Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- trainer_outputs/checkpoint-1000/README.md +21 -0
- trainer_outputs/checkpoint-1000/adapter_config.json +21 -0
- trainer_outputs/checkpoint-1000/adapter_model.bin +3 -0
- trainer_outputs/checkpoint-1000/optimizer.pt +3 -0
- trainer_outputs/checkpoint-1000/rng_state.pth +3 -0
- trainer_outputs/checkpoint-1000/scheduler.pt +3 -0
- trainer_outputs/checkpoint-1000/trainer_state.json +319 -0
- trainer_outputs/checkpoint-1000/training_args.bin +3 -0
- trainer_outputs/checkpoint-1500/README.md +21 -0
- trainer_outputs/checkpoint-1500/adapter_config.json +21 -0
- trainer_outputs/checkpoint-1500/adapter_model.bin +3 -0
- trainer_outputs/checkpoint-1500/optimizer.pt +3 -0
- trainer_outputs/checkpoint-1500/rng_state.pth +3 -0
- trainer_outputs/checkpoint-1500/scheduler.pt +3 -0
- trainer_outputs/checkpoint-1500/trainer_state.json +469 -0
- trainer_outputs/checkpoint-1500/training_args.bin +3 -0
- trainer_outputs/checkpoint-2000/README.md +21 -0
- trainer_outputs/checkpoint-2000/adapter_config.json +21 -0
- trainer_outputs/checkpoint-2000/adapter_model.bin +3 -0
- trainer_outputs/checkpoint-2000/optimizer.pt +3 -0
- trainer_outputs/checkpoint-2000/rng_state.pth +3 -0
- trainer_outputs/checkpoint-2000/scheduler.pt +3 -0
- trainer_outputs/checkpoint-2000/trainer_state.json +619 -0
- trainer_outputs/checkpoint-2000/training_args.bin +3 -0
- trainer_outputs/checkpoint-2500/README.md +21 -0
- trainer_outputs/checkpoint-2500/adapter_config.json +21 -0
- trainer_outputs/checkpoint-2500/adapter_model.bin +3 -0
- trainer_outputs/checkpoint-2500/optimizer.pt +3 -0
- trainer_outputs/checkpoint-2500/rng_state.pth +3 -0
- trainer_outputs/checkpoint-2500/scheduler.pt +3 -0
- trainer_outputs/checkpoint-2500/trainer_state.json +769 -0
- trainer_outputs/checkpoint-2500/training_args.bin +3 -0
- trainer_outputs/checkpoint-3000/README.md +21 -0
- trainer_outputs/checkpoint-3000/adapter_config.json +21 -0
- trainer_outputs/checkpoint-3000/adapter_model.bin +3 -0
- trainer_outputs/checkpoint-3000/optimizer.pt +3 -0
- trainer_outputs/checkpoint-3000/rng_state.pth +3 -0
- trainer_outputs/checkpoint-3000/scheduler.pt +3 -0
- trainer_outputs/checkpoint-3000/trainer_state.json +919 -0
- trainer_outputs/checkpoint-3000/training_args.bin +3 -0
- trainer_outputs/checkpoint-3500/README.md +21 -0
- trainer_outputs/checkpoint-3500/adapter_config.json +21 -0
- trainer_outputs/checkpoint-3500/adapter_model.bin +3 -0
- trainer_outputs/checkpoint-3500/optimizer.pt +3 -0
- trainer_outputs/checkpoint-3500/rng_state.pth +3 -0
- trainer_outputs/checkpoint-3500/scheduler.pt +3 -0
- trainer_outputs/checkpoint-3500/trainer_state.json +1069 -0
- trainer_outputs/checkpoint-3500/training_args.bin +3 -0
- trainer_outputs/checkpoint-4000/README.md +21 -0
- trainer_outputs/checkpoint-4000/adapter_config.json +21 -0
trainer_outputs/checkpoint-1000/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-1000/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
trainer_outputs/checkpoint-1000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82799ca1a45fe916290346f1b9e0f1feddd4e86d9382374bfddf9b91c9ce63cf
|
| 3 |
+
size 25234701
|
trainer_outputs/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66889dd2cdecfb4f607a362a8d178c7677c707a9675e7d809725b0e44b0465e5
|
| 3 |
+
size 50492421
|
trainer_outputs/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f089defdca994fd4a77c942eddae1f8040469d99290aacaa2b7dd2f1c723771a
|
| 3 |
+
size 14575
|
trainer_outputs/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b66e5da39344e1f07ca8f668859ea57276c22f61d58e9090e115dea625966b1
|
| 3 |
+
size 627
|
trainer_outputs/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,319 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.2312272385687034,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1000,
|
| 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": 4e-05,
|
| 14 |
+
"loss": 1.0185,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 0.8649,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 0.7784,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 0.7386,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.7037,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001990530303030303,
|
| 44 |
+
"loss": 0.7019,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001981060606060606,
|
| 50 |
+
"loss": 0.7117,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 0.00019715909090909094,
|
| 56 |
+
"loss": 0.672,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.00019621212121212123,
|
| 62 |
+
"loss": 0.664,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00019526515151515152,
|
| 68 |
+
"loss": 0.6666,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001943181818181818,
|
| 74 |
+
"loss": 0.6685,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 0.00019337121212121213,
|
| 80 |
+
"loss": 0.6788,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.00019242424242424245,
|
| 86 |
+
"loss": 0.6673,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00019147727272727274,
|
| 92 |
+
"loss": 0.6628,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 0.00019053030303030303,
|
| 98 |
+
"loss": 0.6643,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.00018958333333333332,
|
| 104 |
+
"loss": 0.6607,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 0.00018863636363636364,
|
| 110 |
+
"loss": 0.6706,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.00018768939393939396,
|
| 116 |
+
"loss": 0.6709,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 0.00018674242424242425,
|
| 122 |
+
"loss": 0.6616,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.00018579545454545454,
|
| 128 |
+
"loss": 0.6566,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 0.00018484848484848484,
|
| 134 |
+
"loss": 0.6513,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 0.00018390151515151518,
|
| 140 |
+
"loss": 0.6797,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 0.00018295454545454547,
|
| 146 |
+
"loss": 0.6599,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.11,
|
| 151 |
+
"learning_rate": 0.00018200757575757577,
|
| 152 |
+
"loss": 0.6561,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 0.00018106060606060606,
|
| 158 |
+
"loss": 0.662,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 0.00018011363636363638,
|
| 164 |
+
"loss": 0.6629,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001791666666666667,
|
| 170 |
+
"loss": 0.6475,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 0.00017821969696969699,
|
| 176 |
+
"loss": 0.6607,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 0.00017727272727272728,
|
| 182 |
+
"loss": 0.6512,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 0.00017632575757575757,
|
| 188 |
+
"loss": 0.6484,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 0.0001753787878787879,
|
| 194 |
+
"loss": 0.6403,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 0.0001744318181818182,
|
| 200 |
+
"loss": 0.6537,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.15,
|
| 205 |
+
"learning_rate": 0.0001734848484848485,
|
| 206 |
+
"loss": 0.6516,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 0.0001725378787878788,
|
| 212 |
+
"loss": 0.6577,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"learning_rate": 0.00017159090909090908,
|
| 218 |
+
"loss": 0.6374,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 0.0001706439393939394,
|
| 224 |
+
"loss": 0.6551,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.17,
|
| 229 |
+
"learning_rate": 0.00016969696969696972,
|
| 230 |
+
"loss": 0.6388,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 0.00016875,
|
| 236 |
+
"loss": 0.64,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.18,
|
| 241 |
+
"learning_rate": 0.0001678030303030303,
|
| 242 |
+
"loss": 0.6579,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.18,
|
| 247 |
+
"learning_rate": 0.0001668560606060606,
|
| 248 |
+
"loss": 0.6525,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.19,
|
| 253 |
+
"learning_rate": 0.00016590909090909094,
|
| 254 |
+
"loss": 0.6261,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.19,
|
| 259 |
+
"learning_rate": 0.00016496212121212123,
|
| 260 |
+
"loss": 0.6351,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 0.00016401515151515152,
|
| 266 |
+
"loss": 0.6537,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 0.0001630681818181818,
|
| 272 |
+
"loss": 0.6448,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 0.00016212121212121213,
|
| 278 |
+
"loss": 0.638,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 0.00016117424242424245,
|
| 284 |
+
"loss": 0.6503,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 0.00016022727272727274,
|
| 290 |
+
"loss": 0.6378,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 0.00015928030303030303,
|
| 296 |
+
"loss": 0.643,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 0.00015833333333333332,
|
| 302 |
+
"loss": 0.6235,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 0.00015738636363636364,
|
| 308 |
+
"loss": 0.647,
|
| 309 |
+
"step": 1000
|
| 310 |
+
}
|
| 311 |
+
],
|
| 312 |
+
"logging_steps": 20,
|
| 313 |
+
"max_steps": 4324,
|
| 314 |
+
"num_train_epochs": 1,
|
| 315 |
+
"save_steps": 500,
|
| 316 |
+
"total_flos": 1.585613047974052e+17,
|
| 317 |
+
"trial_name": null,
|
| 318 |
+
"trial_params": null
|
| 319 |
+
}
|
trainer_outputs/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228d256901ac224db1b4d229c9c22d5c5a0db9d57b13da26daf55eb856deda8
|
| 3 |
+
size 4027
|
trainer_outputs/checkpoint-1500/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-1500/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
trainer_outputs/checkpoint-1500/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f29b3f38bf25dcaff8e7b129981d4b9c2bee90a0f37f1f989c8d2d617403ffe6
|
| 3 |
+
size 25234701
|
trainer_outputs/checkpoint-1500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c61af784ec13831fee055258efb45cf0e65c5b2c4e37ec22fc7233cfa9bd8201
|
| 3 |
+
size 50492421
|
trainer_outputs/checkpoint-1500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b82c3ec8adf3edbc776662f56f6ace906d215005bbb5145d4decfc9fcf8884dc
|
| 3 |
+
size 14575
|
trainer_outputs/checkpoint-1500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d95b496b8b0cc781be268c6cc8cc1122584ff984d38077c6c85705da817465a
|
| 3 |
+
size 627
|
trainer_outputs/checkpoint-1500/trainer_state.json
ADDED
|
@@ -0,0 +1,469 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.3468408578530551,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 1500,
|
| 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": 4e-05,
|
| 14 |
+
"loss": 1.0185,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 0.8649,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 0.7784,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 0.7386,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.7037,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001990530303030303,
|
| 44 |
+
"loss": 0.7019,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001981060606060606,
|
| 50 |
+
"loss": 0.7117,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 0.00019715909090909094,
|
| 56 |
+
"loss": 0.672,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.00019621212121212123,
|
| 62 |
+
"loss": 0.664,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00019526515151515152,
|
| 68 |
+
"loss": 0.6666,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001943181818181818,
|
| 74 |
+
"loss": 0.6685,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 0.00019337121212121213,
|
| 80 |
+
"loss": 0.6788,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.00019242424242424245,
|
| 86 |
+
"loss": 0.6673,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00019147727272727274,
|
| 92 |
+
"loss": 0.6628,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 0.00019053030303030303,
|
| 98 |
+
"loss": 0.6643,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.00018958333333333332,
|
| 104 |
+
"loss": 0.6607,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 0.00018863636363636364,
|
| 110 |
+
"loss": 0.6706,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.00018768939393939396,
|
| 116 |
+
"loss": 0.6709,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 0.00018674242424242425,
|
| 122 |
+
"loss": 0.6616,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.00018579545454545454,
|
| 128 |
+
"loss": 0.6566,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 0.00018484848484848484,
|
| 134 |
+
"loss": 0.6513,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 0.00018390151515151518,
|
| 140 |
+
"loss": 0.6797,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 0.00018295454545454547,
|
| 146 |
+
"loss": 0.6599,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.11,
|
| 151 |
+
"learning_rate": 0.00018200757575757577,
|
| 152 |
+
