Training in progress, step 40000, checkpoint
Browse files- checkpoint-40000/README.md +21 -0
- checkpoint-40000/adapter_config.json +21 -0
- checkpoint-40000/adapter_model.bin +3 -0
- checkpoint-40000/optimizer.pt +3 -0
- checkpoint-40000/rng_state.pth +3 -0
- checkpoint-40000/scheduler.pt +3 -0
- checkpoint-40000/trainer_state.json +425 -0
- checkpoint-40000/training_args.bin +3 -0
checkpoint-40000/README.md
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 18 |
+
### Framework versions
|
| 19 |
+
|
| 20 |
+
|
| 21 |
+
- PEFT 0.6.0.dev0
|
checkpoint-40000/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "codellama/CodeLlama-13b-Instruct-hf",
|
| 4 |
+
"bias": "lora_only",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 8,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj"
|
| 19 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-40000/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:adf78a97e7504dc04bd7c6d8df6d59e3730166cc412c5822ffef70ae0a52b06c
|
| 3 |
+
size 26271757
|
checkpoint-40000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b21936c3e9d256a4d116dad03c1ce87ae611fdb088eb321af30950f62e7ddcf
|
| 3 |
+
size 13729605
|
checkpoint-40000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a2fac45065a5005849a3ffa471de4cb69e88eec06769e4f02ce0b4d61687a195
|
| 3 |
+
size 14575
|
checkpoint-40000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef3324ba7cb3e76247c320c59ed345f4e80d242cc17e0209f7b8c0323ee36d35
|
| 3 |
+
size 627
|
checkpoint-40000/trainer_state.json
ADDED
|
@@ -0,0 +1,425 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.01576746255159378,
|
| 3 |
+
"best_model_checkpoint": "./text2sql/13b-codellama_instruct_pt_text2sql/checkpoint-36000",
|
| 4 |
+
"epoch": 4.45592463917454,
|
| 5 |
+
"eval_steps": 2000,
|
| 6 |
+
"global_step": 40000,
|
| 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": 1.1139992573338283e-07,
|
| 14 |
+
"loss": 1.0897,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 0.00011139992573338284,
|
| 20 |
+
"loss": 0.2546,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.22,
|
| 25 |
+
"learning_rate": 0.00022279985146676567,
|
| 26 |
+
"loss": 0.0774,
|
| 27 |
+
"step": 2000
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.22,
|
| 31 |
+
"eval_loss": 0.0608125701546669,
|
| 32 |
+
"eval_runtime": 285.1249,
|
| 33 |
+
"eval_samples_per_second": 7.014,
|
| 34 |
+
"eval_steps_per_second": 1.754,
|
| 35 |
+
"step": 2000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.33,
|
| 39 |
+
"learning_rate": 0.00029781686301467276,
|
| 40 |
+
"loss": 0.0652,
|
| 41 |
+
"step": 3000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.45,
|
| 45 |
+
"learning_rate": 0.0002907056676227274,
|
| 46 |
+
"loss": 0.0581,
|
| 47 |
+
"step": 4000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.45,
|
| 51 |
+
"eval_loss": 0.04370184242725372,
|
| 52 |
+
"eval_runtime": 284.9797,
|
| 53 |
+
"eval_samples_per_second": 7.018,
|
| 54 |
+
"eval_steps_per_second": 1.755,
|
| 55 |
+
"step": 4000
|
| 56 |
+
},
|
| 57 |
+
{
|
| 58 |
+
"epoch": 0.56,
|
| 59 |
+
"learning_rate": 0.00028359447223078195,
|
| 60 |
+
"loss": 0.0499,
|
| 61 |
+
"step": 5000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.67,
|
| 65 |
+
"learning_rate": 0.0002764832768388366,
|
| 66 |
+
"loss": 0.0445,
|
| 67 |
+
"step": 6000
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.67,
|
| 71 |
+
"eval_loss": 0.036812592297792435,
|
| 72 |
+
"eval_runtime": 284.5683,
|
| 73 |
+
"eval_samples_per_second": 7.028,
