Upload folder using huggingface_hub
Browse files- checkpoint-6400/config.json +74 -0
- checkpoint-6400/model.safetensors +3 -0
- checkpoint-6400/optimizer.pt +3 -0
- checkpoint-6400/preprocessor_config.json +22 -0
- checkpoint-6400/rng_state.pth +3 -0
- checkpoint-6400/scheduler.pt +3 -0
- checkpoint-6400/trainer_state.json +285 -0
- checkpoint-6400/training_args.bin +3 -0
- model.safetensors +1 -1
checkpoint-6400/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "dima806/facial_age_image_detection",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"ViTForImageClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.0,
|
| 7 |
+
"encoder_stride": 16,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.0,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "01",
|
| 13 |
+
"1": "02",
|
| 14 |
+
"2": "03",
|
| 15 |
+
"3": "04",
|
| 16 |
+
"4": "05",
|
| 17 |
+
"5": "06-07",
|
| 18 |
+
"6": "08-09",
|
| 19 |
+
"7": "10-12",
|
| 20 |
+
"8": "13-15",
|
| 21 |
+
"9": "16-20",
|
| 22 |
+
"10": "21-25",
|
| 23 |
+
"11": "26-30",
|
| 24 |
+
"12": "31-35",
|
| 25 |
+
"13": "36-40",
|
| 26 |
+
"14": "41-45",
|
| 27 |
+
"15": "46-50",
|
| 28 |
+
"16": "51-55",
|
| 29 |
+
"17": "56-60",
|
| 30 |
+
"18": "61-65",
|
| 31 |
+
"19": "66-70",
|
| 32 |
+
"20": "71-80",
|
| 33 |
+
"21": "81-90",
|
| 34 |
+
"22": "90+"
|
| 35 |
+
},
|
| 36 |
+
"image_size": 224,
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": 3072,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"01": 0,
|
| 41 |
+
"02": 1,
|
| 42 |
+
"03": 2,
|
| 43 |
+
"04": 3,
|
| 44 |
+
"05": 4,
|
| 45 |
+
"06-07": 5,
|
| 46 |
+
"08-09": 6,
|
| 47 |
+
"10-12": 7,
|
| 48 |
+
"13-15": 8,
|
| 49 |
+
"16-20": 9,
|
| 50 |
+
"21-25": 10,
|
| 51 |
+
"26-30": 11,
|
| 52 |
+
"31-35": 12,
|
| 53 |
+
"36-40": 13,
|
| 54 |
+
"41-45": 14,
|
| 55 |
+
"46-50": 15,
|
| 56 |
+
"51-55": 16,
|
| 57 |
+
"56-60": 17,
|
| 58 |
+
"61-65": 18,
|
| 59 |
+
"66-70": 19,
|
| 60 |
+
"71-80": 20,
|
| 61 |
+
"81-90": 21,
|
| 62 |
+
"90+": 22
|
| 63 |
+
},
|
| 64 |
+
"layer_norm_eps": 1e-12,
|
| 65 |
+
"model_type": "vit",
|
| 66 |
+
"num_attention_heads": 12,
|
| 67 |
+
"num_channels": 3,
|
| 68 |
+
"num_hidden_layers": 12,
|
| 69 |
+
"patch_size": 16,
|
| 70 |
+
"problem_type": "single_label_classification",
|
| 71 |
+
"qkv_bias": true,
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.38.2"
|
| 74 |
+
}
|
checkpoint-6400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bf9a8e241633abfc6108b6abcff1fbde0fdfbe7daa2e24e802eb9671bea01d8
|
| 3 |
+
size 343288572
|
checkpoint-6400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56a78caf55a779be81c06a624ffe74ecbf1600f40e491e41af27fda3f14b2ddc
|
| 3 |
+
size 686697605
|
checkpoint-6400/preprocessor_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_normalize": true,
|
| 3 |
+
"do_rescale": true,
|
| 4 |
+
"do_resize": true,
|
| 5 |
+
"image_mean": [
|
| 6 |
+
0.5,
|
| 7 |
+
0.5,
|
| 8 |
+
0.5
|
| 9 |
+
],
|
| 10 |
+
"image_processor_type": "ViTImageProcessor",
|
| 11 |
+
"image_std": [
|
| 12 |
+
0.5,
|
| 13 |
+
0.5,
|
| 14 |
+
0.5
|
| 15 |
+
],
|
| 16 |
+
"resample": 2,
|
| 17 |
+
"rescale_factor": 0.00392156862745098,
|
| 18 |
+
"size": {
|
| 19 |
+
"height": 224,
|
| 20 |
+
"width": 224
|
| 21 |
+
}
|
| 22 |
+
}
|
