lr=0.00001 epochs=1500
Browse files- all_results.json +13 -13
- eval_results.json +8 -8
- pytorch_model.bin +1 -1
- train_results.json +6 -6
- trainer_state.json +282 -60
- training_args.bin +1 -1
all_results.json
CHANGED
|
@@ -1,23 +1,23 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_mem_cpu_alloc_delta":
|
| 5 |
-
"eval_mem_cpu_peaked_delta":
|
| 6 |
"eval_mem_gpu_alloc_delta": 0,
|
| 7 |
"eval_mem_gpu_peaked_delta": 379483648,
|
| 8 |
-
"eval_runtime": 0.
|
| 9 |
-
"eval_samples":
|
| 10 |
-
"eval_samples_per_second": 28.
|
| 11 |
"init_mem_cpu_alloc_delta": 66338,
|
| 12 |
"init_mem_cpu_peaked_delta": 19115,
|
| 13 |
"init_mem_gpu_alloc_delta": 454524928,
|
| 14 |
"init_mem_gpu_peaked_delta": 0,
|
| 15 |
-
"perplexity": 1.
|
| 16 |
-
"train_mem_cpu_alloc_delta":
|
| 17 |
-
"train_mem_cpu_peaked_delta":
|
| 18 |
"train_mem_gpu_alloc_delta": 1347066368,
|
| 19 |
"train_mem_gpu_peaked_delta": 3584124928,
|
| 20 |
-
"train_runtime":
|
| 21 |
-
"train_samples":
|
| 22 |
-
"train_samples_per_second": 8.
|
| 23 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1500.0,
|
| 3 |
+
"eval_loss": 0.029992273077368736,
|
| 4 |
+
"eval_mem_cpu_alloc_delta": 72385,
|
| 5 |
+
"eval_mem_cpu_peaked_delta": 26695,
|
| 6 |
"eval_mem_gpu_alloc_delta": 0,
|
| 7 |
"eval_mem_gpu_peaked_delta": 379483648,
|
| 8 |
+
"eval_runtime": 0.6282,
|
| 9 |
+
"eval_samples": 18,
|
| 10 |
+
"eval_samples_per_second": 28.653,
|
| 11 |
"init_mem_cpu_alloc_delta": 66338,
|
| 12 |
"init_mem_cpu_peaked_delta": 19115,
|
| 13 |
"init_mem_gpu_alloc_delta": 454524928,
|
| 14 |
"init_mem_gpu_peaked_delta": 0,
|
| 15 |
+
"perplexity": 1.0304465717418196,
|
| 16 |
+
"train_mem_cpu_alloc_delta": 465658,
|
| 17 |
+
"train_mem_cpu_peaked_delta": 103326056,
|
| 18 |
"train_mem_gpu_alloc_delta": 1347066368,
|
| 19 |
"train_mem_gpu_peaked_delta": 3584124928,
|
| 20 |
+
"train_runtime": 3225.4397,
|
| 21 |
+
"train_samples": 18,
|
| 22 |
+
"train_samples_per_second": 8.371
|
| 23 |
}
|
eval_results.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_loss": 0.
|
| 4 |
-
"eval_mem_cpu_alloc_delta":
|
| 5 |
-
"eval_mem_cpu_peaked_delta":
|
| 6 |
"eval_mem_gpu_alloc_delta": 0,
|
| 7 |
"eval_mem_gpu_peaked_delta": 379483648,
|
| 8 |
-
"eval_runtime": 0.
|
| 9 |
-
"eval_samples":
|
| 10 |
-
"eval_samples_per_second": 28.
|
| 11 |
-
"perplexity": 1.
