Upload 12 files

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "facebook/mbart-large-cc25",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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,
+  "dropout": 0.1,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "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
+  },
+  "max_length": 1024,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "task_specific_params": {
+    "translation_en_to_ro": {
+      "decoder_start_token_id": 250020
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 250027
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672426631befcedfbf772ccaba510e839f13c448a043dc2861babe2cd07f97bd
+size 4887125707

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc3aeaba81c3c9a23d878eef11512c8d4d2ccece51985e662d821d889133bcf3
+size 2444583325

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ec6fe45c8588583f97fa4eb0047a21851862d16198c80ae4a7480625ca917d4
+size 14511

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29f3c90fa821a24986963feaba68fa866c813c388844e57349c94217af02fe51
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a3235efc4f566facee2019a7e97a37e9f3582d4810eec4c94c81c68d8cde67
+size 627

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": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": false, "lowercase": false, "special_tokens_map_file": null, "name_or_path": "./dump", "do_basic_tokenize": true, "never_split": null, "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,132 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.869440459110473,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.7034911525585844e-05,
+      "loss": 2.3749,
+      "step": 500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.4051889048302244e-05,
+      "loss": 1.2761,
+      "step": 1000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.1062888570062176e-05,
+      "loss": 0.9438,
+      "step": 1500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8073888091822094e-05,
+      "loss": 0.7756,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.508488761358202e-05,
+      "loss": 0.7032,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 1.0,
+      "eval_loss": 0.34736406803131104,
+      "eval_runtime": 639.8738,
+      "eval_samples_per_second": 4.357,
+      "eval_steps_per_second": 1.089,
+      "step": 2788
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.209588713534194e-05,
+      "loss": 0.5899,
+      "step": 3000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.9106886657101868e-05,
+      "loss": 0.4577,
+      "step": 3500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6123864179818268e-05,
+      "loss": 0.4712,
+      "step": 4000
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.3134863701578193e-05,
+      "loss": 0.4424,
+      "step": 4500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.0145863223338114e-05,
+      "loss": 0.3883,
+      "step": 5000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 1.715686274509804e-05,
+      "loss": 0.4077,
+      "step": 5500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 0.0,
+      "eval_gen_len": 1.0,
+      "eval_loss": 0.1796296387910843,
+      "eval_runtime": 41.4373,
+      "eval_samples_per_second": 67.282,
+      "eval_steps_per_second": 16.821,
+      "step": 5576
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.4167862266857965e-05,
+      "loss": 0.2923,
+      "step": 6000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 1.1178861788617887e-05,
+      "loss": 0.253,
+      "step": 6500
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 8.18986131037781e-06,
+      "loss": 0.277,
+      "step": 7000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.200860832137733e-06,
+      "loss": 0.2555,
+      "step": 7500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.2118603538976567e-06,
+      "loss": 0.2414,
+      "step": 8000
+    }
+  ],
+  "max_steps": 8364,
+  "num_train_epochs": 3,
+  "total_flos": 2825850447544320.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da85c07b876b8e5bca26b209cf4f66fbb814889603708851877bc43db0382bdd
+size 3195