MHGanainy/gpt2-xl-lora-ecthr-tf-idf-kmeans-imbalanced-uniform-cluster-8-id-2
Browse files- README.md +2 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +476 -0
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# gpt2-xl-lora-ecthr-tf-idf-kmeans-imbalanced-uniform-cluster-8-id-2
|
| 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-tf-idf-kmeans-imbalanced-uniform-cluster-8-id-2
|
| 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: 1.9218
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.9218220710754395,
|
| 4 |
+
"eval_runtime": 62.1945,
|
| 5 |
+
"eval_samples_per_second": 22.269,
|
| 6 |
+
"eval_steps_per_second": 2.798,
|
| 7 |
+
"perplexity": 6.833398069901086,
|
| 8 |
+
"total_flos": 1.1351431053312e+17,
|
| 9 |
+
"train_loss": 2.079003376893422,
|
| 10 |
+
"train_runtime": 1659.922,
|
| 11 |
+
"train_samples_per_second": 7.509,
|
| 12 |
+
"train_steps_per_second": 3.754
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 1.9218220710754395,
|
| 4 |
+
"eval_runtime": 62.1945,
|
| 5 |
+
"eval_samples_per_second": 22.269,
|
| 6 |
+
"eval_steps_per_second": 2.798,
|
| 7 |
+
"perplexity": 6.833398069901086
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.1351431053312e+17,
|
| 4 |
+
"train_loss": 2.079003376893422,
|
| 5 |
+
"train_runtime": 1659.922,
|
| 6 |
+
"train_samples_per_second": 7.509,
|
| 7 |
+
"train_steps_per_second": 3.754
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,476 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6232,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.016046213093709884,
|
| 13 |
+
"grad_norm": 0.17895939946174622,
|
| 14 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 15 |
+
"loss": 2.4769,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.03209242618741977,
|
| 20 |
+
"grad_norm": 0.15942341089248657,
|
| 21 |
+
"learning_rate": 4.000000000000001e-06,
|
| 22 |
+
"loss": 2.4803,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.04813863928112965,
|
| 27 |
+
"grad_norm": 0.24720104038715363,
|
| 28 |
+
"learning_rate": 6e-06,
|
| 29 |
+
"loss": 2.438,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.06418485237483953,
|
| 34 |
+
"grad_norm": 0.39716702699661255,
|
| 35 |
+
"learning_rate": 8.000000000000001e-06,
|
| 36 |
+
"loss": 2.4056,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.08023106546854943,
|
| 41 |
+
"grad_norm": 0.3956620395183563,
|
| 42 |
+
"learning_rate": 1e-05,
|
| 43 |
+
"loss": 2.3633,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.0962772785622593,
|
| 48 |
+
"grad_norm": 0.5021713972091675,
|
| 49 |
+
"learning_rate": 1.2e-05,
|
| 50 |
+
"loss": 2.3186,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.1123234916559692,
|
| 55 |
+
"grad_norm": 0.567215085029602,
|
| 56 |
+
"learning_rate": 1.4e-05,
|
| 57 |
+
"loss": 2.2991,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.12836970474967907,
|
| 62 |
+
"grad_norm": 0.6055766344070435,
|
| 63 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 64 |
+
"loss": 2.2618,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.14441591784338895,
|
| 69 |
+
"grad_norm": 0.5610828995704651,
|
| 70 |
+
"learning_rate": 1.8e-05,
|
| 71 |
+
"loss": 2.2398,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.16046213093709885,
|
| 76 |
+
"grad_norm": 0.6880731582641602,
|
| 77 |
+
"learning_rate": 2e-05,
|
| 78 |
+
"loss": 2.2216,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.17650834403080873,
|
| 83 |
+
"grad_norm": 0.6766607761383057,
|
| 84 |
+
"learning_rate": 1.9981977966686475e-05,
|
| 85 |
+
"loss": 2.1763,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.1925545571245186,
|
| 90 |
