Training in progress, step 50000
Browse files- .gitignore +1 -0
- config.json +31 -0
- last-checkpoint/config.json +31 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/pytorch_model.bin +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scaler.pt +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/trainer_state.json +396 -0
- last-checkpoint/training_args.bin +3 -0
- pytorch_model.bin +3 -0
- training_args.bin +3 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
checkpoint-*/
|
config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "experiments/outputs/checkpoint-3500000/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PIXELForPreTraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"decoder_hidden_size": 512,
|
| 8 |
+
"decoder_intermediate_size": 2048,
|
| 9 |
+
"decoder_num_attention_heads": 16,
|
| 10 |
+
"decoder_num_hidden_layers": 8,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"image_size": [
|
| 15 |
+
368,
|
| 16 |
+
368
|
| 17 |
+
],
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"mask_ratio": 0.29,
|
| 22 |
+
"model_type": "pixel",
|
| 23 |
+
"norm_pix_loss": true,
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"qkv_bias": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.17.0"
|
| 31 |
+
}
|
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "experiments/outputs/checkpoint-3500000/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"PIXELForPreTraining"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"decoder_hidden_size": 512,
|
| 8 |
+
"decoder_intermediate_size": 2048,
|
| 9 |
+
"decoder_num_attention_heads": 16,
|
| 10 |
+
"decoder_num_hidden_layers": 8,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"image_size": [
|
| 15 |
+
368,
|
| 16 |
+
368
|
| 17 |
+
],
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"layer_norm_eps": 1e-12,
|
| 21 |
+
"mask_ratio": 0.29,
|
| 22 |
+
"model_type": "pixel",
|
| 23 |
+
"norm_pix_loss": true,
|
| 24 |
+
"num_attention_heads": 12,
|
| 25 |
+
"num_channels": 3,
|
| 26 |
+
"num_hidden_layers": 12,
|
| 27 |
+
"patch_size": 16,
|
| 28 |
+
"qkv_bias": true,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.17.0"
|
| 31 |
+
}
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e85c754e127f96fab9bc9d48e455704ce7512efed8510af77b8010a080a0369d
|
| 3 |
+
size 893438545
|
last-checkpoint/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b866ac2a0c142a334d09941a5e15fe636c9a8b22a5e9936975120c70f9e0d0b8
|
| 3 |
+
size 449471589
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eed565611d5da9a2f8bc52c2366a559d88adaf9a78fc9f7df8a5a8a77bfa712
|
| 3 |
+
size 21579
|
last-checkpoint/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36a4c916fa043d23e6cbdbe64beffa01ac4985c35b48025064a980920151d69d
|
| 3 |
+
size 559
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4b4c247266efcb8d312a3c033a1c79fe57c4781b1d2d4db480283112b77604f
|
| 3 |
+
size 623
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,396 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.025,
|
| 5 |
+
"global_step": 50000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 7.499999999999999e-07,
|
| 13 |
+
"loss": 1.0632,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.0,
|
| 18 |
+
"learning_rate": 1.4999999999999998e-06,
|
| 19 |
+
"loss": 0.9867,
|
| 20 |
+
"step": 2000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.0,
|
| 24 |
+
"learning_rate": 2.2499999999999996e-06,
|
| 25 |
+
"loss": 0.9811,
|
| 26 |
+
"step": 3000
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.0,
|
| 30 |