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1500.0,
|
| 3 |
+
"eval_loss": 0.029992273077368736,
|
| 4 |
+
"eval_mem_cpu_alloc_delta": 72385,
|
| 5 |
+
"eval_mem_cpu_peaked_delta": 26695,
|
| 6 |
"eval_mem_gpu_alloc_delta": 0,
|
| 7 |
"eval_mem_gpu_peaked_delta": 379483648,
|
| 8 |
+
"eval_runtime": 0.6282,
|
| 9 |
+
"eval_samples": 18,
|
| 10 |
+
"eval_samples_per_second": 28.653,
|
| 11 |
+
"perplexity": 1.0304465717418196
|
| 12 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 454318313
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c18974307ef9fdffba0f9c67b09c930fa2c0bd51209730acdfdfd63e1dd94714
|
| 3 |
size 454318313
|
train_results.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
"init_mem_cpu_alloc_delta": 66338,
|
| 4 |
"init_mem_cpu_peaked_delta": 19115,
|
| 5 |
"init_mem_gpu_alloc_delta": 454524928,
|
| 6 |
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
-
"train_mem_cpu_alloc_delta":
|
| 8 |
-
"train_mem_cpu_peaked_delta":
|
| 9 |
"train_mem_gpu_alloc_delta": 1347066368,
|
| 10 |
"train_mem_gpu_peaked_delta": 3584124928,
|
| 11 |
-
"train_runtime":
|
| 12 |
-
"train_samples":
|
| 13 |
-
"train_samples_per_second": 8.
|
| 14 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 1500.0,
|
| 3 |
"init_mem_cpu_alloc_delta": 66338,
|
| 4 |
"init_mem_cpu_peaked_delta": 19115,
|
| 5 |
"init_mem_gpu_alloc_delta": 454524928,
|
| 6 |
"init_mem_gpu_peaked_delta": 0,
|
| 7 |
+
"train_mem_cpu_alloc_delta": 465658,
|
| 8 |
+
"train_mem_cpu_peaked_delta": 103326056,
|
| 9 |
"train_mem_gpu_alloc_delta": 1347066368,
|
| 10 |
"train_mem_gpu_peaked_delta": 3584124928,
|
| 11 |
+
"train_runtime": 3225.4397,
|
| 12 |
+
"train_samples": 18,
|
| 13 |
+
"train_samples_per_second": 8.371
|
| 14 |
}
|
trainer_state.json
CHANGED
|
@@ -1,125 +1,347 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
-
"epoch":
|
| 12 |
-
"learning_rate": 9.
|
| 13 |
-
"loss": 3.
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
-
"epoch":
|
| 18 |
-
"learning_rate":
|
| 19 |
-
"loss": 1.
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
-
"epoch":
|
| 24 |
-
"learning_rate":
|
| 25 |
-
"loss": 0.
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
-
"epoch":
|
| 30 |
-
"learning_rate":
|
| 31 |
-
"loss": 0.
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
-
"epoch":
|
| 36 |
-
"learning_rate":
|
| 37 |
-
"loss": 0.
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
-
"epoch":
|
| 42 |
-
"learning_rate":
|
| 43 |
-
"loss": 0.
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
-
"epoch":
|
| 48 |
-
"learning_rate":
|
| 49 |
-
"loss": 0.
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
-
"epoch":
|
| 54 |
-
"learning_rate":
|
| 55 |
-
"loss": 0.
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
-
"epoch":
|
| 60 |
-
"learning_rate":
|
| 61 |
-
"loss": 0.
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
-
"epoch":
|
| 66 |
-
"learning_rate":
|
| 67 |
-
"loss": 0.
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
-
"epoch":
|
| 72 |
-
"learning_rate":
|
| 73 |
-
"loss": 0.
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"learning_rate":
|
| 79 |
-
"loss": 0.
|
| 80 |
"step": 6000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
-
"epoch":
|
| 84 |
-
"learning_rate":
|
| 85 |
-
"loss": 0.
|
| 86 |
"step": 6500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
-
"epoch":
|
| 90 |
-
"learning_rate":
|
| 91 |
-
"loss": 0.
|
| 92 |
"step": 7000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
-
"epoch":
|
| 96 |
-
"learning_rate":
|
| 97 |
-
"loss": 0.
|
| 98 |
"step": 7500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
-
"epoch":
|
| 102 |
-
"learning_rate":
|
| 103 |
-
"loss": 0.
|
| 104 |
"step": 8000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
-
"epoch":
|
| 108 |
-
"learning_rate":
|
| 109 |
-
"loss": 0.
