Upload 5 files
Browse files- adapter_config.json +33 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +721 -0
- training_args.bin +3 -0
adapter_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"loftq_config": {},
|
| 12 |
+
"lora_alpha": 64,
|
| 13 |
+
"lora_dropout": 0.05,
|
| 14 |
+
"megatron_config": null,
|
| 15 |
+
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": null,
|
| 17 |
+
"peft_type": "LORA",
|
| 18 |
+
"r": 32,
|
| 19 |
+
"rank_pattern": {},
|
| 20 |
+
"revision": null,
|
| 21 |
+
"target_modules": [
|
| 22 |
+
"v_proj",
|
| 23 |
+
"q_proj",
|
| 24 |
+
"lm_head",
|
| 25 |
+
"gate_proj",
|
| 26 |
+
"down_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"up_proj",
|
| 29 |
+
"k_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_rslora": false
|
| 33 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e646c3c60be9f9d0390eba60877ae652229498ca223b126aebe5237f29c0e29c
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d8ed7d32f13e74eb5c3b270f8c3cf2ad917106f8837b4c8fd4c8a6596d14162
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 6.666666666666667,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.13,
|
| 13 |
+
"learning_rate": 4.9198396793587176e-05,
|
| 14 |
+
"loss": 1.4613,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.13,
|
| 19 |
+
"eval_loss": 1.749655842781067,
|
| 20 |
+
"eval_runtime": 9.1057,
|
| 21 |
+
"eval_samples_per_second": 0.988,
|
| 22 |
+
"eval_steps_per_second": 0.22,
|
| 23 |
+
"step": 10
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.27,
|
| 27 |
+
"learning_rate": 4.829659318637275e-05,
|
| 28 |
+
"loss": 0.8073,
|
| 29 |
+
"step": 20
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.27,
|
| 33 |
+
"eval_loss": 1.7181354761123657,
|
| 34 |
+
"eval_runtime": 9.0405,
|
| 35 |
+
"eval_samples_per_second": 0.996,
|
| 36 |
+
"eval_steps_per_second": 0.221,
|
| 37 |
+
"step": 20
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.4,
|
| 41 |
+
"learning_rate": 4.7294589178356715e-05,
|
| 42 |
+
"loss": 0.5993,
|
| 43 |
+
"step": 30
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 0.4,
|
| 47 |
+
"eval_loss": 1.6926982402801514,
|
| 48 |
+
"eval_runtime": 9.0635,
|
| 49 |
+
"eval_samples_per_second": 0.993,
|
| 50 |
+
"eval_steps_per_second": 0.221,
|
| 51 |
+
"step": 30
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.53,
|
| 55 |
+
"learning_rate": 4.629258517034069e-05,
|
| 56 |
+
"loss": 0.5535,
|
| 57 |
+
"step": 40
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.53,
|
| 61 |
+
"eval_loss": 1.5878939628601074,
|
| 62 |
+
"eval_runtime": 9.0858,
|
| 63 |
+
"eval_samples_per_second": 0.991,
|
| 64 |
+
"eval_steps_per_second": 0.22,
|
| 65 |
+
"step": 40
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.67,
|
| 69 |
+
"learning_rate": 4.529058116232465e-05,
|
| 70 |
+
"loss": 0.4914,
|
| 71 |
+
"step": 50
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.67,
|
| 75 |
+
"eval_loss": 1.6263775825500488,
|
| 76 |
+
"eval_runtime": 9.0441,
|
| 77 |
+
"eval_samples_per_second": 0.995,
|
| 78 |
+
"eval_steps_per_second": 0.221,
|
| 79 |
+
"step": 50
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.8,
|
| 83 |
+
