Training in progress, step 2600, checkpoint
Browse files- checkpoint-2600/README.md +21 -0
- checkpoint-2600/adapter_config.json +21 -0
- checkpoint-2600/adapter_model.bin +3 -0
- checkpoint-2600/optimizer.pt +3 -0
- checkpoint-2600/rng_state.pth +3 -0
- checkpoint-2600/scheduler.pt +3 -0
- checkpoint-2600/trainer_state.json +545 -0
- checkpoint-2600/training_args.bin +3 -0
checkpoint-2600/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-2600/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
|
| 4 |
+
"bias": "lora_only",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 8,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-2600/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6f610de8b8af8078c6c09563d0987b3767ff62b105d1aad06e240e35981e7ff2
|
| 3 |
+
size 16822989
|
checkpoint-2600/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5b7e3cbd7d8a8926483294d5c2ca01a16b6e0b18f725020e71849b2e186c1a06
|
| 3 |
+
size 8555781
|
checkpoint-2600/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb202adbdf1bb9270272c9196c3bafb7eed4207e4a75bdc724dc67048a3673b7
|
| 3 |
+
size 14575
|
checkpoint-2600/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68585c8c53992ffa01ed3cd86f6b9081f6ee9fb2eefd0f84b8bd1f5eb217b009
|
| 3 |
+
size 627
|
checkpoint-2600/trainer_state.json
ADDED
|
@@ -0,0 +1,545 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.23951096832752228,
|
| 3 |
+
"best_model_checkpoint": "./text2sql/codellama_instruct_spider_e10/checkpoint-500",
|
| 4 |
+
"epoch": 9.607390300230946,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 2600,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 3.08641975308642e-07,
|
| 14 |
+
"loss": 1.3897,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.18,
|
| 19 |
+
"learning_rate": 1.54320987654321e-05,
|
| 20 |
+
"loss": 1.3449,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.37,
|
| 25 |
+
"learning_rate": 3.08641975308642e-05,
|
| 26 |
+
"loss": 0.822,
|
| 27 |
+
"step": 100
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.37,
|
| 31 |
+
"eval_loss": 0.5313276648521423,
|
| 32 |
+
"eval_runtime": 34.4984,
|
| 33 |
+
"eval_samples_per_second": 29.972,
|
| 34 |
+
"eval_steps_per_second": 3.768,
|
| 35 |
+
"step": 100
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.55,
|
| 39 |
+
"learning_rate": 4.62962962962963e-05,
|
| 40 |
+
"loss": 0.4342,
|
| 41 |
+
"step": 150
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.74,
|
| 45 |
+
"learning_rate": 4.9251379038613084e-05,
|
| 46 |
+
"loss": 0.3014,
|
| 47 |
+
"step": 200
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.74,
|
| 51 |
+
"eval_loss": 0.2763093411922455,
|
| 52 |
+
"eval_runtime": 34.3952,
|
| 53 |
+
"eval_samples_per_second": 30.062,
|
| 54 |
+
"eval_steps_per_second": 3.78,
|
| 55 |
+
"step": 200
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.92,
|
| 59 |
+
"learning_rate": 4.826635145784082e-05,
|
| 60 |
+
"loss": 0.2401,
|
| 61 |
+
"step": 250
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 1.11,
|
| 65 |
+
"learning_rate": 4.728132387706856e-05,
|
| 66 |
+
"loss": 0.2091,
|
| 67 |
+
"step": 300
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 1.11,
|
| 71 |
+
"eval_loss": 0.24685852229595184,
|
| 72 |
+
"eval_runtime": 34.5214,
|
| 73 |
+
"eval_samples_per_second": 29.952,
|
| 74 |
+
"eval_steps_per_second": 3.766,
|
| 75 |
+
"step": 300
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 1.29,
|
| 79 |
+
