Upload folder using huggingface_hub
Browse files
checkpoint-204/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "vidore/colpaligemma-3b-pt-448-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": "gaussian",
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": "(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
| 23 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 24 |
+
"use_dora": false,
|
| 25 |
+
"use_rslora": false
|
| 26 |
+
}
|
checkpoint-204/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ebcef182f505e54adc721326488e7508050c7df376f6debfad18f155bc49ab2
|
| 3 |
+
size 157071680
|
checkpoint-204/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16dd1d3753e52f1b9d48100abb662ea7b0b843d3f363f6e3e82463a853c7adef
|
| 3 |
+
size 314278906
|
checkpoint-204/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b9c5b06912a4fc32e428d6160536c166cda1c08b4c74517862f2e3d65337d91
|
| 3 |
+
size 14244
|
checkpoint-204/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acb8fe1e5d004b5d71099900aaa993567c53230962d397347705b3c8afb593bd
|
| 3 |
+
size 1064
|
checkpoint-204/trainer_state.json
ADDED
|
@@ -0,0 +1,362 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.978102189781022,
|
| 5 |
+
"eval_steps": 10,
|
| 6 |
+
"global_step": 204,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.014598540145985401,
|
| 13 |
+
"eval_loss": 0.3622247874736786,
|
| 14 |
+
"eval_model_preparation_time": 0.0061,
|
| 15 |
+
"eval_runtime": 39.4414,
|
| 16 |
+
"eval_samples_per_second": 6.947,
|
| 17 |
+
"eval_steps_per_second": 1.749,
|
| 18 |
+
"step": 1
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 0.145985401459854,
|
| 22 |
+
"grad_norm": 50.93666458129883,
|
| 23 |
+
"learning_rate": 5e-06,
|
| 24 |
+
"loss": 1.6392,
|
| 25 |
+
"step": 10
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.145985401459854,
|
| 29 |
+
"eval_loss": 0.3429737687110901,
|
| 30 |
+
"eval_model_preparation_time": 0.0061,
|
| 31 |
+
"eval_runtime": 39.7357,
|
| 32 |
+
"eval_samples_per_second": 6.896,
|
| 33 |
+
"eval_steps_per_second": 1.736,
|
| 34 |
+
"step": 10
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.291970802919708,
|
| 38 |
+
"grad_norm": 44.70755386352539,
|
| 39 |
+
"learning_rate": 1e-05,
|
| 40 |
+
"loss": 1.1999,
|
| 41 |
+
"step": 20
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.291970802919708,
|
| 45 |
+
"eval_loss": 0.304928719997406,
|
| 46 |
+
"eval_model_preparation_time": 0.0061,
|
| 47 |
+
"eval_runtime": 39.7745,
|
| 48 |
+
"eval_samples_per_second": 6.889,
|
| 49 |
+
"eval_steps_per_second": 1.735,
|
| 50 |
+
"step": 20
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.43795620437956206,
|
| 54 |
+
"grad_norm": 16.688669204711914,
|
| 55 |
+
"learning_rate": 1.5e-05,
|
| 56 |
+
"loss": 1.2826,
|
| 57 |
+
"step": 30
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.43795620437956206,
|
| 61 |
+
"eval_loss": 0.2768114507198334,
|
| 62 |
+
"eval_model_preparation_time": 0.0061,
|
| 63 |
+
"eval_runtime": 39.9306,
|
| 64 |
+
"eval_samples_per_second": 6.862,
|
| 65 |
+
"eval_steps_per_second": 1.728,
|
| 66 |
+
"step": 30
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.583941605839416,
|
| 70 |
+
"grad_norm": 25.983545303344727,
|
| 71 |
+