"learning_rate": 4.428857715430862e-05,
|
| 84 |
+
"loss": 0.3532,
|
| 85 |
+
"step": 60
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.8,
|
| 89 |
+
"eval_loss": 1.5376472473144531,
|
| 90 |
+
"eval_runtime": 9.0097,
|
| 91 |
+
"eval_samples_per_second": 0.999,
|
| 92 |
+
"eval_steps_per_second": 0.222,
|
| 93 |
+
"step": 60
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.93,
|
| 97 |
+
"learning_rate": 4.3286573146292584e-05,
|
| 98 |
+
"loss": 0.3079,
|
| 99 |
+
"step": 70
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.93,
|
| 103 |
+
"eval_loss": 1.50021231174469,
|
| 104 |
+
"eval_runtime": 9.0392,
|
| 105 |
+
"eval_samples_per_second": 0.996,
|
| 106 |
+
"eval_steps_per_second": 0.221,
|
| 107 |
+
"step": 70
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.07,
|
| 111 |
+
"learning_rate": 4.228456913827655e-05,
|
| 112 |
+
"loss": 0.32,
|
| 113 |
+
"step": 80
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 1.07,
|
| 117 |
+
"eval_loss": 1.4650906324386597,
|
| 118 |
+
"eval_runtime": 9.0603,
|
| 119 |
+
"eval_samples_per_second": 0.993,
|
| 120 |
+
"eval_steps_per_second": 0.221,
|
| 121 |
+
"step": 80
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.2,
|
| 125 |
+
"learning_rate": 4.128256513026052e-05,
|
| 126 |
+
"loss": 0.22,
|
| 127 |
+
"step": 90
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.2,
|
| 131 |
+
"eval_loss": 1.5176193714141846,
|
| 132 |
+
"eval_runtime": 9.0417,
|
| 133 |
+
"eval_samples_per_second": 0.995,
|
| 134 |
+
"eval_steps_per_second": 0.221,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.33,
|
| 139 |
+
"learning_rate": 4.0280561122244495e-05,
|
| 140 |
+
"loss": 0.2341,
|
| 141 |
+
"step": 100
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.33,
|
| 145 |
+
"eval_loss": 1.4975649118423462,
|
| 146 |
+
"eval_runtime": 9.0642,
|
| 147 |
+
"eval_samples_per_second": 0.993,
|
| 148 |
+
"eval_steps_per_second": 0.221,
|
| 149 |
+
"step": 100
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.47,
|
| 153 |
+
"learning_rate": 3.927855711422846e-05,
|
| 154 |
+
"loss": 0.2391,
|
| 155 |
+
"step": 110
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.47,
|
| 159 |
+
"eval_loss": 1.7257053852081299,
|
| 160 |
+
"eval_runtime": 8.9861,
|
| 161 |
+
"eval_samples_per_second": 1.002,
|
| 162 |
+
"eval_steps_per_second": 0.223,
|
| 163 |
+
"step": 110
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 1.6,
|
| 167 |
+
"learning_rate": 3.8276553106212426e-05,
|
| 168 |
+
"loss": 0.1884,
|
| 169 |
+
"step": 120
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.6,
|
| 173 |
+
"eval_loss": 1.639228105545044,
|
| 174 |
+
"eval_runtime": 9.0813,
|
| 175 |
+
"eval_samples_per_second": 0.991,
|
| 176 |
+
"eval_steps_per_second": 0.22,
|
| 177 |
+
"step": 120
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 1.73,
|
| 181 |
+
"learning_rate": 3.727454909819639e-05,
|
| 182 |
+
"loss": 0.1881,
|
| 183 |
+
"step": 130
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 1.73,
|
| 187 |
+
"eval_loss": 1.5887799263000488,
|
| 188 |
+
"eval_runtime": 9.08,
|
| 189 |
+
"eval_samples_per_second": 0.991,
|
| 190 |
+
"eval_steps_per_second": 0.22,
|
| 191 |
+
"step": 130
