Commit
·
a933c78
1
Parent(s):
3fc3558
Upload 24 files
Browse files- adapter_config.json +17 -0
- adapter_model.bin +3 -0
- checkpoint-200/adapter_config.json +17 -0
- checkpoint-200/adapter_model.bin +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/trainer_state.json +168 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-250/adapter_config.json +17 -0
- checkpoint-250/adapter_model.bin +3 -0
- checkpoint-250/optimizer.pt +3 -0
- checkpoint-250/rng_state.pth +3 -0
- checkpoint-250/scheduler.pt +3 -0
- checkpoint-250/trainer_state.json +206 -0
- checkpoint-250/training_args.bin +3 -0
- checkpoint-300/adapter_config.json +17 -0
- checkpoint-300/adapter_model.bin +3 -0
- checkpoint-300/optimizer.pt +3 -0
- checkpoint-300/rng_state.pth +3 -0
- checkpoint-300/scheduler.pt +3 -0
- checkpoint-300/trainer_state.json +244 -0
- checkpoint-300/training_args.bin +3 -0
- runs/Jun13_13-21-12_u06/events.out.tfevents.1686633673.u06 +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 8,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"q_proj",
|
| 14 |
+
"v_proj"
|
| 15 |
+
],
|
| 16 |
+
"task_type": "CAUSAL_LM"
|
| 17 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
|
| 3 |
+
size 443
|
checkpoint-200/adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 8,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"q_proj",
|
| 14 |
+
"v_proj"
|
| 15 |
+
],
|
| 16 |
+
"task_type": "CAUSAL_LM"
|
| 17 |
+
}
|
checkpoint-200/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
|
| 3 |
+
size 443
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7449b9cde9c4046ca58113a862b0712741674b598f9b693bf9bd8598a085e08
|
| 3 |
+
size 33661637
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:731b23b62c7b7bff5899a842746b91a2c9efc9e81885e9a1e5b09cd152fa13bd
|
| 3 |
+
size 14575
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:733b26a211b260ea1fd3d3e991e0540ad00853a1824d26da983ccafb09e98e4f
|
| 3 |
+
size 627
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8339892625808716,
|
| 3 |
+
"best_model_checkpoint": "/home/user/\u6587\u6863/wxai/experiments/checkpoint-200",
|
| 4 |
+
"epoch": 2.142618011382658,
|
| 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": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 3.3617,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 3.2014,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.8097,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 0.00011099999999999999,
|
| 31 |
+
"loss": 1.9747,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.54,
|
| 36 |
+
"learning_rate": 0.00014099999999999998,
|
| 37 |
+
"loss": 1.3605,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"eval_loss": 1.1962782144546509,
|
| 43 |
+
"eval_runtime": 10.2702,
|
| 44 |
+
"eval_samples_per_second": 19.474,
|
| 45 |
+
"eval_steps_per_second": 2.434,
|
| 46 |
+
"step": 50
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.64,
|
| 50 |
+
"learning_rate": 0.00017099999999999998,
|
| 51 |
+
"loss": 1.1582,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.75,
|
| 56 |
+
"learning_rate": 0.000201,
|
| 57 |
+
"loss": 1.1062,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.86,
|
| 62 |
+
"learning_rate": 0.00023099999999999998,
|
| 63 |
+
"loss": 1.0339,
|
| 64 |
+
"step": 80
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.96,
|
| 68 |
+
"learning_rate": 0.000261,
|
| 69 |
+
"loss": 1.0166,
|
| 70 |
+
"step": 90
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.07,
|
| 74 |
+
"learning_rate": 0.00029099999999999997,
|
| 75 |
+
"loss": 0.9421,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.07,
|
| 80 |
+
"eval_loss": 0.9122775197029114,
|
| 81 |
+
"eval_runtime": 10.2418,
|
| 82 |
+
"eval_samples_per_second": 19.528,
|
| 83 |
+
"eval_steps_per_second": 2.441,
|
| 84 |
+
"step": 100
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.18,
|
| 88 |
+
"learning_rate": 0.0002895,
|
| 89 |
+
"loss": 0.8986,
|
| 90 |
+
"step": 110
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.29,