+
"grad_norm": 0.8101206421852112,
|
| 91 |
+
"learning_rate": 1.992797682548284e-05,
|
| 92 |
+
"loss": 2.1818,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.2086007702182285,
|
| 97 |
+
"grad_norm": 0.8453436493873596,
|
| 98 |
+
"learning_rate": 1.983819121846225e-05,
|
| 99 |
+
"loss": 2.1666,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.2246469833119384,
|
| 104 |
+
"grad_norm": 0.8145064115524292,
|
| 105 |
+
"learning_rate": 1.9712944769464864e-05,
|
| 106 |
+
"loss": 2.1279,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.24069319640564826,
|
| 111 |
+
"grad_norm": 0.8634337782859802,
|
| 112 |
+
"learning_rate": 1.9552688917625927e-05,
|
| 113 |
+
"loss": 2.1279,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.25673940949935814,
|
| 118 |
+
"grad_norm": 1.1356147527694702,
|
| 119 |
+
"learning_rate": 1.9358001290205542e-05,
|
| 120 |
+
"loss": 2.1238,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.27278562259306804,
|
| 125 |
+
"grad_norm": 0.7424245476722717,
|
| 126 |
+
"learning_rate": 1.9129583620585137e-05,
|
| 127 |
+
"loss": 2.1072,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.2888318356867779,
|
| 132 |
+
"grad_norm": 1.1842221021652222,
|
| 133 |
+
"learning_rate": 1.886825921893497e-05,
|
| 134 |
+
"loss": 2.0933,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.3048780487804878,
|
| 139 |
+
"grad_norm": 0.9710640907287598,
|
| 140 |
+
"learning_rate": 1.8574970004669464e-05,
|
| 141 |
+
"loss": 2.0651,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.3209242618741977,
|
| 146 |
+
"grad_norm": 1.1665947437286377,
|
| 147 |
+
"learning_rate": 1.8250773111386633e-05,
|
| 148 |
+
"loss": 2.0682,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.33697047496790755,
|
| 153 |
+
"grad_norm": 1.1069215536117554,
|
| 154 |
+
"learning_rate": 1.7896837076528647e-05,
|
| 155 |
+
"loss": 2.089,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35301668806161746,
|
| 160 |
+
"grad_norm": 1.1600021123886108,
|
| 161 |
+
"learning_rate": 1.751443762949772e-05,
|
| 162 |
+
"loss": 2.0485,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.36906290115532736,
|
| 167 |
+
"grad_norm": 1.4247888326644897,
|
| 168 |
+
"learning_rate": 1.7104953093408548e-05,
|
| 169 |
+
"loss": 2.0807,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3851091142490372,
|
| 174 |
+
"grad_norm": 1.3733174800872803,
|
| 175 |
+
"learning_rate": 1.666985941705128e-05,
|
| 176 |
+
"loss": 2.0503,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.4011553273427471,
|
| 181 |
+
"grad_norm": 1.2357269525527954,
|
| 182 |
+
"learning_rate": 1.6210724854971885e-05,
|
| 183 |
+
"loss": 2.059,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.417201540436457,
|
| 188 |
+
"grad_norm": 1.0586000680923462,
|
| 189 |
+
"learning_rate": 1.5729204314845002e-05,
|
| 190 |
+
"loss": 2.0246,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.43324775353016687,
|
| 195 |
+
"grad_norm": 1.1663570404052734,
|
| 196 |
+
"learning_rate": 1.5227033392513684e-05,
|
| 197 |
+
"loss": 2.0421,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4492939666238768,
|
| 202 |
+
"grad_norm": 1.1528408527374268,
|
| 203 |
+
"learning_rate": 1.4706022116196208e-05,
|
| 204 |
+
"loss": 2.0494,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.4653401797175867,
|
| 209 |
+
"grad_norm": 1.0500417947769165,
|
| 210 |
+
"learning_rate": 1.4168048422408272e-05,
|
| 211 |
+
"loss": 2.008,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.4813863928112965,
|
| 216 |
+
"grad_norm": 1.2136881351470947,
|
| 217 |
+
"learning_rate": 1.3615051387116131e-05,
|
| 218 |
+