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.87,
|
| 195 |
+
"learning_rate": 3.627254509018036e-05,
|
| 196 |
+
"loss": 0.1314,
|
| 197 |
+
"step": 140
|
| 198 |
+
},
|
| 199 |
+
{
|
| 200 |
+
"epoch": 1.87,
|
| 201 |
+
"eval_loss": 1.6493072509765625,
|
| 202 |
+
"eval_runtime": 9.0781,
|
| 203 |
+
"eval_samples_per_second": 0.991,
|
| 204 |
+
"eval_steps_per_second": 0.22,
|
| 205 |
+
"step": 140
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 2.0,
|
| 209 |
+
"learning_rate": 3.527054108216433e-05,
|
| 210 |
+
"loss": 0.1524,
|
| 211 |
+
"step": 150
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.0,
|
| 215 |
+
"eval_loss": 1.6057649850845337,
|
| 216 |
+
"eval_runtime": 9.0159,
|
| 217 |
+
"eval_samples_per_second": 0.998,
|
| 218 |
+
"eval_steps_per_second": 0.222,
|
| 219 |
+
"step": 150
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 2.13,
|
| 223 |
+
"learning_rate": 3.42685370741483e-05,
|
| 224 |
+
"loss": 0.1036,
|
| 225 |
+
"step": 160
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.13,
|
| 229 |
+
"eval_loss": 1.6697440147399902,
|
| 230 |
+
"eval_runtime": 8.9746,
|
| 231 |
+
"eval_samples_per_second": 1.003,
|
| 232 |
+
"eval_steps_per_second": 0.223,
|
| 233 |
+
"step": 160
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.27,
|
| 237 |
+
"learning_rate": 3.326653306613227e-05,
|
| 238 |
+
"loss": 0.1176,
|
| 239 |
+
"step": 170
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.27,
|
| 243 |
+
"eval_loss": 1.6768882274627686,
|
| 244 |
+
"eval_runtime": 9.0646,
|
| 245 |
+
"eval_samples_per_second": 0.993,
|
| 246 |
+
"eval_steps_per_second": 0.221,
|
| 247 |
+
"step": 170
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.4,
|
| 251 |
+
"learning_rate": 3.2264529058116233e-05,
|
| 252 |
+
"loss": 0.1375,
|
| 253 |
+
"step": 180
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 2.4,
|
| 257 |
+
"eval_loss": 1.617688775062561,
|
| 258 |
+
"eval_runtime": 9.0499,
|
| 259 |
+
"eval_samples_per_second": 0.994,
|
| 260 |
+
"eval_steps_per_second": 0.221,
|
| 261 |
+
"step": 180
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.53,
|
| 265 |
+
"learning_rate": 3.12625250501002e-05,
|
| 266 |
+
"loss": 0.1038,
|
| 267 |
+
"step": 190
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.53,
|
| 271 |
+
"eval_loss": 1.6981985569000244,
|
| 272 |
+
"eval_runtime": 9.0561,
|
| 273 |
+
"eval_samples_per_second": 0.994,
|
| 274 |
+
"eval_steps_per_second": 0.221,
|
| 275 |
+
"step": 190
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.67,
|
| 279 |
+
"learning_rate": 3.026052104208417e-05,
|
| 280 |
+
"loss": 0.1068,
|
| 281 |
+
"step": 200
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.67,
|
| 285 |
+
"eval_loss": 1.7827256917953491,
|
| 286 |
+
"eval_runtime": 9.0294,
|
| 287 |
+
"eval_samples_per_second": 0.997,
|
| 288 |
+
"eval_steps_per_second": 0.221,
|
| 289 |
+
"step": 200
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 2.8,
|
| 293 |
+
"learning_rate": 2.925851703406814e-05,
|
| 294 |
+
"loss": 0.1229,
|
| 295 |
+
"step": 210
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 2.8,
|
| 299 |
+
"eval_loss": 1.6968226432800293,
|
| 300 |