|
| 74 |
+
"eval_steps_per_second": 1.757,
|
| 75 |
+
"step": 6000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.78,
|
| 79 |
+
"learning_rate": 0.0002693720814468912,
|
| 80 |
+
"loss": 0.0433,
|
| 81 |
+
"step": 7000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.89,
|
| 85 |
+
"learning_rate": 0.00026226088605494583,
|
| 86 |
+
"loss": 0.0378,
|
| 87 |
+
"step": 8000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.89,
|
| 91 |
+
"eval_loss": 0.03097330778837204,
|
| 92 |
+
"eval_runtime": 354.6673,
|
| 93 |
+
"eval_samples_per_second": 5.639,
|
| 94 |
+
"eval_steps_per_second": 1.41,
|
| 95 |
+
"step": 8000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 1.0,
|
| 99 |
+
"learning_rate": 0.00025514969066300046,
|
| 100 |
+
"loss": 0.0364,
|
| 101 |
+
"step": 9000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.11,
|
| 105 |
+
"learning_rate": 0.00024803849527105503,
|
| 106 |
+
"loss": 0.0312,
|
| 107 |
+
"step": 10000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 1.11,
|
| 111 |
+
"eval_loss": 0.02841157279908657,
|
| 112 |
+
"eval_runtime": 355.7754,
|
| 113 |
+
"eval_samples_per_second": 5.622,
|
| 114 |
+
"eval_steps_per_second": 1.405,
|
| 115 |
+
"step": 10000
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.23,
|
| 119 |
+
"learning_rate": 0.00024092729987910966,
|
| 120 |
+
"loss": 0.0307,
|
| 121 |
+
"step": 11000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.34,
|
| 125 |
+
"learning_rate": 0.00023381610448716428,
|
| 126 |
+
"loss": 0.0316,
|
| 127 |
+
"step": 12000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 1.34,
|
| 131 |
+
"eval_loss": 0.02577413246035576,
|
| 132 |
+
"eval_runtime": 284.3906,
|
| 133 |
+
"eval_samples_per_second": 7.033,
|
| 134 |
+
"eval_steps_per_second": 1.758,
|
| 135 |
+
"step": 12000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 1.45,
|
| 139 |
+
"learning_rate": 0.00022670490909521888,
|
| 140 |
+
"loss": 0.0272,
|
| 141 |
+
"step": 13000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 1.56,
|
| 145 |
+
"learning_rate": 0.0002195937137032735,
|
| 146 |
+
"loss": 0.0279,
|
| 147 |
+
"step": 14000
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 1.56,
|
| 151 |
+
"eval_loss": 0.024905819445848465,
|
| 152 |
+
"eval_runtime": 285.1649,
|
| 153 |
+
"eval_samples_per_second": 7.013,
|
| 154 |
+
"eval_steps_per_second": 1.753,
|
| 155 |
+
"step": 14000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.67,
|
| 159 |
+
"learning_rate": 0.00021248251831132813,
|
| 160 |
+
"loss": 0.0285,
|
| 161 |
+
"step": 15000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 1.78,
|
| 165 |
+
"learning_rate": 0.00020537132291938273,
|
| 166 |
+
"loss": 0.0266,
|
| 167 |
+
"step": 16000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.78,
|
| 171 |
+
"eval_loss": 0.023692620918154716,
|
| 172 |
+
"eval_runtime": 285.1334,
|
| 173 |
+
"eval_samples_per_second": 7.014,
|
| 174 |
+
"eval_steps_per_second": 1.754,
|
| 175 |
+
"step": 16000
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 1.89,
|
| 179 |
+
"learning_rate": 0.00019826012752743733,
|
| 180 |
+
"loss": 0.0266,
|
| 181 |
+
"step": 17000
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 2.01,
|
| 185 |
+
"learning_rate": 0.00019114893213549196,
|
| 186 |
+
"loss": 0.0258,
|
| 187 |
+
"step": 18000
|
| 188 |
+
},
|
| 189 |
+
{
|
| 190 |
+
"epoch": 2.01,
|
| 191 |
+
"eval_loss": 0.021677831187844276,
|
| 192 |
+
"eval_runtime": 285.282,
|
| 193 |
+
"eval_samples_per_second": 7.011,
