MHGanainy/gpt2-xl-lora-multi-3
Browse files- README.md +2 -0
- all_results.json +13 -0
- eval_results.json +8 -0
- train_results.json +8 -0
- trainer_state.json +525 -0
README.md
CHANGED
|
@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 15 |
# gpt2-xl-lora-multi-3
|
| 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-multi-3
|
| 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: 2.4470
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.447016954421997,
|
| 4 |
+
"eval_runtime": 255.0441,
|
| 5 |
+
"eval_samples_per_second": 7.795,
|
| 6 |
+
"eval_steps_per_second": 0.49,
|
| 7 |
+
"perplexity": 11.553829661360664,
|
| 8 |
+
"total_flos": 1.0085141819823227e+18,
|
| 9 |
+
"train_loss": 2.6225888340860033,
|
| 10 |
+
"train_runtime": 2201.4938,
|
| 11 |
+
"train_samples_per_second": 50.3,
|
| 12 |
+
"train_steps_per_second": 3.144
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 2.447016954421997,
|
| 4 |
+
"eval_runtime": 255.0441,
|
| 5 |
+
"eval_samples_per_second": 7.795,
|
| 6 |
+
"eval_steps_per_second": 0.49,
|
| 7 |
+
"perplexity": 11.553829661360664
|
| 8 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1.0085141819823227e+18,
|
| 4 |
+
"train_loss": 2.6225888340860033,
|
| 5 |
+
"train_runtime": 2201.4938,
|
| 6 |
+
"train_samples_per_second": 50.3,
|
| 7 |
+
"train_steps_per_second": 3.144
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,525 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6921,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.014448779078167894,
|
| 13 |
+
"grad_norm": 0.1319790631532669,
|
| 14 |
+
"learning_rate": 3.576589595375723e-07,
|
| 15 |
+
"loss": 2.9859,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.02889755815633579,
|
| 20 |
+
"grad_norm": 0.09819761663675308,
|
| 21 |
+
"learning_rate": 7.153179190751446e-07,
|
| 22 |
+
"loss": 2.9932,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.043346337234503686,
|
| 27 |
+
"grad_norm": 0.1437925547361374,
|
| 28 |
+
"learning_rate": 1.0729768786127169e-06,
|
| 29 |
+
"loss": 2.9802,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05779511631267158,
|
| 34 |
+
"grad_norm": 0.1754620224237442,
|
| 35 |
+
"learning_rate": 1.4306358381502892e-06,
|
| 36 |
+
"loss": 2.951,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.07224389539083947,
|
| 41 |
+
"grad_norm": 0.16474293172359467,
|
| 42 |
+
"learning_rate": 1.791907514450867e-06,
|
| 43 |
+
"loss": 2.9437,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.08669267446900737,
|
| 48 |
+
"grad_norm": 0.19413641095161438,
|
| 49 |
+
"learning_rate": 2.153179190751445e-06,
|
| 50 |
+
"loss": 2.909,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.10114145354717527,
|
| 55 |
+
"grad_norm": 0.21083518862724304,
|
| 56 |
+
"learning_rate": 2.5144508670520235e-06,
|
| 57 |
+
"loss": 2.8579,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.11559023262534315,
|
| 62 |
+
"grad_norm": 0.16336515545845032,
|
| 63 |
+
"learning_rate": 2.8757225433526016e-06,
|
| 64 |
+
"loss": 2.8228,
|
| 65 |
+
"step": 800
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.13003901170351106,
|
| 69 |
+
"grad_norm": 0.20088078081607819,
|
| 70 |
+
"learning_rate": 3.2369942196531797e-06,
|
| 71 |
+
"loss": 2.8003,
|
| 72 |
+
"step": 900
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.14448779078167895,
|
| 76 |
+
"grad_norm": 0.15995082259178162,
|
| 77 |
+
"learning_rate": 3.5982658959537574e-06,
|
| 78 |
+
"loss": 2.7788,
|
| 79 |
+
"step": 1000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.15893656985984683,