+
"eval_runtime": 9.039,
|
| 301 |
+
"eval_samples_per_second": 0.996,
|
| 302 |
+
"eval_steps_per_second": 0.221,
|
| 303 |
+
"step": 210
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.93,
|
| 307 |
+
"learning_rate": 2.8256513026052106e-05,
|
| 308 |
+
"loss": 0.142,
|
| 309 |
+
"step": 220
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.93,
|
| 313 |
+
"eval_loss": 1.7085565328598022,
|
| 314 |
+
"eval_runtime": 9.0746,
|
| 315 |
+
"eval_samples_per_second": 0.992,
|
| 316 |
+
"eval_steps_per_second": 0.22,
|
| 317 |
+
"step": 220
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.07,
|
| 321 |
+
"learning_rate": 2.7254509018036072e-05,
|
| 322 |
+
"loss": 0.0868,
|
| 323 |
+
"step": 230
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.07,
|
| 327 |
+
"eval_loss": 1.814492106437683,
|
| 328 |
+
"eval_runtime": 9.0805,
|
| 329 |
+
"eval_samples_per_second": 0.991,
|
| 330 |
+
"eval_steps_per_second": 0.22,
|
| 331 |
+
"step": 230
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 3.2,
|
| 335 |
+
"learning_rate": 2.625250501002004e-05,
|
| 336 |
+
"loss": 0.0772,
|
| 337 |
+
"step": 240
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"epoch": 3.2,
|
| 341 |
+
"eval_loss": 1.916466236114502,
|
| 342 |
+
"eval_runtime": 9.072,
|
| 343 |
+
"eval_samples_per_second": 0.992,
|
| 344 |
+
"eval_steps_per_second": 0.22,
|
| 345 |
+
"step": 240
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.33,
|
| 349 |
+
"learning_rate": 2.5250501002004006e-05,
|
| 350 |
+
"loss": 0.0644,
|
| 351 |
+
"step": 250
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 3.33,
|
| 355 |
+
"eval_loss": 1.8792904615402222,
|
| 356 |
+
"eval_runtime": 9.0616,
|
| 357 |
+
"eval_samples_per_second": 0.993,
|
| 358 |
+
"eval_steps_per_second": 0.221,
|
| 359 |
+
"step": 250
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 3.47,
|
| 363 |
+
"learning_rate": 2.4248496993987975e-05,
|
| 364 |
+
"loss": 0.0886,
|
| 365 |
+
"step": 260
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.47,
|
| 369 |
+
"eval_loss": 1.7695975303649902,
|
| 370 |
+
"eval_runtime": 9.0109,
|
| 371 |
+
"eval_samples_per_second": 0.999,
|
| 372 |
+
"eval_steps_per_second": 0.222,
|
| 373 |
+
"step": 260
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 3.6,
|
| 377 |
+
"learning_rate": 2.3246492985971944e-05,
|
| 378 |
+
"loss": 0.0807,
|
| 379 |
+
"step": 270
|
| 380 |
+
},
|
| 381 |
+
{
|
| 382 |
+
"epoch": 3.6,
|
| 383 |
+
"eval_loss": 1.7431364059448242,
|
| 384 |
+
"eval_runtime": 9.0009,
|
| 385 |
+
"eval_samples_per_second": 1.0,
|
| 386 |
+
"eval_steps_per_second": 0.222,
|
| 387 |
+
"step": 270
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 3.73,
|
| 391 |
+
"learning_rate": 2.2244488977955913e-05,
|
| 392 |
+
"loss": 0.0873,
|
| 393 |
+
"step": 280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 3.73,
|
| 397 |
+
"eval_loss": 1.8270233869552612,
|
| 398 |
+
"eval_runtime": 9.0218,
|
| 399 |
+
"eval_samples_per_second": 0.998,
|
| 400 |
+
"eval_steps_per_second": 0.222,
|
| 401 |
+
"step": 280
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 3.87,
|
| 405 |
+
"learning_rate": 2.124248496993988e-05,
|
| 406 |
+