+
"learning_rate": 2.9999999999999997e-06,
|
| 31 |
+
"loss": 0.9787,
|
| 32 |
+
"step": 4000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.0,
|
| 36 |
+
"learning_rate": 3.7499999999999997e-06,
|
| 37 |
+
"loss": 0.9729,
|
| 38 |
+
"step": 5000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0,
|
| 42 |
+
"eval_loss": 0.9619815349578857,
|
| 43 |
+
"eval_runtime": 82.8842,
|
| 44 |
+
"eval_samples_per_second": 77.216,
|
| 45 |
+
"eval_steps_per_second": 0.603,
|
| 46 |
+
"step": 5000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.0,
|
| 50 |
+
"learning_rate": 4.499999999999999e-06,
|
| 51 |
+
"loss": 0.9491,
|
| 52 |
+
"step": 6000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.0,
|
| 56 |
+
"learning_rate": 5.25e-06,
|
| 57 |
+
"loss": 0.8618,
|
| 58 |
+
"step": 7000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0,
|
| 62 |
+
"learning_rate": 5.999999999999999e-06,
|
| 63 |
+
"loss": 0.8256,
|
| 64 |
+
"step": 8000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.0,
|
| 68 |
+
"learning_rate": 6.749999999999999e-06,
|
| 69 |
+
"loss": 0.8148,
|
| 70 |
+
"step": 9000
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.01,
|
| 74 |
+
"learning_rate": 7.499999999999999e-06,
|
| 75 |
+
"loss": 0.8019,
|
| 76 |
+
"step": 10000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.01,
|
| 80 |
+
"eval_loss": 0.8153918385505676,
|
| 81 |
+
"eval_runtime": 78.5433,
|
| 82 |
+
"eval_samples_per_second": 81.484,
|
| 83 |
+
"eval_steps_per_second": 0.637,
|
| 84 |
+
"step": 10000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.01,
|
| 88 |
+
"learning_rate": 8.249999999999999e-06,
|
| 89 |
+
"loss": 0.7961,
|
| 90 |
+
"step": 11000
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.01,
|
| 94 |
+
"learning_rate": 8.999999999999999e-06,
|
| 95 |
+
"loss": 0.7914,
|
| 96 |
+
"step": 12000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.01,
|
| 100 |
+
"learning_rate": 9.75e-06,
|
| 101 |
+
"loss": 0.7849,
|
| 102 |
+
"step": 13000
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.01,
|
| 106 |
+
"learning_rate": 1.05e-05,
|
| 107 |
+
"loss": 0.7817,
|
| 108 |
+
"step": 14000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.01,
|
| 112 |
+
"learning_rate": 1.1249999999999999e-05,
|
| 113 |
+
"loss": 0.7777,
|
| 114 |
+
"step": 15000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.01,
|
| 118 |
+
"eval_loss": 0.7774372696876526,
|
| 119 |
+
"eval_runtime": 79.7934,
|
| 120 |
+
"eval_samples_per_second": 80.207,
|
| 121 |
+
"eval_steps_per_second": 0.627,
|
| 122 |
+
"step": 15000
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.01,
|
| 126 |
+
"learning_rate": 1.1999999999999999e-05,
|
| 127 |
+
"loss": 0.7751,
|
| 128 |
+
"step": 16000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.01,
|
| 132 |
+
"learning_rate": 1.2749249999999998e-05,
|
| 133 |
+
"loss": 0.7714,
|
| 134 |
+
"step": 17000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.01,
|
| 138 |
+
"learning_rate": 1.34985e-05,
|
| 139 |
+
"loss": 0.7673,
|
| 140 |
+
"step": 18000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.01,
|
| 144 |
+
"learning_rate": 1.42485e-05,
|
| 145 |
+
"loss": 0.7649,
|
| 146 |
+
"step": 19000
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.01,
|
| 150 |
+
"learning_rate": 1.4998499999999999e-05,
|
| 151 |
+
"loss": 0.7629,
|
| 152 |
+
"step": 20000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.01,
|
| 156 |
+
"eval_loss": 0.7626805305480957,
|
| 157 |
+
"eval_runtime": 78.8878,
|
| 158 |
+