|
| 194 |
+
"eval_steps_per_second": 1.753,
|
| 195 |
+
"step": 18000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 2.12,
|
| 199 |
+
"learning_rate": 0.00018403773674354658,
|
| 200 |
+
"loss": 0.0209,
|
| 201 |
+
"step": 19000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 2.23,
|
| 205 |
+
"learning_rate": 0.0001769265413516012,
|
| 206 |
+
"loss": 0.0211,
|
| 207 |
+
"step": 20000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 2.23,
|
| 211 |
+
"eval_loss": 0.020885193720459938,
|
| 212 |
+
"eval_runtime": 284.9168,
|
| 213 |
+
"eval_samples_per_second": 7.02,
|
| 214 |
+
"eval_steps_per_second": 1.755,
|
| 215 |
+
"step": 20000
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.34,
|
| 219 |
+
"learning_rate": 0.00016981534595965578,
|
| 220 |
+
"loss": 0.0209,
|
| 221 |
+
"step": 21000
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.45,
|
| 225 |
+
"learning_rate": 0.0001627041505677104,
|
| 226 |
+
"loss": 0.0194,
|
| 227 |
+
"step": 22000
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.45,
|
| 231 |
+
"eval_loss": 0.020141348242759705,
|
| 232 |
+
"eval_runtime": 285.3239,
|
| 233 |
+
"eval_samples_per_second": 7.01,
|
| 234 |
+
"eval_steps_per_second": 1.752,
|
| 235 |
+
"step": 22000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 2.56,
|
| 239 |
+
"learning_rate": 0.00015559295517576503,
|
| 240 |
+
"loss": 0.0212,
|
| 241 |
+
"step": 23000
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 2.67,
|
| 245 |
+
"learning_rate": 0.00014848175978381966,
|
| 246 |
+
"loss": 0.0202,
|
| 247 |
+
"step": 24000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 2.67,
|
| 251 |
+
"eval_loss": 0.019859744235873222,
|
| 252 |
+
"eval_runtime": 285.2272,
|
| 253 |
+
"eval_samples_per_second": 7.012,
|
| 254 |
+
"eval_steps_per_second": 1.753,
|
| 255 |
+
"step": 24000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.78,
|
| 259 |
+
"learning_rate": 0.00014137056439187426,
|
| 260 |
+
"loss": 0.0191,
|
| 261 |
+
"step": 25000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.9,
|
| 265 |
+
"learning_rate": 0.00013425936899992888,
|
| 266 |
+
"loss": 0.0183,
|
| 267 |
+
"step": 26000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.9,
|
| 271 |
+
"eval_loss": 0.01871539279818535,
|
| 272 |
+
"eval_runtime": 285.1023,
|
| 273 |
+
"eval_samples_per_second": 7.015,
|
| 274 |
+
"eval_steps_per_second": 1.754,
|
| 275 |
+
"step": 26000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 3.01,
|
| 279 |
+
"learning_rate": 0.00012714817360798348,
|
| 280 |
+
"loss": 0.0175,
|
| 281 |
+
"step": 27000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 3.12,
|
| 285 |
+
"learning_rate": 0.00012003697821603811,
|
| 286 |
+
"loss": 0.0158,
|
| 287 |
+
"step": 28000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 3.12,
|
| 291 |
+
"eval_loss": 0.017088208347558975,
|
| 292 |
+
"eval_runtime": 284.6987,
|
| 293 |
+
"eval_samples_per_second": 7.025,
|
| 294 |
+
"eval_steps_per_second": 1.756,
|
| 295 |
+
"step": 28000
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 3.23,
|
| 299 |
+
"learning_rate": 0.00011292578282409272,
|
| 300 |
+
"loss": 0.0154,
|
| 301 |
+
"step": 29000
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"epoch": 3.34,
|
| 305 |
+
"learning_rate": 0.00010581458743214733,
|
| 306 |
+
"loss": 0.0143,
|
| 307 |
+
"step": 30000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.34,
|
| 311 |
+
"eval_loss": 0.017135081812739372,
|
| 312 |
+
"eval_runtime": 284.2489,
