init

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+language:
+- en
+- ru
+license: apache-2.0
+tags:
+- generated_from_trainer
+model-index:
+- name: ru_coref_g_ccm_lr_5e5
+  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. -->
+
+# ru_coref_g_ccm_lr_5e5
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-ru](https://huggingface.co/Helsinki-NLP/opus-mt-en-ru) on an unknown dataset.
+
+## 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: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.16.0.dev0
+- Pytorch 1.10.1+cu102
+- Datasets 1.17.0
+- Tokenizers 0.10.3

added_tokens.json

@@ -0,0 +1 @@
+{"<ENT0>": 62518, "</ENT0>": 62519, "<ENT1>": 62520, "</ENT1>": 62521, "<ENT2>": 62522, "</ENT2>": 62523, "<ENT3>": 62524, "</ENT3>": 62525, "<ENT4>": 62526, "</ENT4>": 62527, "<ENT5>": 62528, "</ENT5>": 62529, "<ENT6>": 62530, "</ENT6>": 62531, "<ENT7>": 62532, "</ENT7>": 62533, "<ENT8>": 62534, "</ENT8>": 62535, "<ENT9>": 62536, "</ENT9>": 62537, "<ENT10>": 62538, "</ENT10>": 62539, "<ENT11>": 62540, "</ENT11>": 62541, "<ENT12>": 62542, "</ENT12>": 62543, "<ENT13>": 62544, "</ENT13>": 62545, "<ENT14>": 62546, "</ENT14>": 62547, "<ENT15>": 62548, "</ENT15>": 62549, "<ENT16>": 62550, "</ENT16>": 62551, "<ENT17>": 62552, "</ENT17>": 62553, "<ENT18>": 62554, "</ENT18>": 62555, "<ENT19>": 62556, "</ENT19>": 62557, "<MALE>": 62558, "</MALE>": 62559, "<FEMALE>": 62560, "</FEMALE>": 62561}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5740079802226246,
+    "train_runtime": 16384.5833,
+    "train_samples": 246653,
+    "train_samples_per_second": 45.162,
+    "train_steps_per_second": 2.823
+}

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-ru",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      62517
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 62517,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62517,
+  "scale_embedding": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.0.dev0",
+  "use_cache": true,
+  "vocab_size": 62562
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85babe014307057ff66d81be5a96590fd3482bf54042d15ce0977d2bd39e11ad
+size 305025605

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>"}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:745998e51ba5b058e38b7ac7765c25c43ed5c1c39cc92b27163b9b2e323c9d7c
+size 1080169

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "en", "target_lang": "ru", "unk_token": "<unk>", "eos_token": "</s>", "pad_token": "<pad>", "model_max_length": 512, "sp_model_kwargs": {}, "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "Helsinki-NLP/opus-mt-en-ru", "tokenizer_class": "MarianTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5740079802226246,
+    "train_runtime": 16384.5833,
+    "train_samples": 246653,
+    "train_samples_per_second": 45.162,
+    "train_steps_per_second": 2.823
+}