|
| 94 |
+
"learning_rate": 0.0002745,
|
| 95 |
+
"loss": 0.8903,
|
| 96 |
+
"step": 120
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.39,
|
| 100 |
+
"learning_rate": 0.00025949999999999997,
|
| 101 |
+
"loss": 0.882,
|
| 102 |
+
"step": 130
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5,
|
| 106 |
+
"learning_rate": 0.0002445,
|
| 107 |
+
"loss": 0.8761,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.61,
|
| 112 |
+
"learning_rate": 0.0002295,
|
| 113 |
+
"loss": 0.8586,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.61,
|
| 118 |
+
"eval_loss": 0.8551507592201233,
|
| 119 |
+
"eval_runtime": 10.1562,
|
| 120 |
+
"eval_samples_per_second": 19.692,
|
| 121 |
+
"eval_steps_per_second": 2.462,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.71,
|
| 126 |
+
"learning_rate": 0.00021449999999999998,
|
| 127 |
+
"loss": 0.8669,
|
| 128 |
+
"step": 160
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.82,
|
| 132 |
+
"learning_rate": 0.0001995,
|
| 133 |
+
"loss": 0.8369,
|
| 134 |
+
"step": 170
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.93,
|
| 138 |
+
"learning_rate": 0.00018449999999999999,
|
| 139 |
+
"loss": 0.8409,
|
| 140 |
+
"step": 180
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.04,
|
| 144 |
+
"learning_rate": 0.00016949999999999997,
|
| 145 |
+
"loss": 0.8441,
|
| 146 |
+
"step": 190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.14,
|
| 150 |
+
"learning_rate": 0.0001545,
|
| 151 |
+
"loss": 0.8306,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.14,
|
| 156 |
+
"eval_loss": 0.8339892625808716,
|
| 157 |
+
"eval_runtime": 10.1994,
|
| 158 |
+
"eval_samples_per_second": 19.609,
|
| 159 |
+
"eval_steps_per_second": 2.451,
|
| 160 |
+
"step": 200
|
| 161 |
+
}
|
| 162 |
+
],
|
| 163 |
+
"max_steps": 300,
|
| 164 |
+
"num_train_epochs": 4,
|
| 165 |
+
"total_flos": 1.3939195313651712e+17,
|
| 166 |
+
"trial_name": null,
|
| 167 |
+
"trial_params": null
|
| 168 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dca6b194fe33dff64e1bc732ad0af7b76a5fa6005971f28bdc40c57e679fcef
|
| 3 |
+
size 3963
|
checkpoint-250/adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 8,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"q_proj",
|
| 14 |
+
"v_proj"
|
| 15 |
+
],
|
| 16 |
+
"task_type": "CAUSAL_LM"
|
| 17 |
+
}
|
checkpoint-250/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
|
| 3 |
+
size 443
|
checkpoint-250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e43f4b942bfdb265f362a66299f7e26ec81070f466c9bba80efc13c0605276c7
|
| 3 |
+
size 33661637
|
checkpoint-250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:93414ca5509297b3f0f013e9f469d53fde029ae8b842954fbb3cc7e81c2791cf
|
| 3 |
+
size 14575
|
checkpoint-250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a93cc0be32e01f149c701aaba527e3d707dabc0197a8fb87648c36a36633978
|
| 3 |
+
size 627
|
checkpoint-250/trainer_state.json
ADDED
|
@@ -0,0 +1,206 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.823204755783081,
|
| 3 |
+
"best_model_checkpoint": "/home/user/\u6587\u6863/wxai/experiments/checkpoint-250",
|
| 4 |
+
"epoch": 2.678272514228323,
|
| 5 |
+
"global_step": 250,
|
| 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": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 3.3617,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 3.2014,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.8097,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 0.00011099999999999999,
|
| 31 |
+
"loss": 1.9747,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.54,
|
| 36 |
+
"learning_rate": 0.00014099999999999998,
|
| 37 |
+
"loss": 1.3605,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"eval_loss": 1.1962782144546509,
|
| 43 |
+
"eval_runtime": 10.2702,
|
| 44 |
+
"eval_samples_per_second": 19.474,
|
| 45 |
+
"eval_steps_per_second": 2.434,
|
| 46 |
+
"step": 50
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.64,
|
| 50 |
+
"learning_rate": 0.00017099999999999998,