"loss": 0.6561,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 0.00018106060606060606,
|
| 158 |
+
"loss": 0.662,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 0.00018011363636363638,
|
| 164 |
+
"loss": 0.6629,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001791666666666667,
|
| 170 |
+
"loss": 0.6475,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 0.00017821969696969699,
|
| 176 |
+
"loss": 0.6607,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 0.00017727272727272728,
|
| 182 |
+
"loss": 0.6512,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 0.00017632575757575757,
|
| 188 |
+
"loss": 0.6484,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 0.0001753787878787879,
|
| 194 |
+
"loss": 0.6403,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 0.0001744318181818182,
|
| 200 |
+
"loss": 0.6537,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.15,
|
| 205 |
+
"learning_rate": 0.0001734848484848485,
|
| 206 |
+
"loss": 0.6516,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 0.0001725378787878788,
|
| 212 |
+
"loss": 0.6577,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"learning_rate": 0.00017159090909090908,
|
| 218 |
+
"loss": 0.6374,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 0.0001706439393939394,
|
| 224 |
+
"loss": 0.6551,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.17,
|
| 229 |
+
"learning_rate": 0.00016969696969696972,
|
| 230 |
+
"loss": 0.6388,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 0.00016875,
|
| 236 |
+
"loss": 0.64,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.18,
|
| 241 |
+
"learning_rate": 0.0001678030303030303,
|
| 242 |
+
"loss": 0.6579,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.18,
|
| 247 |
+
"learning_rate": 0.0001668560606060606,
|
| 248 |
+
"loss": 0.6525,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.19,
|
| 253 |
+
"learning_rate": 0.00016590909090909094,
|
| 254 |
+
"loss": 0.6261,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.19,
|
| 259 |
+
"learning_rate": 0.00016496212121212123,
|
| 260 |
+
"loss": 0.6351,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 0.00016401515151515152,
|
| 266 |
+
"loss": 0.6537,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 0.0001630681818181818,
|
| 272 |
+
"loss": 0.6448,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 0.00016212121212121213,
|
| 278 |
+
"loss": 0.638,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 0.00016117424242424245,
|
| 284 |
+
"loss": 0.6503,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 0.00016022727272727274,
|
| 290 |
+
"loss": 0.6378,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 0.00015928030303030303,
|
| 296 |
+
"loss": 0.643,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 0.00015833333333333332,
|
| 302 |
+
"loss": 0.6235,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 0.00015738636363636364,
|
| 308 |
+
"loss": 0.647,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 0.00015643939393939396,
|
| 314 |
+
"loss": 0.6408,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.24,
|
| 319 |
+
"learning_rate": 0.00015549242424242425,
|
| 320 |
+
"loss": 0.6391,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 0.00015454545454545454,
|
| 326 |
+
"loss": 0.6356,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.25,
|
| 331 |
+
"learning_rate": 0.00015359848484848484,
|
| 332 |
+
"loss": 0.6317,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.25,
|
| 337 |
+
"learning_rate": 0.00015265151515151515,
|
| 338 |
+
"loss": 0.6413,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.26,
|
| 343 |
+
"learning_rate": 0.00015170454545454547,
|
| 344 |
+
"loss": 0.6338,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 0.00015075757575757576,
|
| 350 |
+
"loss": 0.6422,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.27,
|
| 355 |
+
"learning_rate": 0.00014981060606060606,
|
| 356 |
+
"loss": 0.6442,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.27,
|
| 361 |
+
"learning_rate": 0.00014886363636363635,
|
| 362 |
+
"loss": 0.6523,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.28,
|
| 367 |
+
"learning_rate": 0.0001479166666666667,
|
| 368 |
+
"loss": 0.6349,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.28,
|
| 373 |
+
"learning_rate": 0.00014696969696969698,
|
| 374 |
+
"loss": 0.6389,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.29,
|
| 379 |
+
"learning_rate": 0.00014602272727272728,
|
| 380 |
+
"loss": 0.6468,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29,
|
| 385 |
+
"learning_rate": 0.00014507575757575757,
|
| 386 |
+
"loss": 0.6431,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3,
|
| 391 |
+
"learning_rate": 0.00014412878787878789,
|
| 392 |
+
"loss": 0.6287,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.3,
|
| 397 |
+
"learning_rate": 0.0001431818181818182,
|
| 398 |
+
"loss": 0.6438,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.31,
|
| 403 |
+
"learning_rate": 0.0001422348484848485,
|
| 404 |
+
"loss": 0.6274,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.31,
|
| 409 |
+
"learning_rate": 0.0001412878787878788,
|
| 410 |
+
"loss": 0.6286,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.31,
|
| 415 |
+
"learning_rate": 0.00014034090909090908,
|
| 416 |
+
"loss": 0.6401,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.32,
|
| 421 |
+
"learning_rate": 0.0001393939393939394,
|
| 422 |
+
"loss": 0.6472,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32,
|
| 427 |
+
"learning_rate": 0.00013844696969696972,
|
| 428 |
+
"loss": 0.6458,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.33,
|
| 433 |
+
"learning_rate": 0.0001375,
|
| 434 |
+
"loss": 0.6117,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.33,
|
| 439 |
+
"learning_rate": 0.0001365530303030303,
|
| 440 |
+
"loss": 0.6271,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.34,
|
| 445 |
+
"learning_rate": 0.0001356060606060606,
|
| 446 |
+
"loss": 0.6287,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.34,
|
| 451 |
+
"learning_rate": 0.00013465909090909094,
|
| 452 |
+
"loss": 0.6336,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.35,
|
| 457 |
+
"learning_rate": 0.00013371212121212123,
|
| 458 |
+
"loss": 0.6404,
|
| 459 |
+
"step": 1500
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 20,
|
| 463 |
+
"max_steps": 4324,
|
| 464 |
+
"num_train_epochs": 1,
|
| 465 |
+
"save_steps": 500,
|
| 466 |
+
"total_flos": 2.3869669769642803e+17,
|
| 467 |
+
"trial_name": null,
|
| 468 |
+
"trial_params": null
|
| 469 |
+
}
|
trainer_outputs/checkpoint-1500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228d256901ac224db1b4d229c9c22d5c5a0db9d57b13da26daf55eb856deda8
|
| 3 |
+
size 4027
|
trainer_outputs/checkpoint-2000/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-2000/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
trainer_outputs/checkpoint-2000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5f023896d3bce7e5c49eda104abd6b27e11486aaaecedbc4eae110aedb5f4a3
|
| 3 |
+
size 25234701
|
trainer_outputs/checkpoint-2000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a039b3641a121c8176a70d33b35f5e3be4162fbedc0ec7ccece47cacb8a5911
|
| 3 |
+
size 50492421
|
trainer_outputs/checkpoint-2000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8688f4574528b0dd0a74d53cc2c94a63206527c586044a61ce3ac53363dbbe16
|
| 3 |
+
size 14575
|
trainer_outputs/checkpoint-2000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14717a8990d65aecab81f167499716a720c74df7ac5531a158cd13cf1a7bb0c4
|
| 3 |
+
size 627
|
trainer_outputs/checkpoint-2000/trainer_state.json
ADDED
|
@@ -0,0 +1,619 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4624544771374068,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2000,
|
| 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": 4e-05,
|
| 14 |
+
"loss": 1.0185,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 0.8649,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 0.7784,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 0.7386,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.7037,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001990530303030303,
|
| 44 |
+
"loss": 0.7019,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001981060606060606,
|
| 50 |
+
"loss": 0.7117,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 0.00019715909090909094,
|
| 56 |
+
"loss": 0.672,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.00019621212121212123,
|
| 62 |
+
"loss": 0.664,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00019526515151515152,
|
| 68 |
+
"loss": 0.6666,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001943181818181818,
|
| 74 |
+
"loss": 0.6685,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 0.00019337121212121213,
|
| 80 |
+
"loss": 0.6788,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.00019242424242424245,
|
| 86 |
+
"loss": 0.6673,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00019147727272727274,
|
| 92 |
+
"loss": 0.6628,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 0.00019053030303030303,
|
| 98 |
+
"loss": 0.6643,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.00018958333333333332,
|
| 104 |
+
"loss": 0.6607,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 0.00018863636363636364,
|
| 110 |
+
"loss": 0.6706,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.00018768939393939396,
|
| 116 |
+
"loss": 0.6709,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 0.00018674242424242425,
|
| 122 |
+
"loss": 0.6616,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.00018579545454545454,
|
| 128 |
+
"loss": 0.6566,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 0.00018484848484848484,
|
| 134 |
+
"loss": 0.6513,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 0.00018390151515151518,
|
| 140 |
+
"loss": 0.6797,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 0.00018295454545454547,
|
| 146 |
+
"loss": 0.6599,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.11,
|
| 151 |
+
"learning_rate": 0.00018200757575757577,
|
| 152 |
+
"loss": 0.6561,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 0.00018106060606060606,
|
| 158 |
+
"loss": 0.662,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 0.00018011363636363638,
|
| 164 |
+
"loss": 0.6629,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001791666666666667,
|
| 170 |
+
"loss": 0.6475,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 0.00017821969696969699,
|
| 176 |
+
"loss": 0.6607,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 0.00017727272727272728,
|
| 182 |
+
"loss": 0.6512,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 0.00017632575757575757,
|
| 188 |
+
"loss": 0.6484,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 0.0001753787878787879,
|
| 194 |
+
"loss": 0.6403,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 0.0001744318181818182,
|
| 200 |
+
"loss": 0.6537,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.15,
|
| 205 |
+
"learning_rate": 0.0001734848484848485,
|
| 206 |
+
"loss": 0.6516,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 0.0001725378787878788,
|
| 212 |
+
"loss": 0.6577,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"learning_rate": 0.00017159090909090908,
|
| 218 |
+
"loss": 0.6374,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 0.0001706439393939394,
|
| 224 |
+
"loss": 0.6551,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.17,
|
| 229 |
+
"learning_rate": 0.00016969696969696972,
|
| 230 |
+
"loss": 0.6388,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 0.00016875,
|
| 236 |
+
"loss": 0.64,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.18,
|
| 241 |
+
"learning_rate": 0.0001678030303030303,
|
| 242 |
+
"loss": 0.6579,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.18,
|
| 247 |
+
"learning_rate": 0.0001668560606060606,
|
| 248 |
+
"loss": 0.6525,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.19,
|
| 253 |
+
"learning_rate": 0.00016590909090909094,
|
| 254 |
+
"loss": 0.6261,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.19,
|
| 259 |
+
"learning_rate": 0.00016496212121212123,
|
| 260 |
+
"loss": 0.6351,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 0.00016401515151515152,
|
| 266 |
+
"loss": 0.6537,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 0.0001630681818181818,
|
| 272 |
+
"loss": 0.6448,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 0.00016212121212121213,
|
| 278 |
+
"loss": 0.638,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 0.00016117424242424245,
|
| 284 |
+
"loss": 0.6503,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 0.00016022727272727274,
|
| 290 |
+
"loss": 0.6378,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 0.00015928030303030303,
|
| 296 |
+
"loss": 0.643,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 0.00015833333333333332,
|
| 302 |
+
"loss": 0.6235,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 0.00015738636363636364,