trainer_state.json

@@ -0,0 +1,577 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 46248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.945943608372254e-05,
+      "loss": 1.9245,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.891887216744508e-05,
+      "loss": 1.8947,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.837830825116762e-05,
+      "loss": 1.862,
+      "step": 1500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.783774433489016e-05,
+      "loss": 1.8378,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.72971804186127e-05,
+      "loss": 1.8137,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.675661650233524e-05,
+      "loss": 1.8268,
+      "step": 3000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.621605258605778e-05,
+      "loss": 1.833,
+      "step": 3500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.567548866978032e-05,
+      "loss": 1.8099,
+      "step": 4000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.513492475350286e-05,
+      "loss": 1.797,
+      "step": 4500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 4.4594360837225395e-05,
+      "loss": 1.8208,
+      "step": 5000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.405379692094794e-05,
+      "loss": 1.7937,
+      "step": 5500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 4.351323300467047e-05,
+      "loss": 1.7805,
+      "step": 6000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 4.2972669088393016e-05,
+      "loss": 1.7785,
+      "step": 6500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.2432105172115553e-05,
+      "loss": 1.7621,
+      "step": 7000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.189154125583809e-05,
+      "loss": 1.7649,
+      "step": 7500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 4.135097733956063e-05,
+      "loss": 1.7694,
+      "step": 8000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 4.0810413423283174e-05,
+      "loss": 1.7598,
+      "step": 8500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.0269849507005705e-05,
+      "loss": 1.7519,
+      "step": 9000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.972928559072825e-05,
+      "loss": 1.766,
+      "step": 9500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.918872167445079e-05,
+      "loss": 1.7489,
+      "step": 10000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.8648157758173326e-05,
+      "loss": 1.7528,
+      "step": 10500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.8107593841895864e-05,
+      "loss": 1.7669,
+      "step": 11000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.756702992561841e-05,
+      "loss": 1.7279,
+      "step": 11500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.7026466009340946e-05,
+      "loss": 1.727,
+      "step": 12000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.6485902093063484e-05,
+      "loss": 1.7368,
+      "step": 12500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.594533817678602e-05,
+      "loss": 1.7203,
+      "step": 13000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.540477426050857e-05,
+      "loss": 1.7159,
+      "step": 13500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 3.4864210344231105e-05,
+      "loss": 1.7376,
+      "step": 14000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.432364642795364e-05,
+      "loss": 1.703,
+      "step": 14500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.378308251167619e-05,
+      "loss": 1.7146,
+      "step": 15000
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 3.324251859539872e-05,
+      "loss": 1.7062,
+      "step": 15500
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 3.270195467912126e-05,
+      "loss": 1.5423,
+      "step": 16000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.21613907628438e-05,
+      "loss": 1.5257,
+      "step": 16500
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.162082684656634e-05,
+      "loss": 1.5494,
+      "step": 17000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.108026293028888e-05,
+      "loss": 1.5378,
+      "step": 17500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.053969901401142e-05,
+      "loss": 1.5513,
+      "step": 18000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2.999913509773396e-05,
+      "loss": 1.5425,
+      "step": 18500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.9458571181456497e-05,
+      "loss": 1.5442,
+      "step": 19000
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 2.8918007265179035e-05,
+      "loss": 1.5424,
+      "step": 19500
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 2.8377443348901576e-05,
+      "loss": 1.5471,
+      "step": 20000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.7836879432624114e-05,
+      "loss": 1.5515,
+      "step": 20500
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2.7296315516346656e-05,
+      "loss": 1.5548,
+      "step": 21000
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.6755751600069197e-05,
+      "loss": 1.5423,
+      "step": 21500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.621518768379173e-05,
+      "loss": 1.5581,
+      "step": 22000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.5674623767514273e-05,
+      "loss": 1.5137,
+      "step": 22500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.5134059851236814e-05,
+      "loss": 1.5299,
+      "step": 23000
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2.4593495934959352e-05,
+      "loss": 1.5392,
+      "step": 23500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.405293201868189e-05,
+      "loss": 1.5539,