|
| 51 |
+
"loss": 1.1582,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.75,
|
| 56 |
+
"learning_rate": 0.000201,
|
| 57 |
+
"loss": 1.1062,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.86,
|
| 62 |
+
"learning_rate": 0.00023099999999999998,
|
| 63 |
+
"loss": 1.0339,
|
| 64 |
+
"step": 80
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.96,
|
| 68 |
+
"learning_rate": 0.000261,
|
| 69 |
+
"loss": 1.0166,
|
| 70 |
+
"step": 90
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.07,
|
| 74 |
+
"learning_rate": 0.00029099999999999997,
|
| 75 |
+
"loss": 0.9421,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.07,
|
| 80 |
+
"eval_loss": 0.9122775197029114,
|
| 81 |
+
"eval_runtime": 10.2418,
|
| 82 |
+
"eval_samples_per_second": 19.528,
|
| 83 |
+
"eval_steps_per_second": 2.441,
|
| 84 |
+
"step": 100
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.18,
|
| 88 |
+
"learning_rate": 0.0002895,
|
| 89 |
+
"loss": 0.8986,
|
| 90 |
+
"step": 110
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.29,
|
| 94 |
+
"learning_rate": 0.0002745,
|
| 95 |
+
"loss": 0.8903,
|
| 96 |
+
"step": 120
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.39,
|
| 100 |
+
"learning_rate": 0.00025949999999999997,
|
| 101 |
+
"loss": 0.882,
|
| 102 |
+
"step": 130
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5,
|
| 106 |
+
"learning_rate": 0.0002445,
|
| 107 |
+
"loss": 0.8761,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.61,
|
| 112 |
+
"learning_rate": 0.0002295,
|
| 113 |
+
"loss": 0.8586,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.61,
|
| 118 |
+
"eval_loss": 0.8551507592201233,
|
| 119 |
+
"eval_runtime": 10.1562,
|
| 120 |
+
"eval_samples_per_second": 19.692,
|
| 121 |
+
"eval_steps_per_second": 2.462,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.71,
|
| 126 |
+
"learning_rate": 0.00021449999999999998,
|
| 127 |
+
"loss": 0.8669,
|
| 128 |
+
"step": 160
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.82,
|
| 132 |
+
"learning_rate": 0.0001995,
|
| 133 |
+
"loss": 0.8369,
|
| 134 |
+
"step": 170
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.93,
|
| 138 |
+
"learning_rate": 0.00018449999999999999,
|
| 139 |
+
"loss": 0.8409,
|
| 140 |
+
"step": 180
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.04,
|
| 144 |
+
"learning_rate": 0.00016949999999999997,
|
| 145 |
+
"loss": 0.8441,
|
| 146 |
+
"step": 190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.14,
|
| 150 |
+
"learning_rate": 0.0001545,
|
| 151 |
+
"loss": 0.8306,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.14,
|
| 156 |
+
"eval_loss": 0.8339892625808716,
|
| 157 |
+
"eval_runtime": 10.1994,
|
| 158 |
+
"eval_samples_per_second": 19.609,
|
| 159 |
+
"eval_steps_per_second": 2.451,
|
| 160 |
+
"step": 200
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.25,
|
| 164 |
+
"learning_rate": 0.0001395,
|
| 165 |
+
"loss": 0.8388,
|
| 166 |
+
"step": 210
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.36,
|
| 170 |
+
"learning_rate": 0.0001245,
|
| 171 |
+
"loss": 0.8285,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.46,
|
| 176 |
+
"learning_rate": 0.00010949999999999999,
|
| 177 |
+
"loss": 0.8428,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.57,
|
| 182 |
+
"learning_rate": 9.449999999999999e-05,
|
| 183 |
+
"loss": 0.8116,
|
| 184 |
+
"step": 240
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.68,
|
| 188 |
+
"learning_rate": 7.95e-05,
|
| 189 |
+
"loss": 0.8109,
|
| 190 |
+
"step": 250
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.68,
|
| 194 |
+
"eval_loss": 0.823204755783081,
|
| 195 |
+
"eval_runtime": 10.1897,
|
| 196 |
+
"eval_samples_per_second": 19.628,
|
| 197 |
+
"eval_steps_per_second": 2.453,
|
| 198 |
+
"step": 250
|
| 199 |
+
}
|
| 200 |
+
],
|
| 201 |
+
"max_steps": 300,
|
| 202 |
+
"num_train_epochs": 4,
|
| 203 |
+
"total_flos": 1.7425390498873344e+17,
|
| 204 |
+
"trial_name": null,
|
| 205 |
+
"trial_params": null
|
| 206 |
+
}
|