|
| 308 |
+
"loss": 0.647,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 0.00015643939393939396,
|
| 314 |
+
"loss": 0.6408,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.24,
|
| 319 |
+
"learning_rate": 0.00015549242424242425,
|
| 320 |
+
"loss": 0.6391,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 0.00015454545454545454,
|
| 326 |
+
"loss": 0.6356,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.25,
|
| 331 |
+
"learning_rate": 0.00015359848484848484,
|
| 332 |
+
"loss": 0.6317,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.25,
|
| 337 |
+
"learning_rate": 0.00015265151515151515,
|
| 338 |
+
"loss": 0.6413,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.26,
|
| 343 |
+
"learning_rate": 0.00015170454545454547,
|
| 344 |
+
"loss": 0.6338,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 0.00015075757575757576,
|
| 350 |
+
"loss": 0.6422,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.27,
|
| 355 |
+
"learning_rate": 0.00014981060606060606,
|
| 356 |
+
"loss": 0.6442,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.27,
|
| 361 |
+
"learning_rate": 0.00014886363636363635,
|
| 362 |
+
"loss": 0.6523,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.28,
|
| 367 |
+
"learning_rate": 0.0001479166666666667,
|
| 368 |
+
"loss": 0.6349,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.28,
|
| 373 |
+
"learning_rate": 0.00014696969696969698,
|
| 374 |
+
"loss": 0.6389,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.29,
|
| 379 |
+
"learning_rate": 0.00014602272727272728,
|
| 380 |
+
"loss": 0.6468,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29,
|
| 385 |
+
"learning_rate": 0.00014507575757575757,
|
| 386 |
+
"loss": 0.6431,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3,
|
| 391 |
+
"learning_rate": 0.00014412878787878789,
|
| 392 |
+
"loss": 0.6287,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.3,
|
| 397 |
+
"learning_rate": 0.0001431818181818182,
|
| 398 |
+
"loss": 0.6438,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.31,
|
| 403 |
+
"learning_rate": 0.0001422348484848485,
|
| 404 |
+
"loss": 0.6274,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.31,
|
| 409 |
+
"learning_rate": 0.0001412878787878788,
|
| 410 |
+
"loss": 0.6286,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.31,
|
| 415 |
+
"learning_rate": 0.00014034090909090908,
|
| 416 |
+
"loss": 0.6401,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.32,
|
| 421 |
+
"learning_rate": 0.0001393939393939394,
|
| 422 |
+
"loss": 0.6472,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32,
|
| 427 |
+
"learning_rate": 0.00013844696969696972,
|
| 428 |
+
"loss": 0.6458,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.33,
|
| 433 |
+
"learning_rate": 0.0001375,
|
| 434 |
+
"loss": 0.6117,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.33,
|
| 439 |
+
"learning_rate": 0.0001365530303030303,
|
| 440 |
+
"loss": 0.6271,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.34,
|
| 445 |
+
"learning_rate": 0.0001356060606060606,
|
| 446 |
+
"loss": 0.6287,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.34,
|
| 451 |
+
"learning_rate": 0.00013465909090909094,
|
| 452 |
+
"loss": 0.6336,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.35,
|
| 457 |
+
"learning_rate": 0.00013371212121212123,
|
| 458 |
+
"loss": 0.6404,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.35,
|
| 463 |
+
"learning_rate": 0.00013276515151515152,
|
| 464 |
+
"loss": 0.6312,
|
| 465 |
+
"step": 1520
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.36,
|
| 469 |
+
"learning_rate": 0.0001318181818181818,
|
| 470 |
+
"loss": 0.6168,
|
| 471 |
+
"step": 1540
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.36,
|
| 475 |
+
"learning_rate": 0.00013087121212121213,
|
| 476 |
+
"loss": 0.6272,
|
| 477 |
+
"step": 1560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.37,
|
| 481 |
+
"learning_rate": 0.00012992424242424245,
|
| 482 |
+
"loss": 0.6477,
|
| 483 |
+
"step": 1580
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.37,
|
| 487 |
+
"learning_rate": 0.00012897727272727274,
|
| 488 |
+
"loss": 0.6477,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.37,
|
| 493 |
+
"learning_rate": 0.00012803030303030303,
|
| 494 |
+
"loss": 0.6227,
|
| 495 |
+
"step": 1620
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.38,
|
| 499 |
+
"learning_rate": 0.00012708333333333332,
|
| 500 |
+
"loss": 0.6224,
|
| 501 |
+
"step": 1640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.38,
|
| 505 |
+
"learning_rate": 0.00012613636363636364,
|
| 506 |
+
"loss": 0.6315,
|
| 507 |
+
"step": 1660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.39,
|
| 511 |
+
"learning_rate": 0.00012518939393939396,
|
| 512 |
+
"loss": 0.631,
|
| 513 |
+
"step": 1680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.39,
|
| 517 |
+
"learning_rate": 0.00012424242424242425,
|
| 518 |
+
"loss": 0.6285,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.4,
|
| 523 |
+
"learning_rate": 0.00012329545454545454,
|
| 524 |
+
"loss": 0.6359,
|
| 525 |
+
"step": 1720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.4,
|
| 529 |
+
"learning_rate": 0.00012234848484848484,
|
| 530 |
+
"loss": 0.6282,
|
| 531 |
+
"step": 1740
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.41,
|
| 535 |
+
"learning_rate": 0.00012140151515151517,
|
| 536 |
+
"loss": 0.6196,
|
| 537 |
+
"step": 1760
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.41,
|
| 541 |
+
"learning_rate": 0.00012045454545454546,
|
| 542 |
+
"loss": 0.6346,
|
| 543 |
+
"step": 1780
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.42,
|
| 547 |
+
"learning_rate": 0.00011950757575757576,
|
| 548 |
+
"loss": 0.6323,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.42,
|
| 553 |
+
"learning_rate": 0.00011856060606060606,
|
| 554 |
+
"loss": 0.6108,
|
| 555 |
+
"step": 1820
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.43,
|
| 559 |
+
"learning_rate": 0.00011761363636363636,
|
| 560 |
+
"loss": 0.6324,
|
| 561 |
+
"step": 1840
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.43,
|
| 565 |
+
"learning_rate": 0.00011666666666666668,
|
| 566 |
+
"loss": 0.618,
|
| 567 |
+
"step": 1860
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.43,
|
| 571 |
+
"learning_rate": 0.00011571969696969698,
|
| 572 |
+
"loss": 0.6099,
|
| 573 |
+
"step": 1880
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.44,
|
| 577 |
+
"learning_rate": 0.00011477272727272728,
|
| 578 |
+
"loss": 0.6251,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.44,
|
| 583 |
+
"learning_rate": 0.00011382575757575758,
|
| 584 |
+
"loss": 0.6209,
|
| 585 |
+
"step": 1920
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.45,
|
| 589 |
+
"learning_rate": 0.0001128787878787879,
|
| 590 |
+
"loss": 0.6218,
|
| 591 |
+
"step": 1940
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.45,
|
| 595 |
+
"learning_rate": 0.00011193181818181819,
|
| 596 |
+
"loss": 0.6299,
|
| 597 |
+
"step": 1960
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.46,
|
| 601 |
+
"learning_rate": 0.0001109848484848485,
|
| 602 |
+
"loss": 0.6211,
|
| 603 |
+
"step": 1980
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.46,
|
| 607 |
+
"learning_rate": 0.00011003787878787879,
|
| 608 |
+
"loss": 0.6072,
|
| 609 |
+
"step": 2000
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 20,
|
| 613 |
+
"max_steps": 4324,
|
| 614 |
+
"num_train_epochs": 1,
|
| 615 |
+
"save_steps": 500,
|
| 616 |
+
"total_flos": 3.17991699908395e+17,
|
| 617 |
+
"trial_name": null,
|
| 618 |
+
"trial_params": null
|
| 619 |
+
}
|
trainer_outputs/checkpoint-2000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228d256901ac224db1b4d229c9c22d5c5a0db9d57b13da26daf55eb856deda8
|
| 3 |
+
size 4027
|
trainer_outputs/checkpoint-2500/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-2500/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
trainer_outputs/checkpoint-2500/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:232c8f03d31a9291d76c358dcd1d1ec35c9e353649649655c3cb339d78705648
|
| 3 |
+
size 25234701
|
trainer_outputs/checkpoint-2500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea86e060244a7a635f0bdd53220d40319af85bb4f19b7de97088630fe91b44fb
|
| 3 |
+
size 50492421
|
trainer_outputs/checkpoint-2500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cac5163dde6699de99afde41cd4831c7918e26095b1b779e0b6fe701f6bd9f5
|
| 3 |
+
size 14575
|
trainer_outputs/checkpoint-2500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b98e94e36151b9adbe76956f48af083681c1527c598d294d1c8d293199a3ccb
|
| 3 |
+
size 627
|
trainer_outputs/checkpoint-2500/trainer_state.json
ADDED
|
@@ -0,0 +1,769 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.5780680964217585,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 2500,
|
| 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": 4e-05,
|
| 14 |
+
"loss": 1.0185,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 0.8649,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 0.7784,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 0.7386,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.7037,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001990530303030303,
|
| 44 |
+
"loss": 0.7019,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001981060606060606,
|
| 50 |
+
"loss": 0.7117,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 0.00019715909090909094,
|
| 56 |
+
"loss": 0.672,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.00019621212121212123,
|
| 62 |
+
"loss": 0.664,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00019526515151515152,
|
| 68 |
+
"loss": 0.6666,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001943181818181818,
|
| 74 |
+
"loss": 0.6685,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 0.00019337121212121213,
|
| 80 |
+
"loss": 0.6788,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.00019242424242424245,
|
| 86 |
+
"loss": 0.6673,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00019147727272727274,
|
| 92 |
+
"loss": 0.6628,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 0.00019053030303030303,
|
| 98 |
+
"loss": 0.6643,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.00018958333333333332,
|
| 104 |
+
"loss": 0.6607,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 0.00018863636363636364,
|
| 110 |
+
"loss": 0.6706,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.00018768939393939396,
|
| 116 |
+
"loss": 0.6709,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 0.00018674242424242425,
|
| 122 |
+
"loss": 0.6616,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.00018579545454545454,
|
| 128 |
+
"loss": 0.6566,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 0.00018484848484848484,
|
| 134 |
+
"loss": 0.6513,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 0.00018390151515151518,
|
| 140 |
+
"loss": 0.6797,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 0.00018295454545454547,
|
| 146 |
+
"loss": 0.6599,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.11,
|
| 151 |
+
"learning_rate": 0.00018200757575757577,
|
| 152 |
+
"loss": 0.6561,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 0.00018106060606060606,
|
| 158 |
+
"loss": 0.662,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 0.00018011363636363638,
|
| 164 |
+
"loss": 0.6629,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001791666666666667,
|
| 170 |
+
"loss": 0.6475,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 0.00017821969696969699,
|
| 176 |
+
"loss": 0.6607,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 0.00017727272727272728,
|
| 182 |
+
"loss": 0.6512,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 0.00017632575757575757,
|
| 188 |
+
"loss": 0.6484,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 0.0001753787878787879,
|
| 194 |
+
"loss": 0.6403,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 0.0001744318181818182,
|
| 200 |
+
"loss": 0.6537,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.15,
|
| 205 |
+
"learning_rate": 0.0001734848484848485,
|
| 206 |
+
"loss": 0.6516,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 0.0001725378787878788,
|
| 212 |
+
"loss": 0.6577,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"learning_rate": 0.00017159090909090908,
|
| 218 |
+
"loss": 0.6374,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 0.0001706439393939394,
|
| 224 |
+
"loss": 0.6551,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.17,
|
| 229 |
+
"learning_rate": 0.00016969696969696972,
|
| 230 |
+
"loss": 0.6388,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 0.00016875,
|
| 236 |
+
"loss": 0.64,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.18,
|
| 241 |
+
"learning_rate": 0.0001678030303030303,
|
| 242 |
+
"loss": 0.6579,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.18,
|
| 247 |
+
