add model files

.gitattributes

@@ -25,3 +25,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,160 @@
+{
+  "_name_or_path": "./drive/MyDrive/transformer_add/checkpoint-59000",
+  "architectures": [
+    "EncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "",
+    "add_cross_attention": true,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 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": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 6,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.5.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 64000
+  },
+  "decoder_start_token_id": 2,
+  "encoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "BertForMaskedLM"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 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": 512,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 2048,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 512,
+    "min_length": 0,
+    "model_type": "bert",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 8,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 6,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "position_embedding_type": "absolute",
+    "prefix": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torchscript": false,
+    "transformers_version": "4.5.1",
+    "type_vocab_size": 2,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 64000
+  },
+  "eos_token_id": 3,
+  "is_encoder_decoder": true,
+  "max_length": 40,
+  "min_length": 5,
+  "model_type": "encoder-decoder",
+  "pad_token_id": 0,
+  "vocab_size": 64000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ad4b0020cd0110e673cc69d62cd86fa29e9f3a682acea10e59579d36c7ac93
+size 443293155

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b9d04a5906588f294c7b694d20bf3b1345131e10d8823dc45b2698b907c8560
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "max_len": 512, "do_basic_tokenize": true, "never_split": ["[بريد]", "[مستخدم]", "[رابط]"], "special_tokens_map_file": null, "name_or_path": "aubmindlab/bert-base-arabertv02"}

trainer_state.json

@@ -0,0 +1,1104 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.11565268222492,
+  "global_step": 68000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 9.9046,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 8.965944290161133,
+      "eval_rouge-1": 0.0801,
+      "eval_rouge-2": 0.0016,
+      "eval_rouge-l": 0.0788,
+      "eval_runtime": 123.903,
+      "eval_samples_per_second": 33.688,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.4285714285714285e-05,
+      "loss": 8.3615,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 8.027783393859863,
+      "eval_rouge-1": 0.1331,
+      "eval_rouge-2": 0.0035,
+      "eval_rouge-l": 0.1326,
+      "eval_runtime": 188.3863,
+      "eval_samples_per_second": 22.157,
+      "step": 2000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 7.8626,
+      "step": 3000
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 7.678055286407471,
+      "eval_rouge-1": 0.1526,
+      "eval_rouge-2": 0.0104,
+      "eval_rouge-l": 0.1512,
+      "eval_runtime": 171.3007,
+      "eval_samples_per_second": 24.367,
+      "step": 3000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 2.857142857142857e-05,
+      "loss": 7.5789,
+      "step": 4000
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 7.365678787231445,
+      "eval_rouge-1": 0.1554,
+      "eval_rouge-2": 0.0185,
+      "eval_rouge-l": 0.1514,
+      "eval_runtime": 183.8437,
+      "eval_samples_per_second": 22.704,
