Upload 16 files

README.md

@@ -0,0 +1,49 @@
+---
+tags:
+- generated_from_trainer
+datasets:
+- /home/ullriher/ullriher/src/datasets/feversum3.py
+model-index:
+- name: t5-small-finetuned-xsum_feversum3_text2claim_bs2_ep30
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# t5-small-finetuned-xsum_feversum3_text2claim_bs2_ep30
+
+This model is a fine-tuned version of [/home/ullriher/ullriher/models/claimext23/t5-small-finetuned-xsum_feversum3_text2claim_bs2_ep30/checkpoint-4500](https://huggingface.co//home/ullriher/ullriher/models/claimext23/t5-small-finetuned-xsum_feversum3_text2claim_bs2_ep30/checkpoint-4500) on the /home/ullriher/ullriher/src/datasets/feversum3.py dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Framework versions
+
+- Transformers 4.17.0
+- Pytorch 1.9.0
+- Datasets 2.0.0
+- Tokenizers 0.11.6

all_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 11.9565,
+    "predict_loss": 1.202620506286621,
+    "predict_rouge1": 43.4486,
+    "predict_rouge2": 27.4644,
+    "predict_rougeL": 42.406,
+    "predict_rougeLsum": 42.4409,
+    "predict_runtime": 233.6801,
+    "predict_samples": 5288,
+    "predict_samples_per_second": 22.629,
+    "predict_steps_per_second": 11.315
+}

config.json

@@ -0,0 +1,60 @@
+{
+  "_name_or_path": "darshkk/t5-small-finetuned-xsum",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45597af77efac31ce2cf2f985dcd69663cb1005293068d9d310f5e6942bd5613
+size 484014773

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 11.9565,
+    "predict_loss": 1.202620506286621,
+    "predict_rouge1": 43.4486,
+    "predict_rouge2": 27.4644,
+    "predict_rougeL": 42.406,
+    "predict_rougeLsum": 42.4409,
+    "predict_runtime": 233.6801,
+    "predict_samples": 5288,
+    "predict_samples_per_second": 22.629,
+    "predict_steps_per_second": 11.315
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d337b0c45bf37b3129765f68807fcaf506ae14d62c726256dc1ac87b5d6a75cb
+size 242028283

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb13252e8497f7e36176d1770ab01ede6ed615ec44d592c011dcdd286327be98
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df7259c71c3c308541700c7a662f523cf756e87e6511f5fdcc1340ade97726ec
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afa3e756adfee87110339985ba8f1b155e268e978b735159fa700850ddfbbff0
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "darshkk/t5-small-finetuned-xsum", "special_tokens_map_file": null, "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.21234428086070214,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9961070215175544e-05,
+      "loss": 1.5449,
+      "step": 500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9921747200201335e-05,
+      "loss": 1.4531,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.988242418522713e-05,
+      "loss": 1.3957,
+      "step": 1500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.9843101170252924e-05,
+      "loss": 1.3235,
+      "step": 2000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.980377815527872e-05,
+      "loss": 1.3184,
+      "step": 2500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.976453378633447e-05,
+      "loss": 1.2947,
+      "step": 3000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.972521077136027e-05,
+      "loss": 1.278,
+      "step": 3500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.9685887756386066e-05,
+      "loss": 1.2059,
+      "step": 4000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.964656474141186e-05,
+      "loss": 1.2573,
+      "step": 4500
+    }
+  ],
+  "max_steps": 635760,
+  "num_train_epochs": 30,
+  "total_flos": 1161782482698240.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ba2cac462e13e4165271f14b693e4f1e2a4b3833f6de3fd6162bddc8ff96aa
+size 3311