checkpoint-6400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7f2b04236a9a6ecd803c8e44279db38d5175151106019e220375c88fb3734cff
|
| 3 |
+
size 14575
|
checkpoint-6400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6e13225ea3a64376401f07422bae1da8a692fc329c9a52725084f9dd2e99472
|
| 3 |
+
size 627
|
checkpoint-6400/trainer_state.json
ADDED
|
@@ -0,0 +1,285 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3211654424667358,
|
| 3 |
+
"best_model_checkpoint": "facial_age_image_detection/checkpoint-6400",
|
| 4 |
+
"epoch": 20.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.5492572322126661,
|
| 14 |
+
"eval_loss": 1.3843398094177246,
|
| 15 |
+
"eval_runtime": 53.0532,
|
| 16 |
+
"eval_samples_per_second": 96.431,
|
| 17 |
+
"eval_steps_per_second": 3.016,
|
| 18 |
+
"step": 320
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"epoch": 1.56,
|
| 22 |
+
"grad_norm": 9.20909595489502,
|
| 23 |
+
"learning_rate": 9.291338582677165e-07,
|
| 24 |
+
"loss": 1.0144,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 2.0,
|
| 29 |
+
"eval_accuracy": 0.5471071149335418,
|
| 30 |
+
"eval_loss": 1.3768093585968018,
|
| 31 |
+
"eval_runtime": 52.7424,
|
| 32 |
+
"eval_samples_per_second": 97.0,
|
| 33 |
+
"eval_steps_per_second": 3.034,
|
| 34 |
+
"step": 640
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 3.0,
|
| 38 |
+
"eval_accuracy": 0.5433932759968726,
|
| 39 |
+
"eval_loss": 1.3764420747756958,
|
| 40 |
+
"eval_runtime": 51.5402,
|
| 41 |
+
"eval_samples_per_second": 99.262,
|
| 42 |
+
"eval_steps_per_second": 3.104,
|
| 43 |
+
"step": 960
|
| 44 |
+
},
|
| 45 |
+
{
|
| 46 |
+
"epoch": 3.12,
|
| 47 |
+
"grad_norm": 8.877883911132812,
|
| 48 |
+
"learning_rate": 8.503937007874016e-07,
|
| 49 |
+
"loss": 1.0053,
|
| 50 |
+
"step": 1000
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 4.0,
|
| 54 |
+
"eval_accuracy": 0.547302580140735,
|
| 55 |
+
"eval_loss": 1.366408348083496,
|
| 56 |
+
"eval_runtime": 52.1841,
|
| 57 |
+
"eval_samples_per_second": 98.038,
|
| 58 |
+
"eval_steps_per_second": 3.066,
|
| 59 |
+
"step": 1280
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 4.69,
|
| 63 |
+
"grad_norm": 12.386143684387207,
|
| 64 |
+
"learning_rate": 7.716535433070865e-07,
|
| 65 |
+
"loss": 0.9744,
|
| 66 |
+
"step": 1500
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 5.0,
|
| 70 |
+
"eval_accuracy": 0.5517982799061767,
|
| 71 |
+
"eval_loss": 1.3610535860061646,
|
| 72 |
+
"eval_runtime": 52.1993,
|
| 73 |
+
"eval_samples_per_second": 98.009,
|
| 74 |
+
"eval_steps_per_second": 3.065,
|
| 75 |
+
"step": 1600
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 6.0,
|
| 79 |
+
"eval_accuracy": 0.5521892103205629,
|
| 80 |
+
"eval_loss": 1.3569880723953247,
|
| 81 |
+
"eval_runtime": 51.8422,
|
| 82 |
+
"eval_samples_per_second": 98.684,
|
| 83 |
+
"eval_steps_per_second": 3.086,
|
| 84 |
+
"step": 1920
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 6.25,
|
| 88 |
+
"grad_norm": 12.370375633239746,
|
| 89 |
+
"learning_rate": 6.929133858267716e-07,
|
| 90 |
+
"loss": 0.9667,
|
| 91 |
+
"step": 2000
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 7.0,
|
| 95 |
+
"eval_accuracy": 0.5494526974198592,
|
| 96 |
+
"eval_loss": 1.3512985706329346,
|
| 97 |
+
