End of training
Browse files- all_results.json +11 -0
- eval_results.json +7 -0
- preprocessor_config.json +28 -0
- runs/Aug16_14-43-59_cvrl-flynn-ws2/events.out.tfevents.1692230815.cvrl-flynn-ws2.10527.1 +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- train_results.json +7 -0
- trainer_state.json +385 -0
- vocab.txt +0 -0
all_results.json
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 2.4178671836853027,
|
| 4 |
+
"eval_runtime": 358.3026,
|
| 5 |
+
"eval_samples_per_second": 83.728,
|
| 6 |
+
"eval_steps_per_second": 2.618,
|
| 7 |
+
"train_loss": 0.9465052639431424,
|
| 8 |
+
"train_runtime": 18848.6969,
|
| 9 |
+
"train_samples_per_second": 47.749,
|
| 10 |
+
"train_steps_per_second": 1.492
|
| 11 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 2.4178671836853027,
|
| 4 |
+
"eval_runtime": 358.3026,
|
| 5 |
+
"eval_samples_per_second": 83.728,
|
| 6 |
+
"eval_steps_per_second": 2.618
|
| 7 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": {
|
| 3 |
+
"height": 224,
|
| 4 |
+
"width": 224
|
| 5 |
+
},
|
| 6 |
+
"do_center_crop": true,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"image_mean": [
|
| 12 |
+
0.48145466,
|
| 13 |
+
0.4578275,
|
| 14 |
+
0.40821073
|
| 15 |
+
],
|
| 16 |
+
"image_processor_type": "CLIPImageProcessor",
|
| 17 |
+
"image_std": [
|
| 18 |
+
0.26862954,
|
| 19 |
+
0.26130258,
|
| 20 |
+
0.27577711
|
| 21 |
+
],
|
| 22 |
+
"processor_class": "VisionTextDualEncoderProcessor",
|
| 23 |
+
"resample": 3,
|
| 24 |
+
"rescale_factor": 0.00392156862745098,
|
| 25 |
+
"size": {
|
| 26 |
+
"shortest_edge": 224
|
| 27 |
+
}
|
| 28 |
+
}
|
runs/Aug16_14-43-59_cvrl-flynn-ws2/events.out.tfevents.1692230815.cvrl-flynn-ws2.10527.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b6035945066b87c6e92cecd560ec6c2132cad30111ab4d1b5e7ca0b7832c4c8
|
| 3 |
+
size 364
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"do_basic_tokenize": true,
|
| 5 |
+
"do_lower_case": false,
|
| 6 |
+
"full_tokenizer_file": null,
|
| 7 |
+
"mask_token": "[MASK]",
|
| 8 |
+
"max_len": 512,
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"never_split": null,
|
| 11 |
+
"pad_token": "[PAD]",
|
| 12 |
+
"processor_class": "VisionTextDualEncoderProcessor",
|
| 13 |
+
"sep_token": "[SEP]",
|
| 14 |
+
"strip_accents": null,
|
| 15 |
+
"tokenize_chinese_chars": true,
|
| 16 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 17 |
+
"unk_token": "[UNK]"
|
| 18 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"train_loss": 0.9465052639431424,
|
| 4 |
+
"train_runtime": 18848.6969,
|
| 5 |
+
"train_samples_per_second": 47.749,
|
| 6 |
+
"train_steps_per_second": 1.492
|
| 7 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,385 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 2.4178671836853027,
|
| 3 |
+
"best_model_checkpoint": "clip-mixer-300k/checkpoint-18750",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"global_step": 28125,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.05,
|
| 12 |
+
"learning_rate": 4.9111111111111114e-05,
|
| 13 |
+
"loss": 2.1259,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 4.8222222222222225e-05,
|
| 19 |
+
"loss": 1.8445,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 4.7333333333333336e-05,
|
| 25 |
+
"loss": 1.7594,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 4.644444444444445e-05,
|
| 31 |
+
"loss": 1.7145,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"learning_rate": 4.555555555555556e-05,
|
| 37 |
+
"loss": 1.6367,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.32,
|
| 42 |
+
"learning_rate": 4.466666666666667e-05,
|
| 43 |
+
"loss": 1.6162,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.37,
|
| 48 |
+
"learning_rate": 4.377777777777778e-05,
|
| 49 |
+
"loss": 1.5544,
|
| 50 |
+
"step": 3500
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.43,
|
| 54 |
+
"learning_rate": 4.2888888888888886e-05,
|
| 55 |
+
"loss": 1.5502,
|
| 56 |
+
"step": 4000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.48,
|
| 60 |
+
"learning_rate": 4.2e-05,
|
| 61 |
+
"loss": 1.5128,
|
| 62 |
+
"step": 4500
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.53,
|
| 66 |
+
"learning_rate": 4.111111111111111e-05,
|
| 67 |
+
"loss": 1.473,
|
| 68 |
+
"step": 5000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.59,
|
| 72 |
+
"learning_rate": 4.022222222222222e-05,
|
| 73 |
+
