initial
Browse files- output/adapter_config.json +19 -0
- output/adapter_model.bin +3 -0
- output/checkpoint-200/optimizer.pt +3 -0
- output/checkpoint-200/pytorch_model.bin +3 -0
- output/checkpoint-200/rng_state.pth +3 -0
- output/checkpoint-200/scaler.pt +3 -0
- output/checkpoint-200/scheduler.pt +3 -0
- output/checkpoint-200/trainer_state.json +144 -0
- output/checkpoint-200/training_args.bin +3 -0
- output/checkpoint-400/optimizer.pt +3 -0
- output/checkpoint-400/pytorch_model.bin +3 -0
- output/checkpoint-400/rng_state.pth +3 -0
- output/checkpoint-400/scaler.pt +3 -0
- output/checkpoint-400/scheduler.pt +3 -0
- output/checkpoint-400/trainer_state.json +272 -0
- output/checkpoint-400/training_args.bin +3 -0
output/adapter_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"v_proj"
|
| 17 |
+
],
|
| 18 |
+
"task_type": "CAUSAL_LM"
|
| 19 |
+
}
|
output/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:264ddd3f28010ed2b3694ad851bfabf22177a5f2dd3bc83d3559e4957795916d
|
| 3 |
+
size 16822989
|
output/checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63c42f5446e07f8fdaa2033bf0d8f37570b439506b8ad6642138c012304b787d
|
| 3 |
+
size 33661573
|
output/checkpoint-200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71b2505f42aa0ff61b4406a8139865c60599c0c4077ef16f301ee4e04a855d4a
|
| 3 |
+
size 16822989
|
output/checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:601d4500e39cb956c51c0f30a51406f3b11a9e8229a2f77210205587ec4663b2
|
| 3 |
+
size 14575
|
output/checkpoint-200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fccf0f9be1bb8f24861e4393745b3e09cc2687125a69e3757955fb0f0925ea5
|
| 3 |
+
size 557
|
output/checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5847d9cb02afd98e15bd9d3c1a9609ab5d64f04e31347c2e0420149d64790a46
|
| 3 |
+
size 627
|
output/checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,144 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4859355092048645,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-200",
|
| 4 |
+
"epoch": 2.1498152502519314,
|
| 5 |
+
"global_step": 200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 1.5355,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 1e-05,
|
| 19 |
+
"loss": 1.5218,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 1.5e-05,
|
| 25 |
+
"loss": 1.4822,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 2e-05,
|
| 31 |
+
"loss": 1.4292,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.54,
|
| 36 |
+
"learning_rate": 2.5e-05,
|
| 37 |
+
"loss": 1.3539,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.64,
|
| 42 |
+
"learning_rate": 3e-05,
|
| 43 |
+
"loss": 1.2282,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.75,
|
| 48 |
+
"learning_rate": 3.5e-05,
|
| 49 |
+
"loss": 1.0398,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.86,
|
| 54 |
+
"learning_rate": 4e-05,
|
| 55 |
+
"loss": 0.8365,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.97,
|
| 60 |
+
"learning_rate": 4.5e-05,
|
| 61 |
+
"loss": 0.6591,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.07,
|
| 66 |
+
"learning_rate": 5e-05,
|
| 67 |
+
"loss": 0.5647,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.18,
|
| 72 |
+
"learning_rate": 4.863013698630137e-05,
|
| 73 |
+
"loss": 0.5343,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.29,
|
| 78 |
+
"learning_rate": 4.726027397260274e-05,
|
| 79 |
+
"loss": 0.5249,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.4,
|
| 84 |
+
"learning_rate": 4.589041095890411e-05,
|
| 85 |
+
"loss": 0.5126,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.5,
|
| 90 |
+
"learning_rate": 4.452054794520548e-05,
|
| 91 |
+
"loss": 0.5099,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.61,
|
| 96 |
+
"learning_rate": 4.3150684931506855e-05,
|
| 97 |
+
"loss": 0.5067,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.72,
|
| 102 |
+
"learning_rate": 4.1780821917808224e-05,
|
| 103 |
+
"loss": 0.5047,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.83,
|
| 108 |
+
"learning_rate": 4.041095890410959e-05,
|
| 109 |
+
"loss": 0.4949,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.93,
|
| 114 |
+
"learning_rate": 3.904109589041096e-05,
|
| 115 |
+
"loss": 0.4961,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.04,
|
| 120 |
+
"learning_rate": 3.767123287671233e-05,
|
| 121 |
+
"loss": 0.4933,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.15,
