End of training

Browse files

Files changed (15) hide show

.gitattributes +0 -2
last-checkpoint/generation_config.json → generation_config.json +0 -0
last-checkpoint/config.json +0 -61
last-checkpoint/optimizer.pt +0 -3
last-checkpoint/pytorch_model.bin +0 -3
last-checkpoint/rng_state.pth +0 -3
last-checkpoint/scheduler.pt +0 -3
last-checkpoint/source.spm +0 -3
last-checkpoint/special_tokens_map.json +0 -5
last-checkpoint/target.spm +0 -3
last-checkpoint/tokenizer_config.json +0 -13
last-checkpoint/trainer_state.json +0 -391
last-checkpoint/training_args.bin +0 -3
last-checkpoint/vocab.json +0 -0
pytorch_model.bin +1 -1

.gitattributes CHANGED Viewed

@@ -32,7 +32,5 @@ 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
-last-checkpoint/source.spm filter=lfs diff=lfs merge=lfs -text
-last-checkpoint/target.spm filter=lfs diff=lfs merge=lfs -text
 source.spm filter=lfs diff=lfs merge=lfs -text
 target.spm 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
 target.spm filter=lfs diff=lfs merge=lfs -text

last-checkpoint/generation_config.json → generation_config.json RENAMED Viewed

File without changes

last-checkpoint/config.json DELETED Viewed

@@ -1,61 +0,0 @@
-{
-  "_name_or_path": "./models/opus-mt-en-id",
-  "_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": [
-    [
-      54795
-    ]
-  ],
-  "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": 54795,
-  "decoder_vocab_size": 54796,
-  "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": 4,
-  "num_hidden_layers": 6,
-  "pad_token_id": 54795,
-  "scale_embedding": true,
-  "share_encoder_decoder_embeddings": true,
-  "static_position_embeddings": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
-  "use_cache": true,
-  "vocab_size": 54796
-}

last-checkpoint/optimizer.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a0017ec3f010f6ea9df5950d972e95da8665ea7f0bfbf944ee5b4d3f5f6b214a
-size 577701381

last-checkpoint/pytorch_model.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1a7b8f40f221723b2a5336172c3ccfe79f5fde1596763f0ed4921885e6261e55
-size 289081861

last-checkpoint/rng_state.pth DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:aa3e117ca49b036bfad1c074067bb39ad5d9a9f2db17dbda2ca500f73837b9f2
-size 14511

last-checkpoint/scheduler.pt DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3ee244d99cf1ef6f6077b70a8893738482f9a54a0a3a311433f1846a9680a168
-size 627

last-checkpoint/source.spm DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e88300911c2c573ec5526777a1e84bae698d20925b82dcef9c7248bb0e537ed0
-size 795925

last-checkpoint/special_tokens_map.json DELETED Viewed

@@ -1,5 +0,0 @@
-{
-  "eos_token": "</s>",
-  "pad_token": "<pad>",
-  "unk_token": "<unk>"
-}

last-checkpoint/target.spm DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2a8fefe71c7f26cb0c6aa1b9f0cc0f8d18006b20fe41c547af7f25b9c8333465
-size 800687

last-checkpoint/tokenizer_config.json DELETED Viewed

@@ -1,13 +0,0 @@
-{
-  "eos_token": "</s>",
-  "model_max_length": 512,
-  "name_or_path": "./models/opus-mt-en-id",
-  "pad_token": "<pad>",
-  "separate_vocabs": false,
-  "source_lang": "en",
-  "sp_model_kwargs": {},
-  "special_tokens_map_file": null,
-  "target_lang": "id",
-  "tokenizer_class": "MarianTokenizer",
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json DELETED Viewed