|
| 313 |
+
"eval_samples_per_second": 7.036,
|
| 314 |
+
"eval_steps_per_second": 1.759,
|
| 315 |
+
"step": 30000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 3.45,
|
| 319 |
+
"learning_rate": 9.870339204020194e-05,
|
| 320 |
+
"loss": 0.015,
|
| 321 |
+
"step": 31000
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.56,
|
| 325 |
+
"learning_rate": 9.159219664825657e-05,
|
| 326 |
+
"loss": 0.0148,
|
| 327 |
+
"step": 32000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 3.56,
|
| 331 |
+
"eval_loss": 0.017010025680065155,
|
| 332 |
+
"eval_runtime": 284.4395,
|
| 333 |
+
"eval_samples_per_second": 7.031,
|
| 334 |
+
"eval_steps_per_second": 1.758,
|
| 335 |
+
"step": 32000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.68,
|
| 339 |
+
"learning_rate": 8.448100125631117e-05,
|
| 340 |
+
"loss": 0.0148,
|
| 341 |
+
"step": 33000
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 3.79,
|
| 345 |
+
"learning_rate": 7.73698058643658e-05,
|
| 346 |
+
"loss": 0.013,
|
| 347 |
+
"step": 34000
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 3.79,
|
| 351 |
+
"eval_loss": 0.01629829593002796,
|
| 352 |
+
"eval_runtime": 284.3551,
|
| 353 |
+
"eval_samples_per_second": 7.033,
|
| 354 |
+
"eval_steps_per_second": 1.758,
|
| 355 |
+
"step": 34000
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 3.9,
|
| 359 |
+
"learning_rate": 7.025861047242041e-05,
|
| 360 |
+
"loss": 0.0139,
|
| 361 |
+
"step": 35000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.01,
|
| 365 |
+
"learning_rate": 6.314741508047502e-05,
|
| 366 |
+
"loss": 0.0129,
|
| 367 |
+
"step": 36000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 4.01,
|
| 371 |
+
"eval_loss": 0.01576746255159378,
|
| 372 |
+
"eval_runtime": 284.6218,
|
| 373 |
+
"eval_samples_per_second": 7.027,
|
| 374 |
+
"eval_steps_per_second": 1.757,
|
| 375 |
+
"step": 36000
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 4.12,
|
| 379 |
+
"learning_rate": 5.603621968852963e-05,
|
| 380 |
+
"loss": 0.0104,
|
| 381 |
+
"step": 37000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 4.23,
|
| 385 |
+
"learning_rate": 4.8925024296584245e-05,
|
| 386 |
+
"loss": 0.0104,
|
| 387 |
+
"step": 38000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 4.23,
|
| 391 |
+
"eval_loss": 0.016835128888487816,
|
| 392 |
+
"eval_runtime": 284.6011,
|
| 393 |
+
"eval_samples_per_second": 7.027,
|
| 394 |
+
"eval_steps_per_second": 1.757,
|
| 395 |
+
"step": 38000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 4.34,
|
| 399 |
+
"learning_rate": 4.181382890463887e-05,
|
| 400 |
+
"loss": 0.0102,
|
| 401 |
+
"step": 39000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.46,
|
| 405 |
+
"learning_rate": 3.4702633512693484e-05,
|
| 406 |
+
"loss": 0.0103,
|
| 407 |
+
"step": 40000
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 4.46,
|
| 411 |
+
"eval_loss": 0.015947848558425903,
|
| 412 |
+
"eval_runtime": 284.6501,
|
| 413 |
+
"eval_samples_per_second": 7.026,
|
| 414 |
+
"eval_steps_per_second": 1.757,
|
| 415 |
+
"step": 40000
|
| 416 |
+
}
|
| 417 |
+
],
|
| 418 |
+
"logging_steps": 1000,
|
| 419 |
+
"max_steps": 44880,
|
| 420 |
+
"num_train_epochs": 5,
|
| 421 |
+
"save_steps": 2000,
|
| 422 |
+
"total_flos": 2.753717732442243e+19,
|
| 423 |
+
"trial_name": null,
|
| 424 |
+
"trial_params": null
|
| 425 |
+
}
|
checkpoint-40000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a01f3a3b51470d76c911f16f658a5b2f1c2fa53e2254151c1cfd84b69dd4c6c9
|
| 3 |
+
size 4283
|