"eval_runtime": 52.2761,
|
| 98 |
+
"eval_samples_per_second": 97.865,
|
| 99 |
+
"eval_steps_per_second": 3.061,
|
| 100 |
+
"step": 2240
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 7.81,
|
| 104 |
+
"grad_norm": 11.062934875488281,
|
| 105 |
+
"learning_rate": 6.141732283464567e-07,
|
| 106 |
+
"loss": 0.9536,
|
| 107 |
+
"step": 2500
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 8.0,
|
| 111 |
+
"eval_accuracy": 0.5492572322126661,
|
| 112 |
+
"eval_loss": 1.3439780473709106,
|
| 113 |
+
"eval_runtime": 51.9554,
|
| 114 |
+
"eval_samples_per_second": 98.469,
|
| 115 |
+
"eval_steps_per_second": 3.08,
|
| 116 |
+
"step": 2560
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 9.0,
|
| 120 |
+
"eval_accuracy": 0.5484753713838937,
|
| 121 |
+
"eval_loss": 1.3428295850753784,
|
| 122 |
+
"eval_runtime": 52.082,
|
| 123 |
+
"eval_samples_per_second": 98.23,
|
| 124 |
+
"eval_steps_per_second": 3.072,
|
| 125 |
+
"step": 2880
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 9.38,
|
| 129 |
+
"grad_norm": 12.75069808959961,
|
| 130 |
+
"learning_rate": 5.354330708661418e-07,
|
| 131 |
+
"loss": 0.9437,
|
| 132 |
+
"step": 3000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 10.0,
|
| 136 |
+
"eval_accuracy": 0.5484753713838937,
|
| 137 |
+
"eval_loss": 1.3394215106964111,
|
| 138 |
+
"eval_runtime": 51.1719,
|
| 139 |
+
"eval_samples_per_second": 99.977,
|
| 140 |
+
"eval_steps_per_second": 3.127,
|
| 141 |
+
"step": 3200
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 10.94,
|
| 145 |
+
"grad_norm": 11.664592742919922,
|
| 146 |
+
"learning_rate": 4.5669291338582676e-07,
|
| 147 |
+
"loss": 0.9279,
|
| 148 |
+
"step": 3500
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 11.0,
|
| 152 |
+
"eval_accuracy": 0.5471071149335418,
|
| 153 |
+
"eval_loss": 1.3347781896591187,
|
| 154 |
+
"eval_runtime": 51.4976,
|
| 155 |
+
"eval_samples_per_second": 99.344,
|
| 156 |
+
"eval_steps_per_second": 3.107,
|
| 157 |
+
"step": 3520
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 12.0,
|
| 161 |
+
"eval_accuracy": 0.5541438623924941,
|
| 162 |
+
"eval_loss": 1.3312886953353882,
|
| 163 |
+
"eval_runtime": 51.2447,
|
| 164 |
+
"eval_samples_per_second": 99.835,
|
| 165 |
+
"eval_steps_per_second": 3.122,
|
| 166 |
+
"step": 3840
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 12.5,
|
| 170 |
+
"grad_norm": 8.319609642028809,
|
| 171 |
+
"learning_rate": 3.779527559055118e-07,
|
| 172 |
+
"loss": 0.921,
|
| 173 |
+
"step": 4000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 13.0,
|
| 177 |
+
"eval_accuracy": 0.5547302580140735,
|
| 178 |
+
"eval_loss": 1.3314929008483887,
|
| 179 |
+
"eval_runtime": 51.5959,
|
| 180 |
+
"eval_samples_per_second": 99.155,
|
| 181 |
+
"eval_steps_per_second": 3.101,
|
| 182 |
+
"step": 4160
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 14.0,
|
| 186 |
+
"eval_accuracy": 0.5508209538702111,
|
| 187 |
+
"eval_loss": 1.3308985233306885,
|
| 188 |
+
"eval_runtime": 51.327,
|
| 189 |
+
"eval_samples_per_second": 99.675,
|
| 190 |
+
"eval_steps_per_second": 3.117,
|
| 191 |
+
"step": 4480
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 14.06,
|
| 195 |
+
"grad_norm": 6.9851226806640625,
|
| 196 |
+
"learning_rate": 2.9921259842519687e-07,