|
| 83 |
+
"grad_norm": 0.15541793406009674,
|
| 84 |
+
"learning_rate": 3.9595375722543355e-06,
|
| 85 |
+
"loss": 2.731,
|
| 86 |
+
"step": 1100
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.17338534893801474,
|
| 90 |
+
"grad_norm": 0.16839973628520966,
|
| 91 |
+
"learning_rate": 4.320809248554913e-06,
|
| 92 |
+
"loss": 2.71,
|
| 93 |
+
"step": 1200
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.18783412801618263,
|
| 97 |
+
"grad_norm": 0.16297543048858643,
|
| 98 |
+
"learning_rate": 4.682080924855492e-06,
|
| 99 |
+
"loss": 2.6887,
|
| 100 |
+
"step": 1300
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.20228290709435054,
|
| 104 |
+
"grad_norm": 0.1565973162651062,
|
| 105 |
+
"learning_rate": 5.043352601156069e-06,
|
| 106 |
+
"loss": 2.666,
|
| 107 |
+
"step": 1400
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.21673168617251842,
|
| 111 |
+
"grad_norm": 0.13941773772239685,
|
| 112 |
+
"learning_rate": 5.404624277456648e-06,
|
| 113 |
+
"loss": 2.6619,
|
| 114 |
+
"step": 1500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.2311804652506863,
|
| 118 |
+
"grad_norm": 0.14650990068912506,
|
| 119 |
+
"learning_rate": 5.765895953757226e-06,
|
| 120 |
+
"loss": 2.6402,
|
| 121 |
+
"step": 1600
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.24562924432885422,
|
| 125 |
+
"grad_norm": 0.16068528592586517,
|
| 126 |
+
"learning_rate": 6.127167630057804e-06,
|
| 127 |
+
"loss": 2.639,
|
| 128 |
+
"step": 1700
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.26007802340702213,
|
| 132 |
+
"grad_norm": 0.16715380549430847,
|
| 133 |
+
"learning_rate": 6.488439306358382e-06,
|
| 134 |
+
"loss": 2.6312,
|
| 135 |
+
"step": 1800
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.27452680248519,
|
| 139 |
+
"grad_norm": 0.2185903787612915,
|
| 140 |
+
"learning_rate": 6.84971098265896e-06,
|
| 141 |
+
"loss": 2.627,
|
| 142 |
+
"step": 1900
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.2889755815633579,
|
| 146 |
+
"grad_norm": 0.16029363870620728,
|
| 147 |
+
"learning_rate": 7.210982658959538e-06,
|
| 148 |
+
"loss": 2.6231,
|
| 149 |
+
"step": 2000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.3034243606415258,
|
| 153 |
+
"grad_norm": 0.16060592234134674,
|
| 154 |
+
"learning_rate": 7.5722543352601166e-06,
|
| 155 |
+
"loss": 2.6127,
|
| 156 |
+
"step": 2100
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.31787313971969366,
|
| 160 |
+
"grad_norm": 0.16263119876384735,
|
| 161 |
+
"learning_rate": 7.933526011560694e-06,
|
| 162 |
+
"loss": 2.6082,
|
| 163 |
+
"step": 2200
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.3323219187978616,
|
| 167 |
+
"grad_norm": 0.1585131585597992,
|
| 168 |
+
"learning_rate": 8.294797687861273e-06,
|
| 169 |
+
"loss": 2.6037,
|
| 170 |
+
"step": 2300
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.3467706978760295,
|
| 174 |
+
"grad_norm": 0.16766057908535004,
|
| 175 |
+
"learning_rate": 8.656069364161851e-06,
|
| 176 |
+
"loss": 2.6005,
|
| 177 |
+
"step": 2400
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.36121947695419737,
|
| 181 |
+
"grad_norm": 0.1492636650800705,
|
| 182 |
+
"learning_rate": 9.017341040462428e-06,
|
| 183 |
+
"loss": 2.5915,
|
| 184 |
+
"step": 2500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.37566825603236526,
|
| 188 |
+
"grad_norm": 0.17886599898338318,
|
| 189 |
+
"learning_rate": 9.378612716763007e-06,
|
| 190 |
+
"loss": 2.5881,
|
| 191 |
+
"step": 2600