"eval_samples_per_second": 81.128,
|
| 159 |
+
"eval_steps_per_second": 0.634,
|
| 160 |
+
"step": 20000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.01,
|
| 164 |
+
"learning_rate": 1.57485e-05,
|
| 165 |
+
"loss": 0.7616,
|
| 166 |
+
"step": 21000
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.01,
|
| 170 |
+
"learning_rate": 1.649775e-05,
|
| 171 |
+
"loss": 0.7592,
|
| 172 |
+
"step": 22000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.01,
|
| 176 |
+
"learning_rate": 1.7247749999999998e-05,
|
| 177 |
+
"loss": 0.7577,
|
| 178 |
+
"step": 23000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.01,
|
| 182 |
+
"learning_rate": 1.799775e-05,
|
| 183 |
+
"loss": 0.7557,
|
| 184 |
+
"step": 24000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.01,
|
| 188 |
+
"learning_rate": 1.8747749999999997e-05,
|
| 189 |
+
"loss": 0.7542,
|
| 190 |
+
"step": 25000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.01,
|
| 194 |
+
"eval_loss": 0.7557830810546875,
|
| 195 |
+
"eval_runtime": 80.9075,
|
| 196 |
+
"eval_samples_per_second": 79.103,
|
| 197 |
+
"eval_steps_per_second": 0.618,
|
| 198 |
+
"step": 25000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.01,
|
| 202 |
+
"learning_rate": 1.9497749999999998e-05,
|
| 203 |
+
"loss": 0.7529,
|
| 204 |
+
"step": 26000
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.01,
|
| 208 |
+
"learning_rate": 2.0246999999999998e-05,
|
| 209 |
+
"loss": 0.7526,
|
| 210 |
+
"step": 27000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.01,
|
| 214 |
+
"learning_rate": 2.0996999999999996e-05,
|
| 215 |
+
"loss": 0.7518,
|
| 216 |
+
"step": 28000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.01,
|
| 220 |
+
"learning_rate": 2.1746999999999997e-05,
|
| 221 |
+
"loss": 0.7508,
|
| 222 |
+
"step": 29000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.01,
|
| 226 |
+
"learning_rate": 2.24955e-05,
|
| 227 |
+
"loss": 0.7496,
|
| 228 |
+
"step": 30000
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.01,
|
| 232 |
+
"eval_loss": 0.7457370162010193,
|
| 233 |
+
"eval_runtime": 76.4686,
|
| 234 |
+
"eval_samples_per_second": 83.694,
|
| 235 |
+
"eval_steps_per_second": 0.654,
|
| 236 |
+
"step": 30000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.02,
|
| 240 |
+
"learning_rate": 2.3245499999999996e-05,
|
| 241 |
+
"loss": 0.748,
|
| 242 |
+
"step": 31000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.02,
|
| 246 |
+
"learning_rate": 2.3995499999999998e-05,
|
| 247 |
+
"loss": 0.7472,
|
| 248 |
+
"step": 32000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.02,
|
| 252 |
+
"learning_rate": 2.4744749999999997e-05,
|
| 253 |
+
"loss": 0.7467,
|
| 254 |
+
"step": 33000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.02,
|
| 258 |
+
"learning_rate": 2.549475e-05,
|
| 259 |
+
"loss": 0.7465,
|
| 260 |
+
"step": 34000
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.02,
|
| 264 |
+
"learning_rate": 2.6243999999999998e-05,
|
| 265 |
+
"loss": 0.7447,
|
| 266 |
+
"step": 35000
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.02,
|
| 270 |
+
"eval_loss": 0.7436805963516235,
|
| 271 |
+
"eval_runtime": 80.6483,
|
| 272 |
+
"eval_samples_per_second": 79.357,
|
| 273 |
+
"eval_steps_per_second": 0.62,
|
| 274 |
+
"step": 35000
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.02,
|
| 278 |
+
"learning_rate": 2.6994e-05,
|
| 279 |
+
"loss": 0.7446,
|
| 280 |
+
"step": 36000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.02,
|
| 284 |
+
"learning_rate": 2.774325e-05,
|
| 285 |
+