|
| 126 |
+
"learning_rate": 3.63013698630137e-05,
|
| 127 |
+
"loss": 0.488,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.15,
|
| 132 |
+
"eval_loss": 0.4859355092048645,
|
| 133 |
+
"eval_runtime": 182.5747,
|
| 134 |
+
"eval_samples_per_second": 10.954,
|
| 135 |
+
"eval_steps_per_second": 1.369,
|
| 136 |
+
"step": 200
|
| 137 |
+
}
|
| 138 |
+
],
|
| 139 |
+
"max_steps": 465,
|
| 140 |
+
"num_train_epochs": 5,
|
| 141 |
+
"total_flos": 1.0396612701664051e+18,
|
| 142 |
+
"trial_name": null,
|
| 143 |
+
"trial_params": null
|
| 144 |
+
}
|
output/checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffa36d102a7c05bde31c70e8c3969cc59f38e6bbea8fa02842c42b16923b4cbe
|
| 3 |
+
size 3899
|
output/checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79eaea366a249efe8d0f6ce8b45c1d0632cd88cca387bfe5d8fb0dad8038173f
|
| 3 |
+
size 33661573
|
output/checkpoint-400/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d83107d6383e8e913fd506b45b52b5e8aec39ed53f3355232c01818e1f9267bf
|
| 3 |
+
size 16822989
|
output/checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e1d4cf89ceee65d888e964ca4066fc976bb2f8e750e435b6eb2d1e97d43ca0f
|
| 3 |
+
size 14575
|
output/checkpoint-400/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc40a4be6a52cee4d7658df4041e660ffa02b0d8b5bd143bb8bb397f7b71b1a5
|
| 3 |
+
size 557
|
output/checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:738a2afbc585e0ae0fb6c994dcc0db2ea2a077e0ec8539560958f8a2dfc96a47
|
| 3 |
+
size 627
|
output/checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,272 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.4640955328941345,
|
| 3 |
+
"best_model_checkpoint": "./output/checkpoint-400",
|
| 4 |
+
"epoch": 4.299630500503863,
|
| 5 |
+
"global_step": 400,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.11,
|
| 12 |
+
"learning_rate": 5e-06,
|
| 13 |
+
"loss": 1.5355,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 1e-05,
|
| 19 |
+
"loss": 1.5218,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 1.5e-05,
|
| 25 |
+
"loss": 1.4822,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 2e-05,
|
| 31 |
+
"loss": 1.4292,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.54,
|
| 36 |
+
"learning_rate": 2.5e-05,
|
| 37 |
+
"loss": 1.3539,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.64,
|
| 42 |
+
"learning_rate": 3e-05,
|
| 43 |
+
"loss": 1.2282,
|
| 44 |
+
"step": 60
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.75,
|
| 48 |
+
"learning_rate": 3.5e-05,
|
| 49 |
+
"loss": 1.0398,
|
| 50 |
+
"step": 70
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.86,
|
| 54 |
+
"learning_rate": 4e-05,
|
| 55 |
+
"loss": 0.8365,
|
| 56 |
+
"step": 80
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.97,
|
| 60 |
+
"learning_rate": 4.5e-05,
|
| 61 |
+
"loss": 0.6591,
|
| 62 |
+
"step": 90
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 1.07,
|
| 66 |
+
"learning_rate": 5e-05,
|
| 67 |
+
"loss": 0.5647,
|
| 68 |
+
"step": 100
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 1.18,
|
| 72 |
+
"learning_rate": 4.863013698630137e-05,
|
| 73 |
+
"loss": 0.5343,
|
| 74 |
+
"step": 110
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 1.29,
|
| 78 |
+
"learning_rate": 4.726027397260274e-05,
|
| 79 |
+
"loss": 0.5249,
|
| 80 |
+
"step": 120
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.4,
|
| 84 |
+
"learning_rate": 4.589041095890411e-05,
|
| 85 |
+
"loss": 0.5126,
|
| 86 |
+
"step": 130
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 1.5,
|
| 90 |
+
"learning_rate": 4.452054794520548e-05,
|
| 91 |
+
"loss": 0.5099,
|
| 92 |
+
"step": 140
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 1.61,
|
| 96 |
+
"learning_rate": 4.3150684931506855e-05,
|
| 97 |
+
"loss": 0.5067,
|
| 98 |
+
"step": 150
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.72,
|
| 102 |
+
"learning_rate": 4.1780821917808224e-05,
|
| 103 |
+
"loss": 0.5047,
|
| 104 |
+
"step": 160
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.83,
|
| 108 |
+
"learning_rate": 4.041095890410959e-05,
|
| 109 |
+
"loss": 0.4949,
|
| 110 |
+
"step": 170
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.93,
|
| 114 |
+
"learning_rate": 3.904109589041096e-05,
|
| 115 |
+
"loss": 0.4961,
|
| 116 |
+
"step": 180
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.04,
|
| 120 |
+
"learning_rate": 3.767123287671233e-05,
