Added trainer files

README.md

@@ -1,3 +0,0 @@
----
-license: mit
----

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": 400,
+  "max_position_embeddings": 1024,
+  "min_length": 10,
+  "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": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50264
+}

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": 400,
+  "min_length": 10,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 4,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff445809d72e742a3844289d415bc5a82850fa53af54e3f3b913c6e207ee85b2
+size 3250623963

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b706095d7eb88eed727483d8d66041e947686c78cc6ddd6025767765217d71bc
+size 1625537293

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a55b4ef4157e50c55d54f523016e747508abb1554582ce9247b38bfea435cb
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d06354208fc44b8c8e3e461f66d6df1bf1d9d3760d8d00b6720e8acc70e8986
+size 627

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": 3.154881715774536,
+  "best_model_checkpoint": "bart-large-cnn-samsum-acsi-ami-v2/checkpoint-270",
+  "epoch": 2.0,
+  "global_step": 270,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_gen_len": 128.7058823529412,
+      "eval_loss": 3.1962738037109375,
+      "eval_rouge1": 39.6195,
+      "eval_rouge2": 12.1997,
+      "eval_rougeL": 23.748,
+      "eval_rougeLsum": 36.0979,
+      "eval_runtime": 75.0184,
+      "eval_samples_per_second": 0.453,
+      "eval_steps_per_second": 0.453,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "eval_gen_len": 106.8529411764706,
+      "eval_loss": 3.154881715774536,
+      "eval_rouge1": 40.3461,
+      "eval_rouge2": 12.3457,
+      "eval_rougeL": 23.801,
+      "eval_rougeLsum": 36.6165,
+      "eval_runtime": 63.605,
+      "eval_samples_per_second": 0.535,
+      "eval_steps_per_second": 0.535,
+      "step": 270
+    }
+  ],
+  "max_steps": 2025,
+  "num_train_epochs": 15,
+  "total_flos": 585118242570240.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f22dc9238b0fe0e4d62f7bfb8ef53b48a3af1224fbbcedef039a600cd1330e
+size 3643