Training in progress, step 500

.gitattributes

@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+wandb/run-20220503_171959-a6039xud/run-a6039xud.wandb filter=lfs diff=lfs merge=lfs -text

.gitignore

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

config.json

@@ -0,0 +1,285 @@
+{
+  "_name_or_path": "./",
+  "architectures": [
+    "SpeechEncoderDecoderModel"
+  ],
+  "decoder": {
+    "_name_or_path": "facebook/bart-large",
+    "activation_dropout": 0.1,
+    "activation_function": "gelu",
+    "add_bias_logits": false,
+    "add_cross_attention": true,
+    "add_final_layer_norm": false,
+    "architectures": [
+      "BartModel"
+    ],
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 0,
+    "chunk_size_feed_forward": 0,
+    "classif_dropout": 0.1,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_model": 1024,
+    "decoder_attention_heads": 16,
+    "decoder_ffn_dim": 4096,
+    "decoder_layerdrop": 0.0,
+    "decoder_layers": 12,
+    "decoder_start_token_id": 2,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": true,
+    "encoder_attention_heads": 16,
+    "encoder_ffn_dim": 4096,
+    "encoder_layerdrop": 0.0,
+    "encoder_layers": 12,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": 0,
+    "forced_eos_token_id": 2,
+    "gradient_checkpointing": false,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1",
+      "2": "LABEL_2"
+    },
+    "init_std": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1,
+      "LABEL_2": 2
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 1024,
+    "min_length": 0,
+    "model_type": "bart",
+    "no_repeat_ngram_size": 3,
+    "normalize_before": false,
+    "num_beam_groups": 1,
+    "num_beams": 4,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "task_specific_params": {
+      "summarization": {
+        "length_penalty": 1.0,
+        "max_length": 128,
+        "min_length": 12,
+        "num_beams": 4
+      },
+      "summarization_cnn": {
+        "length_penalty": 2.0,
+        "max_length": 142,
+        "min_length": 56,
+        "num_beams": 4
+      },
+      "summarization_xsum": {
+        "length_penalty": 1.0,
+        "max_length": 62,
+        "min_length": 11,
+        "num_beams": 6
+      }
+    },
+    "temperature": 1.0,
+    "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": "4.19.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "decoder_start_token_id": 0,
+  "encoder": {
+    "_name_or_path": "facebook/wav2vec2-xls-r-300m",
+    "activation_dropout": 0.0,
+    "adapter_kernel_size": 3,
+    "adapter_stride": 2,
+    "add_adapter": true,
+    "add_cross_attention": false,
+    "apply_spec_augment": true,
+    "architectures": [
+      "Wav2Vec2ForPreTraining"
+    ],
+    "attention_dropout": 0.1,
+    "bad_words_ids": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "classifier_proj_size": 256,
+    "codevector_dim": 768,
+    "contrastive_logits_temperature": 0.1,
+    "conv_bias": true,
+    "conv_dim": [
+      512,
+      512,
+      512,
+      512,
+      512,
+      512,
+      512
+    ],
+    "conv_kernel": [
+      10,
+      3,
+      3,
+      3,
+      3,
+      2,
+      2
+    ],
+    "conv_stride": [
+      5,
+      2,
+      2,
+      2,
+      2,
+      2,
+      2
+    ],
+    "cross_attention_hidden_size": null,
+    "ctc_loss_reduction": "sum",
+    "ctc_zero_infinity": false,
+    "decoder_start_token_id": null,
+    "diversity_loss_weight": 0.1,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "do_stable_layer_norm": true,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "feat_extract_activation": "gelu",
+    "feat_extract_dropout": 0.0,
+    "feat_extract_norm": "layer",
+    "feat_proj_dropout": 0.0,
+    "feat_quantizer_dropout": 0.0,
+    "final_dropout": 0.0,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "gradient_checkpointing": false,
+    "hidden_act": "gelu",
+    "hidden_dropout": 0.06862889720223829,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-05,
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "mask_feature_length": 10,
+    "mask_feature_min_masks": 0,
+    "mask_feature_prob": 0.0,
+    "mask_time_length": 10,
+    "mask_time_min_masks": 2,
+    "mask_time_prob": 0.1,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "wav2vec2",
+    "no_repeat_ngram_size": 0,
+    "num_adapter_layers": 3,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codevector_groups": 2,
+    "num_codevectors_per_group": 320,
+    "num_conv_pos_embedding_groups": 16,
+    "num_conv_pos_embeddings": 128,
+    "num_feat_extract_layers": 7,
+    "num_hidden_layers": 24,
+    "num_negatives": 100,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_size": 1024,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "proj_codevector_dim": 768,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "task_specific_params": null,
+    "tdnn_dilation": [
+      1,
+      2,
+      3,
+      1,
+      1
+    ],
+    "tdnn_dim": [
+      512,
+      512,
+      512,
+      512,
+      1500
+    ],
+    "tdnn_kernel": [
+      5,
+      3,
+      3,
+      1,
+      1
+    ],
+    "temperature": 1.0,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "transformers_version": "4.19.0.dev0",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_weighted_layer_sum": false,
+    "vocab_size": 32,
+    "xvector_output_dim": 512
+  },
+  "eos_token_id": 2,
+  "is_encoder_decoder": true,
+  "max_length": 40,
+  "model_type": "speech-encoder-decoder",
+  "pad_token_id": 1,
+  "processor_class": "Wav2Vec2Processor",
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": null,
+  "use_cache": false
+}