"learning_rate": 4.62962962962963e-05,
|
| 80 |
+
"loss": 0.1837,
|
| 81 |
+
"step": 350
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 1.48,
|
| 85 |
+
"learning_rate": 4.5311268715524035e-05,
|
| 86 |
+
"loss": 0.1697,
|
| 87 |
+
"step": 400
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.48,
|
| 91 |
+
"eval_loss": 0.2400880753993988,
|
| 92 |
+
"eval_runtime": 34.3334,
|
| 93 |
+
"eval_samples_per_second": 30.116,
|
| 94 |
+
"eval_steps_per_second": 3.786,
|
| 95 |
+
"step": 400
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.66,
|
| 99 |
+
"learning_rate": 4.432624113475177e-05,
|
| 100 |
+
"loss": 0.1589,
|
| 101 |
+
"step": 450
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.85,
|
| 105 |
+
"learning_rate": 4.334121355397952e-05,
|
| 106 |
+
"loss": 0.1495,
|
| 107 |
+
"step": 500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.85,
|
| 111 |
+
"eval_loss": 0.23951096832752228,
|
| 112 |
+
"eval_runtime": 34.3515,
|
| 113 |
+
"eval_samples_per_second": 30.101,
|
| 114 |
+
"eval_steps_per_second": 3.784,
|
| 115 |
+
"step": 500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 2.03,
|
| 119 |
+
"learning_rate": 4.235618597320725e-05,
|
| 120 |
+
"loss": 0.1356,
|
| 121 |
+
"step": 550
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 2.22,
|
| 125 |
+
"learning_rate": 4.1371158392434986e-05,
|
| 126 |
+
"loss": 0.1256,
|
| 127 |
+
"step": 600
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 2.22,
|
| 131 |
+
"eval_loss": 0.2525351345539093,
|
| 132 |
+
"eval_runtime": 34.4715,
|
| 133 |
+
"eval_samples_per_second": 29.996,
|
| 134 |
+
"eval_steps_per_second": 3.771,
|
| 135 |
+
"step": 600
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 2.4,
|
| 139 |
+
"learning_rate": 4.0386130811662727e-05,
|
| 140 |
+
"loss": 0.1162,
|
| 141 |
+
"step": 650
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 2.59,
|
| 145 |
+
"learning_rate": 3.940110323089047e-05,
|
| 146 |
+
"loss": 0.1097,
|
| 147 |
+
"step": 700
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 2.59,
|
| 151 |
+
"eval_loss": 0.2641294002532959,
|
| 152 |
+
"eval_runtime": 34.4325,
|
| 153 |
+
"eval_samples_per_second": 30.03,
|
| 154 |
+
"eval_steps_per_second": 3.776,
|
| 155 |
+
"step": 700
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 2.77,
|
| 159 |
+
"learning_rate": 3.84160756501182e-05,
|
| 160 |
+
"loss": 0.1059,
|
| 161 |
+
"step": 750
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 2.96,
|
| 165 |
+
"learning_rate": 3.743104806934594e-05,
|
| 166 |
+
"loss": 0.1107,
|
| 167 |
+
"step": 800
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 2.96,
|
| 171 |
+
"eval_loss": 0.2617126703262329,
|
| 172 |
+
"eval_runtime": 34.3286,
|
| 173 |
+
"eval_samples_per_second": 30.121,
|
| 174 |
+
"eval_steps_per_second": 3.787,
|
| 175 |
+
"step": 800
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 3.14,
|
| 179 |
+
"learning_rate": 3.6446020488573684e-05,
|
| 180 |
+
"loss": 0.0929,
|
| 181 |
+
"step": 850
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 3.33,
|
| 185 |
+
"learning_rate": 3.546099290780142e-05,
|
| 186 |
+
"loss": 0.0951,
|
| 187 |
+
"step": 900
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 3.33,
|
| 191 |
+
"eval_loss": 0.26825329661369324,
|
| 192 |
+
"eval_runtime": 34.3778,
|
| 193 |
+
"eval_samples_per_second": 30.078,
|
| 194 |
+
"eval_steps_per_second": 3.782,
|
| 195 |
+
"step": 900
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 3.51,