"learning_rate": 0.0001668560606060606,
|
| 248 |
+
"loss": 0.6525,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.19,
|
| 253 |
+
"learning_rate": 0.00016590909090909094,
|
| 254 |
+
"loss": 0.6261,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.19,
|
| 259 |
+
"learning_rate": 0.00016496212121212123,
|
| 260 |
+
"loss": 0.6351,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 0.00016401515151515152,
|
| 266 |
+
"loss": 0.6537,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 0.0001630681818181818,
|
| 272 |
+
"loss": 0.6448,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 0.00016212121212121213,
|
| 278 |
+
"loss": 0.638,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 0.00016117424242424245,
|
| 284 |
+
"loss": 0.6503,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 0.00016022727272727274,
|
| 290 |
+
"loss": 0.6378,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 0.00015928030303030303,
|
| 296 |
+
"loss": 0.643,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 0.00015833333333333332,
|
| 302 |
+
"loss": 0.6235,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 0.00015738636363636364,
|
| 308 |
+
"loss": 0.647,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 0.00015643939393939396,
|
| 314 |
+
"loss": 0.6408,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.24,
|
| 319 |
+
"learning_rate": 0.00015549242424242425,
|
| 320 |
+
"loss": 0.6391,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 0.00015454545454545454,
|
| 326 |
+
"loss": 0.6356,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.25,
|
| 331 |
+
"learning_rate": 0.00015359848484848484,
|
| 332 |
+
"loss": 0.6317,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.25,
|
| 337 |
+
"learning_rate": 0.00015265151515151515,
|
| 338 |
+
"loss": 0.6413,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.26,
|
| 343 |
+
"learning_rate": 0.00015170454545454547,
|
| 344 |
+
"loss": 0.6338,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 0.00015075757575757576,
|
| 350 |
+
"loss": 0.6422,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.27,
|
| 355 |
+
"learning_rate": 0.00014981060606060606,
|
| 356 |
+
"loss": 0.6442,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.27,
|
| 361 |
+
"learning_rate": 0.00014886363636363635,
|
| 362 |
+
"loss": 0.6523,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.28,
|
| 367 |
+
"learning_rate": 0.0001479166666666667,
|
| 368 |
+
"loss": 0.6349,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.28,
|
| 373 |
+
"learning_rate": 0.00014696969696969698,
|
| 374 |
+
"loss": 0.6389,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.29,
|
| 379 |
+
"learning_rate": 0.00014602272727272728,
|
| 380 |
+
"loss": 0.6468,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29,
|
| 385 |
+
"learning_rate": 0.00014507575757575757,
|
| 386 |
+
"loss": 0.6431,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3,
|
| 391 |
+
"learning_rate": 0.00014412878787878789,
|
| 392 |
+
"loss": 0.6287,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.3,
|
| 397 |
+
"learning_rate": 0.0001431818181818182,
|
| 398 |
+
"loss": 0.6438,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.31,
|
| 403 |
+
"learning_rate": 0.0001422348484848485,
|
| 404 |
+
"loss": 0.6274,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.31,
|
| 409 |
+
"learning_rate": 0.0001412878787878788,
|
| 410 |
+
"loss": 0.6286,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.31,
|
| 415 |
+
"learning_rate": 0.00014034090909090908,
|
| 416 |
+
"loss": 0.6401,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.32,
|
| 421 |
+
"learning_rate": 0.0001393939393939394,
|
| 422 |
+
"loss": 0.6472,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32,
|
| 427 |
+
"learning_rate": 0.00013844696969696972,
|
| 428 |
+
"loss": 0.6458,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.33,
|
| 433 |
+
"learning_rate": 0.0001375,
|
| 434 |
+
"loss": 0.6117,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.33,
|
| 439 |
+
"learning_rate": 0.0001365530303030303,
|
| 440 |
+
"loss": 0.6271,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.34,
|
| 445 |
+
"learning_rate": 0.0001356060606060606,
|
| 446 |
+
"loss": 0.6287,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.34,
|
| 451 |
+
"learning_rate": 0.00013465909090909094,
|
| 452 |
+
"loss": 0.6336,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.35,
|
| 457 |
+
"learning_rate": 0.00013371212121212123,
|
| 458 |
+
"loss": 0.6404,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.35,
|
| 463 |
+
"learning_rate": 0.00013276515151515152,
|
| 464 |
+
"loss": 0.6312,
|
| 465 |
+
"step": 1520
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.36,
|
| 469 |
+
"learning_rate": 0.0001318181818181818,
|
| 470 |
+
"loss": 0.6168,
|
| 471 |
+
"step": 1540
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.36,
|
| 475 |
+
"learning_rate": 0.00013087121212121213,
|
| 476 |
+
"loss": 0.6272,
|
| 477 |
+
"step": 1560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.37,
|
| 481 |
+
"learning_rate": 0.00012992424242424245,
|
| 482 |
+
"loss": 0.6477,
|
| 483 |
+
"step": 1580
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.37,
|
| 487 |
+
"learning_rate": 0.00012897727272727274,
|
| 488 |
+
"loss": 0.6477,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.37,
|
| 493 |
+
"learning_rate": 0.00012803030303030303,
|
| 494 |
+
"loss": 0.6227,
|
| 495 |
+
"step": 1620
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.38,
|
| 499 |
+
"learning_rate": 0.00012708333333333332,
|
| 500 |
+
"loss": 0.6224,
|
| 501 |
+
"step": 1640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.38,
|
| 505 |
+
"learning_rate": 0.00012613636363636364,
|
| 506 |
+
"loss": 0.6315,
|
| 507 |
+
"step": 1660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.39,
|
| 511 |
+
"learning_rate": 0.00012518939393939396,
|
| 512 |
+
"loss": 0.631,
|
| 513 |
+
"step": 1680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.39,
|
| 517 |
+
"learning_rate": 0.00012424242424242425,
|
| 518 |
+
"loss": 0.6285,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.4,
|
| 523 |
+
"learning_rate": 0.00012329545454545454,
|
| 524 |
+
"loss": 0.6359,
|
| 525 |
+
"step": 1720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.4,
|
| 529 |
+
"learning_rate": 0.00012234848484848484,
|
| 530 |
+
"loss": 0.6282,
|
| 531 |
+
"step": 1740
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.41,
|
| 535 |
+
"learning_rate": 0.00012140151515151517,
|
| 536 |
+
"loss": 0.6196,
|
| 537 |
+
"step": 1760
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.41,
|
| 541 |
+
"learning_rate": 0.00012045454545454546,
|
| 542 |
+
"loss": 0.6346,
|
| 543 |
+
"step": 1780
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.42,
|
| 547 |
+
"learning_rate": 0.00011950757575757576,
|
| 548 |
+
"loss": 0.6323,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.42,
|
| 553 |
+
"learning_rate": 0.00011856060606060606,
|
| 554 |
+
"loss": 0.6108,
|
| 555 |
+
"step": 1820
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.43,
|
| 559 |
+
"learning_rate": 0.00011761363636363636,
|
| 560 |
+
"loss": 0.6324,
|
| 561 |
+
"step": 1840
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.43,
|
| 565 |
+
"learning_rate": 0.00011666666666666668,
|
| 566 |
+
"loss": 0.618,
|
| 567 |
+
"step": 1860
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.43,
|
| 571 |
+
"learning_rate": 0.00011571969696969698,
|
| 572 |
+
"loss": 0.6099,
|
| 573 |
+
"step": 1880
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.44,
|
| 577 |
+
"learning_rate": 0.00011477272727272728,
|
| 578 |
+
"loss": 0.6251,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.44,
|
| 583 |
+
"learning_rate": 0.00011382575757575758,
|
| 584 |
+
"loss": 0.6209,
|
| 585 |
+
"step": 1920
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.45,
|
| 589 |
+
"learning_rate": 0.0001128787878787879,
|
| 590 |
+
"loss": 0.6218,
|
| 591 |
+
"step": 1940
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.45,
|
| 595 |
+
"learning_rate": 0.00011193181818181819,
|
| 596 |
+
"loss": 0.6299,
|
| 597 |
+
"step": 1960
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.46,
|
| 601 |
+
"learning_rate": 0.0001109848484848485,
|
| 602 |
+
"loss": 0.6211,
|
| 603 |
+
"step": 1980
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.46,
|
| 607 |
+
"learning_rate": 0.00011003787878787879,
|
| 608 |
+
"loss": 0.6072,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.47,
|
| 613 |
+
"learning_rate": 0.00010909090909090909,
|
| 614 |
+
"loss": 0.6264,
|
| 615 |
+
"step": 2020
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.47,
|
| 619 |
+
"learning_rate": 0.00010814393939393941,
|
| 620 |
+
"loss": 0.6248,
|
| 621 |
+
"step": 2040
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.48,
|
| 625 |
+
"learning_rate": 0.0001071969696969697,
|
| 626 |
+
"loss": 0.6125,
|
| 627 |
+
"step": 2060
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.48,
|
| 631 |
+
"learning_rate": 0.00010625000000000001,
|
| 632 |
+
"loss": 0.6294,
|
| 633 |
+
"step": 2080
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.49,
|
| 637 |
+
"learning_rate": 0.0001053030303030303,
|
| 638 |
+
"loss": 0.6193,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.49,
|
| 643 |
+
"learning_rate": 0.0001043560606060606,
|
| 644 |
+
"loss": 0.6293,
|
| 645 |
+
"step": 2120
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.49,
|
| 649 |
+
"learning_rate": 0.00010340909090909092,
|
| 650 |
+
"loss": 0.629,
|
| 651 |
+
"step": 2140
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.5,
|
| 655 |
+
"learning_rate": 0.00010246212121212121,
|
| 656 |
+
"loss": 0.6353,
|
| 657 |
+
"step": 2160
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.5,
|
| 661 |
+
"learning_rate": 0.00010151515151515152,
|
| 662 |
+
"loss": 0.6268,
|
| 663 |
+
"step": 2180
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.51,
|
| 667 |
+
"learning_rate": 0.00010056818181818181,
|
| 668 |
+
"loss": 0.6256,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.51,
|
| 673 |
+
"learning_rate": 9.962121212121213e-05,
|
| 674 |
+
"loss": 0.6404,
|
| 675 |
+
"step": 2220
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.52,
|
| 679 |
+
"learning_rate": 9.867424242424242e-05,
|
| 680 |
+
"loss": 0.6347,
|
| 681 |
+
"step": 2240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.52,
|
| 685 |
+
"learning_rate": 9.772727272727274e-05,
|
| 686 |
+
"loss": 0.6317,
|
| 687 |
+
"step": 2260
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.53,
|
| 691 |
+
"learning_rate": 9.678030303030303e-05,
|
| 692 |
+
"loss": 0.6335,
|
| 693 |
+
"step": 2280
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.53,
|
| 697 |
+
"learning_rate": 9.583333333333334e-05,
|
| 698 |
+
"loss": 0.6239,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.54,
|
| 703 |
+
"learning_rate": 9.488636363636364e-05,
|
| 704 |
+
"loss": 0.6302,
|
| 705 |
+
"step": 2320
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.54,
|
| 709 |
+
"learning_rate": 9.393939393939395e-05,
|
| 710 |
+
"loss": 0.6182,
|
| 711 |
+
"step": 2340
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.55,
|
| 715 |
+
"learning_rate": 9.299242424242425e-05,
|
| 716 |
+
"loss": 0.6219,
|
| 717 |
+
"step": 2360
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.55,
|
| 721 |
+
"learning_rate": 9.204545454545454e-05,
|
| 722 |
+
"loss": 0.6229,
|
| 723 |
+
"step": 2380
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.55,
|
| 727 |
+
"learning_rate": 9.109848484848486e-05,
|
| 728 |
+
"loss": 0.6413,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.56,
|
| 733 |
+
"learning_rate": 9.015151515151515e-05,
|
| 734 |
+
"loss": 0.6237,
|
| 735 |
+
"step": 2420
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.56,
|
| 739 |
+
"learning_rate": 8.920454545454546e-05,
|
| 740 |
+
"loss": 0.6397,
|
| 741 |
+
"step": 2440
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.57,
|
| 745 |
+
"learning_rate": 8.825757575757576e-05,
|
| 746 |
+
"loss": 0.6259,
|
| 747 |
+
"step": 2460
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.57,
|
| 751 |
+
"learning_rate": 8.731060606060605e-05,
|
| 752 |
+
"loss": 0.634,
|
| 753 |
+
"step": 2480
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.58,
|
| 757 |
+
"learning_rate": 8.636363636363637e-05,
|
| 758 |
+
"loss": 0.622,
|
| 759 |
+
"step": 2500
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 20,
|
| 763 |
+
"max_steps": 4324,
|
| 764 |
+
"num_train_epochs": 1,
|
| 765 |
+
"save_steps": 500,
|
| 766 |
+
"total_flos": 3.972710256835707e+17,
|
| 767 |
+
"trial_name": null,
|
| 768 |
+
"trial_params": null
|
| 769 |
+
}
|
trainer_outputs/checkpoint-2500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228d256901ac224db1b4d229c9c22d5c5a0db9d57b13da26daf55eb856deda8
|
| 3 |
+
size 4027
|
