Added all folders for trainer

README.md

@@ -0,0 +1,67 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: bart-large-cnn-samsum-acsi-ami
+  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. -->
+
+# bart-large-cnn-samsum-acsi-ami
+
+This model is a fine-tuned version of [philschmid/bart-large-cnn-samsum](https://huggingface.co/philschmid/bart-large-cnn-samsum) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.1361
+- Rouge1: 39.7563
+- Rouge2: 11.1286
+- Rougel: 23.2632
+- Rougelsum: 36.5664
+- Gen Len: 108.15
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Rouge1  | Rouge2  | Rougel  | Rougelsum | Gen Len |
+|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
+| No log        | 1.0   | 20   | 3.2095          | 39.8174 | 11.5559 | 24.0296 | 36.3048   | 108.5   |
+| No log        | 2.0   | 40   | 3.1361          | 39.7563 | 11.1286 | 23.2632 | 36.5664   | 108.15  |
+| No log        | 3.0   | 60   | 3.1599          | 41.79   | 12.0967 | 23.5336 | 37.6859   | 122.95  |
+| No log        | 4.0   | 80   | 3.2878          | 42.3161 | 12.2801 | 23.9352 | 38.2391   | 122.7   |
+| No log        | 5.0   | 100  | 3.3671          | 40.7968 | 10.7336 | 22.9434 | 36.4383   | 129.225 |
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 1.13.1
+- Datasets 2.9.0
+- Tokenizers 0.13.2

checkpoint-100/config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "philschmid/bart-large-cnn-samsum",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.0"
+}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbceb293d117c8f8f42f2fdd69f7ea55ec77450a1dd239d35f6e82b386daaf09
+size 3250609115

checkpoint-100/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2db730013cead7febb250b2ba23f73b833ba04ab7007da6d0b26b9a1e4000f
+size 1625530125

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:168baffc75fe07640f4c86924b0139e77204f00fc48bc206978f4a43bc1372e2
+size 13617

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e5bce28bd2d99b5377778d2ca1ab4cdfcb65e303d135d27f19dd08b12dec6b0
+size 627

checkpoint-100/trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": 3.1361048221588135,
+  "best_model_checkpoint": "bart-large-cnn-samsum-acsi-ami/checkpoint-40",
+  "epoch": 5.0,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 108.5,
+      "eval_loss": 3.2094905376434326,
+      "eval_rouge1": 39.8174,
+      "eval_rouge2": 11.5559,
+      "eval_rougeL": 24.0296,
+      "eval_rougeLsum": 36.3048,
+      "eval_runtime": 212.8556,
+      "eval_samples_per_second": 0.188,
+      "eval_steps_per_second": 0.023,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 108.15,
+      "eval_loss": 3.1361048221588135,
+      "eval_rouge1": 39.7563,
+      "eval_rouge2": 11.1286,
+      "eval_rougeL": 23.2632,
+      "eval_rougeLsum": 36.5664,
+      "eval_runtime": 209.462,
+      "eval_samples_per_second": 0.191,
+      "eval_steps_per_second": 0.024,
+      "step": 40
+    },
+    {
+      "epoch": 3.0,
+      "eval_gen_len": 122.95,
+      "eval_loss": 3.1599366664886475,
+      "eval_rouge1": 41.79,
+      "eval_rouge2": 12.0967,
+      "eval_rougeL": 23.5336,
+      "eval_rougeLsum": 37.6859,
+      "eval_runtime": 217.8522,
+      "eval_samples_per_second": 0.184,
+      "eval_steps_per_second": 0.023,
+      "step": 60
+    },
+    {
+      "epoch": 4.0,
+      "eval_gen_len": 122.7,
+      "eval_loss": 3.28777813911438,
+      "eval_rouge1": 42.3161,
+      "eval_rouge2": 12.2801,
+      "eval_rougeL": 23.9352,
+      "eval_rougeLsum": 38.2391,
+      "eval_runtime": 212.5424,
+      "eval_samples_per_second": 0.188,
+      "eval_steps_per_second": 0.024,
+      "step": 80
+    },
+    {
+      "epoch": 5.0,
+      "eval_gen_len": 129.225,
+      "eval_loss": 3.3671374320983887,
+      "eval_rouge1": 40.7968,
+      "eval_rouge2": 10.7336,
+      "eval_rougeL": 22.9434,
+      "eval_rougeLsum": 36.4383,
+      "eval_runtime": 216.6227,
+      "eval_samples_per_second": 0.185,
+      "eval_steps_per_second": 0.023,
+      "step": 100
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 5,
+  "total_flos": 1690341589647360.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16d4bbe3c1a3a528679fd7f699ed3222c17ad7a61017d9a075780b14236299a
+size 3643

checkpoint-40/config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "philschmid/bart-large-cnn-samsum",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

checkpoint-40/generation_config.json

@@ -0,0 +1,16 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "min_length": 56,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.0"
+}

checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ab8639119c1b8569dda18bf98ce0b7b3d8371bf3a909d27132ee761df310ee3
+size 3250609115

checkpoint-40/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062a01b0385214a4b30120e4f5d9aea8075ca9dbb55344ab6b9d8e76ce9a85da
+size 1625530125

checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2482b2cc11a386c3e0e0cc8802f1bb0a9c34f292d4e4acc11ae70f117bb1ae7
+size 13553

checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51cb491e0c1dd48d27b2af6be60fff4e0d3d16435dbf3bb4f48a394c2730266e
+size 627

checkpoint-40/trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 3.1361048221588135,
+  "best_model_checkpoint": "bart-large-cnn-samsum-acsi-ami/checkpoint-40",
+  "epoch": 2.0,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 108.5,
+      "eval_loss": 3.2094905376434326,
+      "eval_rouge1": 39.8174,
+      "eval_rouge2": 11.5559,
+      "eval_rougeL": 24.0296,
+      "eval_rougeLsum": 36.3048,
+      "eval_runtime": 212.8556,
+      "eval_samples_per_second": 0.188,
+      "eval_steps_per_second": 0.023,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 108.15,
+      "eval_loss": 3.1361048221588135,
+      "eval_rouge1": 39.7563,
+      "eval_rouge2": 11.1286,
+      "eval_rougeL": 23.2632,
+      "eval_rougeLsum": 36.5664,
+      "eval_runtime": 209.462,
+      "eval_samples_per_second": 0.191,
+      "eval_steps_per_second": 0.024,
+      "step": 40
+    }
+  ],
+  "max_steps": 100,
+  "num_train_epochs": 5,
+  "total_flos": 676136635858944.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d16d4bbe3c1a3a528679fd7f699ed3222c17ad7a61017d9a075780b14236299a
+size 3643

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "philschmid/bart-large-cnn-samsum",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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
+  },
+  "length_penalty": 2.0,
+  "max_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50264
+}

logs/1676495522.2427351/events.out.tfevents.1676495522.vincents-mbp.lan.89895.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6e285d13ef6541432ca251f0b9e8cc04cfe277d7513df01c56ee1278318824
+size 5939

logs/events.out.tfevents.1676495522.vincents-mbp.lan.89895.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b870631dcb3c2b6d1ce12ee7a988ccd5dc45f745d2c339b0779226fae3238d1c
+size 7890

logs/events.out.tfevents.1676499629.vincents-mbp.lan.89895.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eb5187fa5b8e761c46207df7ed66a522751d44e7032835a218832475504aef9
+size 555

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>"
+}

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1024,
+  "name_or_path": "philschmid/bart-large-cnn-samsum",
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BartTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}