Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,109 @@
+{
+  "_commit_hash": "aa1bf2d3fd3e1b2dbd46e6862fe3bbadd420ecf1",
+  "_name_or_path": "facebook/wmt19-en-ru",
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "FSMTForConditionalGeneration"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 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": 2,
+  "dropout": 0.2,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 8192,
+  "encoder_layerdrop": 0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "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": 1,
+  "scale_embedding": true,
+  "src_vocab_size": 31640,
+  "tgt_vocab_size": 31232,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_cache": true
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17538c5550c74610ffee730a93023351b19f73ad7b71a24a5ddaf9c1045730f5
+size 1164464453

runs/May21_10-39-28_c7ce4759df33/1684665582.059114/events.out.tfevents.1684665582.c7ce4759df33.31.5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e287f51e3356a8d0b9f516e678229eee5f27c6e354a2a08453065c666edcd92
+size 6201

runs/May21_10-39-28_c7ce4759df33/events.out.tfevents.1684665582.c7ce4759df33.31.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1caa9d8bbcde81a8aa6a3f01e134eeb050973dd3122a39e18afdf94e5e4f68c3
+size 6476

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "do_lower_case": false,
+  "langs": [
+    "en",
+    "ru"
+  ],
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "FSMTTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a0edb6ed81a53408d25bf020d2b420d6cc9914fe7e2c99c1130b2e618c96c23
+size 4091