trainer_outputs/checkpoint-3000/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-3000/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
trainer_outputs/checkpoint-3000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e858acac1298d05fd061f5db236358558d7da5467a6f587dfdabc156b10f1007
|
| 3 |
+
size 25234701
|
trainer_outputs/checkpoint-3000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cd8f4f87fafc48f5c57b8c135f3123244df4a6638af1f5dbafdfd8ab9f8d4f2
|
| 3 |
+
size 50492421
|
trainer_outputs/checkpoint-3000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a2c4d029b8b38ce03f11c146ff3d4b63707e299b27e04bbebd26959eb6cf2de
|
| 3 |
+
size 14575
|
trainer_outputs/checkpoint-3000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cff36dfd5c81bbf72d17b2bd6a4adff33fa030d7597ff652e5db60dce81e415
|
| 3 |
+
size 627
|
trainer_outputs/checkpoint-3000/trainer_state.json
ADDED
|
@@ -0,0 +1,919 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.6936817157061101,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3000,
|
| 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": 4e-05,
|
| 14 |
+
"loss": 1.0185,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 0.8649,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 0.7784,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 0.7386,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.7037,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001990530303030303,
|
| 44 |
+
"loss": 0.7019,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001981060606060606,
|
| 50 |
+
"loss": 0.7117,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 0.00019715909090909094,
|
| 56 |
+
"loss": 0.672,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.00019621212121212123,
|
| 62 |
+
"loss": 0.664,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00019526515151515152,
|
| 68 |
+
"loss": 0.6666,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001943181818181818,
|
| 74 |
+
"loss": 0.6685,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 0.00019337121212121213,
|
| 80 |
+
"loss": 0.6788,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.00019242424242424245,
|
| 86 |
+
"loss": 0.6673,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00019147727272727274,
|
| 92 |
+
"loss": 0.6628,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 0.00019053030303030303,
|
| 98 |
+
"loss": 0.6643,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.00018958333333333332,
|
| 104 |
+
"loss": 0.6607,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 0.00018863636363636364,
|
| 110 |
+
"loss": 0.6706,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.00018768939393939396,
|
| 116 |
+
"loss": 0.6709,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 0.00018674242424242425,
|
| 122 |
+
"loss": 0.6616,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.00018579545454545454,
|
| 128 |
+
"loss": 0.6566,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 0.00018484848484848484,
|
| 134 |
+
"loss": 0.6513,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 0.00018390151515151518,
|
| 140 |
+
"loss": 0.6797,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 0.00018295454545454547,
|
| 146 |
+
"loss": 0.6599,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.11,
|
| 151 |
+
"learning_rate": 0.00018200757575757577,
|
| 152 |
+
"loss": 0.6561,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 0.00018106060606060606,
|
| 158 |
+
"loss": 0.662,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 0.00018011363636363638,
|
| 164 |
+
"loss": 0.6629,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001791666666666667,
|
| 170 |
+
"loss": 0.6475,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 0.00017821969696969699,
|
| 176 |
+
"loss": 0.6607,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 0.00017727272727272728,
|
| 182 |
+
"loss": 0.6512,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 0.00017632575757575757,
|
| 188 |
+
"loss": 0.6484,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 0.0001753787878787879,
|
| 194 |
+
"loss": 0.6403,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 0.0001744318181818182,
|
| 200 |
+
"loss": 0.6537,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.15,
|
| 205 |
+
"learning_rate": 0.0001734848484848485,
|
| 206 |
+
"loss": 0.6516,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 0.0001725378787878788,
|
| 212 |
+
"loss": 0.6577,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"learning_rate": 0.00017159090909090908,
|
| 218 |
+
"loss": 0.6374,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 0.0001706439393939394,
|
| 224 |
+
"loss": 0.6551,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.17,
|
| 229 |
+
"learning_rate": 0.00016969696969696972,
|
| 230 |
+
"loss": 0.6388,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 0.00016875,
|
| 236 |
+
"loss": 0.64,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.18,
|
| 241 |
+
"learning_rate": 0.0001678030303030303,
|
| 242 |
+
"loss": 0.6579,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.18,
|
| 247 |
+
"learning_rate": 0.0001668560606060606,
|
| 248 |
+
"loss": 0.6525,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.19,
|
| 253 |
+
"learning_rate": 0.00016590909090909094,
|
| 254 |
+
"loss": 0.6261,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.19,
|
| 259 |
+
"learning_rate": 0.00016496212121212123,
|
| 260 |
+
"loss": 0.6351,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 0.00016401515151515152,
|
| 266 |
+
"loss": 0.6537,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 0.0001630681818181818,
|
| 272 |
+
"loss": 0.6448,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 0.00016212121212121213,
|
| 278 |
+
"loss": 0.638,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 0.00016117424242424245,
|
| 284 |
+
"loss": 0.6503,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 0.00016022727272727274,
|
| 290 |
+
"loss": 0.6378,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 0.00015928030303030303,
|
| 296 |
+
"loss": 0.643,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 0.00015833333333333332,
|
| 302 |
+
"loss": 0.6235,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 0.00015738636363636364,
|
| 308 |
+
"loss": 0.647,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 0.00015643939393939396,
|
| 314 |
+
"loss": 0.6408,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.24,
|
| 319 |
+
"learning_rate": 0.00015549242424242425,
|
| 320 |
+
"loss": 0.6391,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 0.00015454545454545454,
|
| 326 |
+
"loss": 0.6356,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.25,
|
| 331 |
+
"learning_rate": 0.00015359848484848484,
|
| 332 |
+
"loss": 0.6317,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.25,
|
| 337 |
+
"learning_rate": 0.00015265151515151515,
|
| 338 |
+
"loss": 0.6413,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.26,
|
| 343 |
+
"learning_rate": 0.00015170454545454547,
|
| 344 |
+
"loss": 0.6338,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 0.00015075757575757576,
|
| 350 |
+
"loss": 0.6422,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.27,
|
| 355 |
+
"learning_rate": 0.00014981060606060606,
|
| 356 |
+
"loss": 0.6442,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.27,
|
| 361 |
+
"learning_rate": 0.00014886363636363635,
|
| 362 |
+
"loss": 0.6523,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.28,
|
| 367 |
+
"learning_rate": 0.0001479166666666667,
|
| 368 |
+
"loss": 0.6349,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.28,
|
| 373 |
+
"learning_rate": 0.00014696969696969698,
|
| 374 |
+
"loss": 0.6389,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.29,
|
| 379 |
+
"learning_rate": 0.00014602272727272728,
|
| 380 |
+
"loss": 0.6468,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29,
|
| 385 |
+
"learning_rate": 0.00014507575757575757,
|
| 386 |
+
"loss": 0.6431,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3,
|
| 391 |
+
"learning_rate": 0.00014412878787878789,
|
| 392 |
+
"loss": 0.6287,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.3,
|
| 397 |
+
"learning_rate": 0.0001431818181818182,
|
| 398 |
+
"loss": 0.6438,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.31,
|
| 403 |
+
"learning_rate": 0.0001422348484848485,
|
| 404 |
+
"loss": 0.6274,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.31,
|
| 409 |
+
"learning_rate": 0.0001412878787878788,
|
| 410 |
+
"loss": 0.6286,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.31,
|
| 415 |
+
"learning_rate": 0.00014034090909090908,
|
| 416 |
+
"loss": 0.6401,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.32,
|
| 421 |
+
"learning_rate": 0.0001393939393939394,
|
| 422 |
+
"loss": 0.6472,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32,
|
| 427 |
+
"learning_rate": 0.00013844696969696972,
|
| 428 |
+
"loss": 0.6458,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.33,
|
| 433 |
+
"learning_rate": 0.0001375,
|
| 434 |
+
"loss": 0.6117,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.33,
|
| 439 |
+
"learning_rate": 0.0001365530303030303,
|
| 440 |
+
"loss": 0.6271,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.34,
|
| 445 |
+
"learning_rate": 0.0001356060606060606,
|
| 446 |
+
"loss": 0.6287,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.34,
|
| 451 |
+
"learning_rate": 0.00013465909090909094,
|
| 452 |
+
"loss": 0.6336,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.35,
|
| 457 |
+
"learning_rate": 0.00013371212121212123,
|
| 458 |
+
"loss": 0.6404,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.35,
|
| 463 |
+
"learning_rate": 0.00013276515151515152,
|
| 464 |
+
"loss": 0.6312,
|
| 465 |
+
"step": 1520
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.36,
|
| 469 |
+
"learning_rate": 0.0001318181818181818,
|
| 470 |
+
"loss": 0.6168,
|
| 471 |
+
"step": 1540
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.36,
|
| 475 |
+
"learning_rate": 0.00013087121212121213,
|
| 476 |
+
"loss": 0.6272,
|
| 477 |
+
"step": 1560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.37,
|
| 481 |
+
"learning_rate": 0.00012992424242424245,
|
| 482 |
+
"loss": 0.6477,
|
| 483 |
+
"step": 1580
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.37,
|
| 487 |
+
"learning_rate": 0.00012897727272727274,
|
| 488 |
+
"loss": 0.6477,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.37,
|
| 493 |
+
"learning_rate": 0.00012803030303030303,
|
| 494 |
+
"loss": 0.6227,
|
| 495 |
+
"step": 1620
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.38,
|
| 499 |
+
"learning_rate": 0.00012708333333333332,
|
| 500 |
+
"loss": 0.6224,
|
| 501 |
+
"step": 1640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.38,
|
| 505 |
+
"learning_rate": 0.00012613636363636364,
|
| 506 |
+
"loss": 0.6315,
|
| 507 |
+
"step": 1660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.39,
|
| 511 |
+
"learning_rate": 0.00012518939393939396,
|
| 512 |
+
"loss": 0.631,
|
| 513 |
+
"step": 1680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.39,
|
| 517 |
+
"learning_rate": 0.00012424242424242425,
|
| 518 |
+
"loss": 0.6285,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.4,
|
| 523 |
+
"learning_rate": 0.00012329545454545454,
|
| 524 |
+
"loss": 0.6359,
|
| 525 |
+
"step": 1720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.4,
|
| 529 |
+
"learning_rate": 0.00012234848484848484,
|
| 530 |
+
"loss": 0.6282,
|
| 531 |
+
"step": 1740
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.41,
|
| 535 |
+
"learning_rate": 0.00012140151515151517,
|
| 536 |
+
"loss": 0.6196,
|
| 537 |
+
"step": 1760
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.41,
|
| 541 |
+
"learning_rate": 0.00012045454545454546,
|
| 542 |
+
"loss": 0.6346,
|
| 543 |
+
"step": 1780
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.42,
|
| 547 |
+
"learning_rate": 0.00011950757575757576,
|
| 548 |
+
"loss": 0.6323,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.42,
|
| 553 |
+
"learning_rate": 0.00011856060606060606,
|
| 554 |
+
"loss": 0.6108,
|
| 555 |
+
"step": 1820
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.43,
|
| 559 |
+
"learning_rate": 0.00011761363636363636,
|
| 560 |
+
"loss": 0.6324,
|
| 561 |
+
"step": 1840
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.43,
|
| 565 |
+
"learning_rate": 0.00011666666666666668,
|
| 566 |
+
"loss": 0.618,
|
| 567 |
+
"step": 1860
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.43,
|
| 571 |
+
"learning_rate": 0.00011571969696969698,
|
| 572 |
+
"loss": 0.6099,
|
| 573 |
+
"step": 1880
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.44,
|
| 577 |
+
"learning_rate": 0.00011477272727272728,
|
| 578 |
+
"loss": 0.6251,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.44,
|
| 583 |
+
"learning_rate": 0.00011382575757575758,
|
| 584 |
+
"loss": 0.6209,
|
| 585 |
+
"step": 1920
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.45,