"learning_rate": 2e-05,
|
| 72 |
+
"loss": 0.7583,
|
| 73 |
+
"step": 40
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.583941605839416,
|
| 77 |
+
"eval_loss": 0.24917608499526978,
|
| 78 |
+
"eval_model_preparation_time": 0.0061,
|
| 79 |
+
"eval_runtime": 39.8008,
|
| 80 |
+
"eval_samples_per_second": 6.884,
|
| 81 |
+
"eval_steps_per_second": 1.734,
|
| 82 |
+
"step": 40
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.7299270072992701,
|
| 86 |
+
"grad_norm": 33.70819091796875,
|
| 87 |
+
"learning_rate": 2.5e-05,
|
| 88 |
+
"loss": 0.603,
|
| 89 |
+
"step": 50
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.7299270072992701,
|
| 93 |
+
"eval_loss": 0.2258419543504715,
|
| 94 |
+
"eval_model_preparation_time": 0.0061,
|
| 95 |
+
"eval_runtime": 39.8305,
|
| 96 |
+
"eval_samples_per_second": 6.879,
|
| 97 |
+
"eval_steps_per_second": 1.732,
|
| 98 |
+
"step": 50
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.8759124087591241,
|
| 102 |
+
"grad_norm": 22.157100677490234,
|
| 103 |
+
"learning_rate": 3e-05,
|
| 104 |
+
"loss": 1.014,
|
| 105 |
+
"step": 60
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.8759124087591241,
|
| 109 |
+
"eval_loss": 0.19583500921726227,
|
| 110 |
+
"eval_model_preparation_time": 0.0061,
|
| 111 |
+
"eval_runtime": 39.774,
|
| 112 |
+
"eval_samples_per_second": 6.889,
|
| 113 |
+
"eval_steps_per_second": 1.735,
|
| 114 |
+
"step": 60
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 1.0218978102189782,
|
| 118 |
+
"grad_norm": 9.168417930603027,
|
| 119 |
+
"learning_rate": 3.5e-05,
|
| 120 |
+
"loss": 0.8131,
|
| 121 |
+
"step": 70
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 1.0218978102189782,
|
| 125 |
+
"eval_loss": 0.16876357793807983,
|
| 126 |
+
"eval_model_preparation_time": 0.0061,
|
| 127 |
+
"eval_runtime": 40.0137,
|
| 128 |
+
"eval_samples_per_second": 6.848,
|
| 129 |
+
"eval_steps_per_second": 1.724,
|
| 130 |
+
"step": 70
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.167883211678832,
|
| 134 |
+
"grad_norm": 17.78595542907715,
|
| 135 |
+
"learning_rate": 4e-05,
|
| 136 |
+
"loss": 0.6346,
|
| 137 |
+
"step": 80
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.167883211678832,
|
| 141 |
+
"eval_loss": 0.1590624302625656,
|
| 142 |
+
"eval_model_preparation_time": 0.0061,
|
| 143 |
+
"eval_runtime": 40.2219,
|
| 144 |
+
"eval_samples_per_second": 6.812,
|
| 145 |
+
"eval_steps_per_second": 1.715,
|
| 146 |
+
"step": 80
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.313868613138686,
|
| 150 |
+
"grad_norm": 12.886183738708496,
|
| 151 |
+
"learning_rate": 4.5e-05,
|
| 152 |
+
"loss": 0.5089,
|
| 153 |
+
"step": 90
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 1.313868613138686,
|
| 157 |
+
"eval_loss": 0.15023882687091827,
|
| 158 |
+
"eval_model_preparation_time": 0.0061,
|
| 159 |
+
"eval_runtime": 40.1557,
|
| 160 |
+
"eval_samples_per_second": 6.823,
|
| 161 |
+
"eval_steps_per_second": 1.718,
|
| 162 |
+
"step": 90
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.4598540145985401,
|
| 166 |
+
"grad_norm": 5.830733299255371,
|
| 167 |
+
"learning_rate": 5e-05,
|
| 168 |
+
"loss": 0.4616,
|
| 169 |
+
"step": 100
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 1.4598540145985401,
|