+      "step": 4000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 7.2362,
+      "step": 5000
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 7.026582717895508,
+      "eval_rouge-1": 0.1762,
+      "eval_rouge-2": 0.0294,
+      "eval_rouge-l": 0.1713,
+      "eval_runtime": 186.2412,
+      "eval_samples_per_second": 22.412,
+      "step": 5000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.2857142857142856e-05,
+      "loss": 6.8796,
+      "step": 6000
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 6.7096028327941895,
+      "eval_rouge-1": 0.1867,
+      "eval_rouge-2": 0.0358,
+      "eval_rouge-l": 0.181,
+      "eval_runtime": 187.2555,
+      "eval_samples_per_second": 22.29,
+      "step": 6000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5e-05,
+      "loss": 6.5408,
+      "step": 7000
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 6.399764060974121,
+      "eval_rouge-1": 0.1998,
+      "eval_rouge-2": 0.0414,
+      "eval_rouge-l": 0.1933,
+      "eval_runtime": 215.0406,
+      "eval_samples_per_second": 19.41,
+      "step": 7000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 4.984689346847537e-05,
+      "loss": 6.203,
+      "step": 8000
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 6.118791580200195,
+      "eval_rouge-1": 0.2166,
+      "eval_rouge-2": 0.0499,
+      "eval_rouge-l": 0.2054,
+      "eval_runtime": 223.5995,
+      "eval_samples_per_second": 18.667,
+      "step": 8000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.969378693695073e-05,
+      "loss": 5.8343,
+      "step": 9000
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 5.871669769287109,
+      "eval_rouge-1": 0.2189,
+      "eval_rouge-2": 0.0564,
+      "eval_rouge-l": 0.2095,
+      "eval_runtime": 173.6387,
+      "eval_samples_per_second": 24.038,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.9540680405426096e-05,
+      "loss": 5.6021,
+      "step": 10000
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 5.661921501159668,
+      "eval_rouge-1": 0.2366,
+      "eval_rouge-2": 0.0626,
+      "eval_rouge-l": 0.2242,
+      "eval_runtime": 196.6013,
+      "eval_samples_per_second": 21.231,
+      "step": 10000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.938757387390146e-05,
+      "loss": 5.3839,
+      "step": 11000
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 5.473762512207031,
+      "eval_rouge-1": 0.2505,
+      "eval_rouge-2": 0.0733,
+      "eval_rouge-l": 0.2382,
+      "eval_runtime": 195.5436,
+      "eval_samples_per_second": 21.346,
+      "step": 11000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 4.923446734237683e-05,
+      "loss": 5.1467,
+      "step": 12000
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 5.313476085662842,
+      "eval_rouge-1": 0.2547,
+      "eval_rouge-2": 0.0778,
+      "eval_rouge-l": 0.2423,
+      "eval_runtime": 184.8247,
+      "eval_samples_per_second": 22.584,
+      "step": 12000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 4.90813608108522e-05,
+      "loss": 4.9939,
+      "step": 13000
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 5.17720365524292,
+      "eval_rouge-1": 0.2666,
+      "eval_rouge-2": 0.0886,
+      "eval_rouge-l": 0.2517,
+      "eval_runtime": 201.6984,
+      "eval_samples_per_second": 20.694,
+      "step": 13000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.892825427932756e-05,
+      "loss": 4.8392,
+      "step": 14000
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 5.034477710723877,