|
| 110 |
"step": 8500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 500.0,
|
| 114 |
-
"
|
| 115 |
-
"
|
| 116 |
-
"
|
| 117 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
}
|
| 119 |
],
|
| 120 |
-
"max_steps":
|
| 121 |
-
"num_train_epochs":
|
| 122 |
-
"total_flos":
|
| 123 |
"trial_name": null,
|
| 124 |
"trial_params": null
|
| 125 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1500.0,
|
| 5 |
+
"global_step": 27000,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
| 9 |
"log_history": [
|
| 10 |
{
|
| 11 |
+
"epoch": 27.78,
|
| 12 |
+
"learning_rate": 9.814814814814815e-06,
|
| 13 |
+
"loss": 3.2486,
|
| 14 |
"step": 500
|
| 15 |
},
|
| 16 |
{
|
| 17 |
+
"epoch": 55.56,
|
| 18 |
+
"learning_rate": 9.62962962962963e-06,
|
| 19 |
+
"loss": 1.3764,
|
| 20 |
"step": 1000
|
| 21 |
},
|
| 22 |
{
|
| 23 |
+
"epoch": 83.33,
|
| 24 |
+
"learning_rate": 9.444444444444445e-06,
|
| 25 |
+
"loss": 0.5771,
|
| 26 |
"step": 1500
|
| 27 |
},
|
| 28 |
{
|
| 29 |
+
"epoch": 111.11,
|
| 30 |
+
"learning_rate": 9.25925925925926e-06,
|
| 31 |
+
"loss": 0.2647,
|
| 32 |
"step": 2000
|
| 33 |
},
|
| 34 |
{
|
| 35 |
+
"epoch": 138.89,
|
| 36 |
+
"learning_rate": 9.074074074074075e-06,
|
| 37 |
+
"loss": 0.1349,
|
| 38 |
"step": 2500
|
| 39 |
},
|
| 40 |
{
|
| 41 |
+
"epoch": 166.67,
|
| 42 |
+
"learning_rate": 8.888888888888888e-06,
|
| 43 |
+
"loss": 0.0852,
|
| 44 |
"step": 3000
|
| 45 |
},
|
| 46 |
{
|
| 47 |
+
"epoch": 194.44,
|
| 48 |
+
"learning_rate": 8.703703703703705e-06,
|
| 49 |
+
"loss": 0.0669,
|
| 50 |
"step": 3500
|
| 51 |
},
|
| 52 |
{
|
| 53 |
+
"epoch": 222.22,
|
| 54 |
+
"learning_rate": 8.518518518518519e-06,
|
| 55 |
+
"loss": 0.0575,
|
| 56 |
"step": 4000
|
| 57 |
},
|
| 58 |
{
|
| 59 |
+
"epoch": 250.0,
|
| 60 |
+
"learning_rate": 8.333333333333334e-06,
|
| 61 |
+
"loss": 0.0514,
|
| 62 |
"step": 4500
|
| 63 |
},
|
| 64 |
{
|
| 65 |
+
"epoch": 277.78,
|
| 66 |
+
"learning_rate": 8.148148148148148e-06,
|
| 67 |
+
"loss": 0.0477,
|
| 68 |
"step": 5000
|
| 69 |
},
|
| 70 |
{
|
| 71 |
+
"epoch": 305.56,
|
| 72 |
+
"learning_rate": 7.962962962962963e-06,
|
| 73 |
+
"loss": 0.0446,
|
| 74 |
"step": 5500
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 333.33,
|
| 78 |
+
"learning_rate": 7.77777777777778e-06,
|
| 79 |
+
"loss": 0.0428,
|
| 80 |
"step": 6000
|
| 81 |
},
|
| 82 |
{
|
| 83 |
+
"epoch": 361.11,
|
| 84 |
+
"learning_rate": 7.592592592592594e-06,
|
| 85 |
+
"loss": 0.0412,
|
| 86 |
"step": 6500
|
| 87 |
},
|
| 88 |
{
|
| 89 |
+
"epoch": 388.89,
|
| 90 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 91 |
+
"loss": 0.0401,
|
| 92 |
"step": 7000
|
| 93 |
},
|
| 94 |
{
|
| 95 |
+
"epoch": 416.67,
|
| 96 |
+
"learning_rate": 7.222222222222223e-06,
|
| 97 |
+
"loss": 0.0393,
|
| 98 |
"step": 7500
|
| 99 |
},
|
| 100 |
{
|
| 101 |
+
"epoch": 444.44,
|
| 102 |
+
"learning_rate": 7.0370370370370375e-06,
|
| 103 |
+
"loss": 0.0384,
|
| 104 |
"step": 8000
|
| 105 |
},
|
| 106 |
{
|
| 107 |
+
"epoch": 472.22,
|
| 108 |
+
"learning_rate": 6.851851851851853e-06,
|
| 109 |
+
"loss": 0.0376,
|
| 110 |
"step": 8500
|
| 111 |
},
|
| 112 |
{
|
| 113 |
"epoch": 500.0,
|
| 114 |
+
"learning_rate": 6.666666666666667e-06,
|
| 115 |
+
"loss": 0.037,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 527.78,
