Upload 12 files

.gitattributes

@@ -33,3 +33,4 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-ru-en",
+  "_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,
+  "decoder_vocab_size": 62518,
+  "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": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 62517,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0",
+  "use_cache": true,
+  "vocab_size": 62518
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9050e8624e78f1da804fa27db916f1b005c3dd8fd4debb84617ffc8ee85ca98
+size 609330181

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0444920f02cd17ce109af160c5c6d4194d52445c54da8a8161244d32686c4439
+size 304937349

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:900ec533efb25db26976bd99730fd8bdd1f1e0e84956d3a8fc7ecaa8abfbbb08
+size 14639

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa54ab9050b0de63c4a117fee3b97fc78ed1ddd112d00ac9a6197425c9b0c43d
+size 627

source.spm

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

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"source_lang": "ru", "target_lang": "en", "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-ru-en", "tokenizer_class": "MarianTokenizer"}

trainer_state.json

@@ -0,0 +1,148 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.51086956521739,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 62.8839,
+      "eval_gen_len": 18.6587,
+      "eval_loss": 0.6685489416122437,
+      "eval_runtime": 219.9201,
+      "eval_samples_per_second": 6.689,
+      "eval_steps_per_second": 0.418,
+      "step": 368
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.456521739130435e-05,
+      "loss": 0.9723,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 70.5409,
+      "eval_gen_len": 18.0659,
+      "eval_loss": 0.5173786878585815,
+      "eval_runtime": 185.8072,
+      "eval_samples_per_second": 7.917,
+      "eval_steps_per_second": 0.495,
+      "step": 736
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2.91304347826087e-05,
+      "loss": 0.4138,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 70.6822,
+      "eval_gen_len": 18.2522,
+      "eval_loss": 0.4692835211753845,
+      "eval_runtime": 305.3472,
+      "eval_samples_per_second": 4.817,
+      "eval_steps_per_second": 0.301,
+      "step": 1104
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 76.1884,
+      "eval_gen_len": 18.2624,
+      "eval_loss": 0.43825143575668335,
+      "eval_runtime": 180.0844,
+      "eval_samples_per_second": 8.168,
+      "eval_steps_per_second": 0.511,
+      "step": 1472
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 2.3695652173913045e-05,
+      "loss": 0.2544,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 76.4649,
+      "eval_gen_len": 17.9884,
+      "eval_loss": 0.42623549699783325,
+      "eval_runtime": 265.6449,
+      "eval_samples_per_second": 5.537,
+      "eval_steps_per_second": 0.346,
+      "step": 1840
+    },
+    {
+      "epoch": 5.43,
+      "learning_rate": 1.8260869565217393e-05,
+      "loss": 0.1709,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 77.8959,
+      "eval_gen_len": 17.9952,
+      "eval_loss": 0.41967156529426575,
+      "eval_runtime": 222.1851,
+      "eval_samples_per_second": 6.621,
+      "eval_steps_per_second": 0.414,
+      "step": 2208
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 1.282608695652174e-05,
+      "loss": 0.1287,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 78.8909,
+      "eval_gen_len": 18.0598,
+      "eval_loss": 0.4178922474384308,
+      "eval_runtime": 226.0293,
+      "eval_samples_per_second": 6.508,
+      "eval_steps_per_second": 0.407,
+      "step": 2576
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 78.7098,
+      "eval_gen_len": 18.0034,
+      "eval_loss": 0.4161533713340759,
+      "eval_runtime": 218.1192,
+      "eval_samples_per_second": 6.744,
+      "eval_steps_per_second": 0.422,
+      "step": 2944
+    },
+    {
+      "epoch": 8.15,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 0.1028,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu": 79.2546,
+      "eval_gen_len": 18.0659,
+      "eval_loss": 0.4158268868923187,
+      "eval_runtime": 170.3307,
+      "eval_samples_per_second": 8.636,
+      "eval_steps_per_second": 0.54,
+      "step": 3312
+    },
+    {
+      "epoch": 9.51,
+      "learning_rate": 1.956521739130435e-06,
+      "loss": 0.084,
+      "step": 3500
+    }
+  ],
+  "max_steps": 3680,
+  "num_train_epochs": 10,
+  "total_flos": 2284115790790656.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c994e33704d5251793ac8647fd6fffed18bf29cdf2d8f7dfe8c4837fa16c68
+size 3067