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.39011703511053314,
|
| 195 |
+
"grad_norm": 0.18520204722881317,
|
| 196 |
+
"learning_rate": 9.739884393063585e-06,
|
| 197 |
+
"loss": 2.5915,
|
| 198 |
+
"step": 2700
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.4045658141887011,
|
| 202 |
+
"grad_norm": 0.1520683318376541,
|
| 203 |
+
"learning_rate": 1.0101156069364162e-05,
|
| 204 |
+
"loss": 2.5806,
|
| 205 |
+
"step": 2800
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.41901459326686896,
|
| 209 |
+
"grad_norm": 0.1854362040758133,
|
| 210 |
+
"learning_rate": 1.046242774566474e-05,
|
| 211 |
+
"loss": 2.5711,
|
| 212 |
+
"step": 2900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.43346337234503685,
|
| 216 |
+
"grad_norm": 0.18411140143871307,
|
| 217 |
+
"learning_rate": 1.0823699421965319e-05,
|
| 218 |
+
"loss": 2.5841,
|
| 219 |
+
"step": 3000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.44791215142320473,
|
| 223 |
+
"grad_norm": 0.1857396364212036,
|
| 224 |
+
"learning_rate": 1.1184971098265898e-05,
|
| 225 |
+
"loss": 2.5727,
|
| 226 |
+
"step": 3100
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4623609305013726,
|
| 230 |
+
"grad_norm": 0.23173969984054565,
|
| 231 |
+
"learning_rate": 1.1546242774566474e-05,
|
| 232 |
+
"loss": 2.5793,
|
| 233 |
+
"step": 3200
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.47680970957954055,
|
| 237 |
+
"grad_norm": 0.17829596996307373,
|
| 238 |
+
"learning_rate": 1.1907514450867053e-05,
|
| 239 |
+
"loss": 2.574,
|
| 240 |
+
"step": 3300
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.49125848865770844,
|
| 244 |
+
"grad_norm": 0.1748592108488083,
|
| 245 |
+
"learning_rate": 1.2268786127167632e-05,
|
| 246 |
+
"loss": 2.5675,
|
| 247 |
+
"step": 3400
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.5057072677358763,
|
| 251 |
+
"grad_norm": 0.18341368436813354,
|
| 252 |
+
"learning_rate": 1.263005780346821e-05,
|
| 253 |
+
"loss": 2.5695,
|
| 254 |
+
"step": 3500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.5201560468140443,
|
| 258 |
+
"grad_norm": 0.17201048135757446,
|
| 259 |
+
"learning_rate": 1.2991329479768787e-05,
|
| 260 |
+
"loss": 2.565,
|
| 261 |
+
"step": 3600
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.5346048258922121,
|
| 265 |
+
"grad_norm": 0.21022534370422363,
|
| 266 |
+
"learning_rate": 1.3352601156069365e-05,
|
| 267 |
+
"loss": 2.5662,
|
| 268 |
+
"step": 3700
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.54905360497038,
|
| 272 |
+
"grad_norm": 0.17963945865631104,
|
| 273 |
+
"learning_rate": 1.3713872832369944e-05,
|
| 274 |
+
"loss": 2.5645,
|
| 275 |
+
"step": 3800
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5635023840485479,
|
| 279 |
+
"grad_norm": 0.18298958241939545,
|
| 280 |
+
"learning_rate": 1.4075144508670523e-05,
|
| 281 |
+
"loss": 2.5634,
|
| 282 |
+
"step": 3900
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5779511631267158,
|
| 286 |
+
"grad_norm": 0.221732035279274,
|
| 287 |
+
"learning_rate": 1.4436416184971101e-05,
|
| 288 |
+
"loss": 2.5532,
|
| 289 |
+
"step": 4000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5923999422048837,
|
| 293 |
+
"grad_norm": 0.19882583618164062,
|
| 294 |
+
"learning_rate": 1.4797687861271676e-05,
|
| 295 |
+
"loss": 2.5595,
|
| 296 |
+
"step": 4100
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.6068487212830516,
|
| 300 |
+
"grad_norm": 0.21510709822177887,
|
| 301 |
+
"learning_rate": 1.5158959537572255e-05,
|
| 302 |
+
"loss": 2.5632,
|