|
| 197 |
+
"loss": 0.9223,
|
| 198 |
+
"step": 4500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 15.0,
|
| 202 |
+
"eval_accuracy": 0.5564894448788116,
|
| 203 |
+
"eval_loss": 1.3276044130325317,
|
| 204 |
+
"eval_runtime": 51.4978,
|
| 205 |
+
"eval_samples_per_second": 99.344,
|
| 206 |
+
"eval_steps_per_second": 3.107,
|
| 207 |
+
"step": 4800
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 15.62,
|
| 211 |
+
"grad_norm": 6.1127119064331055,
|
| 212 |
+
"learning_rate": 2.2047244094488187e-07,
|
| 213 |
+
"loss": 0.9054,
|
| 214 |
+
"step": 5000
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 16.0,
|
| 218 |
+
"eval_accuracy": 0.5545347928068803,
|
| 219 |
+
"eval_loss": 1.3215641975402832,
|
| 220 |
+
"eval_runtime": 51.1737,
|
| 221 |
+
"eval_samples_per_second": 99.973,
|
| 222 |
+
"eval_steps_per_second": 3.127,
|
| 223 |
+
"step": 5120
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 17.0,
|
| 227 |
+
"eval_accuracy": 0.5568803752931978,
|
| 228 |
+
"eval_loss": 1.324193000793457,
|
| 229 |
+
"eval_runtime": 51.5617,
|
| 230 |
+
"eval_samples_per_second": 99.221,
|
| 231 |
+
"eval_steps_per_second": 3.103,
|
| 232 |
+
"step": 5440
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 17.19,
|
| 236 |
+
"grad_norm": 7.823403358459473,
|
| 237 |
+
"learning_rate": 1.4173228346456693e-07,
|
| 238 |
+
"loss": 0.9092,
|
| 239 |
+
"step": 5500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 18.0,
|
| 243 |
+
"eval_accuracy": 0.5551211884284597,
|
| 244 |
+
"eval_loss": 1.3241610527038574,
|
| 245 |
+
"eval_runtime": 52.1852,
|
| 246 |
+
"eval_samples_per_second": 98.035,
|
| 247 |
+
"eval_steps_per_second": 3.066,
|
| 248 |
+
"step": 5760
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 18.75,
|
| 252 |
+
"grad_norm": 8.171327590942383,
|
| 253 |
+
"learning_rate": 6.299212598425197e-08,
|
| 254 |
+
"loss": 0.9017,
|
| 255 |
+
"step": 6000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 19.0,
|
| 259 |
+
"eval_accuracy": 0.5576622361219703,
|
| 260 |
+
"eval_loss": 1.3216114044189453,
|
| 261 |
+
"eval_runtime": 51.9014,
|
| 262 |
+
"eval_samples_per_second": 98.572,
|
| 263 |
+
"eval_steps_per_second": 3.083,
|
| 264 |
+
"step": 6080
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 20.0,
|
| 268 |
+
"eval_accuracy": 0.5586395621579359,
|
| 269 |
+
"eval_loss": 1.3211654424667358,
|
| 270 |
+
"eval_runtime": 51.4519,
|
| 271 |
+
"eval_samples_per_second": 99.433,
|
| 272 |
+
"eval_steps_per_second": 3.11,
|
| 273 |
+
"step": 6400
|
| 274 |
+
}
|
| 275 |
+
],
|
| 276 |
+
"logging_steps": 500,
|
| 277 |
+
"max_steps": 6400,
|
| 278 |
+
"num_input_tokens_seen": 0,
|
| 279 |
+
"num_train_epochs": 20,
|
| 280 |
+
"save_steps": 500,
|
| 281 |
+
"total_flos": 3.171569043869614e+19,
|
| 282 |
+
"train_batch_size": 64,
|
| 283 |
+
"trial_name": null,
|
| 284 |
+
"trial_params": null
|
| 285 |
+
}
|
checkpoint-6400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f6a197bb61538af9105ff3f98f5f8f19f1a1b0dc25898782642a1539f61d8e6
|
| 3 |
+
size 4411
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 343288572
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2bf9a8e241633abfc6108b6abcff1fbde0fdfbe7daa2e24e802eb9671bea01d8
|
| 3 |
size 343288572
|