checkpoint-250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dca6b194fe33dff64e1bc732ad0af7b76a5fa6005971f28bdc40c57e679fcef
|
| 3 |
+
size 3963
|
checkpoint-300/adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"modules_to_save": null,
|
| 10 |
+
"peft_type": "LORA",
|
| 11 |
+
"r": 8,
|
| 12 |
+
"target_modules": [
|
| 13 |
+
"q_proj",
|
| 14 |
+
"v_proj"
|
| 15 |
+
],
|
| 16 |
+
"task_type": "CAUSAL_LM"
|
| 17 |
+
}
|
checkpoint-300/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5e1621f48d9ad8feb1d6d31050275f0aafd080c5c07153301fe2f48411f4406
|
| 3 |
+
size 443
|
checkpoint-300/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89d15d7f18a8728bcea5fec6196b20919f8b7a5bdeb12fcef05d1ee3bdc2189f
|
| 3 |
+
size 33661637
|
checkpoint-300/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad259645b5c784a0dff5bf576951a8a2d7330bead065328d556e759d0f0b7d77
|
| 3 |
+
size 14575
|
checkpoint-300/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91282cdc194ccfea92191c2ef14e9f21cca2b690f6095e9ad447fd4cded1beec
|
| 3 |
+
size 627
|
checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,244 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8181629776954651,
|
| 3 |
+
"best_model_checkpoint": "/home/user/\u6587\u6863/wxai/experiments/checkpoint-300",
|
| 4 |
+
"epoch": 3.213927017073987,
|
| 5 |
+
"global_step": 300,
|
| 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": 2.9999999999999997e-05,
|
| 13 |
+
"loss": 3.3617,
|
| 14 |
+
"step": 10
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.21,
|
| 18 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 19 |
+
"loss": 3.2014,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.32,
|
| 24 |
+
"learning_rate": 8.999999999999999e-05,
|
| 25 |
+
"loss": 2.8097,
|
| 26 |
+
"step": 30
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.43,
|
| 30 |
+
"learning_rate": 0.00011099999999999999,
|
| 31 |
+
"loss": 1.9747,
|
| 32 |
+
"step": 40
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.54,
|
| 36 |
+
"learning_rate": 0.00014099999999999998,
|
| 37 |
+
"loss": 1.3605,
|
| 38 |
+
"step": 50
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.54,
|
| 42 |
+
"eval_loss": 1.1962782144546509,
|
| 43 |
+
"eval_runtime": 10.2702,
|
| 44 |
+
"eval_samples_per_second": 19.474,
|
| 45 |
+
"eval_steps_per_second": 2.434,
|
| 46 |
+
"step": 50
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.64,
|
| 50 |
+
"learning_rate": 0.00017099999999999998,
|
| 51 |
+
"loss": 1.1582,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.75,
|
| 56 |
+
"learning_rate": 0.000201,
|
| 57 |
+
"loss": 1.1062,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.86,
|
| 62 |
+
"learning_rate": 0.00023099999999999998,
|
| 63 |
+
"loss": 1.0339,
|
| 64 |
+
"step": 80
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.96,
|
| 68 |
+
"learning_rate": 0.000261,
|
| 69 |
+
"loss": 1.0166,
|
| 70 |
+
"step": 90
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.07,
|
| 74 |
+
"learning_rate": 0.00029099999999999997,
|
| 75 |
+
"loss": 0.9421,
|
| 76 |
+
"step": 100
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 1.07,
|
| 80 |
+
"eval_loss": 0.9122775197029114,
|
| 81 |
+
"eval_runtime": 10.2418,
|
| 82 |
+
"eval_samples_per_second": 19.528,
|
| 83 |
+
"eval_steps_per_second": 2.441,
|
| 84 |
+
"step": 100
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.18,
|
| 88 |
+
"learning_rate": 0.0002895,
|
| 89 |
+
"loss": 0.8986,
|
| 90 |
+
"step": 110
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.29,
|
| 94 |
+
"learning_rate": 0.0002745,
|
| 95 |
+
"loss": 0.8903,
|
| 96 |
+
"step": 120
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 1.39,
|
| 100 |
+
"learning_rate": 0.00025949999999999997,
|
| 101 |
+
"loss": 0.882,
|
| 102 |
+
"step": 130
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 1.5,
|
| 106 |
+
"learning_rate": 0.0002445,
|
| 107 |
+
"loss": 0.8761,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.61,
|
| 112 |
+
"learning_rate": 0.0002295,