|
| 120 |
+
"learning_rate": 6.481481481481482e-06,
|
| 121 |
+
"loss": 0.0366,
|
| 122 |
+
"step": 9500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 555.56,
|
| 126 |
+
"learning_rate": 6.296296296296297e-06,
|
| 127 |
+
"loss": 0.0362,
|
| 128 |
+
"step": 10000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 583.33,
|
| 132 |
+
"learning_rate": 6.111111111111112e-06,
|
| 133 |
+
"loss": 0.0356,
|
| 134 |
+
"step": 10500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 611.11,
|
| 138 |
+
"learning_rate": 5.925925925925926e-06,
|
| 139 |
+
"loss": 0.0353,
|
| 140 |
+
"step": 11000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 638.89,
|
| 144 |
+
"learning_rate": 5.740740740740741e-06,
|
| 145 |
+
"loss": 0.0348,
|
| 146 |
+
"step": 11500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 666.67,
|
| 150 |
+
"learning_rate": 5.555555555555557e-06,
|
| 151 |
+
"loss": 0.0346,
|
| 152 |
+
"step": 12000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 694.44,
|
| 156 |
+
"learning_rate": 5.370370370370371e-06,
|
| 157 |
+
"loss": 0.0343,
|
| 158 |
+
"step": 12500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 722.22,
|
| 162 |
+
"learning_rate": 5.185185185185185e-06,
|
| 163 |
+
"loss": 0.0339,
|
| 164 |
+
"step": 13000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 750.0,
|
| 168 |
+
"learning_rate": 5e-06,
|
| 169 |
+
"loss": 0.0338,
|
| 170 |
+
"step": 13500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 777.78,
|
| 174 |
+
"learning_rate": 4.814814814814815e-06,
|
| 175 |
+
"loss": 0.0335,
|
| 176 |
+
"step": 14000
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 805.56,
|
| 180 |
+
"learning_rate": 4.62962962962963e-06,
|
| 181 |
+
"loss": 0.0335,
|
| 182 |
+
"step": 14500
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 833.33,
|
| 186 |
+
"learning_rate": 4.444444444444444e-06,
|
| 187 |
+
"loss": 0.0331,
|
| 188 |
+
"step": 15000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 861.11,
|
| 192 |
+
"learning_rate": 4.2592592592592596e-06,
|
| 193 |
+
"loss": 0.0329,
|
| 194 |
+
"step": 15500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 888.89,
|
| 198 |
+
"learning_rate": 4.074074074074074e-06,
|
| 199 |
+
"loss": 0.0327,
|
| 200 |
+
"step": 16000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 916.67,
|
| 204 |
+
"learning_rate": 3.88888888888889e-06,
|
| 205 |
+
"loss": 0.0325,
|
| 206 |
+
"step": 16500
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 944.44,
|
| 210 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 211 |
+
"loss": 0.0322,
|
| 212 |
+
"step": 17000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 972.22,
|
| 216 |
+
"learning_rate": 3.5185185185185187e-06,
|
| 217 |
+
"loss": 0.0323,
|
| 218 |
+
"step": 17500
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1000.0,
|
| 222 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 223 |
+
"loss": 0.032,
|
| 224 |
+
"step": 18000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1027.78,
|
| 228 |
+
"learning_rate": 3.1481481481481483e-06,
|
| 229 |
+
"loss": 0.0319,
|
| 230 |
+
"step": 18500
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1055.56,
|
| 234 |
+
"learning_rate": 2.962962962962963e-06,
|
| 235 |
+
"loss": 0.0316,
|
| 236 |
+
