small dataset finish

last-checkpoint/config.json

@@ -1,37 +0,0 @@
-{
-  "_name_or_path": "Nekofox/M2M100-ja-zh",
-  "activation_dropout": 0.0,
-  "activation_function": "relu",
-  "architectures": [
-    "M2M100ForConditionalGeneration"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 0,
-  "d_model": 1024,
-  "decoder_attention_heads": 16,
-  "decoder_ffn_dim": 4096,
-  "decoder_layerdrop": 0.05,
-  "decoder_layers": 12,
-  "decoder_start_token_id": 2,
-  "dropout": 0.1,
-  "early_stopping": true,
-  "encoder_attention_heads": 16,
-  "encoder_ffn_dim": 4096,
-  "encoder_layerdrop": 0.05,
-  "encoder_layers": 12,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "init_std": 0.02,
-  "is_encoder_decoder": true,
-  "max_length": 200,
-  "max_position_embeddings": 1024,
-  "model_type": "m2m_100",
-  "num_beams": 5,
-  "num_hidden_layers": 12,
-  "pad_token_id": 1,
-  "scale_embedding": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.28.1",
-  "use_cache": true,
-  "vocab_size": 128112
-}

last-checkpoint/generation_config.json

@@ -1,10 +0,0 @@
-{
-  "bos_token_id": 0,
-  "decoder_start_token_id": 2,
-  "early_stopping": true,
-  "eos_token_id": 2,
-  "max_length": 200,
-  "num_beams": 5,
-  "pad_token_id": 1,
-  "transformers_version": "4.28.1"
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a70da9c307b89e0f6803e6b4d790724eaf22f16cf5a39b89e5be664b7c6ef817
-size 3871543575

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9e2279d0b00eea02275f19b0918fc5caf16bc305821941ac3a1bfabdaec14495
-size 1944201353

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9add67e0e7c64985d7f86ed3237947f4d8273983a833a5710b022a6a1bea08e2
-size 14575

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5dc9eacfeb00bd0bfeb98934a2309be01be65b288e0d747bbfc423b32679169f
-size 557

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:753fb611d101de33818037c538ed00dd755c130ad830e2fc514a0dba409c9a50
-size 627

last-checkpoint/sentencepiece.bpe.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d8f7c76ed2a5e0822be39f0a4f95a55eb19c78f4593ce609e2edbc2aea4d380a
-size 2423393

last-checkpoint/special_tokens_map.json

@@ -1,109 +0,0 @@
-{
-  "additional_special_tokens": [
-    "__af__",
-    "__am__",
-    "__ar__",
-    "__ast__",
-    "__az__",
-    "__ba__",
-    "__be__",
-    "__bg__",
-    "__bn__",
-    "__br__",
-    "__bs__",
-    "__ca__",
-    "__ceb__",
-    "__cs__",
-    "__cy__",
-    "__da__",
-    "__de__",
-    "__el__",
-    "__en__",
-    "__es__",
-    "__et__",
-    "__fa__",
-    "__ff__",
-    "__fi__",
-    "__fr__",
-    "__fy__",
-    "__ga__",
-    "__gd__",
-    "__gl__",
-    "__gu__",
-    "__ha__",
-    "__he__",
-    "__hi__",
-    "__hr__",
-    "__ht__",
-    "__hu__",
-    "__hy__",
-    "__id__",
-    "__ig__",
-    "__ilo__",
-    "__is__",
-    "__it__",
-    "__ja__",
-    "__jv__",
-    "__ka__",
-    "__kk__",
-    "__km__",
-    "__kn__",
-    "__ko__",
-    "__lb__",
-    "__lg__",
-    "__ln__",
-    "__lo__",
-    "__lt__",
-    "__lv__",
-    "__mg__",
-    "__mk__",
-    "__ml__",
-    "__mn__",
-    "__mr__",
-    "__ms__",
-    "__my__",
-    "__ne__",
-    "__nl__",
-    "__no__",
-    "__ns__",
-    "__oc__",
-    "__or__",
-    "__pa__",
-    "__pl__",
-    "__ps__",
-    "__pt__",
-    "__ro__",
-    "__ru__",
-    "__sd__",
-    "__si__",
-    "__sk__",
-    "__sl__",
-    "__so__",
-    "__sq__",
-    "__sr__",
-    "__ss__",
-    "__su__",
-    "__sv__",
-    "__sw__",
-    "__ta__",
-    "__th__",
-    "__tl__",
-    "__tn__",
-    "__tr__",
-    "__uk__",
-    "__ur__",
-    "__uz__",
-    "__vi__",
-    "__wo__",
-    "__xh__",
-    "__yi__",
-    "__yo__",
-    "__zh__",
-    "__zu__"
-  ],
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "unk_token": "<unk>"
-}