+      "eval_rouge-1": 0.2827,
+      "eval_rouge-2": 0.0953,
+      "eval_rouge-l": 0.2666,
+      "eval_runtime": 190.2704,
+      "eval_samples_per_second": 21.937,
+      "step": 14000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 4.8775147747802924e-05,
+      "loss": 4.7284,
+      "step": 15000
+    },
+    {
+      "epoch": 1.35,
+      "eval_loss": 4.909021854400635,
+      "eval_rouge-1": 0.288,
+      "eval_rouge-2": 0.1,
+      "eval_rouge-l": 0.2726,
+      "eval_runtime": 181.3965,
+      "eval_samples_per_second": 23.01,
+      "step": 15000
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 4.862204121627829e-05,
+      "loss": 4.6145,
+      "step": 16000
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 4.801566123962402,
+      "eval_rouge-1": 0.2952,
+      "eval_rouge-2": 0.1042,
+      "eval_rouge-l": 0.2789,
+      "eval_runtime": 182.1022,
+      "eval_samples_per_second": 22.921,
+      "step": 16000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 4.846893468475365e-05,
+      "loss": 4.3908,
+      "step": 17000
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 4.704518795013428,
+      "eval_rouge-1": 0.3059,
+      "eval_rouge-2": 0.1151,
+      "eval_rouge-l": 0.2893,
+      "eval_runtime": 174.1469,
+      "eval_samples_per_second": 23.968,
+      "step": 17000
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 4.831582815322902e-05,
+      "loss": 4.304,
+      "step": 18000
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 4.603546619415283,
+      "eval_rouge-1": 0.3086,
+      "eval_rouge-2": 0.1182,
+      "eval_rouge-l": 0.2909,
+      "eval_runtime": 182.7874,
+      "eval_samples_per_second": 22.835,
+      "step": 18000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 4.8162721621704385e-05,
+      "loss": 4.2481,
+      "step": 19000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 4.504889488220215,
+      "eval_rouge-1": 0.3163,
+      "eval_rouge-2": 0.1253,
+      "eval_rouge-l": 0.2994,
+      "eval_runtime": 179.5495,
+      "eval_samples_per_second": 23.247,
+      "step": 19000
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 4.800961509017975e-05,
+      "loss": 4.1473,
+      "step": 20000
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 4.4253692626953125,
+      "eval_rouge-1": 0.3199,
+      "eval_rouge-2": 0.1264,
+      "eval_rouge-l": 0.3014,
+      "eval_runtime": 182.3622,
+      "eval_samples_per_second": 22.889,
+      "step": 20000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.785650855865512e-05,
+      "loss": 4.0769,
+      "step": 21000
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 4.35316276550293,
+      "eval_rouge-1": 0.324,
+      "eval_rouge-2": 0.1333,
+      "eval_rouge-l": 0.306,
+      "eval_runtime": 175.6652,
+      "eval_samples_per_second": 23.761,
+      "step": 21000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 4.770340202713048e-05,
+      "loss": 3.999,
+      "step": 22000
+    },
+    {
+      "epoch": 1.98,
+      "eval_loss": 4.278110027313232,
+      "eval_rouge-1": 0.3268,
+      "eval_rouge-2": 0.1368,
+      "eval_rouge-l": 0.3089,
+      "eval_runtime": 189.2177,
+      "eval_samples_per_second": 22.059,
+      "step": 22000
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 4.7550295495605846e-05,
+      "loss": 3.8351,
+      "step": 23000
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 4.208358287811279,
+      "eval_rouge-1": 0.3308,
+      "eval_rouge-2": 0.1427,
+      "eval_rouge-l": 0.3144,
+      "eval_runtime": 178.6224,