|
| 199 |
+
"learning_rate": 3.447596532702916e-05,
|
| 200 |
+
"loss": 0.0885,
|
| 201 |
+
"step": 950
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 3.7,
|
| 205 |
+
"learning_rate": 3.349093774625689e-05,
|
| 206 |
+
"loss": 0.0882,
|
| 207 |
+
"step": 1000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.7,
|
| 211 |
+
"eval_loss": 0.28923752903938293,
|
| 212 |
+
"eval_runtime": 34.5013,
|
| 213 |
+
"eval_samples_per_second": 29.97,
|
| 214 |
+
"eval_steps_per_second": 3.768,
|
| 215 |
+
"step": 1000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 3.88,
|
| 219 |
+
"learning_rate": 3.2505910165484634e-05,
|
| 220 |
+
"loss": 0.0861,
|
| 221 |
+
"step": 1050
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 4.06,
|
| 225 |
+
"learning_rate": 3.1520882584712375e-05,
|
| 226 |
+
"loss": 0.0818,
|
| 227 |
+
"step": 1100
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 4.06,
|
| 231 |
+
"eval_loss": 0.31338369846343994,
|
| 232 |
+
"eval_runtime": 34.3826,
|
| 233 |
+
"eval_samples_per_second": 30.073,
|
| 234 |
+
"eval_steps_per_second": 3.781,
|
| 235 |
+
"step": 1100
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 4.25,
|
| 239 |
+
"learning_rate": 3.053585500394011e-05,
|
| 240 |
+
"loss": 0.0714,
|
| 241 |
+
"step": 1150
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.43,
|
| 245 |
+
"learning_rate": 2.9550827423167847e-05,
|
| 246 |
+
"loss": 0.075,
|
| 247 |
+
"step": 1200
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 4.43,
|
| 251 |
+
"eval_loss": 0.2977830767631531,
|
| 252 |
+
"eval_runtime": 34.4574,
|
| 253 |
+
"eval_samples_per_second": 30.008,
|
| 254 |
+
"eval_steps_per_second": 3.773,
|
| 255 |
+
"step": 1200
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 4.62,
|
| 259 |
+
"learning_rate": 2.8565799842395592e-05,
|
| 260 |
+
"loss": 0.0725,
|
| 261 |
+
"step": 1250
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 4.8,
|
| 265 |
+
"learning_rate": 2.758077226162333e-05,
|
| 266 |
+
"loss": 0.0745,
|
| 267 |
+
"step": 1300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.8,
|
| 271 |
+
"eval_loss": 0.3094833493232727,
|
| 272 |
+
"eval_runtime": 34.5265,
|
| 273 |
+
"eval_samples_per_second": 29.948,
|
| 274 |
+
"eval_steps_per_second": 3.765,
|
| 275 |
+
"step": 1300
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 4.99,
|
| 279 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 280 |
+
"loss": 0.0737,
|
| 281 |
+
"step": 1350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 5.17,
|
| 285 |
+
"learning_rate": 2.56107171000788e-05,
|
| 286 |
+
"loss": 0.0642,
|
| 287 |
+
"step": 1400
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 5.17,
|
| 291 |
+
"eval_loss": 0.32607167959213257,
|
| 292 |
+
"eval_runtime": 34.3998,
|
| 293 |
+
"eval_samples_per_second": 30.058,
|
| 294 |
+
"eval_steps_per_second": 3.779,
|
| 295 |
+
"step": 1400
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.36,
|
| 299 |
+
"learning_rate": 2.4625689519306542e-05,
|
| 300 |
+
"loss": 0.0667,
|
| 301 |
+
"step": 1450
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 5.54,
|
| 305 |
+
"learning_rate": 2.364066193853428e-05,
|
| 306 |
+
"loss": 0.0622,
|
| 307 |
+
"step": 1500
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 5.54,
|
| 311 |
+
"eval_loss": 0.3201189637184143,
|
| 312 |
+
"eval_runtime": 34.3251,
|
| 313 |
+
"eval_samples_per_second": 30.124,
|
| 314 |
+
"eval_steps_per_second": 3.787,
|
| 315 |
+
"step": 1500