|
| 121 |
+
"loss": 0.4933,
|
| 122 |
+
"step": 190
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 2.15,
|
| 126 |
+
"learning_rate": 3.63013698630137e-05,
|
| 127 |
+
"loss": 0.488,
|
| 128 |
+
"step": 200
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 2.15,
|
| 132 |
+
"eval_loss": 0.4859355092048645,
|
| 133 |
+
"eval_runtime": 182.5747,
|
| 134 |
+
"eval_samples_per_second": 10.954,
|
| 135 |
+
"eval_steps_per_second": 1.369,
|
| 136 |
+
"step": 200
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 2.26,
|
| 140 |
+
"learning_rate": 3.493150684931507e-05,
|
| 141 |
+
"loss": 0.4836,
|
| 142 |
+
"step": 210
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 2.36,
|
| 146 |
+
"learning_rate": 3.356164383561644e-05,
|
| 147 |
+
"loss": 0.4798,
|
| 148 |
+
"step": 220
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 2.47,
|
| 152 |
+
"learning_rate": 3.219178082191781e-05,
|
| 153 |
+
"loss": 0.4815,
|
| 154 |
+
"step": 230
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 2.58,
|
| 158 |
+
"learning_rate": 3.082191780821918e-05,
|
| 159 |
+
"loss": 0.4738,
|
| 160 |
+
"step": 240
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.69,
|
| 164 |
+
"learning_rate": 2.945205479452055e-05,
|
| 165 |
+
"loss": 0.4751,
|
| 166 |
+
"step": 250
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.79,
|
| 170 |
+
"learning_rate": 2.808219178082192e-05,
|
| 171 |
+
"loss": 0.4771,
|
| 172 |
+
"step": 260
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.9,
|
| 176 |
+
"learning_rate": 2.671232876712329e-05,
|
| 177 |
+
"loss": 0.4767,
|
| 178 |
+
"step": 270
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 3.01,
|
| 182 |
+
"learning_rate": 2.534246575342466e-05,
|
| 183 |
+
"loss": 0.4756,
|
| 184 |
+
"step": 280
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 3.12,
|
| 188 |
+
"learning_rate": 2.3972602739726026e-05,
|
| 189 |
+
"loss": 0.4681,
|
| 190 |
+
"step": 290
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 3.22,
|
| 194 |
+
"learning_rate": 2.2602739726027396e-05,
|
| 195 |
+
"loss": 0.4707,
|
| 196 |
+
"step": 300
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 3.33,
|
| 200 |
+
"learning_rate": 2.1232876712328768e-05,
|
| 201 |
+
"loss": 0.4704,
|
| 202 |
+
"step": 310
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 3.44,
|
| 206 |
+
"learning_rate": 1.9863013698630137e-05,
|
| 207 |
+
"loss": 0.4677,
|
| 208 |
+
"step": 320
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 3.55,
|
| 212 |
+
"learning_rate": 1.8493150684931506e-05,
|
| 213 |
+
"loss": 0.4676,
|
| 214 |
+
"step": 330
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 3.65,
|
| 218 |
+
"learning_rate": 1.7123287671232875e-05,
|
| 219 |
+
"loss": 0.4659,
|
| 220 |
+
"step": 340
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.76,
|
| 224 |
+
"learning_rate": 1.5753424657534248e-05,
|
| 225 |
+
"loss": 0.4717,
|
| 226 |
+
"step": 350
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 3.87,
|
| 230 |
+
"learning_rate": 1.4383561643835617e-05,
|
| 231 |
+
"loss": 0.4679,
|
| 232 |
+
"step": 360
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 3.98,
|
| 236 |
+
"learning_rate": 1.3013698630136986e-05,
|
| 237 |
+
"loss": 0.466,
|
| 238 |
+
"step": 370
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 4.08,
|
| 242 |
+
"learning_rate": 1.1643835616438355e-05,
|
| 243 |
+
"loss": 0.4644,
|
| 244 |
+
"step": 380
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 4.19,
|
| 248 |
+
"learning_rate": 1.0273972602739726e-05,
|
| 249 |
+
"loss": 0.4671,
|
| 250 |
+
"step": 390
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 4.3,
|
| 254 |
+
"learning_rate": 8.904109589041095e-06,
|
| 255 |
+
"loss": 0.4649,
|
| 256 |
+
"step": 400
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 4.3,
|
| 260 |
+
"eval_loss": 0.4640955328941345,
|
| 261 |
+
"eval_runtime": 182.5257,
|
| 262 |
+
"eval_samples_per_second": 10.957,
|
| 263 |
+
"eval_steps_per_second": 1.37,
|
| 264 |
+
"step": 400
|
| 265 |
+
}
|
| 266 |
+
],
|
| 267 |
+
"max_steps": 465,
|
| 268 |
+
"num_train_epochs": 5,
|
| 269 |
+
"total_flos": 2.0793225403328102e+18,
|
| 270 |
+
"trial_name": null,
|
| 271 |
+
"trial_params": null
|
| 272 |
+
}
|
output/checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffa36d102a7c05bde31c70e8c3969cc59f38e6bbea8fa02842c42b16923b4cbe
|
| 3 |
+
size 3899
|