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0,
+  "return_attention_mask": true,
+  "sampling_rate": 16000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008e06044c5250309092dc773bd06898ae5bf91e5bddf24e216307b3e34cbee0
+size 2353867057

run.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-CUDA_VISIBLE_DEVICES=1 python run_xtreme_s.py \
+CUDA_VISIBLE_DEVICES=0 python run_xtreme_s.py \
     --model_name_or_path="./" \
     --task="covost2" \
     --language="fr.en" \

run_xtreme_s.py

@@ -41,6 +41,7 @@ from transformers import (
     HfArgumentParser,
     Seq2SeqTrainer,
     Seq2SeqTrainingArguments,
+    SpeechEncoderDecoderModel,
     Trainer,
     set_seed,
 )
@@ -547,9 +548,9 @@ def main():
 
     def remove_special_characters(batch):
         if chars_to_ignore_regex is not None:
-            batch["target_text"] = re.sub(chars_to_ignore_regex, "", batch[target_column_name]).lower() + " "
+            batch["target_text"] = re.sub(chars_to_ignore_regex, "", batch[target_column_name]).lower()
         else:
-            batch["target_text"] = batch[target_column_name].lower() + " "
+            batch["target_text"] = batch[target_column_name].lower()
         return batch
 
     if is_text_target:
@@ -565,6 +566,30 @@ def main():
         unk_token = data_args.unk_token
         pad_token = data_args.pad_token
 
+
+    encoder_id = "facebook/wav2vec2-xls-r-300m"
+    decoder_id = "facebook/bart-large"
+
+    model = SpeechEncoderDecoderModel.from_encoder_decoder_pretrained(encoder_id, decoder_id, encoder_add_adapter=True)
+    model.config.encoder.feat_proj_dropout = 0.0
+    model.config.encoder.final_dropout = 0.0
+    model.config.encoder.mask_time_prob = 0.1
+    model.config.decoder_start_token_id = model.decoder.config.bos_token_id
+    model.config.pad_token_id = model.decoder.config.pad_token_id
+    model.config.eos_token_id = model.decoder.config.eos_token_id
+    model.config.max_length = 40
+    model.config.num_beams = 1
+    model.config.encoder.layerdrop = 0.0
+    model.config.use_cache = False
+    model.config.processor_class = "Wav2Vec2Processor"
+
+    model.save_pretrained(model_args.model_name_or_path)
+
+    feature_etxractor = AutoFeatureExtractor.from_pretrained(encoder_id)
+    feature_etxractor.save_pretrained(model_args.model_name_or_path)
+    tokenizer = AutoTokenizer.from_pretrained(decoder_id)
+    tokenizer.save_pretrained(model_args.model_name_or_path)
+    
     # 3. Next, let's load the config as we might need it to create
     # the tokenizer
     config = AutoConfig.from_pretrained(

runs/May03_12-39-14_sanchit--v100/1651584502.8814862/events.out.tfevents.1651584502.sanchit--v100.38894.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a5e50bb326f116678bb0d2af94ee25e92d82ce3268121a68b288dd930e13470
+size 5184

runs/May03_12-39-14_sanchit--v100/events.out.tfevents.1651584502.sanchit--v100.38894.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a28e37ffdeeb562c734e7a4815296918b93b818763a73a70ab20d29627105c
+size 10592

runs/May03_15-33-55_sanchit--v100/1651592261.409201/events.out.tfevents.1651592261.sanchit--v100.40140.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3651206b236f0c31a3ff08bbeb2416a7fde03f54ccb583a7df7f8256f3fd29
+size 5184