| 303 |
+
"step": 4200
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.6212975003612194,
|
| 307 |
+
"grad_norm": 0.17533738911151886,
|
| 308 |
+
"learning_rate": 1.5520231213872833e-05,
|
| 309 |
+
"loss": 2.5448,
|
| 310 |
+
"step": 4300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.6357462794393873,
|
| 314 |
+
"grad_norm": 0.19394342601299286,
|
| 315 |
+
"learning_rate": 1.5881502890173412e-05,
|
| 316 |
+
"loss": 2.5597,
|
| 317 |
+
"step": 4400
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.6501950585175552,
|
| 321 |
+
"grad_norm": 0.196193665266037,
|
| 322 |
+
"learning_rate": 1.624277456647399e-05,
|
| 323 |
+
"loss": 2.551,
|
| 324 |
+
"step": 4500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6646438375957232,
|
| 328 |
+
"grad_norm": 0.1857462376356125,
|
| 329 |
+
"learning_rate": 1.660404624277457e-05,
|
| 330 |
+
"loss": 2.5478,
|
| 331 |
+
"step": 4600
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6790926166738911,
|
| 335 |
+
"grad_norm": 0.20186574757099152,
|
| 336 |
+
"learning_rate": 1.6965317919075147e-05,
|
| 337 |
+
"loss": 2.5508,
|
| 338 |
+
"step": 4700
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.693541395752059,
|
| 342 |
+
"grad_norm": 0.22574672102928162,
|
| 343 |
+
"learning_rate": 1.7326589595375726e-05,
|
| 344 |
+
"loss": 2.5492,
|
| 345 |
+
"step": 4800
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.7079901748302269,
|
| 349 |
+
"grad_norm": 0.21713367104530334,
|
| 350 |
+
"learning_rate": 1.76878612716763e-05,
|
| 351 |
+
"loss": 2.5326,
|
| 352 |
+
"step": 4900
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.7224389539083947,
|
| 356 |
+
"grad_norm": 0.2183527648448944,
|
| 357 |
+
"learning_rate": 1.804913294797688e-05,
|
| 358 |
+
"loss": 2.5512,
|
| 359 |
+
"step": 5000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.7368877329865626,
|
| 363 |
+
"grad_norm": 0.23467661440372467,
|
| 364 |
+
"learning_rate": 1.8410404624277458e-05,
|
| 365 |
+
"loss": 2.5462,
|
| 366 |
+
"step": 5100
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.7513365120647305,
|
| 370 |
+
"grad_norm": 0.20273762941360474,
|
| 371 |
+
"learning_rate": 1.8771676300578037e-05,
|
| 372 |
+
"loss": 2.5493,
|
| 373 |
+
"step": 5200
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.7657852911428984,
|
| 377 |
+
"grad_norm": 0.20707377791404724,
|
| 378 |
+
"learning_rate": 1.9132947976878615e-05,
|
| 379 |
+
"loss": 2.5425,
|
| 380 |
+
"step": 5300
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7802340702210663,
|
| 384 |
+
"grad_norm": 0.20679670572280884,
|
| 385 |
+
"learning_rate": 1.949421965317919e-05,
|
| 386 |
+
"loss": 2.5424,
|
| 387 |
+
"step": 5400
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7946828492992342,
|
| 391 |
+
"grad_norm": 0.22911733388900757,
|
| 392 |
+
"learning_rate": 1.985549132947977e-05,
|
| 393 |
+
"loss": 2.5369,
|
| 394 |
+
"step": 5500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.8091316283774022,
|
| 398 |
+
"grad_norm": 0.2293398678302765,
|
| 399 |
+
"learning_rate": 1.990752970486014e-05,
|
| 400 |
+
"loss": 2.5414,
|
| 401 |
+
"step": 5600
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.82358040745557,
|
| 405 |
+
"grad_norm": 0.21145911514759064,
|
| 406 |
+
"learning_rate": 1.934861471129627e-05,
|
| 407 |
+
"loss": 2.5341,
|
| 408 |
+
"step": 5700
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.8380291865337379,
|
| 412 |
+
"grad_norm": 0.22642740607261658,
|
| 413 |
+
"learning_rate": 1.8310755913154726e-05,
|
