Instructions to use mohammedRiad/flant5-summaryModel with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mohammedRiad/flant5-summaryModel with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("mohammedRiad/flant5-summaryModel") model = AutoModelForSeq2SeqLM.from_pretrained("mohammedRiad/flant5-summaryModel", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload 8 files
Browse files- config.json +62 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +194 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "google/flan-t5-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 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"tie_word_embeddings": false,
|
| 58 |
+
"torch_dtype": "float32",
|
| 59 |
+
"transformers_version": "4.37.2",
|
| 60 |
+
"use_cache": true,
|
| 61 |
+
"vocab_size": 32128
|
| 62 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.37.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5098457d90f87ef10ebeec3fde6cd89f5a9c9f362b77cb1134e5acaaa71ff7b2
|
| 3 |
+
size 990345064
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b24a7a4cdd0cdec0a74f10864aecf2539450a6c0386b5337bb0dd4cc831ed02
|
| 3 |
+
size 1980860410
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a11ef4320e95074f08e8bda003554ebbcb57b7633319a235f9d1e8b878bc7503
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d3440efa4944ce6c2eabfac8f9c0b04613f5513e70b2e20bef1733e3ccc9139
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.3700677156448364,
|
| 3 |
+
"best_model_checkpoint": "/content/drive/MyDrive/Graduation_Models/Summary_Model/output/checkpoint-7368",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 9210,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.27,
|
| 13 |
+
"learning_rate": 4.728555917480999e-05,
|
| 14 |
+
"loss": 1.4736,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.54,
|
| 19 |
+
"learning_rate": 4.457111834961998e-05,
|
| 20 |
+
"loss": 1.44,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.81,
|
| 25 |
+
"learning_rate": 4.185667752442997e-05,
|
| 26 |
+
"loss": 1.4497,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.0,
|
| 31 |
+
"eval_gen_len": 17.29181929181929,
|
| 32 |
+
"eval_loss": 1.3855763673782349,
|
| 33 |
+
"eval_rouge1": 46.4182,
|
| 34 |
+
"eval_rouge2": 22.6793,
|
| 35 |
+
"eval_rougeL": 38.696,
|
| 36 |
+
"eval_rougeLsum": 42.6475,
|
| 37 |
+
"eval_runtime": 121.3592,
|
| 38 |
+
"eval_samples_per_second": 6.749,
|
| 39 |
+
"eval_steps_per_second": 0.849,
|
| 40 |
+
"step": 1842
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 1.09,
|
| 44 |
+
"learning_rate": 3.914223669923996e-05,
|
| 45 |
+
"loss": 1.4192,
|
| 46 |
+
"step": 2000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 1.36,
|
| 50 |
+
"learning_rate": 3.642779587404995e-05,
|
| 51 |
+
"loss": 1.3345,
|
| 52 |
+
"step": 2500
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.63,
|
| 56 |
+
"learning_rate": 3.3713355048859935e-05,
|
| 57 |
+
"loss": 1.3562,
|
| 58 |
+
"step": 3000
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.9,
|
| 62 |
+
"learning_rate": 3.099891422366993e-05,
|
| 63 |
+
"loss": 1.3474,
|
| 64 |
+
"step": 3500
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 2.0,
|
| 68 |
+
"eval_gen_len": 17.273504273504273,
|
| 69 |
+
"eval_loss": 1.3723567724227905,
|
| 70 |
+
"eval_rouge1": 47.1674,
|
| 71 |
+
"eval_rouge2": 23.3092,
|
| 72 |
+
"eval_rougeL": 39.4164,
|
| 73 |
+
"eval_rougeLsum": 43.3552,
|
| 74 |
+
"eval_runtime": 119.0693,
|
| 75 |
+
"eval_samples_per_second": 6.878,
|
| 76 |
+
"eval_steps_per_second": 0.865,
|
| 77 |
+
"step": 3684
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 2.17,