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 5.73,
|
| 319 |
+
"learning_rate": 2.2655634357762018e-05,
|
| 320 |
+
"loss": 0.0582,
|
| 321 |
+
"step": 1550
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.91,
|
| 325 |
+
"learning_rate": 2.167060677698976e-05,
|
| 326 |
+
"loss": 0.0573,
|
| 327 |
+
"step": 1600
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 5.91,
|
| 331 |
+
"eval_loss": 0.33428019285202026,
|
| 332 |
+
"eval_runtime": 34.4673,
|
| 333 |
+
"eval_samples_per_second": 29.999,
|
| 334 |
+
"eval_steps_per_second": 3.772,
|
| 335 |
+
"step": 1600
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 6.1,
|
| 339 |
+
"learning_rate": 2.0685579196217493e-05,
|
| 340 |
+
"loss": 0.0562,
|
| 341 |
+
"step": 1650
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 6.28,
|
| 345 |
+
"learning_rate": 1.9700551615445234e-05,
|
| 346 |
+
"loss": 0.0552,
|
| 347 |
+
"step": 1700
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 6.28,
|
| 351 |
+
"eval_loss": 0.3396373391151428,
|
| 352 |
+
"eval_runtime": 34.4691,
|
| 353 |
+
"eval_samples_per_second": 29.998,
|
| 354 |
+
"eval_steps_per_second": 3.771,
|
| 355 |
+
"step": 1700
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 6.47,
|
| 359 |
+
"learning_rate": 1.871552403467297e-05,
|
| 360 |
+
"loss": 0.0535,
|
| 361 |
+
"step": 1750
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 6.65,
|
| 365 |
+
"learning_rate": 1.773049645390071e-05,
|
| 366 |
+
"loss": 0.0523,
|
| 367 |
+
"step": 1800
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 6.65,
|
| 371 |
+
"eval_loss": 0.3602007329463959,
|
| 372 |
+
"eval_runtime": 34.3058,
|
| 373 |
+
"eval_samples_per_second": 30.141,
|
| 374 |
+
"eval_steps_per_second": 3.789,
|
| 375 |
+
"step": 1800
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.84,
|
| 379 |
+
"learning_rate": 1.6745468873128447e-05,
|
| 380 |
+
"loss": 0.0513,
|
| 381 |
+
"step": 1850
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 7.02,
|
| 385 |
+
"learning_rate": 1.5760441292356188e-05,
|
| 386 |
+
"loss": 0.0538,
|
| 387 |
+
"step": 1900
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 7.02,
|
| 391 |
+
"eval_loss": 0.34643229842185974,
|
| 392 |
+
"eval_runtime": 34.374,
|
| 393 |
+
"eval_samples_per_second": 30.081,
|
| 394 |
+
"eval_steps_per_second": 3.782,
|
| 395 |
+
"step": 1900
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 7.21,
|
| 399 |
+
"learning_rate": 1.4775413711583924e-05,
|
| 400 |
+
"loss": 0.0457,
|
| 401 |
+
"step": 1950
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 7.39,
|
| 405 |
+
"learning_rate": 1.3790386130811665e-05,
|
| 406 |
+
"loss": 0.0467,
|
| 407 |
+
"step": 2000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 7.39,
|
| 411 |
+
"eval_loss": 0.3621950149536133,
|
| 412 |
+
"eval_runtime": 34.4567,
|
| 413 |
+
"eval_samples_per_second": 30.009,
|
| 414 |
+
"eval_steps_per_second": 3.773,
|
| 415 |
+
"step": 2000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 7.58,
|
| 419 |
+
"learning_rate": 1.28053585500394e-05,
|
| 420 |
+
"loss": 0.0471,
|
| 421 |
+
"step": 2050
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 7.76,
|
| 425 |
+
"learning_rate": 1.182033096926714e-05,
|
| 426 |
+
"loss": 0.0465,
|
| 427 |
+
"step": 2100
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 7.76,
|
| 431 |
+
"eval_loss": 0.3696867823600769,
|
| 432 |
+
"eval_runtime": 34.3098,
|
| 433 |
+
"eval_samples_per_second": 30.137,