+      "eval_samples_per_second": 23.368,
+      "step": 23000
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 4.7397188964081206e-05,
+      "loss": 3.7519,
+      "step": 24000
+    },
+    {
+      "epoch": 2.16,
+      "eval_loss": 4.136488914489746,
+      "eval_rouge-1": 0.3361,
+      "eval_rouge-2": 0.1442,
+      "eval_rouge-l": 0.3184,
+      "eval_runtime": 191.1592,
+      "eval_samples_per_second": 21.835,
+      "step": 24000
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 4.724408243255657e-05,
+      "loss": 3.6917,
+      "step": 25000
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 4.072964668273926,
+      "eval_rouge-1": 0.3394,
+      "eval_rouge-2": 0.1488,
+      "eval_rouge-l": 0.3217,
+      "eval_runtime": 178.8323,
+      "eval_samples_per_second": 23.34,
+      "step": 25000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 4.709097590103194e-05,
+      "loss": 3.6526,
+      "step": 26000
+    },
+    {
+      "epoch": 2.34,
+      "eval_loss": 4.014794826507568,
+      "eval_rouge-1": 0.3437,
+      "eval_rouge-2": 0.1511,
+      "eval_rouge-l": 0.3254,
+      "eval_runtime": 182.0303,
+      "eval_samples_per_second": 22.93,
+      "step": 26000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 4.693786936950731e-05,
+      "loss": 3.485,
+      "step": 27000
+    },
+    {
+      "epoch": 2.43,
+      "eval_loss": 3.9730067253112793,
+      "eval_rouge-1": 0.3472,
+      "eval_rouge-2": 0.1575,
+      "eval_rouge-l": 0.329,
+      "eval_runtime": 106.9008,
+      "eval_samples_per_second": 39.046,
+      "step": 27000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.6784762837982674e-05,
+      "loss": 3.4744,
+      "step": 28000
+    },
+    {
+      "epoch": 2.52,
+      "eval_loss": 3.905726909637451,
+      "eval_rouge-1": 0.3524,
+      "eval_rouge-2": 0.1605,
+      "eval_rouge-l": 0.3328,
+      "eval_runtime": 109.2943,
+      "eval_samples_per_second": 38.19,
+      "step": 28000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 4.663165630645804e-05,
+      "loss": 3.4398,
+      "step": 29000
+    },
+    {
+      "epoch": 2.61,
+      "eval_loss": 3.861633062362671,
+      "eval_rouge-1": 0.3555,
+      "eval_rouge-2": 0.1648,
+      "eval_rouge-l": 0.3369,
+      "eval_runtime": 109.0651,
+      "eval_samples_per_second": 38.271,
+      "step": 29000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.64785497749334e-05,
+      "loss": 3.4033,
+      "step": 30000
+    },
+    {
+      "epoch": 2.7,
+      "eval_loss": 3.814605712890625,
+      "eval_rouge-1": 0.3616,
+      "eval_rouge-2": 0.1696,
+      "eval_rouge-l": 0.3426,
+      "eval_runtime": 111.7482,
+      "eval_samples_per_second": 37.352,
+      "step": 30000
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 4.632544324340877e-05,
+      "loss": 3.3852,
+      "step": 31000
+    },
+    {
+      "epoch": 2.79,
+      "eval_loss": 3.7633745670318604,
+      "eval_rouge-1": 0.3618,
+      "eval_rouge-2": 0.1729,
+      "eval_rouge-l": 0.3431,
+      "eval_runtime": 108.2348,
+      "eval_samples_per_second": 38.564,
+      "step": 31000
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 4.617233671188413e-05,
+      "loss": 3.3591,
+      "step": 32000
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 3.70929217338562,
+      "eval_rouge-1": 0.3665,
+      "eval_rouge-2": 0.1758,
+      "eval_rouge-l": 0.3483,
+      "eval_runtime": 107.2167,
+      "eval_samples_per_second": 38.93,