"loss": 0.0704,
|
| 407 |
+
"step": 290
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 3.87,
|
| 411 |
+
"eval_loss": 1.8161801099777222,
|
| 412 |
+
"eval_runtime": 9.0309,
|
| 413 |
+
"eval_samples_per_second": 0.997,
|
| 414 |
+
"eval_steps_per_second": 0.221,
|
| 415 |
+
"step": 290
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.0,
|
| 419 |
+
"learning_rate": 2.0240480961923848e-05,
|
| 420 |
+
"loss": 0.0729,
|
| 421 |
+
"step": 300
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 4.0,
|
| 425 |
+
"eval_loss": 1.8546494245529175,
|
| 426 |
+
"eval_runtime": 9.0378,
|
| 427 |
+
"eval_samples_per_second": 0.996,
|
| 428 |
+
"eval_steps_per_second": 0.221,
|
| 429 |
+
"step": 300
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 4.13,
|
| 433 |
+
"learning_rate": 1.9238476953907817e-05,
|
| 434 |
+
"loss": 0.063,
|
| 435 |
+
"step": 310
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 4.13,
|
| 439 |
+
"eval_loss": 1.9666298627853394,
|
| 440 |
+
"eval_runtime": 9.008,
|
| 441 |
+
"eval_samples_per_second": 0.999,
|
| 442 |
+
"eval_steps_per_second": 0.222,
|
| 443 |
+
"step": 310
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 4.27,
|
| 447 |
+
"learning_rate": 1.8236472945891783e-05,
|
| 448 |
+
"loss": 0.0541,
|
| 449 |
+
"step": 320
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 4.27,
|
| 453 |
+
"eval_loss": 1.9620505571365356,
|
| 454 |
+
"eval_runtime": 9.0643,
|
| 455 |
+
"eval_samples_per_second": 0.993,
|
| 456 |
+
"eval_steps_per_second": 0.221,
|
| 457 |
+
"step": 320
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 4.4,
|
| 461 |
+
"learning_rate": 1.7234468937875752e-05,
|
| 462 |
+
"loss": 0.0648,
|
| 463 |
+
"step": 330
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 4.4,
|
| 467 |
+
"eval_loss": 1.962950348854065,
|
| 468 |
+
"eval_runtime": 9.0685,
|
| 469 |
+
"eval_samples_per_second": 0.992,
|
| 470 |
+
"eval_steps_per_second": 0.221,
|
| 471 |
+
"step": 330
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 4.53,
|
| 475 |
+
"learning_rate": 1.623246492985972e-05,
|
| 476 |
+
"loss": 0.0631,
|
| 477 |
+
"step": 340
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 4.53,
|
| 481 |
+
"eval_loss": 1.9116477966308594,
|
| 482 |
+
"eval_runtime": 9.0789,
|
| 483 |
+
"eval_samples_per_second": 0.991,
|
| 484 |
+
"eval_steps_per_second": 0.22,
|
| 485 |
+
"step": 340
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 4.67,
|
| 489 |
+
"learning_rate": 1.523046092184369e-05,
|
| 490 |
+
"loss": 0.0545,
|
| 491 |
+
"step": 350
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 4.67,
|
| 495 |
+
"eval_loss": 1.9107557535171509,
|
| 496 |
+
"eval_runtime": 9.0172,
|
| 497 |
+
"eval_samples_per_second": 0.998,
|
| 498 |
+
"eval_steps_per_second": 0.222,
|
| 499 |
+
"step": 350
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 4.8,
|
| 503 |
+
"learning_rate": 1.4228456913827657e-05,
|
| 504 |
+
"loss": 0.0622,
|
| 505 |
+
"step": 360
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 4.8,
|
| 509 |
+
"eval_loss": 1.965379238128662,
|
| 510 |
+
"eval_runtime": 8.9497,
|
| 511 |
+
"eval_samples_per_second": 1.006,
|
| 512 |
+
"eval_steps_per_second": 0.223,