|
| 434 |
+
"eval_steps_per_second": 3.789,
|
| 435 |
+
"step": 2100
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 7.94,
|
| 439 |
+
"learning_rate": 1.083530338849488e-05,
|
| 440 |
+
"loss": 0.0442,
|
| 441 |
+
"step": 2150
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 8.13,
|
| 445 |
+
"learning_rate": 9.850275807722617e-06,
|
| 446 |
+
"loss": 0.044,
|
| 447 |
+
"step": 2200
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 8.13,
|
| 451 |
+
"eval_loss": 0.38901907205581665,
|
| 452 |
+
"eval_runtime": 34.3303,
|
| 453 |
+
"eval_samples_per_second": 30.119,
|
| 454 |
+
"eval_steps_per_second": 3.787,
|
| 455 |
+
"step": 2200
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 8.31,
|
| 459 |
+
"learning_rate": 8.865248226950355e-06,
|
| 460 |
+
"loss": 0.0409,
|
| 461 |
+
"step": 2250
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 8.5,
|
| 465 |
+
"learning_rate": 7.880220646178094e-06,
|
| 466 |
+
"loss": 0.043,
|
| 467 |
+
"step": 2300
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 8.5,
|
| 471 |
+
"eval_loss": 0.37854906916618347,
|
| 472 |
+
"eval_runtime": 34.4655,
|
| 473 |
+
"eval_samples_per_second": 30.001,
|
| 474 |
+
"eval_steps_per_second": 3.772,
|
| 475 |
+
"step": 2300
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 8.68,
|
| 479 |
+
"learning_rate": 6.895193065405832e-06,
|
| 480 |
+
"loss": 0.0404,
|
| 481 |
+
"step": 2350
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"epoch": 8.87,
|
| 485 |
+
"learning_rate": 5.91016548463357e-06,
|
| 486 |
+
"loss": 0.0375,
|
| 487 |
+
"step": 2400
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 8.87,
|
| 491 |
+
"eval_loss": 0.386026531457901,
|
| 492 |
+
"eval_runtime": 34.3357,
|
| 493 |
+
"eval_samples_per_second": 30.114,
|
| 494 |
+
"eval_steps_per_second": 3.786,
|
| 495 |
+
"step": 2400
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 9.05,
|
| 499 |
+
"learning_rate": 4.9251379038613084e-06,
|
| 500 |
+
"loss": 0.0398,
|
| 501 |
+
"step": 2450
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 9.24,
|
| 505 |
+
"learning_rate": 3.940110323089047e-06,
|
| 506 |
+
"loss": 0.0384,
|
| 507 |
+
"step": 2500
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 9.24,
|
| 511 |
+
"eval_loss": 0.3951684236526489,
|
| 512 |
+
"eval_runtime": 34.329,
|
| 513 |
+
"eval_samples_per_second": 30.12,
|
| 514 |
+
"eval_steps_per_second": 3.787,
|
| 515 |
+
"step": 2500
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 9.42,
|
| 519 |
+
"learning_rate": 2.955082742316785e-06,
|
| 520 |
+
"loss": 0.038,
|
| 521 |
+
"step": 2550
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 9.61,
|
| 525 |
+
"learning_rate": 1.9700551615445235e-06,
|
| 526 |
+
"loss": 0.0363,
|
| 527 |
+
"step": 2600
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 9.61,
|
| 531 |
+
"eval_loss": 0.3940494656562805,
|
| 532 |
+
"eval_runtime": 34.4728,
|
| 533 |
+
"eval_samples_per_second": 29.995,
|
| 534 |
+
"eval_steps_per_second": 3.771,
|
| 535 |
+
"step": 2600
|
| 536 |
+
}
|
| 537 |
+
],
|
| 538 |
+
"logging_steps": 50,
|
| 539 |
+
"max_steps": 2700,
|
| 540 |
+
"num_train_epochs": 10,
|
| 541 |
+
"save_steps": 100,
|
| 542 |
+
"total_flos": 7.939827703309271e+17,
|
| 543 |
+
"trial_name": null,
|
| 544 |
+
"trial_params": null
|
| 545 |
+
}
|
checkpoint-2600/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f894492930ff690bb0d1428d042fd66b325480fe96ad5ff777a305a69efec314
|
| 3 |
+
size 4219
|