@@ -1,391 +0,0 @@
-{
-  "best_metric": 1.7099316120147705,
-  "best_model_checkpoint": "models/opus-mt-en-id-opus100/checkpoint-31250",
-  "epoch": 25.0,
-  "global_step": 781250,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 1.0,
-      "learning_rate": 9.649404953361209e-05,
-      "loss": 1.6086,
-      "step": 31250
-    },
-    {
-      "epoch": 1.0,
-      "eval_bleu": 29.4293,
-      "eval_loss": 1.7099316120147705,
-      "eval_runtime": 35.1916,
-      "eval_samples_per_second": 56.832,
-      "eval_steps_per_second": 1.79,
-      "step": 31250
-    },
-    {
-      "epoch": 2.0,
-      "learning_rate": 9.247346413637826e-05,
-      "loss": 1.5762,
-      "step": 62500
-    },
-    {
-      "epoch": 2.0,
-      "eval_bleu": 28.948,
-      "eval_loss": 1.7409919500350952,
-      "eval_runtime": 34.945,
-      "eval_samples_per_second": 57.233,
-      "eval_steps_per_second": 1.803,
-      "step": 62500
-    },
-    {
-      "epoch": 3.0,
-      "learning_rate": 8.845287873914442e-05,
-      "loss": 1.5027,
-      "step": 93750
-    },
-    {
-      "epoch": 3.0,
-      "eval_bleu": 28.6931,
-      "eval_loss": 1.767769694328308,
-      "eval_runtime": 34.3563,
-      "eval_samples_per_second": 58.214,
-      "eval_steps_per_second": 1.834,
-      "step": 93750
-    },
-    {
-      "epoch": 4.0,
-      "learning_rate": 8.443229334191058e-05,
-      "loss": 1.4377,
-      "step": 125000
-    },
-    {
-      "epoch": 4.0,
-      "eval_bleu": 28.9463,
-      "eval_loss": 1.779849648475647,
-      "eval_runtime": 34.8763,
-      "eval_samples_per_second": 57.345,
-      "eval_steps_per_second": 1.806,
-      "step": 125000
-    },
-    {
-      "epoch": 5.0,
-      "learning_rate": 8.041170794467674e-05,
-      "loss": 1.3763,
-      "step": 156250
-    },
-    {
-      "epoch": 5.0,
-      "eval_bleu": 28.4966,
-      "eval_loss": 1.8018742799758911,
-      "eval_runtime": 37.3892,
-      "eval_samples_per_second": 53.491,
-      "eval_steps_per_second": 1.685,
-      "step": 156250
-    },
-    {
-      "epoch": 6.0,
-      "learning_rate": 7.63911225474429e-05,
-      "loss": 1.3198,
-      "step": 187500
-    },
-    {
-      "epoch": 6.0,
-      "eval_bleu": 29.6279,
-      "eval_loss": 1.8202235698699951,
-      "eval_runtime": 35.8037,
-      "eval_samples_per_second": 55.86,
-      "eval_steps_per_second": 1.76,
-      "step": 187500
-    },
-    {
-      "epoch": 7.0,
-      "learning_rate": 7.237053715020908e-05,
-      "loss": 1.2648,
-      "step": 218750
-    },
-    {
-      "epoch": 7.0,
-      "eval_bleu": 29.8151,
-      "eval_loss": 1.8312174081802368,
-      "eval_runtime": 34.1488,
-      "eval_samples_per_second": 58.567,
-      "eval_steps_per_second": 1.845,
-      "step": 218750
-    },
-    {
-      "epoch": 8.0,
-      "learning_rate": 6.834995175297524e-05,
-      "loss": 1.2115,
-      "step": 250000
-    },
-    {
-      "epoch": 8.0,
-      "eval_bleu": 29.3032,
-      "eval_loss": 1.8490322828292847,
-      "eval_runtime": 35.0418,
-      "eval_samples_per_second": 57.075,
-      "eval_steps_per_second": 1.798,
-      "step": 250000
-    },
-    {
-      "epoch": 9.0,
-      "learning_rate": 6.43293663557414e-05,
-      "loss": 1.1584,
-      "step": 281250
-    },
-    {
-      "epoch": 9.0,
-      "eval_bleu": 28.7282,
-      "eval_loss": 1.8729382753372192,