"loss": 1.4328,
|
| 74 |
+
"step": 5500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.64,
|
| 78 |
+
"learning_rate": 3.933333333333333e-05,
|
| 79 |
+
"loss": 1.4208,
|
| 80 |
+
"step": 6000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.69,
|
| 84 |
+
"learning_rate": 3.844444444444444e-05,
|
| 85 |
+
"loss": 1.4009,
|
| 86 |
+
"step": 6500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.75,
|
| 90 |
+
"learning_rate": 3.7555555555555554e-05,
|
| 91 |
+
"loss": 1.3752,
|
| 92 |
+
"step": 7000
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 97 |
+
"loss": 1.3387,
|
| 98 |
+
"step": 7500
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.85,
|
| 102 |
+
"learning_rate": 3.577777777777778e-05,
|
| 103 |
+
"loss": 1.3141,
|
| 104 |
+
"step": 8000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.91,
|
| 108 |
+
"learning_rate": 3.4888888888888895e-05,
|
| 109 |
+
"loss": 1.3023,
|
| 110 |
+
"step": 8500
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.96,
|
| 114 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 115 |
+
"loss": 1.2811,
|
| 116 |
+
"step": 9000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.0,
|
| 120 |
+
"eval_loss": 2.599307060241699,
|
| 121 |
+
"eval_runtime": 359.2177,
|
| 122 |
+
"eval_samples_per_second": 83.515,
|
| 123 |
+
"eval_steps_per_second": 2.611,
|
| 124 |
+
"step": 9375
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.01,
|
| 128 |
+
"learning_rate": 3.311111111111112e-05,
|
| 129 |
+
"loss": 1.1965,
|
| 130 |
+
"step": 9500
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.07,
|
| 134 |
+
"learning_rate": 3.222222222222223e-05,
|
| 135 |
+
"loss": 0.9531,
|
| 136 |
+
"step": 10000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.12,
|
| 140 |
+
"learning_rate": 3.1333333333333334e-05,
|
| 141 |
+
"loss": 0.9502,
|
| 142 |
+
"step": 10500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 1.17,
|
| 146 |
+
"learning_rate": 3.044444444444445e-05,
|
| 147 |
+
"loss": 0.9351,
|
| 148 |
+
"step": 11000
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 1.23,
|
| 152 |
+
"learning_rate": 2.955555555555556e-05,
|
| 153 |
+
"loss": 0.9377,
|
| 154 |
+
"step": 11500
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 1.28,
|
| 158 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 159 |
+
"loss": 0.9437,
|
| 160 |
+
"step": 12000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.33,
|
| 164 |
+
"learning_rate": 2.777777777777778e-05,
|
| 165 |
+
"loss": 0.9403,
|
| 166 |
+
"step": 12500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.39,
|
| 170 |
+
"learning_rate": 2.688888888888889e-05,
|
| 171 |
+
"loss": 0.9138,
|
| 172 |
+
"step": 13000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.44,
|
| 176 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 177 |
+
"loss": 0.9201,
|
| 178 |
+
"step": 13500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.49,
|
| 182 |
+
"learning_rate": 2.5111111111111113e-05,
|
| 183 |
+
"loss": 0.8969,
|
| 184 |
+
"step": 14000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 1.55,
|
| 188 |
+
"learning_rate": 2.4222222222222224e-05,
|
| 189 |
+
"loss": 0.9031,
|
| 190 |
+
"step": 14500
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 1.6,
|
| 194 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 195 |
+
"loss": 0.8836,
|
| 196 |
+
"step": 15000
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 1.65,
|
| 200 |
+
"learning_rate": 2.2444444444444447e-05,
|
| 201 |
+
"loss": 0.8711,
|
| 202 |
+
"step": 15500
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 1.71,
|
| 206 |
+
"learning_rate": 2.1555555555555555e-05,
|
| 207 |
+
"loss": 0.8671,
|
| 208 |
+
"step": 16000
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 1.76,
|
| 212 |
+
"learning_rate": 2.0666666666666666e-05,
|
| 213 |
+
"loss": 0.8494,
|
| 214 |
+
"step": 16500
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.81,
|
| 218 |
+
"learning_rate": 1.9777777777777778e-05,
|
| 219 |
+
"loss": 0.8346,
|
| 220 |
+
"step": 17000
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 1.87,
|
| 224 |
+
"learning_rate": 1.888888888888889e-05,
|
| 225 |
+
"loss": 0.8396,
|
| 226 |
+
"step": 17500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.92,
|
| 230 |
+
"learning_rate": 1.8e-05,
|
| 231 |
+
"loss": 0.802,
|
| 232 |
+
"step": 18000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 1.97,
