e-06,
|
| 316 |
+
"loss": 1.9704,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.831331978570109,
|
| 321 |
+
"grad_norm": 0.9588233232498169,
|
| 322 |
+
"learning_rate": 2.0389207865489768e-06,
|
| 323 |
+
"loss": 2.0161,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.8498060225383336,
|
| 328 |
+
"grad_norm": 0.9501762390136719,
|
| 329 |
+
"learning_rate": 1.6286426276973566e-06,
|
| 330 |
+
"loss": 2.025,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.8682800665065583,
|
| 335 |
+
"grad_norm": 0.9268977046012878,
|
| 336 |
+
"learning_rate": 1.2607721328198097e-06,
|
| 337 |
+
"loss": 2.0091,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.8867541104747829,
|
| 342 |
+
"grad_norm": 1.1910320520401,
|
| 343 |
+
"learning_rate": 9.371728621060306e-07,
|
| 344 |
+
"loss": 2.0051,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.9052281544430075,
|
| 349 |
+
"grad_norm": 0.8244079351425171,
|
| 350 |
+
"learning_rate": 6.594841063573099e-07,
|
| 351 |
+
"loss": 1.9783,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.9237021984112322,
|
| 356 |
+
"grad_norm": 0.8305772542953491,
|
| 357 |
+
"learning_rate": 4.2911258265898814e-07,
|
| 358 |
+
"loss": 1.9705,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.9421762423794569,
|
| 363 |
+
"grad_norm": 1.3943135738372803,
|
| 364 |
+
"learning_rate": 2.472253082260456e-07,
|
| 365 |
+
"loss": 1.9858,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.9606502863476815,
|
| 370 |
+
"grad_norm": 1.1412353515625,
|
| 371 |
+
"learning_rate": 1.1474368852145035e-07,
|
| 372 |
+
"loss": 2.0018,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.9791243303159062,
|
| 377 |
+
"grad_norm": 1.0674628019332886,
|
| 378 |
+
"learning_rate": 3.233884959577327e-08,
|
| 379 |
+
"loss": 2.0122,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.9975983742841308,
|
| 384 |
+
"grad_norm": 1.0804530382156372,
|
| 385 |
+
"learning_rate": 4.2823829348170866e-10,
|
| 386 |
+
"loss": 2.0582,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.0,
|
| 391 |
+
"step": 5413,
|
| 392 |
+
"total_flos": 9.859643179008e+16,
|
| 393 |
+
"train_loss": 2.0996591644456246,
|
| 394 |
+
"train_runtime": 1436.8604,
|
| 395 |
+
"train_samples_per_second": 7.534,
|
| 396 |
+
"train_steps_per_second": 3.767
|
| 397 |
+
}
|
| 398 |
+
],
|
| 399 |
+
"logging_steps": 100,
|
| 400 |
+
"max_steps": 5413,
|
| 401 |
+
"num_input_tokens_seen": 0,
|
| 402 |
+
"num_train_epochs": 1,
|
| 403 |
+
"save_steps": 500,
|
| 404 |
+
"stateful_callbacks": {
|
| 405 |
+
"TrainerControl": {
|
| 406 |
+
"args": {
|
| 407 |
+
"should_epoch_stop": false,
|
| 408 |
+
"should_evaluate": false,
|
| 409 |
+
"should_log": false,
|
| 410 |
+
"should_save": true,
|
| 411 |
+
"should_training_stop": true
|
| 412 |
+
},
|
| 413 |
+
"attributes": {}
|
| 414 |
+
}
|
| 415 |
+
},
|
| 416 |
+
"total_flos": 9.859643179008e+16,
|
| 417 |
+
"train_batch_size": 2,
|
| 418 |
+
"trial_name": null,
|
| 419 |
+
"trial_params": null
|
| 420 |
+
}
|