runs/May03_15-33-55_sanchit--v100/events.out.tfevents.1651592261.sanchit--v100.40140.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c965accf9ea2be03062bfecc4c45cdb54eb6b4b444ea37a2c9533c8db4fed044
+size 87941

runs/May03_15-58-13_sanchit--v100/1651596054.9030492/events.out.tfevents.1651596054.sanchit--v100.40903.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e39c8c39b9be3c4531fd72d066671f7365b550e8079fee72b6060a36be59f6
+size 5184

runs/May03_15-58-13_sanchit--v100/events.out.tfevents.1651596054.sanchit--v100.40903.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:410298c8949435d86a040fb00c0e0a7bde2f0445544abeadadae587ba569bfba
+size 73654

runs/May03_17-15-22_sanchit--v100/1651598399.7088904/events.out.tfevents.1651598399.sanchit--v100.42111.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61b94cd769015be4bbc81b78b8074c963d947a90c91e7cf517abaad8c3ff3078
+size 5184

runs/May03_17-15-22_sanchit--v100/events.out.tfevents.1651598399.sanchit--v100.42111.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:031a66a2aa473ef2b64f357fd6f9159fb836bed0b5c5036f7eb9c55c533a7ad7
+size 88290

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

sweep.yaml

@@ -4,6 +4,7 @@ command:
 - --overwrite_output_dir
 - --freeze_feature_encoder
 - --gradient_checkpointing
+- --predict_with_generate
 - --fp16
 - --group_by_length
 - --do_train
@@ -26,7 +27,7 @@ parameters:
   eval_split_name:
     value: test
   output_dir:
-    value: ./output_dir
+    value: ./
   num_train_epochs:
     value: 3
   per_device_train_batch_size:

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "./", "tokenizer_class": "BartTokenizer"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94e05d5641aa58db52aee32293e970801889668d13a72d205ffa6fe324861d4b
+size 3247

wandb/debug-cli.log

@@ -0,0 +1,155 @@
+2022-05-03 17:09:46 INFO Running runs: []
+2022-05-03 17:09:46 INFO Agent received command: run
+2022-05-03 17:09:46 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.036619638921206475
+	language: fr.en
+	learning_rate: 0.00024391819705381628
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./output_dir
+	per_device_eval_batch_size: 4
+	per_device_train_batch_size: 4
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-03 17:09:46 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.036619638921206475 --language=fr.en --learning_rate=0.00024391819705381628 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./output_dir --per_device_eval_batch_size=4 --per_device_train_batch_size=4 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-03 17:09:51 INFO Running runs: ['vz5ppd75']
+2022-05-03 17:10:26 INFO Cleaning up finished run: vz5ppd75
+2022-05-03 17:10:28 INFO Agent received command: run
+2022-05-03 17:10:28 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.1875094322808032
+	language: fr.en
+	learning_rate: 0.00024438201183496223
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./output_dir
+	per_device_eval_batch_size: 4
+	per_device_train_batch_size: 4
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-03 17:10:36 INFO Running runs: []
+2022-05-03 17:10:36 INFO Agent received command: run
+2022-05-03 17:10:36 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.055722391000930585
+	language: fr.en
+	learning_rate: 0.0006457481677728278
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./output_dir
+	per_device_eval_batch_size: 4
+	per_device_train_batch_size: 4
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-03 17:10:36 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.055722391000930585 --language=fr.en --learning_rate=0.0006457481677728278 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./output_dir --per_device_eval_batch_size=4 --per_device_train_batch_size=4 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-03 17:10:41 INFO Running runs: ['ldsojzle']
+2022-05-03 17:11:07 INFO Cleaning up finished run: ldsojzle
+2022-05-03 17:11:07 INFO Agent received command: run
+2022-05-03 17:11:07 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.056807662149569525
+	language: fr.en
+	learning_rate: 0.0005558468401613797
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./output_dir
+	per_device_eval_batch_size: 4
+	per_device_train_batch_size: 4
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-03 17:11:07 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.056807662149569525 --language=fr.en --learning_rate=0.0005558468401613797 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./output_dir --per_device_eval_batch_size=4 --per_device_train_batch_size=4 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-03 17:11:12 INFO Running runs: ['qv3vjr6j']
+2022-05-03 17:10:28 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.1875094322808032 --language=fr.en --learning_rate=0.00024438201183496223 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./output_dir --per_device_eval_batch_size=4 --per_device_train_batch_size=4 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-03 17:11:29 INFO Running runs: ['irggvkgd']
+2022-05-03 17:11:37 INFO Cleaning up finished run: qv3vjr6j
+2022-05-03 17:11:37 INFO Agent received command: run
+2022-05-03 17:11:37 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.03413483050532159
+	language: fr.en
+	learning_rate: 0.00022086866790135088
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./output_dir
+	per_device_eval_batch_size: 4
+	per_device_train_batch_size: 4
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-03 17:11:37 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.03413483050532159 --language=fr.en --learning_rate=0.00022086866790135088 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./output_dir --per_device_eval_batch_size=4 --per_device_train_batch_size=4 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-03 17:15:19 INFO Running runs: []
+2022-05-03 17:15:19 INFO Agent received command: run
+2022-05-03 17:15:19 INFO Agent starting run with config:
+	eval_split_name: test
+	eval_steps: 500
+	evaluation_strategy: steps
+	generation_max_length: 40
+	generation_num_beams: 1
+	gradient_accumulation_steps: 8
+	greater_is_better: True
+	hidden_dropout: 0.06862889720223829
+	language: fr.en
+	learning_rate: 0.0004848089062550082
+	logging_steps: 1
+	max_duration_in_seconds: 20
+	metric_for_best_model: bleu
+	model_name_or_path: ./
+	num_train_epochs: 3
+	output_dir: ./
+	per_device_eval_batch_size: 4
+	per_device_train_batch_size: 4
+	save_steps: 500
+	task: covost2
+	warmup_steps: 500
+2022-05-03 17:15:19 INFO About to run command: python3 run_xtreme_s.py --overwrite_output_dir --freeze_feature_encoder --gradient_checkpointing --predict_with_generate --fp16 --group_by_length --do_train --do_eval --load_best_model_at_end --push_to_hub --use_auth_token --eval_split_name=test --eval_steps=500 --evaluation_strategy=steps --generation_max_length=40 --generation_num_beams=1 --gradient_accumulation_steps=8 --greater_is_better=True --hidden_dropout=0.06862889720223829 --language=fr.en --learning_rate=0.0004848089062550082 --logging_steps=1 --max_duration_in_seconds=20 --metric_for_best_model=bleu --model_name_or_path=./ --num_train_epochs=3 --output_dir=./ --per_device_eval_batch_size=4 --per_device_train_batch_size=4 --save_steps=500 --task=covost2 --warmup_steps=500
+2022-05-03 17:15:24 INFO Running runs: ['a6039xud']