|
| 513 |
+
"step": 360
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 4.93,
|
| 517 |
+
"learning_rate": 1.3226452905811623e-05,
|
| 518 |
+
"loss": 0.0523,
|
| 519 |
+
"step": 370
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 4.93,
|
| 523 |
+
"eval_loss": 2.0281553268432617,
|
| 524 |
+
"eval_runtime": 9.0358,
|
| 525 |
+
"eval_samples_per_second": 0.996,
|
| 526 |
+
"eval_steps_per_second": 0.221,
|
| 527 |
+
"step": 370
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 5.07,
|
| 531 |
+
"learning_rate": 1.2224448897795592e-05,
|
| 532 |
+
"loss": 0.0479,
|
| 533 |
+
"step": 380
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.07,
|
| 537 |
+
"eval_loss": 2.065614938735962,
|
| 538 |
+
"eval_runtime": 9.0421,
|
| 539 |
+
"eval_samples_per_second": 0.995,
|
| 540 |
+
"eval_steps_per_second": 0.221,
|
| 541 |
+
"step": 380
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 5.2,
|
| 545 |
+
"learning_rate": 1.122244488977956e-05,
|
| 546 |
+
"loss": 0.0373,
|
| 547 |
+
"step": 390
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.2,
|
| 551 |
+
"eval_loss": 2.0752174854278564,
|
| 552 |
+
"eval_runtime": 9.0688,
|
| 553 |
+
"eval_samples_per_second": 0.992,
|
| 554 |
+
"eval_steps_per_second": 0.221,
|
| 555 |
+
"step": 390
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 5.33,
|
| 559 |
+
"learning_rate": 1.0220440881763528e-05,
|
| 560 |
+
"loss": 0.0406,
|
| 561 |
+
"step": 400
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.33,
|
| 565 |
+
"eval_loss": 2.0857064723968506,
|
| 566 |
+
"eval_runtime": 9.0511,
|
| 567 |
+
"eval_samples_per_second": 0.994,
|
| 568 |
+
"eval_steps_per_second": 0.221,
|
| 569 |
+
"step": 400
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.47,
|
| 573 |
+
"learning_rate": 9.218436873747496e-06,
|
| 574 |
+
"loss": 0.0463,
|
| 575 |
+
"step": 410
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.47,
|
| 579 |
+
"eval_loss": 2.118208885192871,
|
| 580 |
+
"eval_runtime": 9.0064,
|
| 581 |
+
"eval_samples_per_second": 0.999,
|
| 582 |
+
"eval_steps_per_second": 0.222,
|
| 583 |
+
"step": 410
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 5.6,
|
| 587 |
+
"learning_rate": 8.216432865731463e-06,
|
| 588 |
+
"loss": 0.0433,
|
| 589 |
+
"step": 420
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.6,
|
| 593 |
+
"eval_loss": 2.1232292652130127,
|
| 594 |
+
"eval_runtime": 9.0773,
|
| 595 |
+
"eval_samples_per_second": 0.991,
|
| 596 |
+
"eval_steps_per_second": 0.22,
|
| 597 |
+
"step": 420
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 5.73,
|
| 601 |
+
"learning_rate": 7.214428857715432e-06,
|
| 602 |
+
"loss": 0.0425,
|
| 603 |
+
"step": 430
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 5.73,
|
| 607 |
+
"eval_loss": 2.124908924102783,
|
| 608 |
+
"eval_runtime": 9.0585,
|
| 609 |
+
"eval_samples_per_second": 0.994,
|
| 610 |
+
"eval_steps_per_second": 0.221,
|
| 611 |
+
"step": 430
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 5.87,
|
| 615 |
+
"learning_rate": 6.212424849699399e-06,
|
| 616 |
+
"loss": 0.0413,
|
| 617 |
+
"step": 440
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 5.87,
|
| 621 |
+