last-checkpoint/tokenizer_config.json

@@ -1,118 +0,0 @@
-{
-  "additional_special_tokens": [
-    "__af__",
-    "__am__",
-    "__ar__",
-    "__ast__",
-    "__az__",
-    "__ba__",
-    "__be__",
-    "__bg__",
-    "__bn__",
-    "__br__",
-    "__bs__",
-    "__ca__",
-    "__ceb__",
-    "__cs__",
-    "__cy__",
-    "__da__",
-    "__de__",
-    "__el__",
-    "__en__",
-    "__es__",
-    "__et__",
-    "__fa__",
-    "__ff__",
-    "__fi__",
-    "__fr__",
-    "__fy__",
-    "__ga__",
-    "__gd__",
-    "__gl__",
-    "__gu__",
-    "__ha__",
-    "__he__",
-    "__hi__",
-    "__hr__",
-    "__ht__",
-    "__hu__",
-    "__hy__",
-    "__id__",
-    "__ig__",
-    "__ilo__",
-    "__is__",
-    "__it__",
-    "__ja__",
-    "__jv__",
-    "__ka__",
-    "__kk__",
-    "__km__",
-    "__kn__",
-    "__ko__",
-    "__lb__",
-    "__lg__",
-    "__ln__",
-    "__lo__",
-    "__lt__",
-    "__lv__",
-    "__mg__",
-    "__mk__",
-    "__ml__",
-    "__mn__",
-    "__mr__",
-    "__ms__",
-    "__my__",
-    "__ne__",
-    "__nl__",
-    "__no__",
-    "__ns__",
-    "__oc__",
-    "__or__",
-    "__pa__",
-    "__pl__",
-    "__ps__",
-    "__pt__",
-    "__ro__",
-    "__ru__",
-    "__sd__",
-    "__si__",
-    "__sk__",
-    "__sl__",
-    "__so__",
-    "__sq__",
-    "__sr__",
-    "__ss__",
-    "__su__",
-    "__sv__",
-    "__sw__",
-    "__ta__",
-    "__th__",
-    "__tl__",
-    "__tn__",
-    "__tr__",
-    "__uk__",
-    "__ur__",
-    "__uz__",
-    "__vi__",
-    "__wo__",
-    "__xh__",
-    "__yi__",
-    "__yo__",
-    "__zh__",
-    "__zu__"
-  ],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": true,
-  "eos_token": "</s>",
-  "language_codes": "m2m100",
-  "model_max_length": 1024,
-  "num_madeup_words": 8,
-  "pad_token": "<pad>",
-  "sep_token": "</s>",
-  "sp_model_kwargs": {},
-  "src_lang": "ja",
-  "tgt_lang": "zh",
-  "tokenizer_class": "M2M100Tokenizer",
-  "tokenizer_file": null,
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,32 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 20.0,
-  "global_step": 600,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 16.67,
-      "learning_rate": 3.0977443609452007e-06,
-      "loss": 0.3114,
-      "step": 500
-    },
-    {
-      "epoch": 16.67,
-      "eval_bleu": 23.7507,
-      "eval_gen_len": 20.007,
-      "eval_loss": 2.0595486164093018,
-      "eval_runtime": 132.2443,
-      "eval_samples_per_second": 4.31,
-      "eval_steps_per_second": 0.484,
-      "step": 500
-    }
-  ],
-  "max_steps": 600,
-  "num_train_epochs": 20,
-  "total_flos": 229044332888064.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a6548a11b5bf41ca0d30d25ae762960cdd697b755d28048f063b6a4fe41abe08
-size 3771

runs/May10_05-47-52_beffab83ea5d/events.out.tfevents.1683697688.beffab83ea5d.12842.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02843b4001406abec31e4ed18c77db8e05eda2bed214207d672cdd6b3a9a6804
-size 4988
+oid sha256:bc41e552613bca8ff0f5415e7f382fcfabd27c67a186071c5a267e2fd0d08519
+size 5342