"loss": 2.026,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.49743260590500643,
|
| 223 |
+
"grad_norm": 1.1245627403259277,
|
| 224 |
+
"learning_rate": 1.3049024236518244e-05,
|
| 225 |
+
"loss": 1.9962,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.5134788189987163,
|
| 230 |
+
"grad_norm": 1.0942673683166504,
|
| 231 |
+
"learning_rate": 1.24720071626475e-05,
|
| 232 |
+
"loss": 2.0102,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.5295250320924262,
|
| 237 |
+
"grad_norm": 1.087973952293396,
|
| 238 |
+
"learning_rate": 1.1886079969689454e-05,
|
| 239 |
+
"loss": 1.9989,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.5455712451861361,
|
| 244 |
+
"grad_norm": 1.1616392135620117,
|
| 245 |
+
"learning_rate": 1.1293354577522264e-05,
|
| 246 |
+
"loss": 2.0078,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.561617458279846,
|
| 251 |
+
"grad_norm": 1.0014444589614868,
|
| 252 |
+
"learning_rate": 1.0695967409498614e-05,
|
| 253 |
+
"loss": 1.9948,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5776636713735558,
|
| 258 |
+
"grad_norm": 1.045386552810669,
|
| 259 |
+
"learning_rate": 1.0096071691907137e-05,
|
| 260 |
+
"loss": 2.0031,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5937098844672657,
|
| 265 |
+
"grad_norm": 1.7991660833358765,
|
| 266 |
+
"learning_rate": 9.495829692869255e-06,
|
| 267 |
+
"loss": 2.0029,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6097560975609756,
|
| 272 |
+
"grad_norm": 1.1647707223892212,
|
| 273 |
+
"learning_rate": 8.897404928645529e-06,
|
| 274 |
+
"loss": 1.9819,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.6258023106546855,
|
| 279 |
+
"grad_norm": 1.0043553113937378,
|
| 280 |
+
"learning_rate": 8.302954365443264e-06,
|
| 281 |
+
"loss": 2.0047,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.6418485237483954,
|
| 286 |
+
"grad_norm": 1.0303337574005127,
|
| 287 |
+
"learning_rate": 7.71462064483311e-06,
|
| 288 |
+
"loss": 1.986,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.6578947368421053,
|
| 293 |
+
"grad_norm": 1.3229223489761353,
|
| 294 |
+
"learning_rate": 7.13452436079753e-06,
|
| 295 |
+
"loss": 2.0151,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6739409499358151,
|
| 300 |
+
"grad_norm": 1.4595571756362915,
|
| 301 |
+
"learning_rate": 6.564756416247712e-06,
|
| 302 |
+
"loss": 1.9585,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.689987163029525,
|
| 307 |
+
"grad_norm": 1.1201053857803345,
|
| 308 |
+
"learning_rate": 6.007370486559185e-06,
|
| 309 |
+
"loss": 1.9846,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.7060333761232349,
|
| 314 |
+
"grad_norm": 1.0485244989395142,
|
| 315 |
+
"learning_rate": 5.46437561729062e-06,
|
| 316 |
+
"loss": 1.9853,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.7220795892169448,
|
| 321 |
+
"grad_norm": 1.0388679504394531,
|
| 322 |
+
"learning_rate": 4.937728982766622e-06,
|
| 323 |
+
"loss": 2.0268,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.7381258023106547,
|
| 328 |
+
"grad_norm": 1.3947858810424805,
|
| 329 |
+
"learning_rate": 4.429328831625565e-06,
|
| 330 |
+
"loss": 1.9645,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.7541720154043645,
|
| 335 |
+
"grad_norm": 1.3646990060806274,
|
| 336 |
+
"learning_rate": 3.941007644759535e-06,
|
| 337 |
+
"loss": 1.9704,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.7702182284980744,
|
| 342 |
+
"grad_norm": 1.2408106327056885,
|
| 343 |
+
"learning_rate": 3.474525530308016e-06,
|
| 344 |
+
"loss": 2.0122,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7862644415917843,
|
| 349 |
+
"grad_norm": 1.3304516077041626,