|
| 81 |
+
"learning_rate": 2.8284473398479917e-05,
|
| 82 |
+
"loss": 1.2971,
|
| 83 |
+
"step": 4000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 2.44,
|
| 87 |
+
"learning_rate": 2.5570032573289905e-05,
|
| 88 |
+
"loss": 1.2711,
|
| 89 |
+
"step": 4500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.71,
|
| 93 |
+
"learning_rate": 2.2855591748099893e-05,
|
| 94 |
+
"loss": 1.2859,
|
| 95 |
+
"step": 5000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.99,
|
| 99 |
+
"learning_rate": 2.0141150922909884e-05,
|
| 100 |
+
"loss": 1.2818,
|
| 101 |
+
"step": 5500
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 3.0,
|
| 105 |
+
"eval_gen_len": 17.247863247863247,
|
| 106 |
+
"eval_loss": 1.3706920146942139,
|
| 107 |
+
"eval_rouge1": 47.4185,
|
| 108 |
+
"eval_rouge2": 23.5442,
|
| 109 |
+
"eval_rougeL": 39.7883,
|
| 110 |
+
"eval_rougeLsum": 43.4867,
|
| 111 |
+
"eval_runtime": 118.5587,
|
| 112 |
+
"eval_samples_per_second": 6.908,
|
| 113 |
+
"eval_steps_per_second": 0.869,
|
| 114 |
+
"step": 5526
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 3.26,
|
| 118 |
+
"learning_rate": 1.742671009771987e-05,
|
| 119 |
+
"loss": 1.2272,
|
| 120 |
+
"step": 6000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 3.53,
|
| 124 |
+
"learning_rate": 1.471226927252986e-05,
|
| 125 |
+
"loss": 1.2389,
|
| 126 |
+
"step": 6500
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 3.8,
|
| 130 |
+
"learning_rate": 1.1997828447339848e-05,
|
| 131 |
+
"loss": 1.2285,
|
| 132 |
+
"step": 7000
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 4.0,
|
| 136 |
+
"eval_gen_len": 17.35286935286935,
|
| 137 |
+
"eval_loss": 1.3700677156448364,
|
| 138 |
+
"eval_rouge1": 47.4833,
|
| 139 |
+
"eval_rouge2": 23.614,
|
| 140 |
+
"eval_rougeL": 39.8945,
|
| 141 |
+
"eval_rougeLsum": 43.6297,
|
| 142 |
+
"eval_runtime": 118.838,
|
| 143 |
+
"eval_samples_per_second": 6.892,
|
| 144 |
+
"eval_steps_per_second": 0.867,
|
| 145 |
+
"step": 7368
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 4.07,
|
| 149 |
+
"learning_rate": 9.283387622149838e-06,
|
| 150 |
+
"loss": 1.1985,
|
| 151 |
+
"step": 7500
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 4.34,
|
| 155 |
+
"learning_rate": 6.568946796959827e-06,
|
| 156 |
+
"loss": 1.1972,
|
| 157 |
+
"step": 8000
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 4.61,
|
| 161 |
+
"learning_rate": 3.854505971769816e-06,
|
| 162 |
+
"loss": 1.2093,
|
| 163 |
+
"step": 8500
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 4.89,
|
| 167 |
+
"learning_rate": 1.1400651465798045e-06,
|
| 168 |
+
"loss": 1.196,
|
| 169 |
+
"step": 9000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 5.0,
|
| 173 |
+
"eval_gen_len": 17.313797313797313,
|
| 174 |
+
"eval_loss": 1.3741676807403564,
|
| 175 |
+
"eval_rouge1": 47.4109,
|
| 176 |
+
"eval_rouge2": 23.6186,
|
| 177 |
+
"eval_rougeL": 39.6383,
|
| 178 |
+
"eval_rougeLsum": 43.5567,
|
| 179 |
+
"eval_runtime": 122.3234,
|
| 180 |
+
"eval_samples_per_second": 6.695,
|
| 181 |
+
"eval_steps_per_second": 0.842,
|
| 182 |
+
"step": 9210
|
| 183 |
+
}
|
| 184 |
+
],
|
| 185 |
+
"logging_steps": 500,
|
| 186 |
+
"max_steps": 9210,
|
| 187 |
+
"num_input_tokens_seen": 0,
|
| 188 |
+
"num_train_epochs": 5,
|
| 189 |
+
"save_steps": 500,
|
| 190 |
+
"total_flos": 5.048305105187635e+16,
|
| 191 |
+
"train_batch_size": 8,
|
| 192 |
+
"trial_name": null,
|
| 193 |
+
"trial_params": null
|
| 194 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a639ab2b24605f3acffac838cf390754b379d999fa1d31893617559394994dd
|
| 3 |
+
size 4920
|