-      "eval_runtime": 35.1809,
-      "eval_samples_per_second": 56.849,
-      "eval_steps_per_second": 1.791,
-      "step": 281250
-    },
-    {
-      "epoch": 10.0,
-      "learning_rate": 6.030878095850756e-05,
-      "loss": 1.1067,
-      "step": 312500
-    },
-    {
-      "epoch": 10.0,
-      "eval_bleu": 29.4797,
-      "eval_loss": 1.8971490859985352,
-      "eval_runtime": 35.2599,
-      "eval_samples_per_second": 56.722,
-      "eval_steps_per_second": 1.787,
-      "step": 312500
-    },
-    {
-      "epoch": 11.0,
-      "learning_rate": 5.6288195561273725e-05,
-      "loss": 1.0555,
-      "step": 343750
-    },
-    {
-      "epoch": 11.0,
-      "eval_bleu": 29.3416,
-      "eval_loss": 1.940462589263916,
-      "eval_runtime": 37.5609,
-      "eval_samples_per_second": 53.247,
-      "eval_steps_per_second": 1.677,
-      "step": 343750
-    },
-    {
-      "epoch": 12.0,
-      "learning_rate": 5.2267610164039885e-05,
-      "loss": 1.0052,
-      "step": 375000
-    },
-    {
-      "epoch": 12.0,
-      "eval_bleu": 29.0168,
-      "eval_loss": 1.9554133415222168,
-      "eval_runtime": 34.6681,
-      "eval_samples_per_second": 57.69,
-      "eval_steps_per_second": 1.817,
-      "step": 375000
-    },
-    {
-      "epoch": 13.0,
-      "learning_rate": 4.8247024766806045e-05,
-      "loss": 0.956,
-      "step": 406250
-    },
-    {
-      "epoch": 13.0,
-      "eval_bleu": 28.2454,
-      "eval_loss": 2.0001118183135986,
-      "eval_runtime": 35.9349,
-      "eval_samples_per_second": 55.656,
-      "eval_steps_per_second": 1.753,
-      "step": 406250
-    },
-    {
-      "epoch": 14.0,
-      "learning_rate": 4.422643936957221e-05,
-      "loss": 0.9069,
-      "step": 437500
-    },
-    {
-      "epoch": 14.0,
-      "eval_bleu": 28.6705,
-      "eval_loss": 2.028186082839966,
-      "eval_runtime": 36.16,
-      "eval_samples_per_second": 55.31,
-      "eval_steps_per_second": 1.742,
-      "step": 437500
-    },
-    {
-      "epoch": 15.0,
-      "learning_rate": 4.020585397233837e-05,
-      "loss": 0.8589,
-      "step": 468750
-    },
-    {
-      "epoch": 15.0,
-      "eval_bleu": 28.1988,
-      "eval_loss": 2.059141159057617,
-      "eval_runtime": 36.5906,
-      "eval_samples_per_second": 54.659,
-      "eval_steps_per_second": 1.722,
-      "step": 468750
-    },
-    {
-      "epoch": 16.0,
-      "learning_rate": 3.618526857510454e-05,
-      "loss": 0.8115,
-      "step": 500000
-    },
-    {
-      "epoch": 16.0,
-      "eval_bleu": 28.2227,
-      "eval_loss": 2.0944082736968994,
-      "eval_runtime": 37.202,
-      "eval_samples_per_second": 53.761,
-      "eval_steps_per_second": 1.693,
-      "step": 500000
-    },
-    {
-      "epoch": 17.0,
-      "learning_rate": 3.21646831778707e-05,
-      "loss": 0.765,
-      "step": 531250
-    },
-    {
-      "epoch": 17.0,
-      "eval_bleu": 28.4351,
-      "eval_loss": 2.129401922225952,
-      "eval_runtime": 35.9887,
-      "eval_samples_per_second": 55.573,
-      "eval_steps_per_second": 1.751,
-      "step": 531250
-    },
-    {
-      "epoch": 18.0,
-      "learning_rate": 2.8144097780636862e-05,
-      "loss": 0.7203,
-      "step": 562500
-    },
-    {
-      "epoch": 18.0,
-      "eval_bleu": 27.9764,
-      "eval_loss": 2.1680092811584473,
-      "eval_runtime": 36.2256,
