Upload with huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+test_results.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,77 @@
+{
+  "_name_or_path": "sdadas/polish-bart-base",
+  "activation_dropout": 0.1,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "classif_dropout": 0.1,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "do_blenderbot_90_layernorm": false,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "extra_pos_embeddings": 2,
+  "force_bos_token_to_be_generated": false,
+  "forced_eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_position_embeddings": 1024,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "normalize_embedding": true,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "scale_embedding": false,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "summarization": {
+      "length_penalty": 1.0,
+      "max_length": 128,
+      "min_length": 12,
+      "num_beams": 4
+    },
+    "summarization_cnn": {
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "num_beams": 4
+    },
+    "summarization_xsum": {
+      "length_penalty": 1.0,
+      "max_length": 62,
+      "min_length": 11,
+      "num_beams": 6
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "vocab_size": 50002
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccfb794fa5527704b7d52d37175bc54c2c75810046556c6ba039c8eee303b53
+size 1113899461

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de04a30a8728d63b0671f8b268bcb2afd000ea53c134f5a28079de7ba07f00e3
+size 557162269

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f70819ccc6cd52aede7d4ebaa44cda792ec28db8e1104ab7f512c61a4169f29
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a00faa5d4edafd806f74f6a1358e82a6dd9cd47a5c48200ec97367bb88f6fc7
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59da308fb523624b20d2700dd094398f7232d040b8905ac5a739f283a765ed03
+size 627

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

test_results.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6d026ebfb678ef7594f7aebca28b510f196325943d9b0fe1b21440ae7954e17
+size 16333037

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,292 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9856861232536214,
+  "global_step": 23000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 3.9153167052369926e-06,
+      "loss": 2.8668,
+      "step": 500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 3.829776292105939e-06,
+      "loss": 2.6094,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 3.7442358789748862e-06,
+      "loss": 2.5971,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 3.6585240421702235e-06,
+      "loss": 2.5186,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 3.572812205365561e-06,
+      "loss": 2.4816,
+      "step": 2500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 3.487100368560898e-06,
+      "loss": 2.4647,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 3.401388531756235e-06,
+      "loss": 2.4669,
+      "step": 3500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 3.3156766949515727e-06,
+      "loss": 2.4315,
+      "step": 4000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 3.22996485814691e-06,
+      "loss": 2.4304,
+      "step": 4500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.1442530213422473e-06,
+      "loss": 2.3974,
+      "step": 5000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.0585411845375846e-06,
+      "loss": 2.3895,
+      "step": 5500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.972829347732922e-06,
+      "loss": 2.359,
+      "step": 6000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 2.8871175109282592e-06,
+      "loss": 2.4182,
+      "step": 6500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 2.801405674123596e-06,
+      "loss": 2.4022,
+      "step": 7000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2.7156938373189334e-06,
+      "loss": 2.4052,
+      "step": 7500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 2.6299820005142707e-06,
+      "loss": 2.3957,
+      "step": 8000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.544270163709608e-06,
+      "loss": 2.3473,
+      "step": 8500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 2.4585583269049453e-06,
+      "loss": 2.3853,
+      "step": 9000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.373017913773892e-06,
+      "loss": 2.3702,
+      "step": 9500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.287306076969229e-06,
+      "loss": 2.3517,
+      "step": 10000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.2015942401645663e-06,
+      "loss": 2.3135,
+      "step": 10500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.115882403359904e-06,
+      "loss": 2.2946,
+      "step": 11000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.0301705665552413e-06,
+      "loss": 2.3325,
+      "step": 11500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.9444587297505786e-06,
+      "loss": 2.3025,
+      "step": 12000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.8587468929459157e-06,
+      "loss": 2.2971,
+      "step": 12500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 1.773035056141253e-06,
+      "loss": 2.3086,
+      "step": 13000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.6873232193365903e-06,
+      "loss": 2.2943,
+      "step": 13500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.601782806205537e-06,
+      "loss": 2.2983,
+      "step": 14000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5160709694008742e-06,
+      "loss": 2.297,
+      "step": 14500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.4303591325962115e-06,
+      "loss": 2.3029,
+      "step": 15000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3446472957915486e-06,
+      "loss": 2.3202,
+      "step": 15500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.2589354589868861e-06,
+      "loss": 2.3167,
+      "step": 16000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.1732236221822234e-06,
+      "loss": 2.3015,
+      "step": 16500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.0875117853775605e-06,
+      "loss": 2.2858,
+      "step": 17000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.0017999485728978e-06,
+      "loss": 2.298,
+      "step": 17500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 9.160881117682352e-07,
+      "loss": 2.2984,
+      "step": 18000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.303762749635724e-07,
+      "loss": 2.3221,
+      "step": 18500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 7.44835861832519e-07,
+      "loss": 2.2805,
+      "step": 19000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 6.592954487014657e-07,
+      "loss": 2.3499,
+      "step": 19500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 5.73583611896803e-07,
+      "loss": 2.2966,
+      "step": 20000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.878717750921403e-07,
+      "loss": 2.2836,
+      "step": 20500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.023313619610868e-07,
+      "loss": 2.2698,
+      "step": 21000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.1661952515642407e-07,
+      "loss": 2.308,
+      "step": 21500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.310791120253707e-07,
+      "loss": 2.2932,
+      "step": 22000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.4536727522070796e-07,
+      "loss": 2.2692,
+      "step": 22500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 5.965543841604526e-08,
+      "loss": 2.275,
+      "step": 23000
+    }
+  ],
+  "max_steps": 23334,
+  "num_train_epochs": 1,
+  "total_flos": 2.099179778282496e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad1cc3eb7cc7c1370d65f4f31e8d3bec993d1c33783455335d5506807b577c5
+size 3835