|
| 350 |
+
"learning_rate": 3.0315638795123726e-06,
|
| 351 |
+
"loss": 1.9989,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.8023106546854942,
|
| 356 |
+
"grad_norm": 1.200531005859375,
|
| 357 |
+
"learning_rate": 2.6137193062980506e-06,
|
| 358 |
+
"loss": 2.0135,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.8183568677792041,
|
| 363 |
+
"grad_norm": 1.3504362106323242,
|
| 364 |
+
"learning_rate": 2.2224978924287243e-06,
|
| 365 |
+
"loss": 2.0073,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.834403080872914,
|
| 370 |
+
"grad_norm": 1.4387364387512207,
|
| 371 |
+
"learning_rate": 1.8593097589751318e-06,
|
| 372 |
+
"loss": 1.9344,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.8504492939666238,
|
| 377 |
+
"grad_norm": 1.4003574848175049,
|
| 378 |
+
"learning_rate": 1.5254639836653117e-06,
|
| 379 |
+
"loss": 2.0001,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.8664955070603337,
|
| 384 |
+
"grad_norm": 1.2966829538345337,
|
| 385 |
+
"learning_rate": 1.222163882436107e-06,
|
| 386 |
+
"loss": 1.9852,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.8825417201540436,
|
| 391 |
+
"grad_norm": 1.3298251628875732,
|
| 392 |
+
"learning_rate": 9.505026721931898e-07,
|
| 393 |
+
"loss": 1.9768,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8985879332477535,
|
| 398 |
+
"grad_norm": 1.1031887531280518,
|
| 399 |
+
"learning_rate": 7.114595304127536e-07,
|
| 400 |
+
"loss": 1.9921,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.9146341463414634,
|
| 405 |
+
"grad_norm": 1.3485647439956665,
|
| 406 |
+
"learning_rate": 5.077834417277494e-07,
|
| 407 |
+
"loss": 1.9674,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9306803594351734,
|
| 412 |
+
"grad_norm": 1.056166172027588,
|
| 413 |
+
"learning_rate": 3.3609511784804427e-07,
|
| 414 |
+
"loss": 2.0047,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.9467265725288831,
|
| 419 |
+
"grad_norm": 1.2811501026153564,
|
| 420 |
+
"learning_rate": 1.9923943711331996e-07,
|
| 421 |
+
"loss": 1.9755,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.962772785622593,
|
| 426 |
+
"grad_norm": 1.4452365636825562,
|
| 427 |
+
"learning_rate": 9.770968305104822e-08,
|
| 428 |
+
"loss": 1.9793,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.978818998716303,
|
| 433 |
+
"grad_norm": 1.8246029615402222,
|
| 434 |
+
"learning_rate": 3.18718101832316e-08,
|
| 435 |
+
"loss": 2.0008,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.9948652118100129,
|
| 440 |
+
"grad_norm": 1.3338468074798584,
|
| 441 |
+
"learning_rate": 1.963124977494291e-09,
|
| 442 |
+
"loss": 1.9654,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.0,
|
| 447 |
+
"step": 6232,
|
| 448 |
+
"total_flos": 1.1351431053312e+17,
|
| 449 |
+
"train_loss": 2.079003376893422,
|
| 450 |
+
"train_runtime": 1659.922,
|
| 451 |
+
"train_samples_per_second": 7.509,
|
| 452 |
+
"train_steps_per_second": 3.754
|
| 453 |
+
}
|
| 454 |
+
],
|
| 455 |
+
"logging_steps": 100,
|
| 456 |
+
"max_steps": 6232,
|
| 457 |
+
"num_input_tokens_seen": 0,
|
| 458 |
+
"num_train_epochs": 1,
|
| 459 |
+
"save_steps": 500,
|
| 460 |
+
"stateful_callbacks": {
|
| 461 |
+
"TrainerControl": {
|
| 462 |
+
"args": {
|
| 463 |
+
"should_epoch_stop": false,
|
| 464 |
+
"should_evaluate": false,
|
| 465 |
+
"should_log": false,
|
| 466 |
+
"should_save": true,
|
| 467 |
+
"should_training_stop": true
|
| 468 |
+
},
|
| 469 |
+
"attributes": {}
|
| 470 |
+
}
|
| 471 |
+
},
|
| 472 |
+
"total_flos": 1.1351431053312e+17,
|
| 473 |
+
"train_batch_size": 2,
|
| 474 |
+
"trial_name": null,
|
| 475 |
+
"trial_params": null
|
| 476 |
+
}
|