+      "step": 32000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.6019230180359495e-05,
+      "loss": 3.3347,
+      "step": 33000
+    },
+    {
+      "epoch": 2.97,
+      "eval_loss": 3.6575114727020264,
+      "eval_rouge-1": 0.3664,
+      "eval_rouge-2": 0.1771,
+      "eval_rouge-l": 0.3479,
+      "eval_runtime": 111.8035,
+      "eval_samples_per_second": 37.333,
+      "step": 33000
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 4.586612364883486e-05,
+      "loss": 3.1412,
+      "step": 34000
+    },
+    {
+      "epoch": 3.06,
+      "eval_loss": 3.6294667720794678,
+      "eval_rouge-1": 0.3687,
+      "eval_rouge-2": 0.1799,
+      "eval_rouge-l": 0.3504,
+      "eval_runtime": 108.0977,
+      "eval_samples_per_second": 38.613,
+      "step": 34000
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 4.571301711731022e-05,
+      "loss": 3.0681,
+      "step": 35000
+    },
+    {
+      "epoch": 3.15,
+      "eval_loss": 3.5905728340148926,
+      "eval_rouge-1": 0.369,
+      "eval_rouge-2": 0.1812,
+      "eval_rouge-l": 0.3495,
+      "eval_runtime": 109.8754,
+      "eval_samples_per_second": 37.988,
+      "step": 35000
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 4.5559910585785595e-05,
+      "loss": 3.047,
+      "step": 36000
+    },
+    {
+      "epoch": 3.24,
+      "eval_loss": 3.5687978267669678,
+      "eval_rouge-1": 0.3751,
+      "eval_rouge-2": 0.1869,
+      "eval_rouge-l": 0.3562,
+      "eval_runtime": 112.5879,
+      "eval_samples_per_second": 37.073,
+      "step": 36000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 4.540680405426096e-05,
+      "loss": 3.0482,
+      "step": 37000
+    },
+    {
+      "epoch": 3.33,
+      "eval_loss": 3.522142171859741,
+      "eval_rouge-1": 0.374,
+      "eval_rouge-2": 0.1885,
+      "eval_rouge-l": 0.3553,
+      "eval_runtime": 110.8835,
+      "eval_samples_per_second": 37.643,
+      "step": 37000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 4.525369752273632e-05,
+      "loss": 3.0085,
+      "step": 38000
+    },
+    {
+      "epoch": 3.42,
+      "eval_loss": 3.497309446334839,
+      "eval_rouge-1": 0.3754,
+      "eval_rouge-2": 0.1889,
+      "eval_rouge-l": 0.3563,
+      "eval_runtime": 116.7032,
+      "eval_samples_per_second": 35.766,
+      "step": 38000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 4.510059099121169e-05,
+      "loss": 3.0179,
+      "step": 39000
+    },
+    {
+      "epoch": 3.51,
+      "eval_loss": 3.45327091217041,
+      "eval_rouge-1": 0.3766,
+      "eval_rouge-2": 0.1913,
+      "eval_rouge-l": 0.3568,
+      "eval_runtime": 110.7354,
+      "eval_samples_per_second": 37.693,
+      "step": 39000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 4.494748445968705e-05,
+      "loss": 3.0008,
+      "step": 40000
+    },
+    {
+      "epoch": 3.6,
+      "eval_loss": 3.4268550872802734,
+      "eval_rouge-1": 0.3802,
+      "eval_rouge-2": 0.1942,
+      "eval_rouge-l": 0.3614,
+      "eval_runtime": 108.7986,
+      "eval_samples_per_second": 38.364,
+      "step": 40000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 4.4794377928162417e-05,
+      "loss": 2.973,
+      "step": 41000
+    },
+    {
+      "epoch": 3.69,
+      "eval_loss": 3.393805980682373,
+      "eval_rouge-1": 0.3835,
+      "eval_rouge-2": 0.197,
+      "eval_rouge-l": 0.3648,
+      "eval_runtime": 112.0812,
+      "eval_samples_per_second": 37.241,
+      "step": 41000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 4.4641271396637783e-05,
+      "loss": 2.9718,