| 173 |
+
"eval_loss": 0.1340549886226654,
|
| 174 |
+
"eval_model_preparation_time": 0.0061,
|
| 175 |
+
"eval_runtime": 40.1143,
|
| 176 |
+
"eval_samples_per_second": 6.83,
|
| 177 |
+
"eval_steps_per_second": 1.72,
|
| 178 |
+
"step": 100
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.6058394160583942,
|
| 182 |
+
"grad_norm": 8.617661476135254,
|
| 183 |
+
"learning_rate": 4.519230769230769e-05,
|
| 184 |
+
"loss": 0.4498,
|
| 185 |
+
"step": 110
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.6058394160583942,
|
| 189 |
+
"eval_loss": 0.11359694600105286,
|
| 190 |
+
"eval_model_preparation_time": 0.0061,
|
| 191 |
+
"eval_runtime": 39.9036,
|
| 192 |
+
"eval_samples_per_second": 6.867,
|
| 193 |
+
"eval_steps_per_second": 1.729,
|
| 194 |
+
"step": 110
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.7518248175182483,
|
| 198 |
+
"grad_norm": 120.68909454345703,
|
| 199 |
+
"learning_rate": 4.038461538461539e-05,
|
| 200 |
+
"loss": 0.4422,
|
| 201 |
+
"step": 120
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.7518248175182483,
|
| 205 |
+
"eval_loss": 0.10619519650936127,
|
| 206 |
+
"eval_model_preparation_time": 0.0061,
|
| 207 |
+
"eval_runtime": 39.9903,
|
| 208 |
+
"eval_samples_per_second": 6.852,
|
| 209 |
+
"eval_steps_per_second": 1.725,
|
| 210 |
+
"step": 120
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.897810218978102,
|
| 214 |
+
"grad_norm": 5.805586338043213,
|
| 215 |
+
"learning_rate": 3.557692307692308e-05,
|
| 216 |
+
"loss": 0.3519,
|
| 217 |
+
"step": 130
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 1.897810218978102,
|
| 221 |
+
"eval_loss": 0.09886428713798523,
|
| 222 |
+
"eval_model_preparation_time": 0.0061,
|
| 223 |
+
"eval_runtime": 39.9675,
|
| 224 |
+
"eval_samples_per_second": 6.856,
|
| 225 |
+
"eval_steps_per_second": 1.726,
|
| 226 |
+
"step": 130
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 2.0437956204379564,
|
| 230 |
+
"grad_norm": 11.567919731140137,
|
| 231 |
+
"learning_rate": 3.0769230769230774e-05,
|
| 232 |
+
"loss": 0.2382,
|
| 233 |
+
"step": 140
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.0437956204379564,
|
| 237 |
+
"eval_loss": 0.09246355295181274,
|
| 238 |
+
"eval_model_preparation_time": 0.0061,
|
| 239 |
+
"eval_runtime": 39.9889,
|
| 240 |
+
"eval_samples_per_second": 6.852,
|
| 241 |
+
"eval_steps_per_second": 1.725,
|
| 242 |
+
"step": 140
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.18978102189781,
|
| 246 |
+
"grad_norm": 38.91920852661133,
|
| 247 |
+
"learning_rate": 2.5961538461538464e-05,
|
| 248 |
+
"loss": 0.242,
|
| 249 |
+
"step": 150
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.18978102189781,
|
| 253 |
+
"eval_loss": 0.08943724632263184,
|
| 254 |
+
"eval_model_preparation_time": 0.0061,
|
| 255 |
+
"eval_runtime": 40.1851,
|
| 256 |
+
"eval_samples_per_second": 6.818,
|
| 257 |
+
"eval_steps_per_second": 1.717,
|
| 258 |
+
"step": 150
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.335766423357664,
|
| 262 |
+
"grad_norm": 0.6526745557785034,
|
| 263 |
+
"learning_rate": 2.1153846153846154e-05,
|
| 264 |
+
"loss": 0.3462,
|
| 265 |
+
"step": 160
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 2.335766423357664,
|
| 269 |
+