"step": 19000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1083.33,
|
| 240 |
+
"learning_rate": 2.7777777777777783e-06,
|
| 241 |
+
"loss": 0.0317,
|
| 242 |
+
"step": 19500
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1111.11,
|
| 246 |
+
"learning_rate": 2.5925925925925925e-06,
|
| 247 |
+
"loss": 0.0315,
|
| 248 |
+
"step": 20000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1138.89,
|
| 252 |
+
"learning_rate": 2.4074074074074075e-06,
|
| 253 |
+
"loss": 0.0313,
|
| 254 |
+
"step": 20500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1166.67,
|
| 258 |
+
"learning_rate": 2.222222222222222e-06,
|
| 259 |
+
"loss": 0.0312,
|
| 260 |
+
"step": 21000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1194.44,
|
| 264 |
+
"learning_rate": 2.037037037037037e-06,
|
| 265 |
+
"loss": 0.0312,
|
| 266 |
+
"step": 21500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1222.22,
|
| 270 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 271 |
+
"loss": 0.031,
|
| 272 |
+
"step": 22000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1250.0,
|
| 276 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 277 |
+
"loss": 0.031,
|
| 278 |
+
"step": 22500
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1277.78,
|
| 282 |
+
"learning_rate": 1.4814814814814815e-06,
|
| 283 |
+
"loss": 0.031,
|
| 284 |
+
"step": 23000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1305.56,
|
| 288 |
+
"learning_rate": 1.2962962962962962e-06,
|
| 289 |
+
"loss": 0.0308,
|
| 290 |
+
"step": 23500
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1333.33,
|
| 294 |
+
"learning_rate": 1.111111111111111e-06,
|
| 295 |
+
"loss": 0.0306,
|
| 296 |
+
"step": 24000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1361.11,
|
| 300 |
+
"learning_rate": 9.259259259259259e-07,
|
| 301 |
+
"loss": 0.0307,
|
| 302 |
+
"step": 24500
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1388.89,
|
| 306 |
+
"learning_rate": 7.407407407407407e-07,
|
| 307 |
+
"loss": 0.0306,
|
| 308 |
+
"step": 25000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1416.67,
|
| 312 |
+
"learning_rate": 5.555555555555555e-07,
|
| 313 |
+
"loss": 0.0306,
|
| 314 |
+
"step": 25500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1444.44,
|
| 318 |
+
"learning_rate": 3.7037037037037036e-07,
|
| 319 |
+
"loss": 0.0305,
|
| 320 |
+
"step": 26000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 1472.22,
|
| 324 |
+
"learning_rate": 1.8518518518518518e-07,
|
| 325 |
+
"loss": 0.0305,
|
| 326 |
+
"step": 26500
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1500.0,
|
| 330 |
+
"learning_rate": 0.0,
|
| 331 |
+
"loss": 0.0305,
|
| 332 |
+
"step": 27000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1500.0,
|
| 336 |
+
"step": 27000,
|
| 337 |
+
"total_flos": 1.8317092847616e+16,
|
| 338 |
+
"train_runtime": 3225.4397,
|
| 339 |
+
"train_samples_per_second": 8.371
|
| 340 |
}
|
| 341 |
],
|
| 342 |
+
"max_steps": 27000,
|
| 343 |
+
"num_train_epochs": 1500,
|
| 344 |
+
"total_flos": 1.8317092847616e+16,
|
| 345 |
"trial_name": null,
|
| 346 |
"trial_params": null
|
| 347 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2223
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cc08195dd90d5df8382410a4f5620699ec455e4a8a72b85641d3d471eeb800d
|
| 3 |
size 2223
|