| 414 |
+
"loss": 2.5312,
|
| 415 |
+
"step": 5800
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.8524779656119058,
|
| 419 |
+
"grad_norm": 0.22286154329776764,
|
| 420 |
+
"learning_rate": 1.6847124401206384e-05,
|
| 421 |
+
"loss": 2.5354,
|
| 422 |
+
"step": 5900
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.8669267446900737,
|
| 426 |
+
"grad_norm": 0.22432397305965424,
|
| 427 |
+
"learning_rate": 1.5032704252395315e-05,
|
| 428 |
+
"loss": 2.5355,
|
| 429 |
+
"step": 6000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.8813755237682416,
|
| 433 |
+
"grad_norm": 0.21558962762355804,
|
| 434 |
+
"learning_rate": 1.2960450981095643e-05,
|
| 435 |
+
"loss": 2.5481,
|
| 436 |
+
"step": 6100
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.8958243028464095,
|
| 440 |
+
"grad_norm": 0.2449900358915329,
|
| 441 |
+
"learning_rate": 1.0736529286191087e-05,
|
| 442 |
+
"loss": 2.5352,
|
| 443 |
+
"step": 6200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.9102730819245773,
|
| 447 |
+
"grad_norm": 0.22407910227775574,
|
| 448 |
+
"learning_rate": 8.474874071465144e-06,
|
| 449 |
+
"loss": 2.5261,
|
| 450 |
+
"step": 6300
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.9247218610027452,
|
| 454 |
+
"grad_norm": 0.20298534631729126,
|
| 455 |
+
"learning_rate": 6.291353386531074e-06,
|
| 456 |
+
"loss": 2.5389,
|
| 457 |
+
"step": 6400
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.9391706400809131,
|
| 461 |
+
"grad_norm": 0.2112707942724228,
|
| 462 |
+
"learning_rate": 4.297832329749687e-06,
|
| 463 |
+
"loss": 2.5369,
|
| 464 |
+
"step": 6500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.9536194191590811,
|
| 468 |
+
"grad_norm": 0.22108633816242218,
|
| 469 |
+
"learning_rate": 2.596442028451194e-06,
|
| 470 |
+
"loss": 2.5331,
|
| 471 |
+
"step": 6600
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.968068198237249,
|
| 475 |
+
"grad_norm": 0.21827644109725952,
|
| 476 |
+
"learning_rate": 1.2743473053542842e-06,
|
| 477 |
+
"loss": 2.5279,
|
| 478 |
+
"step": 6700
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.9825169773154169,
|
| 482 |
+
"grad_norm": 0.22307871282100677,
|
| 483 |
+
"learning_rate": 3.9928109162008953e-07,
|
| 484 |
+
"loss": 2.5346,
|
| 485 |
+
"step": 6800
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9969657563935848,
|
| 489 |
+
"grad_norm": 0.22532746195793152,
|
| 490 |
+
"learning_rate": 1.6074365378105915e-08,
|
| 491 |
+
"loss": 2.5428,
|
| 492 |
+
"step": 6900
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 1.0,
|
| 496 |
+
"step": 6921,
|
| 497 |
+
"total_flos": 1.0085141819823227e+18,
|
| 498 |
+
"train_loss": 2.6225888340860033,
|
| 499 |
+
"train_runtime": 2201.4938,
|
| 500 |
+
"train_samples_per_second": 50.3,
|
| 501 |
+
"train_steps_per_second": 3.144
|
| 502 |
+
}
|
| 503 |
+
],
|
| 504 |
+
"logging_steps": 100,
|
| 505 |
+
"max_steps": 6921,
|
| 506 |
+
"num_input_tokens_seen": 0,
|
| 507 |
+
"num_train_epochs": 1,
|
| 508 |
+
"save_steps": 500,
|
| 509 |
+
"stateful_callbacks": {
|
| 510 |
+
"TrainerControl": {
|
| 511 |
+
"args": {
|
| 512 |
+
"should_epoch_stop": false,
|
| 513 |
+
"should_evaluate": false,
|
| 514 |
+
"should_log": false,
|
| 515 |
+
"should_save": true,
|
| 516 |
+
"should_training_stop": true
|
| 517 |
+
},
|
| 518 |
+
"attributes": {}
|
| 519 |
+
}
|
| 520 |
+
},
|
| 521 |
+
"total_flos": 1.0085141819823227e+18,
|
| 522 |
+
"train_batch_size": 2,
|
| 523 |
+
"trial_name": null,
|
| 524 |
+
"trial_params": null
|
| 525 |
+
}
|