Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,108 @@
+{
+  "_commit_hash": "c5ae7939087b30f964295f98e5a53f0b81093a8f",
+  "_name_or_path": "facebook/wmt19-en-de",
+  "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": "4.27.4",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "vocab_size": 42024
+  },
+  "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",
+    "de"
+  ],
+  "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": 42024,
+  "tgt_vocab_size": 42024,
+  "tie_word_embeddings": true,
+  "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 sha256:59f33ea3fc3675218d74343a3750d54938e9377e5c3f71aac5b47ba07f313239
+size 1251201349

runs/Apr07_16-07-57_f1fe05b9ea23/1680883699.1197946/events.out.tfevents.1680883699.f1fe05b9ea23.158.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5ada166a807737feb91d1b4c5b07796887afacbbb02e8f0836920c557763170
+size 6095

runs/Apr07_16-07-57_f1fe05b9ea23/events.out.tfevents.1680883699.f1fe05b9ea23.158.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d00f97ae934ffb44092e24bdfa20d0f73fe9068f151d4f323d594b7c6fd9a0a
+size 6404

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 +1,15 @@
+{
+  "bos_token": "<s>",
+  "do_lower_case": false,
+  "langs": [
+    "en",
+    "de"
+  ],
+  "model_max_length": 1024,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "src_lang": "en_XX",
+  "tokenizer_class": "FSMTTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daa24427671420b5474ff47a32bfaae68eeecc01d2dab08bfb043618a503825a
+size 3707