+      "step": 24000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.351236810240443e-05,
+      "loss": 1.5464,
+      "step": 24500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.297180418612697e-05,
+      "loss": 1.5622,
+      "step": 25000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2431240269849507e-05,
+      "loss": 1.5474,
+      "step": 25500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.189067635357205e-05,
+      "loss": 1.5424,
+      "step": 26000
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 2.1350112437294586e-05,
+      "loss": 1.5372,
+      "step": 26500
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.0809548521017124e-05,
+      "loss": 1.537,
+      "step": 27000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.0268984604739665e-05,
+      "loss": 1.551,
+      "step": 27500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 1.9728420688462203e-05,
+      "loss": 1.5424,
+      "step": 28000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.9187856772184745e-05,
+      "loss": 1.526,
+      "step": 28500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 1.8647292855907283e-05,
+      "loss": 1.5433,
+      "step": 29000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 1.810672893962982e-05,
+      "loss": 1.5287,
+      "step": 29500
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7566165023352362e-05,
+      "loss": 1.531,
+      "step": 30000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 1.70256011070749e-05,
+      "loss": 1.5208,
+      "step": 30500
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.648503719079744e-05,
+      "loss": 1.4804,
+      "step": 31000
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.594447327451998e-05,
+      "loss": 1.4182,
+      "step": 31500
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 1.540390935824252e-05,
+      "loss": 1.3974,
+      "step": 32000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.486334544196506e-05,
+      "loss": 1.3985,
+      "step": 32500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.4322781525687598e-05,
+      "loss": 1.3941,
+      "step": 33000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 1.3782217609410136e-05,
+      "loss": 1.3968,
+      "step": 33500
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3241653693132677e-05,
+      "loss": 1.4081,
+      "step": 34000
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2701089776855215e-05,
+      "loss": 1.409,
+      "step": 34500
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.2160525860577754e-05,
+      "loss": 1.4122,
+      "step": 35000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1619961944300296e-05,
+      "loss": 1.4138,
+      "step": 35500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1079398028022835e-05,
+      "loss": 1.4052,
+      "step": 36000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0538834111745373e-05,
+      "loss": 1.39,
+      "step": 36500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 9.998270195467913e-06,
+      "loss": 1.4037,
+      "step": 37000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.457706279190453e-06,
+      "loss": 1.4046,
+      "step": 37500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.917142362912992e-06,
+      "loss": 1.398,
+      "step": 38000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 8.37657844663553e-06,
+      "loss": 1.4122,
+      "step": 38500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 7.83601453035807e-06,
+      "loss": 1.3967,
+      "step": 39000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.295450614080609e-06,
+      "loss": 1.3963,
+      "step": 39500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 6.754886697803149e-06,
+      "loss": 1.4131,
+      "step": 40000
+    },
+    {
+      "epoch": 2.63,
+      "learning_rate": 6.2143227815256884e-06,
+      "loss": 1.381,
+      "step": 40500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.673758865248227e-06,
+      "loss": 1.4123,
+      "step": 41000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.133194948970767e-06,
+      "loss": 1.4132,
+      "step": 41500
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 4.5926310326933056e-06,
+      "loss": 1.4029,
+      "step": 42000
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 4.052067116415845e-06,
+      "loss": 1.3981,
+      "step": 42500
+    },
+    {
+      "epoch": 2.79,
+      "learning_rate": 3.5115032001383844e-06,
+      "loss": 1.3978,
+      "step": 43000
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 2.970939283860924e-06,
+      "loss": 1.4081,
+      "step": 43500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 2.430375367583463e-06,
+      "loss": 1.4115,
+      "step": 44000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.8898114513060028e-06,
+      "loss": 1.4018,
+      "step": 44500
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 1.3492475350285417e-06,
+      "loss": 1.3923,
+      "step": 45000
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 8.086836187510811e-07,
+      "loss": 1.3863,
+      "step": 45500
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 2.681197024736205e-07,
+      "loss": 1.3951,
+      "step": 46000
+    },
+    {
+      "epoch": 3.0,
+      "step": 46248,
+      "total_flos": 1.7013927281688576e+16,
+      "train_loss": 1.5740079802226246,
+      "train_runtime": 16384.5833,
+      "train_samples_per_second": 45.162,
+      "train_steps_per_second": 2.823
+    }
+  ],
+  "max_steps": 46248,
+  "num_train_epochs": 3,
+  "total_flos": 1.7013927281688576e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db9ecb791db02928b6980b482166ba2e9c9155836a04e95429121cd9bc0efe42
+size 3247