"loss": 0.7432,
|
| 286 |
+
"step": 37000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.02,
|
| 290 |
+
"learning_rate": 2.849325e-05,
|
| 291 |
+
"loss": 0.7435,
|
| 292 |
+
"step": 38000
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.02,
|
| 296 |
+
"learning_rate": 2.9243249999999995e-05,
|
| 297 |
+
"loss": 0.7398,
|
| 298 |
+
"step": 39000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.02,
|
| 302 |
+
"learning_rate": 2.9992499999999994e-05,
|
| 303 |
+
"loss": 0.7365,
|
| 304 |
+
"step": 40000
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.02,
|
| 308 |
+
"eval_loss": 0.7301322817802429,
|
| 309 |
+
"eval_runtime": 81.961,
|
| 310 |
+
"eval_samples_per_second": 78.086,
|
| 311 |
+
"eval_steps_per_second": 0.61,
|
| 312 |
+
"step": 40000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.02,
|
| 316 |
+
"learning_rate": 3.07425e-05,
|
| 317 |
+
"loss": 0.7345,
|
| 318 |
+
"step": 41000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.02,
|
| 322 |
+
"learning_rate": 3.149175e-05,
|
| 323 |
+
"loss": 0.7318,
|
| 324 |
+
"step": 42000
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.02,
|
| 328 |
+
"learning_rate": 3.224175e-05,
|
| 329 |
+
"loss": 0.7293,
|
| 330 |
+
"step": 43000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 0.02,
|
| 334 |
+
"learning_rate": 3.2990999999999996e-05,
|
| 335 |
+
"loss": 0.7263,
|
| 336 |
+
"step": 44000
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 0.02,
|
| 340 |
+
"learning_rate": 3.3740999999999994e-05,
|
| 341 |
+
"loss": 0.719,
|
| 342 |
+
"step": 45000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 0.02,
|
| 346 |
+
"eval_loss": 0.70879727602005,
|
| 347 |
+
"eval_runtime": 80.7536,
|
| 348 |
+
"eval_samples_per_second": 79.253,
|
| 349 |
+
"eval_steps_per_second": 0.619,
|
| 350 |
+
"step": 45000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.02,
|
| 354 |
+
"learning_rate": 3.4489499999999996e-05,
|
| 355 |
+
"loss": 0.7129,
|
| 356 |
+
"step": 46000
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 0.02,
|
| 360 |
+
"learning_rate": 3.5239499999999994e-05,
|
| 361 |
+
"loss": 0.7101,
|
| 362 |
+
"step": 47000
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 0.02,
|
| 366 |
+
"learning_rate": 3.59895e-05,
|
| 367 |
+
"loss": 0.7054,
|
| 368 |
+
"step": 48000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.02,
|
| 372 |
+
"learning_rate": 3.6739499999999996e-05,
|
| 373 |
+
"loss": 0.7032,
|
| 374 |
+
"step": 49000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.03,
|
| 378 |
+
"learning_rate": 3.74895e-05,
|
| 379 |
+
"loss": 0.6997,
|
| 380 |
+
"step": 50000
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.03,
|
| 384 |
+
"eval_loss": 0.6915566921234131,
|
| 385 |
+
"eval_runtime": 80.6444,
|
| 386 |
+
"eval_samples_per_second": 79.361,
|
| 387 |
+
"eval_steps_per_second": 0.62,
|
| 388 |
+
"step": 50000
|
| 389 |
+
}
|
| 390 |
+
],
|
| 391 |
+
"max_steps": 2000000,
|
| 392 |
+
"num_train_epochs": 9223372036854775807,
|
| 393 |
+
"total_flos": 4.38126636957696e+20,
|
| 394 |
+
"trial_name": null,
|
| 395 |
+
"trial_params": null
|
| 396 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79f569ba85d4ea897c5f1850bbddb8de43c7b64aa00b563a7f0fb3bf95de3460
|
| 3 |
+
size 5551
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b866ac2a0c142a334d09941a5e15fe636c9a8b22a5e9936975120c70f9e0d0b8
|
| 3 |
+
size 449471589
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79f569ba85d4ea897c5f1850bbddb8de43c7b64aa00b563a7f0fb3bf95de3460
|
| 3 |
+
size 5551
|