|
| 589 |
+
"learning_rate": 0.0001128787878787879,
|
| 590 |
+
"loss": 0.6218,
|
| 591 |
+
"step": 1940
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.45,
|
| 595 |
+
"learning_rate": 0.00011193181818181819,
|
| 596 |
+
"loss": 0.6299,
|
| 597 |
+
"step": 1960
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.46,
|
| 601 |
+
"learning_rate": 0.0001109848484848485,
|
| 602 |
+
"loss": 0.6211,
|
| 603 |
+
"step": 1980
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.46,
|
| 607 |
+
"learning_rate": 0.00011003787878787879,
|
| 608 |
+
"loss": 0.6072,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.47,
|
| 613 |
+
"learning_rate": 0.00010909090909090909,
|
| 614 |
+
"loss": 0.6264,
|
| 615 |
+
"step": 2020
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.47,
|
| 619 |
+
"learning_rate": 0.00010814393939393941,
|
| 620 |
+
"loss": 0.6248,
|
| 621 |
+
"step": 2040
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.48,
|
| 625 |
+
"learning_rate": 0.0001071969696969697,
|
| 626 |
+
"loss": 0.6125,
|
| 627 |
+
"step": 2060
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.48,
|
| 631 |
+
"learning_rate": 0.00010625000000000001,
|
| 632 |
+
"loss": 0.6294,
|
| 633 |
+
"step": 2080
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.49,
|
| 637 |
+
"learning_rate": 0.0001053030303030303,
|
| 638 |
+
"loss": 0.6193,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.49,
|
| 643 |
+
"learning_rate": 0.0001043560606060606,
|
| 644 |
+
"loss": 0.6293,
|
| 645 |
+
"step": 2120
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.49,
|
| 649 |
+
"learning_rate": 0.00010340909090909092,
|
| 650 |
+
"loss": 0.629,
|
| 651 |
+
"step": 2140
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.5,
|
| 655 |
+
"learning_rate": 0.00010246212121212121,
|
| 656 |
+
"loss": 0.6353,
|
| 657 |
+
"step": 2160
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.5,
|
| 661 |
+
"learning_rate": 0.00010151515151515152,
|
| 662 |
+
"loss": 0.6268,
|
| 663 |
+
"step": 2180
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.51,
|
| 667 |
+
"learning_rate": 0.00010056818181818181,
|
| 668 |
+
"loss": 0.6256,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.51,
|
| 673 |
+
"learning_rate": 9.962121212121213e-05,
|
| 674 |
+
"loss": 0.6404,
|
| 675 |
+
"step": 2220
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.52,
|
| 679 |
+
"learning_rate": 9.867424242424242e-05,
|
| 680 |
+
"loss": 0.6347,
|
| 681 |
+
"step": 2240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.52,
|
| 685 |
+
"learning_rate": 9.772727272727274e-05,
|
| 686 |
+
"loss": 0.6317,
|
| 687 |
+
"step": 2260
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.53,
|
| 691 |
+
"learning_rate": 9.678030303030303e-05,
|
| 692 |
+
"loss": 0.6335,
|
| 693 |
+
"step": 2280
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.53,
|
| 697 |
+
"learning_rate": 9.583333333333334e-05,
|
| 698 |
+
"loss": 0.6239,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.54,
|
| 703 |
+
"learning_rate": 9.488636363636364e-05,
|
| 704 |
+
"loss": 0.6302,
|
| 705 |
+
"step": 2320
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.54,
|
| 709 |
+
"learning_rate": 9.393939393939395e-05,
|
| 710 |
+
"loss": 0.6182,
|
| 711 |
+
"step": 2340
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.55,
|
| 715 |
+
"learning_rate": 9.299242424242425e-05,
|
| 716 |
+
"loss": 0.6219,
|
| 717 |
+
"step": 2360
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.55,
|
| 721 |
+
"learning_rate": 9.204545454545454e-05,
|
| 722 |
+
"loss": 0.6229,
|
| 723 |
+
"step": 2380
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.55,
|
| 727 |
+
"learning_rate": 9.109848484848486e-05,
|
| 728 |
+
"loss": 0.6413,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.56,
|
| 733 |
+
"learning_rate": 9.015151515151515e-05,
|
| 734 |
+
"loss": 0.6237,
|
| 735 |
+
"step": 2420
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.56,
|
| 739 |
+
"learning_rate": 8.920454545454546e-05,
|
| 740 |
+
"loss": 0.6397,
|
| 741 |
+
"step": 2440
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.57,
|
| 745 |
+
"learning_rate": 8.825757575757576e-05,
|
| 746 |
+
"loss": 0.6259,
|
| 747 |
+
"step": 2460
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.57,
|
| 751 |
+
"learning_rate": 8.731060606060605e-05,
|
| 752 |
+
"loss": 0.634,
|
| 753 |
+
"step": 2480
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.58,
|
| 757 |
+
"learning_rate": 8.636363636363637e-05,
|
| 758 |
+
"loss": 0.622,
|
| 759 |
+
"step": 2500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.58,
|
| 763 |
+
"learning_rate": 8.541666666666666e-05,
|
| 764 |
+
"loss": 0.6279,
|
| 765 |
+
"step": 2520
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.59,
|
| 769 |
+
"learning_rate": 8.446969696969697e-05,
|
| 770 |
+
"loss": 0.6306,
|
| 771 |
+
"step": 2540
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.59,
|
| 775 |
+
"learning_rate": 8.352272727272727e-05,
|
| 776 |
+
"loss": 0.6288,
|
| 777 |
+
"step": 2560
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6,
|
| 781 |
+
"learning_rate": 8.257575757575758e-05,
|
| 782 |
+
"loss": 0.6297,
|
| 783 |
+
"step": 2580
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.6,
|
| 787 |
+
"learning_rate": 8.162878787878789e-05,
|
| 788 |
+
"loss": 0.6119,
|
| 789 |
+
"step": 2600
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.61,
|
| 793 |
+
"learning_rate": 8.068181818181818e-05,
|
| 794 |
+
"loss": 0.6227,
|
| 795 |
+
"step": 2620
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.61,
|
| 799 |
+
"learning_rate": 7.97348484848485e-05,
|
| 800 |
+
"loss": 0.6317,
|
| 801 |
+
"step": 2640
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.62,
|
| 805 |
+
"learning_rate": 7.878787878787879e-05,
|
| 806 |
+
"loss": 0.619,
|
| 807 |
+
"step": 2660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.62,
|
| 811 |
+
"learning_rate": 7.784090909090909e-05,
|
| 812 |
+
"loss": 0.6156,
|
| 813 |
+
"step": 2680
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.62,
|
| 817 |
+
"learning_rate": 7.68939393939394e-05,
|
| 818 |
+
"loss": 0.6116,
|
| 819 |
+
"step": 2700
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.63,
|
| 823 |
+
"learning_rate": 7.59469696969697e-05,
|
| 824 |
+
"loss": 0.6009,
|
| 825 |
+
"step": 2720
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.63,
|
| 829 |
+
"learning_rate": 7.500000000000001e-05,
|
| 830 |
+
"loss": 0.6226,
|
| 831 |
+
"step": 2740
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.64,
|
| 835 |
+
"learning_rate": 7.40530303030303e-05,
|
| 836 |
+
"loss": 0.6246,
|
| 837 |
+
"step": 2760
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.64,
|
| 841 |
+
"learning_rate": 7.310606060606062e-05,
|
| 842 |
+
"loss": 0.6035,
|
| 843 |
+
"step": 2780
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.65,
|
| 847 |
+
"learning_rate": 7.215909090909091e-05,
|
| 848 |
+
"loss": 0.6059,
|
| 849 |
+
"step": 2800
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.65,
|
| 853 |
+
"learning_rate": 7.121212121212121e-05,
|
| 854 |
+
"loss": 0.6387,
|
| 855 |
+
"step": 2820
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.66,
|
| 859 |
+
"learning_rate": 7.026515151515152e-05,
|
| 860 |
+
"loss": 0.6314,
|
| 861 |
+
"step": 2840
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.66,
|
| 865 |
+
"learning_rate": 6.931818181818182e-05,
|
| 866 |
+
"loss": 0.6246,
|
| 867 |
+
"step": 2860
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.67,
|
| 871 |
+
"learning_rate": 6.837121212121213e-05,
|
| 872 |
+
"loss": 0.6448,
|
| 873 |
+
"step": 2880
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.67,
|
| 877 |
+
"learning_rate": 6.742424242424242e-05,
|
| 878 |
+
"loss": 0.5997,
|
| 879 |
+
"step": 2900
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.68,
|
| 883 |
+
"learning_rate": 6.647727272727274e-05,
|
| 884 |
+
"loss": 0.6238,
|
| 885 |
+
"step": 2920
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.68,
|
| 889 |
+
"learning_rate": 6.553030303030303e-05,
|
| 890 |
+
"loss": 0.614,
|
| 891 |
+
"step": 2940
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.68,
|
| 895 |
+
"learning_rate": 6.458333333333334e-05,
|
| 896 |
+
"loss": 0.6162,
|
| 897 |
+
"step": 2960
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.69,
|
| 901 |
+
"learning_rate": 6.363636363636364e-05,
|
| 902 |
+
"loss": 0.6087,
|
| 903 |
+
"step": 2980
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.69,
|
| 907 |
+
"learning_rate": 6.268939393939395e-05,
|
| 908 |
+
"loss": 0.6215,
|
| 909 |
+
"step": 3000
|
| 910 |
+
}
|
| 911 |
+
],
|
| 912 |
+
"logging_steps": 20,
|
| 913 |
+
"max_steps": 4324,
|
| 914 |
+
"num_train_epochs": 1,
|
| 915 |
+
"save_steps": 500,
|
| 916 |
+
"total_flos": 4.765794561611612e+17,
|
| 917 |
+
"trial_name": null,
|
| 918 |
+
"trial_params": null
|
| 919 |
+
}
|
trainer_outputs/checkpoint-3000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228d256901ac224db1b4d229c9c22d5c5a0db9d57b13da26daf55eb856deda8
|
| 3 |
+
size 4027
|
trainer_outputs/checkpoint-3500/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-3500/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
trainer_outputs/checkpoint-3500/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8aa6a4b12739df4688b250dd42d8865ac502c5a0dd524517df8835286483fe6
|
| 3 |
+
size 25234701
|
trainer_outputs/checkpoint-3500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bd31c79477c8bb20a9e4fb58d06bfaa1153405e0d8f485f44dbeab8a05279f9
|
| 3 |
+
size 50492421
|
trainer_outputs/checkpoint-3500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0d2c9d6c9d4ebaf9f40dab1df0a6bc899fcb38fbb02ef45403f0219e1031b81
|
| 3 |
+
size 14575
|
trainer_outputs/checkpoint-3500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2396934a3bf1f6f3d1949f841a8f1c1aa502806ee333ffb75a170b9c1a5fbbe
|
| 3 |
+
size 627
|
trainer_outputs/checkpoint-3500/trainer_state.json
ADDED
|
@@ -0,0 +1,1069 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.8092953349904619,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3500,
|
| 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": 4e-05,
|
| 14 |
+
"loss": 1.0185,
|
| 15 |
+
"step": 20
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8e-05,
|
| 20 |
+
"loss": 0.8649,
|
| 21 |
+
"step": 40
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 0.00012,
|
| 26 |
+
"loss": 0.7784,
|
| 27 |
+
"step": 60
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 0.00016,
|
| 32 |
+
"loss": 0.7386,
|
| 33 |
+
"step": 80
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 0.0002,
|
| 38 |
+
"loss": 0.7037,
|
| 39 |
+
"step": 100
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 0.0001990530303030303,
|
| 44 |
+
"loss": 0.7019,
|
| 45 |
+
"step": 120
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 0.0001981060606060606,
|
| 50 |
+
"loss": 0.7117,
|
| 51 |
+
"step": 140
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 0.00019715909090909094,
|
| 56 |
+
"loss": 0.672,
|
| 57 |
+
"step": 160
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 0.00019621212121212123,
|
| 62 |
+
"loss": 0.664,
|
| 63 |
+
"step": 180
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 0.00019526515151515152,
|
| 68 |
+
"loss": 0.6666,
|
| 69 |
+
"step": 200
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 0.0001943181818181818,
|
| 74 |
+
"loss": 0.6685,
|
| 75 |
+
"step": 220
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 0.00019337121212121213,
|
| 80 |
+
"loss": 0.6788,
|
| 81 |
+
"step": 240
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 0.00019242424242424245,
|
| 86 |
+
"loss": 0.6673,
|
| 87 |
+
"step": 260
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.06,
|
| 91 |
+
"learning_rate": 0.00019147727272727274,
|
| 92 |
+
"loss": 0.6628,
|
| 93 |
+
"step": 280
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 0.00019053030303030303,
|
| 98 |
+
"loss": 0.6643,
|
| 99 |
+
"step": 300
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.07,
|
| 103 |
+
"learning_rate": 0.00018958333333333332,
|
| 104 |
+
"loss": 0.6607,
|
| 105 |
+
"step": 320
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 0.00018863636363636364,
|
| 110 |
+
"loss": 0.6706,
|
| 111 |
+
"step": 340
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.08,
|
| 115 |
+
"learning_rate": 0.00018768939393939396,
|
| 116 |
+
"loss": 0.6709,
|
| 117 |
+
"step": 360
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 0.00018674242424242425,
|
| 122 |
+
"loss": 0.6616,
|
| 123 |
+
"step": 380
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.09,
|
| 127 |
+
"learning_rate": 0.00018579545454545454,
|
| 128 |
+
"loss": 0.6566,
|
| 129 |
+
"step": 400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 0.00018484848484848484,
|
| 134 |
+
"loss": 0.6513,
|
| 135 |
+
"step": 420
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.1,
|
| 139 |
+
