upload configs
Browse files- config.json +32 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +192 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/t5-v1_1-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.33.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32128
|
| 32 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f880360b3b0c98aa6af39064acb0c7b46481326fc7cbc0da47217cca6139cdc7
|
| 3 |
+
size 14503
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ce0aa67de6923bd378a0ca31406a7792fe5b7fe842f3d7493bf608ed7373500
|
| 3 |
+
size 623
|
trainer_state.json
ADDED
|
@@ -0,0 +1,192 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.2853470437017995,
|
| 5 |
+
"global_step": 12000,
|
| 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": 9.583333333333334e-05,
|
| 13 |
+
"loss": 3.2628,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.11,
|
| 18 |
+
"learning_rate": 9.166666666666667e-05,
|
| 19 |
+
"loss": 3.0271,
|
| 20 |
+
"step": 1000
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"learning_rate": 8.75e-05,
|
| 25 |
+
"loss": 2.9068,
|
| 26 |
+
"step": 1500
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.21,
|
| 30 |
+
"learning_rate": 8.333333333333334e-05,
|
| 31 |
+
"loss": 2.8076,
|
| 32 |
+
"step": 2000
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.27,
|
| 36 |
+
"learning_rate": 7.916666666666666e-05,
|
| 37 |
+
"loss": 2.7127,
|
| 38 |
+
"step": 2500
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.27,
|
| 42 |
+
"eval_loss": 2.140660047531128,
|
| 43 |
+
"eval_runtime": 0.4247,
|
| 44 |
+
"eval_samples_per_second": 70.636,
|
| 45 |
+
"eval_steps_per_second": 18.836,
|
| 46 |
+
"step": 2500
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.32,
|
| 50 |
+
"learning_rate": 7.500000000000001e-05,
|
| 51 |
+
"loss": 2.6721,
|
| 52 |
+
"step": 3000
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.37,
|
| 56 |
+
"learning_rate": 7.083333333333334e-05,
|
| 57 |
+
"loss": 2.6106,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.43,
|
| 62 |
+
"learning_rate": 6.666666666666667e-05,
|
| 63 |
+
"loss": 2.5446,
|
| 64 |
+
"step": 4000
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.48,
|
| 68 |
+
"learning_rate": 6.25e-05,
|
| 69 |
+
"loss": 2.4866,
|
| 70 |
+
"step": 4500
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.54,
|
| 74 |
+
"learning_rate": 5.833333333333334e-05,
|
| 75 |
+
"loss": 2.448,
|
| 76 |
+
"step": 5000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.54,
|
| 80 |
+
"eval_loss": 1.8471120595932007,
|
| 81 |
+
"eval_runtime": 0.3083,
|
| 82 |
+
"eval_samples_per_second": 97.294,
|
| 83 |
+
"eval_steps_per_second": 25.945,
|
| 84 |
+
"step": 5000
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.59,
|
| 88 |
+
"learning_rate": 5.4166666666666664e-05,
|
| 89 |
+
"loss": 2.4026,
|
| 90 |
+
"step": 5500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.64,
|
| 94 |
+
"learning_rate": 5e-05,
|
| 95 |
+
"loss": 2.3545,
|
| 96 |
+
"step": 6000
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.7,
|
| 100 |
+
"learning_rate": 4.5833333333333334e-05,
|
| 101 |
+
"loss": 2.3271,
|
| 102 |
+
"step": 6500
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.75,
|
| 106 |
+
"learning_rate": 4.166666666666667e-05,
|
| 107 |
+
"loss": 2.3042,
|
| 108 |
+
"step": 7000
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.8,
|
| 112 |
+
"learning_rate": 3.7500000000000003e-05,
|
| 113 |
+
"loss": 2.2588,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.8,
|
| 118 |
+
"eval_loss": 1.6695691347122192,
|
| 119 |
+
"eval_runtime": 0.3452,
|
| 120 |
+
"eval_samples_per_second": 86.916,
|
| 121 |
+
"eval_steps_per_second": 23.178,
|
| 122 |
+
"step": 7500
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.86,
|
| 126 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 127 |
+
"loss": 2.2482,
|
| 128 |
+
"step": 8000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.91,
|
| 132 |
+
"learning_rate": 2.916666666666667e-05,
|
| 133 |
+
"loss": 2.2186,
|
| 134 |
+
"step": 8500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.96,
|
| 138 |
+
"learning_rate": 2.5e-05,
|
| 139 |
+
"loss": 2.1842,
|
| 140 |
+
"step": 9000
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.02,
|
| 144 |
+
"learning_rate": 2.0833333333333336e-05,
|
| 145 |
+
"loss": 2.1561,
|
| 146 |
+
"step": 9500
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 1.07,
|
| 150 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 151 |
+
"loss": 2.0767,
|
| 152 |
+
"step": 10000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.07,
|
| 156 |
+
"eval_loss": 1.5715681314468384,
|
| 157 |
+
"eval_runtime": 0.3186,
|
| 158 |
+
"eval_samples_per_second": 94.171,
|
| 159 |
+
"eval_steps_per_second": 25.112,
|
| 160 |
+
"step": 10000
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 1.12,
|
| 164 |
+
"learning_rate": 1.25e-05,
|
| 165 |
+
"loss": 2.0821,
|
| 166 |
+
"step": 10500
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 1.18,
|
| 170 |
+
"learning_rate": 8.333333333333334e-06,
|
| 171 |
+
"loss": 2.0631,
|
| 172 |
+
"step": 11000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.23,
|
| 176 |
+
"learning_rate": 4.166666666666667e-06,
|
| 177 |
+
"loss": 2.0524,
|
| 178 |
+
"step": 11500
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 1.29,
|
| 182 |
+
"learning_rate": 0.0,
|
| 183 |
+
"loss": 2.0579,
|
| 184 |
+
"step": 12000
|
| 185 |
+
}
|
| 186 |
+
],
|
| 187 |
+
"max_steps": 12000,
|
| 188 |
+
"num_train_epochs": 2,
|
| 189 |
+
"total_flos": 1.1691961050857472e+17,
|
| 190 |
+
"trial_name": null,
|
| 191 |
+
"trial_params": null
|
| 192 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21d49cbe44fbb829299536943b11233d57945f91697b301189be49914a5c1e93
|
| 3 |
+
size 3375
|