-      "eval_samples_per_second": 55.21,
-      "eval_steps_per_second": 1.739,
-      "step": 562500
-    },
-    {
-      "epoch": 19.0,
-      "learning_rate": 2.4123512383403023e-05,
-      "loss": 0.6769,
-      "step": 593750
-    },
-    {
-      "epoch": 19.0,
-      "eval_bleu": 28.2986,
-      "eval_loss": 2.2012977600097656,
-      "eval_runtime": 36.0197,
-      "eval_samples_per_second": 55.525,
-      "eval_steps_per_second": 1.749,
-      "step": 593750
-    },
-    {
-      "epoch": 20.0,
-      "learning_rate": 2.0102926986169186e-05,
-      "loss": 0.6349,
-      "step": 625000
-    },
-    {
-      "epoch": 20.0,
-      "eval_bleu": 27.165,
-      "eval_loss": 2.2338688373565674,
-      "eval_runtime": 35.5633,
-      "eval_samples_per_second": 56.238,
-      "eval_steps_per_second": 1.771,
-      "step": 625000
-    },
-    {
-      "epoch": 21.0,
-      "learning_rate": 1.608234158893535e-05,
-      "loss": 0.5957,
-      "step": 656250
-    },
-    {
-      "epoch": 21.0,
-      "eval_bleu": 27.5845,
-      "eval_loss": 2.279478073120117,
-      "eval_runtime": 37.6573,
-      "eval_samples_per_second": 53.111,
-      "eval_steps_per_second": 1.673,
-      "step": 656250
-    },
-    {
-      "epoch": 22.0,
-      "learning_rate": 1.2061756191701511e-05,
-      "loss": 0.5589,
-      "step": 687500
-    },
-    {
-      "epoch": 22.0,
-      "eval_bleu": 27.7201,
-      "eval_loss": 2.3037407398223877,
-      "eval_runtime": 35.3323,
-      "eval_samples_per_second": 56.605,
-      "eval_steps_per_second": 1.783,
-      "step": 687500
-    },
-    {
-      "epoch": 23.0,
-      "learning_rate": 8.041170794467675e-06,
-      "loss": 0.5246,
-      "step": 718750
-    },
-    {
-      "epoch": 23.0,
-      "eval_bleu": 27.3305,
-      "eval_loss": 2.3310611248016357,
-      "eval_runtime": 36.9324,
-      "eval_samples_per_second": 54.153,
-      "eval_steps_per_second": 1.706,
-      "step": 718750
-    },
-    {
-      "epoch": 24.0,
-      "learning_rate": 4.020585397233837e-06,
-      "loss": 0.4944,
-      "step": 750000
-    },
-    {
-      "epoch": 24.0,
-      "eval_bleu": 27.3965,
-      "eval_loss": 2.3486976623535156,
-      "eval_runtime": 35.9377,
-      "eval_samples_per_second": 55.652,
-      "eval_steps_per_second": 1.753,
-      "step": 750000
-    },
-    {
-      "epoch": 25.0,
-      "learning_rate": 0.0,
-      "loss": 0.469,
-      "step": 781250
-    },
-    {
-      "epoch": 25.0,
-      "eval_bleu": 27.5354,
-      "eval_loss": 2.3682210445404053,
-      "eval_runtime": 36.123,
-      "eval_samples_per_second": 55.366,
-      "eval_steps_per_second": 1.744,
-      "step": 781250
-    }
-  ],
-  "max_steps": 781250,
-  "num_train_epochs": 25,
-  "total_flos": 2.0779618887165542e+17,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin DELETED Viewed

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:134225c4d6c87d884c98ae0cd64d54fb1c06f950adddd7d3864b356197075820
-size 3643

last-checkpoint/vocab.json DELETED Viewed

The diff for this file is too large to render. See raw diff

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a7b8f40f221723b2a5336172c3ccfe79f5fde1596763f0ed4921885e6261e55
 size 289081861

 version https://git-lfs.github.com/spec/v1
+oid sha256:bc812b7edce24addb5f19eb121f3d47d5da047a90a9cb09f4642d7064630b283
 size 289081861