Upload 13 files

config.json

@@ -0,0 +1,197 @@
+{
+  "_commit_hash": null,
+  "_name_or_path": "custom_model",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "decoder",
+    "activation_function": "gelu_new",
+    "add_cross_attention": true,
+    "architectures": [
+      "GPT2LMHeadModel"
+    ],
+    "attn_pdrop": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 50256,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "embd_pdrop": 0.1,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 50256,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "gpt2",
+    "n_ctx": 1024,
+    "n_embd": 768,
+    "n_head": 12,
+    "n_inner": null,
+    "n_layer": 12,
+    "n_positions": 1024,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "reorder_and_upcast_attn": false,
+    "repetition_penalty": 1.0,
+    "resid_pdrop": 0.1,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_attn_by_inverse_layer_idx": false,
+    "scale_attn_weights": true,
+    "sep_token_id": null,
+    "summary_activation": null,
+    "summary_first_dropout": 0.1,
+    "summary_proj_to_labels": true,
+    "summary_type": "cls_index",
+    "summary_use_proj": true,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "text-generation": {
+        "do_sample": true,
+        "max_length": 50
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.26.1",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50257
+  },
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "encoder": {
+    "_name_or_path": "encoder",
+    "add_cross_attention": false,
+    "architectures": [
+      "RobertaForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 514,
+    "min_length": 0,
+    "model_type": "roberta",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "transformers_version": "4.26.1",
+    "type_vocab_size": 1,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "length_penalty": 2.0,
+  "max_length": 80,
+  "min_length": 20,
+  "model_type": "encoder-decoder",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 7,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "decoder_start_token_id": 0,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "length_penalty": 2.0,
+  "max_length": 80,
+  "min_length": 20,
+  "no_repeat_ngram_size": 3,
+  "num_beams": 7,
+  "pad_token_id": 1,
+  "transformers_version": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:571e5149bc69137d527f581ed8d7809ddc6b12369db70bb3781bb0d5bccfd06a
+size 2215152645

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf060edb388b98e8de972d47b2bed0c03aa1a154406021caedf448abec80241
+size 1135147069

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4268854b24657237cfa1c673be0da49e83f0e535a2062d89c419aec55b76bde8
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd871621b02c90b1ed80fe60b1abda001596d8ec7fb492f8428db1bd7c10034f
+size 627

special_tokens_map.json

@@ -0,0 +1,39 @@
+{
+  "bos_token": "<s>",
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

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": 512,
+  "name_or_path": "custom_model",
+  "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": "encoder/special_tokens_map.json",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,226 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.0,
+  "global_step": 11268,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 5.8584,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 5.2538,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 5e-05,
+      "loss": 4.9787,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu1_score": 0.0914,
+      "eval_bleu2_score": 0.0332,
+      "eval_bleu3_score": 0.0145,
+      "eval_bleu4_score": 0.0068,
+      "eval_loss": 4.642809867858887,
+      "eval_rougeL": 0.0644,
+      "eval_runtime": 1678.0874,
+      "eval_samples_per_second": 0.995,
+      "eval_steps_per_second": 0.125,
+      "step": 1878
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.744062244062245e-05,
+      "loss": 4.7678,
+      "step": 2000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.4881244881244886e-05,
+      "loss": 4.39,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 4.2321867321867324e-05,
+      "loss": 4.3397,
+      "step": 3000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.976248976248976e-05,
+      "loss": 4.3018,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu1_score": 0.1042,
+      "eval_bleu2_score": 0.0416,
+      "eval_bleu3_score": 0.0195,
+      "eval_bleu4_score": 0.0096,
+      "eval_loss": 4.3901753425598145,
+      "eval_rougeL": 0.0812,
+      "eval_runtime": 1428.6395,
+      "eval_samples_per_second": 1.169,
+      "eval_steps_per_second": 0.146,
+      "step": 3756
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 3.720311220311221e-05,
+      "loss": 3.9973,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 3.4643734643734647e-05,
+      "loss": 3.7469,
+      "step": 4500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 3.2084357084357085e-05,
+      "loss": 3.7297,
+      "step": 5000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.952497952497953e-05,
+      "loss": 3.7295,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu1_score": 0.1094,
+      "eval_bleu2_score": 0.0438,
+      "eval_bleu3_score": 0.0205,
+      "eval_bleu4_score": 0.0099,
+      "eval_loss": 4.351379871368408,
+      "eval_rougeL": 0.0896,
+      "eval_runtime": 1580.9203,
+      "eval_samples_per_second": 1.056,
+      "eval_steps_per_second": 0.132,
+      "step": 5634
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 2.6965601965601965e-05,
+      "loss": 3.343,
+      "step": 6000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 2.4406224406224407e-05,
+      "loss": 3.1757,
+      "step": 6500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 2.1846846846846845e-05,
+      "loss": 3.2114,
+      "step": 7000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.928746928746929e-05,
+      "loss": 3.1804,
+      "step": 7500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu1_score": 0.1138,
+      "eval_bleu2_score": 0.0499,
+      "eval_bleu3_score": 0.0251,
+      "eval_bleu4_score": 0.0135,
+      "eval_loss": 4.437016010284424,
+      "eval_rougeL": 0.0915,
+      "eval_runtime": 1588.6623,
+      "eval_samples_per_second": 1.051,
+      "eval_steps_per_second": 0.132,
+      "step": 7512
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 1.672809172809173e-05,
+      "loss": 2.7489,
+      "step": 8000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 1.416871416871417e-05,
+      "loss": 2.7514,
+      "step": 8500
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 1.1609336609336611e-05,
+      "loss": 2.751,
+      "step": 9000
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu1_score": 0.1147,
+      "eval_bleu2_score": 0.0506,
+      "eval_bleu3_score": 0.0263,
+      "eval_bleu4_score": 0.0141,
+      "eval_loss": 4.623700141906738,
+      "eval_rougeL": 0.0944,
+      "eval_runtime": 1602.0629,
+      "eval_samples_per_second": 1.042,
+      "eval_steps_per_second": 0.13,
+      "step": 9390
+    },
+    {
+      "epoch": 5.06,
+      "learning_rate": 9.049959049959051e-06,
+      "loss": 2.7029,
+      "step": 9500
+    },
+    {
+      "epoch": 5.32,
+      "learning_rate": 6.49058149058149e-06,
+      "loss": 2.416,
+      "step": 10000
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 3.931203931203931e-06,
+      "loss": 2.4479,
+      "step": 10500
+    },
+    {
+      "epoch": 5.86,
+      "learning_rate": 1.371826371826372e-06,
+      "loss": 2.4352,
+      "step": 11000
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu1_score": 0.1211,
+      "eval_bleu2_score": 0.0542,
+      "eval_bleu3_score": 0.0277,
+      "eval_bleu4_score": 0.0147,
+      "eval_loss": 4.784670352935791,
+      "eval_rougeL": 0.0996,
+      "eval_runtime": 1556.44,
+      "eval_samples_per_second": 1.073,
+      "eval_steps_per_second": 0.134,
+      "step": 11268
+    }
+  ],
+  "max_steps": 11268,
+  "num_train_epochs": 6,
+  "total_flos": 5.512311147331584e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45d01f377b1b0b8e9c11d858e92cad7965ad080c7a8106bb17c2e58a93c86a85
+size 3579