+      "step": 42000
+    },
+    {
+      "epoch": 3.78,
+      "eval_loss": 3.350437879562378,
+      "eval_rouge-1": 0.3877,
+      "eval_rouge-2": 0.2013,
+      "eval_rouge-l": 0.3682,
+      "eval_runtime": 111.3062,
+      "eval_samples_per_second": 37.5,
+      "step": 42000
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 4.4488164865113144e-05,
+      "loss": 2.9702,
+      "step": 43000
+    },
+    {
+      "epoch": 3.87,
+      "eval_loss": 3.321171998977661,
+      "eval_rouge-1": 0.3859,
+      "eval_rouge-2": 0.1992,
+      "eval_rouge-l": 0.3672,
+      "eval_runtime": 109.8134,
+      "eval_samples_per_second": 38.01,
+      "step": 43000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 4.433505833358852e-05,
+      "loss": 2.6419,
+      "step": 44000
+    },
+    {
+      "epoch": 3.96,
+      "eval_loss": 3.341356039047241,
+      "eval_rouge-1": 0.3839,
+      "eval_rouge-2": 0.2012,
+      "eval_rouge-l": 0.3653,
+      "eval_runtime": 182.4115,
+      "eval_samples_per_second": 22.882,
+      "step": 44000
+    },
+    {
+      "epoch": 4.05,
+      "learning_rate": 4.418195180206388e-05,
+      "loss": 2.6177,
+      "step": 45000
+    },
+    {
+      "epoch": 4.05,
+      "eval_loss": 3.31478214263916,
+      "eval_rouge-1": 0.3896,
+      "eval_rouge-2": 0.2053,
+      "eval_rouge-l": 0.37,
+      "eval_runtime": 185.1687,
+      "eval_samples_per_second": 22.542,
+      "step": 45000
+    },
+    {
+      "epoch": 4.14,
+      "learning_rate": 4.4028845270539244e-05,
+      "loss": 2.5985,
+      "step": 46000
+    },
+    {
+      "epoch": 4.14,
+      "eval_loss": 3.3024539947509766,
+      "eval_rouge-1": 0.3911,
+      "eval_rouge-2": 0.2066,
+      "eval_rouge-l": 0.3717,
+      "eval_runtime": 183.1915,
+      "eval_samples_per_second": 22.785,
+      "step": 46000
+    },
+    {
+      "epoch": 4.23,
+      "learning_rate": 4.387573873901461e-05,
+      "loss": 2.615,
+      "step": 47000
+    },
+    {
+      "epoch": 4.23,
+      "eval_loss": 3.285188913345337,
+      "eval_rouge-1": 0.3894,
+      "eval_rouge-2": 0.2047,
+      "eval_rouge-l": 0.371,
+      "eval_runtime": 183.8267,
+      "eval_samples_per_second": 22.706,
+      "step": 47000
+    },
+    {
+      "epoch": 4.32,
+      "learning_rate": 4.372263220748997e-05,
+      "loss": 2.6202,
+      "step": 48000
+    },
+    {
+      "epoch": 4.32,
+      "eval_loss": 3.2647767066955566,
+      "eval_rouge-1": 0.394,
+      "eval_rouge-2": 0.2099,
+      "eval_rouge-l": 0.3747,
+      "eval_runtime": 186.2005,
+      "eval_samples_per_second": 22.417,
+      "step": 48000
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 4.356952567596534e-05,
+      "loss": 2.6072,
+      "step": 49000
+    },
+    {
+      "epoch": 4.41,
+      "eval_loss": 3.2533161640167236,
+      "eval_rouge-1": 0.3925,
+      "eval_rouge-2": 0.2099,
+      "eval_rouge-l": 0.373,
+      "eval_runtime": 180.2911,
+      "eval_samples_per_second": 23.151,
+      "step": 49000
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 4.3416419144440705e-05,
+      "loss": 2.612,
+      "step": 50000
+    },
+    {
+      "epoch": 4.5,
+      "eval_loss": 3.2256064414978027,
+      "eval_rouge-1": 0.3933,
+      "eval_rouge-2": 0.2113,
+      "eval_rouge-l": 0.3738,
+      "eval_runtime": 182.776,
+      "eval_samples_per_second": 22.837,
+      "step": 50000
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 4.3263312612916065e-05,
+      "loss": 2.6108,
+      "step": 51000
+    },
+    {
+      "epoch": 4.59,
