Training in progress, step 500

config.json

@@ -1,61 +1,109 @@
 {
-  "_name_or_path": "Helsinki-NLP/opus-mt-en-ru",
-  "_num_labels": 3,
+  "_commit_hash": "aa1bf2d3fd3e1b2dbd46e6862fe3bbadd420ecf1",
+  "_name_or_path": "facebook/wmt19-en-ru",
   "activation_dropout": 0.0,
-  "activation_function": "swish",
-  "add_bias_logits": false,
-  "add_final_layer_norm": false,
+  "activation_function": "relu",
   "architectures": [
-    "MarianMTModel"
-  ],
-  "attention_dropout": 0.0,
-  "bad_words_ids": [
-    [
-      62517
-    ]
+    "FSMTForConditionalGeneration"
   ],
+  "attention_dropout": 0.1,
   "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,
+  "d_model": 1024,
+  "decoder": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": null,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 2,
+    "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,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "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"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "fsmt_decoder",
+    "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,
+    "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": "4.29.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 31232
+  },
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 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,
+  "decoder_start_token_id": 2,
+  "dropout": 0.2,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
   "encoder_layers": 6,
-  "eos_token_id": 0,
-  "forced_eos_token_id": 0,
-  "id2label": {
-    "0": "LABEL_0",
-    "1": "LABEL_1",
-    "2": "LABEL_2"
-  },
+  "eos_token_id": 2,
+  "forced_eos_token_id": 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,
+  "langs": [
+    "en",
+    "ru"
+  ],
+  "length_penalty": 1.15,
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "fsmt",
+  "num_beams": 5,
   "num_hidden_layers": 6,
-  "pad_token_id": 62517,
+  "pad_token_id": 1,
   "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
-  "static_position_embeddings": true,
+  "src_vocab_size": 31640,
+  "tgt_vocab_size": 31232,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.29.2",
-  "use_cache": true,
-  "vocab_size": 62518
+  "transformers_version": null,
+  "use_cache": true
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4439985befbc28c96da47efb754afe0852deaed8f4ff3fb885ded09931e937ac
-size 304927429
+oid sha256:8264320801e8ab386d6c4049b7f5bec27eae142f9f2c2e0566edba50a22f5d60
+size 1164464453

runs/May20_18-38-01_36e7aceae669/1684617419.9729273/events.out.tfevents.1684617419.36e7aceae669.31.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35a45952ad65082926d11475531848ff72c34a690f0c2358286d6e6c3a46a8ad
+size 6207

runs/May20_18-38-01_36e7aceae669/events.out.tfevents.1684617419.36e7aceae669.31.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3180840067d1828d5b5ebab565666a036eefd726fa09599548752318b3edcba7
+size 6482

special_tokens_map.json

@@ -1,5 +1,6 @@
 {
-  "eos_token": "</s>",
+  "bos_token": "<s>",
   "pad_token": "<pad>",
+  "sep_token": "</s>",
   "unk_token": "<unk>"
 }

tokenizer_config.json

@@ -1,12 +1,14 @@
 {
+  "bos_token": "<s>",
   "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "model_max_length": 512,
+  "do_lower_case": false,
+  "langs": [
+    "en",
+    "ru"
+  ],
+  "model_max_length": 1024,
   "pad_token": "<pad>",
-  "separate_vocabs": false,
-  "source_lang": "en",
-  "sp_model_kwargs": {},
-  "target_lang": "ru",
-  "tokenizer_class": "MarianTokenizer",
+  "sep_token": "</s>",
+  "tokenizer_class": "FSMTTokenizer",
   "unk_token": "<unk>"
 }