"eval_loss": 2.125481605529785,
|
| 622 |
+
"eval_runtime": 9.0338,
|
| 623 |
+
"eval_samples_per_second": 0.996,
|
| 624 |
+
"eval_steps_per_second": 0.221,
|
| 625 |
+
"step": 440
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.0,
|
| 629 |
+
"learning_rate": 5.2104208416833665e-06,
|
| 630 |
+
"loss": 0.0579,
|
| 631 |
+
"step": 450
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"epoch": 6.0,
|
| 635 |
+
"eval_loss": 2.1075000762939453,
|
| 636 |
+
"eval_runtime": 9.0414,
|
| 637 |
+
"eval_samples_per_second": 0.995,
|
| 638 |
+
"eval_steps_per_second": 0.221,
|
| 639 |
+
"step": 450
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.13,
|
| 643 |
+
"learning_rate": 4.208416833667335e-06,
|
| 644 |
+
"loss": 0.0326,
|
| 645 |
+
"step": 460
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 6.13,
|
| 649 |
+
"eval_loss": 2.112290382385254,
|
| 650 |
+
"eval_runtime": 8.9941,
|
| 651 |
+
"eval_samples_per_second": 1.001,
|
| 652 |
+
"eval_steps_per_second": 0.222,
|
| 653 |
+
"step": 460
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.27,
|
| 657 |
+
"learning_rate": 3.2064128256513024e-06,
|
| 658 |
+
"loss": 0.0378,
|
| 659 |
+
"step": 470
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 6.27,
|
| 663 |
+
"eval_loss": 2.1354782581329346,
|
| 664 |
+
"eval_runtime": 9.0542,
|
| 665 |
+
"eval_samples_per_second": 0.994,
|
| 666 |
+
"eval_steps_per_second": 0.221,
|
| 667 |
+
"step": 470
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 6.4,
|
| 671 |
+
"learning_rate": 2.2044088176352706e-06,
|
| 672 |
+
"loss": 0.0384,
|
| 673 |
+
"step": 480
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 6.4,
|
| 677 |
+
"eval_loss": 2.1528055667877197,
|
| 678 |
+
"eval_runtime": 9.0296,
|
| 679 |
+
"eval_samples_per_second": 0.997,
|
| 680 |
+
"eval_steps_per_second": 0.221,
|
| 681 |
+
"step": 480
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.53,
|
| 685 |
+
"learning_rate": 1.2024048096192386e-06,
|
| 686 |
+
"loss": 0.0328,
|
| 687 |
+
"step": 490
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 6.53,
|
| 691 |
+
"eval_loss": 2.162899971008301,
|
| 692 |
+
"eval_runtime": 9.0663,
|
| 693 |
+
"eval_samples_per_second": 0.993,
|
| 694 |
+
"eval_steps_per_second": 0.221,
|
| 695 |
+
"step": 490
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 6.67,
|
| 699 |
+
"learning_rate": 2.004008016032064e-07,
|
| 700 |
+
"loss": 0.0356,
|
| 701 |
+
"step": 500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 6.67,
|
| 705 |
+
"eval_loss": 2.1663544178009033,
|
| 706 |
+
"eval_runtime": 9.0766,
|
| 707 |
+
"eval_samples_per_second": 0.992,
|
| 708 |
+
"eval_steps_per_second": 0.22,
|
| 709 |
+
"step": 500
|
| 710 |
+
}
|
| 711 |
+
],
|
| 712 |
+
"logging_steps": 10,
|
| 713 |
+
"max_steps": 500,
|
| 714 |
+
"num_input_tokens_seen": 0,
|
| 715 |
+
"num_train_epochs": 7,
|
| 716 |
+
"save_steps": 50,
|
| 717 |
+
"total_flos": 3.411755398324224e+16,
|
| 718 |
+
"train_batch_size": 2,
|
| 719 |
+
"trial_name": null,
|
| 720 |
+
"trial_params": null
|
| 721 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61053cc9e8844ba81799021f4340e492ec7ac6d6e44581930651ba291216bb86
|
| 3 |
+
size 4728
|