+      "eval_loss": 3.2123188972473145,
+      "eval_rouge-1": 0.3951,
+      "eval_rouge-2": 0.2122,
+      "eval_rouge-l": 0.3767,
+      "eval_runtime": 182.0897,
+      "eval_samples_per_second": 22.923,
+      "step": 51000
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 4.311020608139143e-05,
+      "loss": 2.6334,
+      "step": 52000
+    },
+    {
+      "epoch": 4.68,
+      "eval_loss": 3.193678140640259,
+      "eval_rouge-1": 0.3971,
+      "eval_rouge-2": 0.2123,
+      "eval_rouge-l": 0.3779,
+      "eval_runtime": 184.0687,
+      "eval_samples_per_second": 22.676,
+      "step": 52000
+    },
+    {
+      "epoch": 4.77,
+      "learning_rate": 4.29570995498668e-05,
+      "loss": 2.6086,
+      "step": 53000
+    },
+    {
+      "epoch": 4.77,
+      "eval_loss": 3.1697912216186523,
+      "eval_rouge-1": 0.3979,
+      "eval_rouge-2": 0.215,
+      "eval_rouge-l": 0.3786,
+      "eval_runtime": 183.0622,
+      "eval_samples_per_second": 22.801,
+      "step": 53000
+    },
+    {
+      "epoch": 4.86,
+      "learning_rate": 4.2803993018342166e-05,
+      "loss": 2.3308,
+      "step": 54000
+    },
+    {
+      "epoch": 4.86,
+      "eval_loss": 3.189683437347412,
+      "eval_rouge-1": 0.3961,
+      "eval_rouge-2": 0.2152,
+      "eval_rouge-l": 0.378,
+      "eval_runtime": 207.2919,
+      "eval_samples_per_second": 20.136,
+      "step": 54000
+    },
+    {
+      "epoch": 4.95,
+      "learning_rate": 4.265088648681753e-05,
+      "loss": 2.3303,
+      "step": 55000
+    },
+    {
+      "epoch": 4.95,
+      "eval_loss": 3.19010591506958,
+      "eval_rouge-1": 0.3982,
+      "eval_rouge-2": 0.2151,
+      "eval_rouge-l": 0.3788,
+      "eval_runtime": 209.6218,
+      "eval_samples_per_second": 19.912,
+      "step": 55000
+    },
+    {
+      "epoch": 5.04,
+      "learning_rate": 4.249777995529289e-05,
+      "loss": 2.3079,
+      "step": 56000
+    },
+    {
+      "epoch": 5.04,
+      "eval_loss": 3.1867759227752686,
+      "eval_rouge-1": 0.3958,
+      "eval_rouge-2": 0.2146,
+      "eval_rouge-l": 0.3764,
+      "eval_runtime": 209.3472,
+      "eval_samples_per_second": 19.938,
+      "step": 56000
+    },
+    {
+      "epoch": 5.13,
+      "learning_rate": 4.234467342376826e-05,
+      "loss": 2.2662,
+      "step": 57000
+    },
+    {
+      "epoch": 5.13,
+      "eval_loss": 3.1843576431274414,
+      "eval_rouge-1": 0.3966,
+      "eval_rouge-2": 0.2116,
+      "eval_rouge-l": 0.3765,
+      "eval_runtime": 216.9453,
+      "eval_samples_per_second": 19.24,
+      "step": 57000
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 4.219156689224362e-05,
+      "loss": 2.2889,
+      "step": 58000
+    },
+    {
+      "epoch": 5.22,
+      "eval_loss": 3.1772937774658203,
+      "eval_rouge-1": 0.3928,
+      "eval_rouge-2": 0.2142,
+      "eval_rouge-l": 0.375,
+      "eval_runtime": 208.5252,
+      "eval_samples_per_second": 20.017,
+      "step": 58000
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 4.203846036071899e-05,
+      "loss": 2.3055,
+      "step": 59000
+    },
+    {
+      "epoch": 5.31,
+      "eval_loss": 3.1666276454925537,
+      "eval_rouge-1": 0.3996,
+      "eval_rouge-2": 0.2174,
+      "eval_rouge-l": 0.3811,
+      "eval_runtime": 208.7841,
+      "eval_samples_per_second": 19.992,
+      "step": 59000
+    },
+    {
+      "epoch": 5.4,
+      "learning_rate": 4.1885353829194354e-05,
+      "loss": 2.1645,
+      "step": 60000
+    },
+    {
+      "epoch": 5.4,
+      "eval_loss": 3.172426700592041,