"eval_loss": 0.09070777893066406,
|
| 270 |
+
"eval_model_preparation_time": 0.0061,
|
| 271 |
+
"eval_runtime": 40.0427,
|
| 272 |
+
"eval_samples_per_second": 6.843,
|
| 273 |
+
"eval_steps_per_second": 1.723,
|
| 274 |
+
"step": 160
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 2.4817518248175183,
|
| 278 |
+
"grad_norm": 9.621135711669922,
|
| 279 |
+
"learning_rate": 1.6346153846153847e-05,
|
| 280 |
+
"loss": 0.1371,
|
| 281 |
+
"step": 170
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.4817518248175183,
|
| 285 |
+
"eval_loss": 0.08618415892124176,
|
| 286 |
+
"eval_model_preparation_time": 0.0061,
|
| 287 |
+
"eval_runtime": 39.9436,
|
| 288 |
+
"eval_samples_per_second": 6.86,
|
| 289 |
+
"eval_steps_per_second": 1.727,
|
| 290 |
+
"step": 170
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 2.627737226277372,
|
| 294 |
+
"grad_norm": 20.143051147460938,
|
| 295 |
+
"learning_rate": 1.153846153846154e-05,
|
| 296 |
+
"loss": 0.2691,
|
| 297 |
+
"step": 180
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.627737226277372,
|
| 301 |
+
"eval_loss": 0.08378317207098007,
|
| 302 |
+
"eval_model_preparation_time": 0.0061,
|
| 303 |
+
"eval_runtime": 40.04,
|
| 304 |
+
"eval_samples_per_second": 6.843,
|
| 305 |
+
"eval_steps_per_second": 1.723,
|
| 306 |
+
"step": 180
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.7737226277372264,
|
| 310 |
+
"grad_norm": 0.41237956285476685,
|
| 311 |
+
"learning_rate": 6.730769230769231e-06,
|
| 312 |
+
"loss": 0.0869,
|
| 313 |
+
"step": 190
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.7737226277372264,
|
| 317 |
+
"eval_loss": 0.08326868712902069,
|
| 318 |
+
"eval_model_preparation_time": 0.0061,
|
| 319 |
+
"eval_runtime": 39.9047,
|
| 320 |
+
"eval_samples_per_second": 6.866,
|
| 321 |
+
"eval_steps_per_second": 1.729,
|
| 322 |
+
"step": 190
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 2.9197080291970803,
|
| 326 |
+
"grad_norm": 0.11198130249977112,
|
| 327 |
+
"learning_rate": 1.9230769230769234e-06,
|
| 328 |
+
"loss": 0.3401,
|
| 329 |
+
"step": 200
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 2.9197080291970803,
|
| 333 |
+
"eval_loss": 0.0814913883805275,
|
| 334 |
+
"eval_model_preparation_time": 0.0061,
|
| 335 |
+
"eval_runtime": 39.93,
|
| 336 |
+
"eval_samples_per_second": 6.862,
|
| 337 |
+
"eval_steps_per_second": 1.728,
|
| 338 |
+
"step": 200
|
| 339 |
+
}
|
| 340 |
+
],
|
| 341 |
+
"logging_steps": 10,
|
| 342 |
+
"max_steps": 204,
|
| 343 |
+
"num_input_tokens_seen": 0,
|
| 344 |
+
"num_train_epochs": 3,
|
| 345 |
+
"save_steps": 10,
|
| 346 |
+
"stateful_callbacks": {
|
| 347 |
+
"TrainerControl": {
|
| 348 |
+
"args": {
|
| 349 |
+
"should_epoch_stop": false,
|
| 350 |
+
"should_evaluate": false,
|
| 351 |
+
"should_log": false,
|
| 352 |
+
"should_save": true,
|
| 353 |
+
"should_training_stop": true
|
| 354 |
+
},
|
| 355 |
+
"attributes": {}
|
| 356 |
+
}
|
| 357 |
+
},
|
| 358 |
+
"total_flos": 4.9136781869568e+16,
|
| 359 |
+
"train_batch_size": 4,
|
| 360 |
+
"trial_name": null,
|
| 361 |
+
"trial_params": null
|
| 362 |
+
}
|
checkpoint-204/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:669ba7c5243f079413201308d424089324b69c5a9c0b207e1d78881c731c29c6
|
| 3 |
+
size 5240
|