|
| 113 |
+
"loss": 0.8586,
|
| 114 |
+
"step": 150
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.61,
|
| 118 |
+
"eval_loss": 0.8551507592201233,
|
| 119 |
+
"eval_runtime": 10.1562,
|
| 120 |
+
"eval_samples_per_second": 19.692,
|
| 121 |
+
"eval_steps_per_second": 2.462,
|
| 122 |
+
"step": 150
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.71,
|
| 126 |
+
"learning_rate": 0.00021449999999999998,
|
| 127 |
+
"loss": 0.8669,
|
| 128 |
+
"step": 160
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.82,
|
| 132 |
+
"learning_rate": 0.0001995,
|
| 133 |
+
"loss": 0.8369,
|
| 134 |
+
"step": 170
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.93,
|
| 138 |
+
"learning_rate": 0.00018449999999999999,
|
| 139 |
+
"loss": 0.8409,
|
| 140 |
+
"step": 180
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 2.04,
|
| 144 |
+
"learning_rate": 0.00016949999999999997,
|
| 145 |
+
"loss": 0.8441,
|
| 146 |
+
"step": 190
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 2.14,
|
| 150 |
+
"learning_rate": 0.0001545,
|
| 151 |
+
"loss": 0.8306,
|
| 152 |
+
"step": 200
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.14,
|
| 156 |
+
"eval_loss": 0.8339892625808716,
|
| 157 |
+
"eval_runtime": 10.1994,
|
| 158 |
+
"eval_samples_per_second": 19.609,
|
| 159 |
+
"eval_steps_per_second": 2.451,
|
| 160 |
+
"step": 200
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 2.25,
|
| 164 |
+
"learning_rate": 0.0001395,
|
| 165 |
+
"loss": 0.8388,
|
| 166 |
+
"step": 210
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.36,
|
| 170 |
+
"learning_rate": 0.0001245,
|
| 171 |
+
"loss": 0.8285,
|
| 172 |
+
"step": 220
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.46,
|
| 176 |
+
"learning_rate": 0.00010949999999999999,
|
| 177 |
+
"loss": 0.8428,
|
| 178 |
+
"step": 230
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.57,
|
| 182 |
+
"learning_rate": 9.449999999999999e-05,
|
| 183 |
+
"loss": 0.8116,
|
| 184 |
+
"step": 240
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 2.68,
|
| 188 |
+
"learning_rate": 7.95e-05,
|
| 189 |
+
"loss": 0.8109,
|
| 190 |
+
"step": 250
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 2.68,
|
| 194 |
+
"eval_loss": 0.823204755783081,
|
| 195 |
+
"eval_runtime": 10.1897,
|
| 196 |
+
"eval_samples_per_second": 19.628,
|
| 197 |
+
"eval_steps_per_second": 2.453,
|
| 198 |
+
"step": 250
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 2.79,
|
| 202 |
+
"learning_rate": 6.45e-05,
|
| 203 |
+
"loss": 0.8487,
|
| 204 |
+
"step": 260
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 2.89,
|
| 208 |
+
"learning_rate": 4.95e-05,
|
| 209 |
+
"loss": 0.8112,
|
| 210 |
+
"step": 270
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 3.0,
|
| 214 |
+
"learning_rate": 3.45e-05,
|
| 215 |
+
"loss": 0.8179,
|
| 216 |
+
"step": 280
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 3.11,
|
| 220 |
+
"learning_rate": 1.95e-05,
|
| 221 |
+
"loss": 0.8083,
|
| 222 |
+
"step": 290
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 3.21,
|
| 226 |
+
"learning_rate": 4.499999999999999e-06,
|
| 227 |
+
"loss": 0.8288,
|
| 228 |
+
"step": 300
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 3.21,
|
| 232 |
+
"eval_loss": 0.8181629776954651,
|
| 233 |
+
"eval_runtime": 10.2544,
|
| 234 |
+
"eval_samples_per_second": 19.504,
|
| 235 |
+
"eval_steps_per_second": 2.438,
|
| 236 |
+
"step": 300
|
| 237 |
+
}
|
| 238 |
+
],
|
| 239 |
+
"max_steps": 300,
|
| 240 |
+
"num_train_epochs": 4,
|
| 241 |
+
"total_flos": 2.0900668712681472e+17,
|
| 242 |
+
"trial_name": null,
|
| 243 |
+
"trial_params": null
|
| 244 |
+
}
|
checkpoint-300/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3dca6b194fe33dff64e1bc732ad0af7b76a5fa6005971f28bdc40c57e679fcef
|
| 3 |
+
size 3963
|
runs/Jun13_13-21-12_u06/events.out.tfevents.1686633673.u06
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71c414fec7fea7e4c3d8047aa32ad38fc9543e5b4b0d401aee3563d1b9f78f35
|
| 3 |
+
size 10968
|