+      "eval_rouge-1": 0.3976,
+      "eval_rouge-2": 0.2148,
+      "eval_rouge-l": 0.378,
+      "eval_runtime": 211.5986,
+      "eval_samples_per_second": 19.726,
+      "step": 60000
+    },
+    {
+      "epoch": 5.49,
+      "learning_rate": 4.173224729766972e-05,
+      "loss": 2.2381,
+      "step": 61000
+    },
+    {
+      "epoch": 5.49,
+      "eval_loss": 3.160379409790039,
+      "eval_rouge-1": 0.3999,
+      "eval_rouge-2": 0.2183,
+      "eval_rouge-l": 0.3808,
+      "eval_runtime": 207.4561,
+      "eval_samples_per_second": 20.12,
+      "step": 61000
+    },
+    {
+      "epoch": 5.58,
+      "learning_rate": 4.157914076614509e-05,
+      "loss": 2.2566,
+      "step": 62000
+    },
+    {
+      "epoch": 5.58,
+      "eval_loss": 3.148230791091919,
+      "eval_rouge-1": 0.398,
+      "eval_rouge-2": 0.2167,
+      "eval_rouge-l": 0.379,
+      "eval_runtime": 205.4861,
+      "eval_samples_per_second": 20.313,
+      "step": 62000
+    },
+    {
+      "epoch": 5.67,
+      "learning_rate": 4.1426034234620455e-05,
+      "loss": 2.2723,
+      "step": 63000
+    },
+    {
+      "epoch": 5.67,
+      "eval_loss": 3.145291566848755,
+      "eval_rouge-1": 0.3968,
+      "eval_rouge-2": 0.2183,
+      "eval_rouge-l": 0.3781,
+      "eval_runtime": 201.6935,
+      "eval_samples_per_second": 20.695,
+      "step": 63000
+    },
+    {
+      "epoch": 5.76,
+      "learning_rate": 4.1272927703095815e-05,
+      "loss": 2.288,
+      "step": 64000
+    },
+    {
+      "epoch": 5.76,
+      "eval_loss": 3.124877452850342,
+      "eval_rouge-1": 0.3998,
+      "eval_rouge-2": 0.2156,
+      "eval_rouge-l": 0.3792,
+      "eval_runtime": 203.9639,
+      "eval_samples_per_second": 20.464,
+      "step": 64000
+    },
+    {
+      "epoch": 5.85,
+      "learning_rate": 4.111982117157118e-05,
+      "loss": 2.2889,
+      "step": 65000
+    },
+    {
+      "epoch": 5.85,
+      "eval_loss": 3.128246545791626,
+      "eval_rouge-1": 0.4007,
+      "eval_rouge-2": 0.2195,
+      "eval_rouge-l": 0.3822,
+      "eval_runtime": 212.1813,
+      "eval_samples_per_second": 19.672,
+      "step": 65000
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 4.096671464004654e-05,
+      "loss": 2.294,
+      "step": 66000
+    },
+    {
+      "epoch": 5.94,
+      "eval_loss": 3.1073431968688965,
+      "eval_rouge-1": 0.3977,
+      "eval_rouge-2": 0.2188,
+      "eval_rouge-l": 0.3797,
+      "eval_runtime": 205.3765,
+      "eval_samples_per_second": 20.324,
+      "step": 66000
+    },
+    {
+      "epoch": 6.03,
+      "learning_rate": 4.081360810852191e-05,
+      "loss": 2.2157,
+      "step": 67000
+    },
+    {
+      "epoch": 6.03,
+      "eval_loss": 3.1187493801116943,
+      "eval_rouge-1": 0.3977,
+      "eval_rouge-2": 0.2172,
+      "eval_rouge-l": 0.3789,
+      "eval_runtime": 204.9076,
+      "eval_samples_per_second": 20.37,
+      "step": 67000
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 4.0660501576997276e-05,
+      "loss": 1.9904,
+      "step": 68000
+    },
+    {
+      "epoch": 6.12,
+      "eval_loss": 3.1339566707611084,
+      "eval_rouge-1": 0.4014,
+      "eval_rouge-2": 0.2191,
+      "eval_rouge-l": 0.3822,
+      "eval_runtime": 206.8966,
+      "eval_samples_per_second": 20.174,
+      "step": 68000
+    }
+  ],
+  "max_steps": 333570,
+  "num_train_epochs": 30,
+  "total_flos": 2.6905869526822502e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:549768a1d0f2034fe1fd23498022e7fc827aeda2486b4b5c385c8b0a583d282b
+size 2415