|
| 236 |
+
"learning_rate": 1.7111111111111112e-05,
|
| 237 |
+
"loss": 0.8159,
|
| 238 |
+
"step": 18500
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 2.0,
|
| 242 |
+
"eval_loss": 2.4178671836853027,
|
| 243 |
+
"eval_runtime": 360.9468,
|
| 244 |
+
"eval_samples_per_second": 83.115,
|
| 245 |
+
"eval_steps_per_second": 2.599,
|
| 246 |
+
"step": 18750
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 2.03,
|
| 250 |
+
"learning_rate": 1.6222222222222223e-05,
|
| 251 |
+
"loss": 0.637,
|
| 252 |
+
"step": 19000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 2.08,
|
| 256 |
+
"learning_rate": 1.5333333333333334e-05,
|
| 257 |
+
"loss": 0.4617,
|
| 258 |
+
"step": 19500
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 2.13,
|
| 262 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 263 |
+
"loss": 0.4634,
|
| 264 |
+
"step": 20000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.19,
|
| 268 |
+
"learning_rate": 1.3555555555555557e-05,
|
| 269 |
+
"loss": 0.4644,
|
| 270 |
+
"step": 20500
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 2.24,
|
| 274 |
+
"learning_rate": 1.2666666666666668e-05,
|
| 275 |
+
"loss": 0.4426,
|
| 276 |
+
"step": 21000
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 2.29,
|
| 280 |
+
"learning_rate": 1.1777777777777778e-05,
|
| 281 |
+
"loss": 0.4559,
|
| 282 |
+
"step": 21500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 2.35,
|
| 286 |
+
"learning_rate": 1.088888888888889e-05,
|
| 287 |
+
"loss": 0.443,
|
| 288 |
+
"step": 22000
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 2.4,
|
| 292 |
+
"learning_rate": 1e-05,
|
| 293 |
+
"loss": 0.4359,
|
| 294 |
+
"step": 22500
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 2.45,
|
| 298 |
+
"learning_rate": 9.111111111111112e-06,
|
| 299 |
+
"loss": 0.4303,
|
| 300 |
+
"step": 23000
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 2.51,
|
| 304 |
+
"learning_rate": 8.222222222222223e-06,
|
| 305 |
+
"loss": 0.4228,
|
| 306 |
+
"step": 23500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 2.56,
|
| 310 |
+
"learning_rate": 7.333333333333334e-06,
|
| 311 |
+
"loss": 0.4125,
|
| 312 |
+
"step": 24000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 2.61,
|
| 316 |
+
"learning_rate": 6.4444444444444445e-06,
|
| 317 |
+
"loss": 0.4139,
|
| 318 |
+
"step": 24500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 2.67,
|
| 322 |
+
"learning_rate": 5.555555555555556e-06,
|
| 323 |
+
"loss": 0.4146,
|
| 324 |
+
"step": 25000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 2.72,
|
| 328 |
+
"learning_rate": 4.666666666666667e-06,
|
| 329 |
+
"loss": 0.3986,
|
| 330 |
+
"step": 25500
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 2.77,
|
| 334 |
+
"learning_rate": 3.777777777777778e-06,
|
| 335 |
+
"loss": 0.4017,
|
| 336 |
+
"step": 26000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 2.83,
|
| 340 |
+
"learning_rate": 2.888888888888889e-06,
|
| 341 |
+
"loss": 0.3922,
|
| 342 |
+
"step": 26500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 2.88,
|
| 346 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 347 |
+
"loss": 0.3917,
|
| 348 |
+
"step": 27000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.93,
|
| 352 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 353 |
+
"loss": 0.385,
|
| 354 |
+
"step": 27500
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 2.99,
|
| 358 |
+
"learning_rate": 2.2222222222222224e-07,
|
| 359 |
+
"loss": 0.374,
|
| 360 |
+
"step": 28000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.0,
|
| 364 |
+
"eval_loss": 2.4597387313842773,
|
| 365 |
+
"eval_runtime": 361.6503,
|
| 366 |
+
"eval_samples_per_second": 82.953,
|
| 367 |
+
"eval_steps_per_second": 2.594,
|
| 368 |
+
"step": 28125
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 3.0,
|
| 372 |
+
"step": 28125,
|
| 373 |
+
"total_flos": 9.03625120512e+16,
|
| 374 |
+
"train_loss": 0.9465052639431424,
|
| 375 |
+
"train_runtime": 18848.6969,
|
| 376 |
+
"train_samples_per_second": 47.749,
|
| 377 |
+
"train_steps_per_second": 1.492
|
| 378 |
+
}
|
| 379 |
+
],
|
| 380 |
+
"max_steps": 28125,
|
| 381 |
+
"num_train_epochs": 3,
|
| 382 |
+
"total_flos": 9.03625120512e+16,
|
| 383 |
+
"trial_name": null,
|
| 384 |
+
"trial_params": null
|
| 385 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|