"learning_rate": 0.00018390151515151518,
|
| 140 |
+
"loss": 0.6797,
|
| 141 |
+
"step": 440
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 0.00018295454545454547,
|
| 146 |
+
"loss": 0.6599,
|
| 147 |
+
"step": 460
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.11,
|
| 151 |
+
"learning_rate": 0.00018200757575757577,
|
| 152 |
+
"loss": 0.6561,
|
| 153 |
+
"step": 480
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 0.00018106060606060606,
|
| 158 |
+
"loss": 0.662,
|
| 159 |
+
"step": 500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 0.00018011363636363638,
|
| 164 |
+
"loss": 0.6629,
|
| 165 |
+
"step": 520
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.12,
|
| 169 |
+
"learning_rate": 0.0001791666666666667,
|
| 170 |
+
"loss": 0.6475,
|
| 171 |
+
"step": 540
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 0.00017821969696969699,
|
| 176 |
+
"loss": 0.6607,
|
| 177 |
+
"step": 560
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.13,
|
| 181 |
+
"learning_rate": 0.00017727272727272728,
|
| 182 |
+
"loss": 0.6512,
|
| 183 |
+
"step": 580
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 0.00017632575757575757,
|
| 188 |
+
"loss": 0.6484,
|
| 189 |
+
"step": 600
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.14,
|
| 193 |
+
"learning_rate": 0.0001753787878787879,
|
| 194 |
+
"loss": 0.6403,
|
| 195 |
+
"step": 620
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 0.0001744318181818182,
|
| 200 |
+
"loss": 0.6537,
|
| 201 |
+
"step": 640
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.15,
|
| 205 |
+
"learning_rate": 0.0001734848484848485,
|
| 206 |
+
"loss": 0.6516,
|
| 207 |
+
"step": 660
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 0.0001725378787878788,
|
| 212 |
+
"loss": 0.6577,
|
| 213 |
+
"step": 680
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.16,
|
| 217 |
+
"learning_rate": 0.00017159090909090908,
|
| 218 |
+
"loss": 0.6374,
|
| 219 |
+
"step": 700
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 0.0001706439393939394,
|
| 224 |
+
"loss": 0.6551,
|
| 225 |
+
"step": 720
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.17,
|
| 229 |
+
"learning_rate": 0.00016969696969696972,
|
| 230 |
+
"loss": 0.6388,
|
| 231 |
+
"step": 740
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 0.00016875,
|
| 236 |
+
"loss": 0.64,
|
| 237 |
+
"step": 760
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.18,
|
| 241 |
+
"learning_rate": 0.0001678030303030303,
|
| 242 |
+
"loss": 0.6579,
|
| 243 |
+
"step": 780
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.18,
|
| 247 |
+
"learning_rate": 0.0001668560606060606,
|
| 248 |
+
"loss": 0.6525,
|
| 249 |
+
"step": 800
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.19,
|
| 253 |
+
"learning_rate": 0.00016590909090909094,
|
| 254 |
+
"loss": 0.6261,
|
| 255 |
+
"step": 820
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.19,
|
| 259 |
+
"learning_rate": 0.00016496212121212123,
|
| 260 |
+
"loss": 0.6351,
|
| 261 |
+
"step": 840
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.2,
|
| 265 |
+
"learning_rate": 0.00016401515151515152,
|
| 266 |
+
"loss": 0.6537,
|
| 267 |
+
"step": 860
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.2,
|
| 271 |
+
"learning_rate": 0.0001630681818181818,
|
| 272 |
+
"loss": 0.6448,
|
| 273 |
+
"step": 880
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.21,
|
| 277 |
+
"learning_rate": 0.00016212121212121213,
|
| 278 |
+
"loss": 0.638,
|
| 279 |
+
"step": 900
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.21,
|
| 283 |
+
"learning_rate": 0.00016117424242424245,
|
| 284 |
+
"loss": 0.6503,
|
| 285 |
+
"step": 920
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.22,
|
| 289 |
+
"learning_rate": 0.00016022727272727274,
|
| 290 |
+
"loss": 0.6378,
|
| 291 |
+
"step": 940
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.22,
|
| 295 |
+
"learning_rate": 0.00015928030303030303,
|
| 296 |
+
"loss": 0.643,
|
| 297 |
+
"step": 960
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 0.00015833333333333332,
|
| 302 |
+
"loss": 0.6235,
|
| 303 |
+
"step": 980
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.23,
|
| 307 |
+
"learning_rate": 0.00015738636363636364,
|
| 308 |
+
"loss": 0.647,
|
| 309 |
+
"step": 1000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 0.00015643939393939396,
|
| 314 |
+
"loss": 0.6408,
|
| 315 |
+
"step": 1020
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.24,
|
| 319 |
+
"learning_rate": 0.00015549242424242425,
|
| 320 |
+
"loss": 0.6391,
|
| 321 |
+
"step": 1040
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 0.00015454545454545454,
|
| 326 |
+
"loss": 0.6356,
|
| 327 |
+
"step": 1060
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.25,
|
| 331 |
+
"learning_rate": 0.00015359848484848484,
|
| 332 |
+
"loss": 0.6317,
|
| 333 |
+
"step": 1080
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.25,
|
| 337 |
+
"learning_rate": 0.00015265151515151515,
|
| 338 |
+
"loss": 0.6413,
|
| 339 |
+
"step": 1100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.26,
|
| 343 |
+
"learning_rate": 0.00015170454545454547,
|
| 344 |
+
"loss": 0.6338,
|
| 345 |
+
"step": 1120
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.26,
|
| 349 |
+
"learning_rate": 0.00015075757575757576,
|
| 350 |
+
"loss": 0.6422,
|
| 351 |
+
"step": 1140
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.27,
|
| 355 |
+
"learning_rate": 0.00014981060606060606,
|
| 356 |
+
"loss": 0.6442,
|
| 357 |
+
"step": 1160
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.27,
|
| 361 |
+
"learning_rate": 0.00014886363636363635,
|
| 362 |
+
"loss": 0.6523,
|
| 363 |
+
"step": 1180
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.28,
|
| 367 |
+
"learning_rate": 0.0001479166666666667,
|
| 368 |
+
"loss": 0.6349,
|
| 369 |
+
"step": 1200
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.28,
|
| 373 |
+
"learning_rate": 0.00014696969696969698,
|
| 374 |
+
"loss": 0.6389,
|
| 375 |
+
"step": 1220
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.29,
|
| 379 |
+
"learning_rate": 0.00014602272727272728,
|
| 380 |
+
"loss": 0.6468,
|
| 381 |
+
"step": 1240
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.29,
|
| 385 |
+
"learning_rate": 0.00014507575757575757,
|
| 386 |
+
"loss": 0.6431,
|
| 387 |
+
"step": 1260
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.3,
|
| 391 |
+
"learning_rate": 0.00014412878787878789,
|
| 392 |
+
"loss": 0.6287,
|
| 393 |
+
"step": 1280
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.3,
|
| 397 |
+
"learning_rate": 0.0001431818181818182,
|
| 398 |
+
"loss": 0.6438,
|
| 399 |
+
"step": 1300
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.31,
|
| 403 |
+
"learning_rate": 0.0001422348484848485,
|
| 404 |
+
"loss": 0.6274,
|
| 405 |
+
"step": 1320
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.31,
|
| 409 |
+
"learning_rate": 0.0001412878787878788,
|
| 410 |
+
"loss": 0.6286,
|
| 411 |
+
"step": 1340
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.31,
|
| 415 |
+
"learning_rate": 0.00014034090909090908,
|
| 416 |
+
"loss": 0.6401,
|
| 417 |
+
"step": 1360
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.32,
|
| 421 |
+
"learning_rate": 0.0001393939393939394,
|
| 422 |
+
"loss": 0.6472,
|
| 423 |
+
"step": 1380
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.32,
|
| 427 |
+
"learning_rate": 0.00013844696969696972,
|
| 428 |
+
"loss": 0.6458,
|
| 429 |
+
"step": 1400
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.33,
|
| 433 |
+
"learning_rate": 0.0001375,
|
| 434 |
+
"loss": 0.6117,
|
| 435 |
+
"step": 1420
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.33,
|
| 439 |
+
"learning_rate": 0.0001365530303030303,
|
| 440 |
+
"loss": 0.6271,
|
| 441 |
+
"step": 1440
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.34,
|
| 445 |
+
"learning_rate": 0.0001356060606060606,
|
| 446 |
+
"loss": 0.6287,
|
| 447 |
+
"step": 1460
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.34,
|
| 451 |
+
"learning_rate": 0.00013465909090909094,
|
| 452 |
+
"loss": 0.6336,
|
| 453 |
+
"step": 1480
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.35,
|
| 457 |
+
"learning_rate": 0.00013371212121212123,
|
| 458 |
+
"loss": 0.6404,
|
| 459 |
+
"step": 1500
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.35,
|
| 463 |
+
"learning_rate": 0.00013276515151515152,
|
| 464 |
+
"loss": 0.6312,
|
| 465 |
+
"step": 1520
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.36,
|
| 469 |
+
"learning_rate": 0.0001318181818181818,
|
| 470 |
+
"loss": 0.6168,
|
| 471 |
+
"step": 1540
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.36,
|
| 475 |
+
"learning_rate": 0.00013087121212121213,
|
| 476 |
+
"loss": 0.6272,
|
| 477 |
+
"step": 1560
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.37,
|
| 481 |
+
"learning_rate": 0.00012992424242424245,
|
| 482 |
+
"loss": 0.6477,
|
| 483 |
+
"step": 1580
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.37,
|
| 487 |
+
"learning_rate": 0.00012897727272727274,
|
| 488 |
+
"loss": 0.6477,
|
| 489 |
+
"step": 1600
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.37,
|
| 493 |
+
"learning_rate": 0.00012803030303030303,
|
| 494 |
+
"loss": 0.6227,
|
| 495 |
+
"step": 1620
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.38,
|
| 499 |
+
"learning_rate": 0.00012708333333333332,
|
| 500 |
+
"loss": 0.6224,
|
| 501 |
+
"step": 1640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.38,
|
| 505 |
+
"learning_rate": 0.00012613636363636364,
|
| 506 |
+
"loss": 0.6315,
|
| 507 |
+
"step": 1660
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.39,
|
| 511 |
+
"learning_rate": 0.00012518939393939396,
|
| 512 |
+
"loss": 0.631,
|
| 513 |
+
"step": 1680
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.39,
|
| 517 |
+
"learning_rate": 0.00012424242424242425,
|
| 518 |
+
"loss": 0.6285,
|
| 519 |
+
"step": 1700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.4,
|
| 523 |
+
"learning_rate": 0.00012329545454545454,
|
| 524 |
+
"loss": 0.6359,
|
| 525 |
+
"step": 1720
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.4,
|
| 529 |
+
"learning_rate": 0.00012234848484848484,
|
| 530 |
+
"loss": 0.6282,
|
| 531 |
+
"step": 1740
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.41,
|
| 535 |
+
"learning_rate": 0.00012140151515151517,
|
| 536 |
+
"loss": 0.6196,
|
| 537 |
+
"step": 1760
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.41,
|
| 541 |
+
"learning_rate": 0.00012045454545454546,
|
| 542 |
+
"loss": 0.6346,
|
| 543 |
+
"step": 1780
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.42,
|
| 547 |
+
"learning_rate": 0.00011950757575757576,
|
| 548 |
+
"loss": 0.6323,
|
| 549 |
+
"step": 1800
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.42,
|
| 553 |
+
"learning_rate": 0.00011856060606060606,
|
| 554 |
+
"loss": 0.6108,
|
| 555 |
+
"step": 1820
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.43,
|
| 559 |
+
"learning_rate": 0.00011761363636363636,
|
| 560 |
+
"loss": 0.6324,
|
| 561 |
+
"step": 1840
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.43,
|
| 565 |
+
"learning_rate": 0.00011666666666666668,
|
| 566 |
+
"loss": 0.618,
|
| 567 |
+
"step": 1860
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.43,
|
| 571 |
+
"learning_rate": 0.00011571969696969698,
|
| 572 |
+
"loss": 0.6099,
|
| 573 |
+
"step": 1880
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.44,
|
| 577 |
+
"learning_rate": 0.00011477272727272728,
|
| 578 |
+
"loss": 0.6251,
|
| 579 |
+
"step": 1900
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.44,
|
| 583 |
+
"learning_rate": 0.00011382575757575758,
|
| 584 |
+
"loss": 0.6209,
|
| 585 |
+
"step": 1920
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.45,
|
| 589 |
+
"learning_rate": 0.0001128787878787879,
|
| 590 |
+
"loss": 0.6218,
|
| 591 |
+
"step": 1940
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.45,
|
| 595 |
+
"learning_rate": 0.00011193181818181819,
|
| 596 |
+
"loss": 0.6299,
|
| 597 |
+
"step": 1960
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.46,
|
| 601 |
+
"learning_rate": 0.0001109848484848485,
|
| 602 |
+
"loss": 0.6211,
|
| 603 |
+
"step": 1980
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.46,
|
| 607 |
+
"learning_rate": 0.00011003787878787879,
|
| 608 |
+
"loss": 0.6072,
|
| 609 |
+
"step": 2000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.47,
|
| 613 |
+
"learning_rate": 0.00010909090909090909,
|
| 614 |
+
"loss": 0.6264,
|
| 615 |
+
"step": 2020
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.47,
|
| 619 |
+
"learning_rate": 0.00010814393939393941,
|
| 620 |
+
"loss": 0.6248,
|
| 621 |
+
"step": 2040
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.48,
|
| 625 |
+
"learning_rate": 0.0001071969696969697,
|
| 626 |
+
"loss": 0.6125,
|
| 627 |
+
"step": 2060
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.48,
|
| 631 |
+
"learning_rate": 0.00010625000000000001,
|
| 632 |
+
"loss": 0.6294,
|
| 633 |
+
"step": 2080
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.49,
|
| 637 |
+
"learning_rate": 0.0001053030303030303,
|
| 638 |
+
"loss": 0.6193,
|
| 639 |
+
"step": 2100
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.49,
|
| 643 |
+
"learning_rate": 0.0001043560606060606,
|
| 644 |
+
"loss": 0.6293,
|
| 645 |
+
"step": 2120
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.49,
|
| 649 |
+
"learning_rate": 0.00010340909090909092,
|
| 650 |
+
"loss": 0.629,
|
| 651 |
+
"step": 2140
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.5,
|
| 655 |
+
"learning_rate": 0.00010246212121212121,
|
| 656 |
+
"loss": 0.6353,
|
| 657 |
+
"step": 2160
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.5,
|
| 661 |
+
"learning_rate": 0.00010151515151515152,
|
| 662 |
+
"loss": 0.6268,
|
| 663 |
+
"step": 2180
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.51,
|
| 667 |
+
"learning_rate": 0.00010056818181818181,
|
| 668 |
+
"loss": 0.6256,
|
| 669 |
+
"step": 2200
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.51,
|
| 673 |
+
"learning_rate": 9.962121212121213e-05,
|
| 674 |
+
"loss": 0.6404,
|
| 675 |
+
"step": 2220
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.52,
|
| 679 |
+
"learning_rate": 9.867424242424242e-05,
|
| 680 |
+
"loss": 0.6347,
|
| 681 |
+
"step": 2240
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.52,
|
| 685 |
+
"learning_rate": 9.772727272727274e-05,
|
| 686 |
+
"loss": 0.6317,
|
| 687 |
+
"step": 2260
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.53,
|
| 691 |
+
"learning_rate": 9.678030303030303e-05,
|
| 692 |
+
"loss": 0.6335,
|
| 693 |
+
"step": 2280
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.53,
|
| 697 |
+
"learning_rate": 9.583333333333334e-05,
|
| 698 |
+
"loss": 0.6239,
|
| 699 |
+
"step": 2300
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.54,
|
| 703 |
+
"learning_rate": 9.488636363636364e-05,
|
| 704 |
+
"loss": 0.6302,
|
| 705 |
+
"step": 2320
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.54,
|
| 709 |
+
"learning_rate": 9.393939393939395e-05,
|
| 710 |
+
"loss": 0.6182,
|
| 711 |
+
"step": 2340
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.55,
|
| 715 |
+
"learning_rate": 9.299242424242425e-05,
|
| 716 |
+
"loss": 0.6219,
|
| 717 |
+
"step": 2360
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.55,
|
| 721 |
+
"learning_rate": 9.204545454545454e-05,
|
| 722 |
+
"loss": 0.6229,
|
| 723 |
+
"step": 2380
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.55,
|
| 727 |
+
"learning_rate": 9.109848484848486e-05,
|
| 728 |
+
"loss": 0.6413,
|
| 729 |
+
"step": 2400
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.56,
|
| 733 |
+
"learning_rate": 9.015151515151515e-05,
|
| 734 |
+
"loss": 0.6237,
|
| 735 |
+
"step": 2420
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.56,
|
| 739 |
+
"learning_rate": 8.920454545454546e-05,
|
| 740 |
+
"loss": 0.6397,
|
| 741 |
+
"step": 2440
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.57,
|
| 745 |
+
"learning_rate": 8.825757575757576e-05,
|
| 746 |
+
"loss": 0.6259,
|
| 747 |
+
"step": 2460
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.57,
|
| 751 |
+
"learning_rate": 8.731060606060605e-05,
|
| 752 |
+
"loss": 0.634,
|
| 753 |
+
"step": 2480
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.58,
|
| 757 |
+
"learning_rate": 8.636363636363637e-05,
|
| 758 |
+
"loss": 0.622,
|
| 759 |
+
"step": 2500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.58,
|
| 763 |
+
"learning_rate": 8.541666666666666e-05,
|
| 764 |
+
"loss": 0.6279,
|
| 765 |
+
"step": 2520
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.59,
|
| 769 |
+
"learning_rate": 8.446969696969697e-05,
|
| 770 |
+
"loss": 0.6306,
|
| 771 |
+
"step": 2540
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.59,
|
| 775 |
+
"learning_rate": 8.352272727272727e-05,
|
| 776 |
+
"loss": 0.6288,
|
| 777 |
+
"step": 2560
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.6,
|
| 781 |
+
"learning_rate": 8.257575757575758e-05,
|
| 782 |
+
"loss": 0.6297,
|
| 783 |
+
"step": 2580
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.6,
|
| 787 |
+
"learning_rate": 8.162878787878789e-05,
|
| 788 |
+
"loss": 0.6119,
|
| 789 |
+
"step": 2600
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.61,
|
| 793 |
+
"learning_rate": 8.068181818181818e-05,
|
| 794 |
+
"loss": 0.6227,
|
| 795 |
+
"step": 2620
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.61,
|
| 799 |
+
"learning_rate": 7.97348484848485e-05,
|
| 800 |
+
"loss": 0.6317,
|
| 801 |
+
"step": 2640
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.62,
|
| 805 |
+
"learning_rate": 7.878787878787879e-05,
|
| 806 |
+
"loss": 0.619,
|
| 807 |
+
"step": 2660
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.62,
|
| 811 |
+
"learning_rate": 7.784090909090909e-05,
|
| 812 |
+
"loss": 0.6156,
|
| 813 |
+
"step": 2680
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.62,
|
| 817 |
+
"learning_rate": 7.68939393939394e-05,
|
| 818 |
+
"loss": 0.6116,
|
| 819 |
+
"step": 2700
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.63,
|
| 823 |
+
"learning_rate": 7.59469696969697e-05,
|
| 824 |
+
"loss": 0.6009,
|
| 825 |
+
"step": 2720
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.63,
|
| 829 |
+
"learning_rate": 7.500000000000001e-05,
|
| 830 |
+
"loss": 0.6226,
|
| 831 |
+
"step": 2740
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.64,
|
| 835 |
+
"learning_rate": 7.40530303030303e-05,
|
| 836 |
+
"loss": 0.6246,
|
| 837 |
+
"step": 2760
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.64,
|
| 841 |
+
"learning_rate": 7.310606060606062e-05,
|
| 842 |
+
"loss": 0.6035,
|
| 843 |
+
"step": 2780
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.65,
|
| 847 |
+
"learning_rate": 7.215909090909091e-05,
|
| 848 |
+
"loss": 0.6059,
|
| 849 |
+
"step": 2800
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.65,
|
| 853 |
+
"learning_rate": 7.121212121212121e-05,
|
| 854 |
+
"loss": 0.6387,
|
| 855 |
+
"step": 2820
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.66,
|
| 859 |
+
"learning_rate": 7.026515151515152e-05,
|
| 860 |
+
"loss": 0.6314,
|
| 861 |
+
"step": 2840
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.66,
|
| 865 |
+
"learning_rate": 6.931818181818182e-05,
|
| 866 |
+
"loss": 0.6246,
|
| 867 |
+
"step": 2860
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.67,
|
| 871 |
+
"learning_rate": 6.837121212121213e-05,
|
| 872 |
+
"loss": 0.6448,
|
| 873 |
+
"step": 2880
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.67,
|
| 877 |
+
"learning_rate": 6.742424242424242e-05,
|
| 878 |
+
"loss": 0.5997,
|
| 879 |
+
"step": 2900
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.68,
|
| 883 |
+
"learning_rate": 6.647727272727274e-05,
|
| 884 |
+
"loss": 0.6238,
|
| 885 |
+
"step": 2920
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.68,
|
| 889 |
+
"learning_rate": 6.553030303030303e-05,
|
| 890 |
+
"loss": 0.614,
|
| 891 |
+
"step": 2940
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.68,
|
| 895 |
+
"learning_rate": 6.458333333333334e-05,
|
| 896 |
+
"loss": 0.6162,
|
| 897 |
+
"step": 2960
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.69,
|
| 901 |
+
"learning_rate": 6.363636363636364e-05,
|
| 902 |
+
"loss": 0.6087,
|
| 903 |
+
"step": 2980
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.69,
|
| 907 |
+
"learning_rate": 6.268939393939395e-05,
|
| 908 |
+
"loss": 0.6215,
|
| 909 |
+
"step": 3000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.7,
|
| 913 |
+
"learning_rate": 6.174242424242425e-05,
|
| 914 |
+
"loss": 0.6022,
|
| 915 |
+
"step": 3020
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.7,
|
| 919 |
+
"learning_rate": 6.079545454545454e-05,
|
| 920 |
+
"loss": 0.6294,
|
| 921 |
+
"step": 3040
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.71,
|
| 925 |
+
"learning_rate": 5.9848484848484854e-05,
|
| 926 |
+
"loss": 0.6187,
|
| 927 |
+
"step": 3060
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.71,
|
| 931 |
+
"learning_rate": 5.890151515151515e-05,
|
| 932 |
+
"loss": 0.6194,
|
| 933 |
+
"step": 3080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.72,
|
| 937 |
+
"learning_rate": 5.7954545454545464e-05,
|
| 938 |
+
"loss": 0.6109,
|
| 939 |
+
"step": 3100
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 0.72,
|
| 943 |
+
"learning_rate": 5.700757575757576e-05,
|
| 944 |
+
"loss": 0.638,
|
| 945 |
+
"step": 3120
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.73,
|
| 949 |
+
"learning_rate": 5.606060606060606e-05,
|
| 950 |
+
"loss": 0.6156,
|
| 951 |
+
"step": 3140
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.73,
|
| 955 |
+
"learning_rate": 5.5113636363636366e-05,
|
| 956 |
+
"loss": 0.6209,
|
| 957 |
+
"step": 3160
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.74,
|
| 961 |
+
"learning_rate": 5.4166666666666664e-05,
|
| 962 |
+
"loss": 0.6068,
|
| 963 |
+
"step": 3180
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.74,
|
| 967 |
+
"learning_rate": 5.3219696969696976e-05,
|
| 968 |
+
"loss": 0.6161,
|
| 969 |
+
"step": 3200
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.74,
|
| 973 |
+
"learning_rate": 5.2272727272727274e-05,
|
| 974 |
+
"loss": 0.6354,
|
| 975 |
+
"step": 3220
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.75,
|
| 979 |
+
"learning_rate": 5.132575757575758e-05,
|
| 980 |
+
"loss": 0.6317,
|
| 981 |
+
"step": 3240
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.75,
|
| 985 |
+
"learning_rate": 5.037878787878788e-05,
|
| 986 |
+
"loss": 0.6227,
|
| 987 |
+
"step": 3260
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.76,
|
| 991 |
+
"learning_rate": 4.943181818181818e-05,
|
| 992 |
+
"loss": 0.6176,
|
| 993 |
+
"step": 3280
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.76,
|
| 997 |
+
"learning_rate": 4.848484848484849e-05,
|
| 998 |
+
"loss": 0.6274,
|
| 999 |
+
"step": 3300
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.77,
|
| 1003 |
+
"learning_rate": 4.753787878787879e-05,
|
| 1004 |
+
"loss": 0.6159,
|
| 1005 |
+
"step": 3320
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.77,
|
| 1009 |
+
"learning_rate": 4.659090909090909e-05,
|
| 1010 |
+
"loss": 0.6093,
|
| 1011 |
+
"step": 3340
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.78,
|
| 1015 |
+
"learning_rate": 4.5643939393939396e-05,
|
| 1016 |
+
"loss": 0.6166,
|
| 1017 |
+
"step": 3360
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.78,
|
| 1021 |
+
"learning_rate": 4.46969696969697e-05,
|
| 1022 |
+
"loss": 0.6046,
|
| 1023 |
+
"step": 3380
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.79,
|
| 1027 |
+
"learning_rate": 4.375e-05,
|
| 1028 |
+
"loss": 0.6297,
|
| 1029 |
+
"step": 3400
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.79,
|
| 1033 |
+
"learning_rate": 4.2803030303030305e-05,
|
| 1034 |
+
"loss": 0.6106,
|
| 1035 |
+
"step": 3420
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.8,
|
| 1039 |
+
"learning_rate": 4.185606060606061e-05,
|
| 1040 |
+
"loss": 0.6064,
|
| 1041 |
+
"step": 3440
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.8,
|
| 1045 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 1046 |
+
"loss": 0.6138,
|
| 1047 |
+
"step": 3460
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.8,
|
| 1051 |
+
"learning_rate": 3.996212121212121e-05,
|
| 1052 |
+
"loss": 0.6102,
|
| 1053 |
+
"step": 3480
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.81,
|
| 1057 |
+
"learning_rate": 3.901515151515152e-05,
|
| 1058 |
+
"loss": 0.61,
|
| 1059 |
+
"step": 3500
|
| 1060 |
+
}
|
| 1061 |
+
],
|
| 1062 |
+
"logging_steps": 20,
|
| 1063 |
+
"max_steps": 4324,
|
| 1064 |
+
"num_train_epochs": 1,
|
| 1065 |
+
"save_steps": 500,
|
| 1066 |
+
"total_flos": 5.559685980090532e+17,
|
| 1067 |
+
"trial_name": null,
|
| 1068 |
+
"trial_params": null
|
| 1069 |
+
}
|
trainer_outputs/checkpoint-3500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7228d256901ac224db1b4d229c9c22d5c5a0db9d57b13da26daf55eb856deda8
|
| 3 |
+
size 4027
|
trainer_outputs/checkpoint-4000/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: QuantizationMethod.BITS_AND_BYTES
|
| 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 0.4.0.dev0
|
trainer_outputs/checkpoint-4000/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-chat-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"fan_in_fan_out": false,
|
| 5 |
+
"inference_mode": true,
|
| 6 |
+
"init_lora_weights": true,
|
| 7 |
+
"layers_pattern": null,
|
| 8 |
+
"layers_to_transform": null,
|
| 9 |
+
"lora_alpha": 32,
|
| 10 |
+
"lora_dropout": 0.05,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"revision": null,
|
| 15 |
+
"target_modules": [
|
| 16 |
+
"q_proj",
|
| 17 |
+
"k_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|