wandb/debug-internal.log

@@ -0,0 +1 @@
+run-20220503_171959-a6039xud/logs/debug-internal.log

wandb/debug.log

@@ -0,0 +1 @@
+run-20220503_171959-a6039xud/logs/debug.log

wandb/latest-run

@@ -0,0 +1 @@
+run-20220503_171959-a6039xud

wandb/run-20220503_171959-a6039xud/files/requirements.txt

@@ -0,0 +1,287 @@
+absl-py==1.0.0
+aiohttp==3.8.1
+aiosignal==1.2.0
+alembic==1.7.7
+anyio==3.5.0
+appdirs==1.4.4
+apscheduler==3.9.1
+argon2-cffi-bindings==21.2.0
+argon2-cffi==21.3.0
+arrow==1.2.2
+asttokens==2.0.5
+astunparse==1.6.3
+async-timeout==4.0.2
+attrs==21.4.0
+audioread==2.1.9
+autopage==0.5.0
+babel==2.9.1
+backcall==0.2.0
+backoff==1.11.1
+binaryornot==0.4.4
+bitsandbytes-cuda113==0.26.0
+black==22.1.0
+bleach==4.1.0
+boto3==1.16.34
+botocore==1.19.63
+brotli==1.0.9
+cachetools==5.0.0
+certifi==2021.10.8
+cffi==1.15.0
+chardet==4.0.0
+charset-normalizer==2.0.11
+chex==0.1.0
+click==8.0.3
+cliff==3.10.1
+clldutils==3.10.1
+cmaes==0.8.2
+cmd2==2.4.0
+codecarbon==1.2.0
+colorlog==6.6.0
+cookiecutter==1.7.3
+cryptography==36.0.2
+csvw==1.11.0
+cycler==0.11.0
+dash-bootstrap-components==1.1.0
+dash-core-components==2.0.0
+dash-html-components==2.0.0
+dash-table==5.0.0
+dash==2.3.1
+datasets==2.1.1.dev0
+debugpy==1.5.1
+decorator==5.1.1
+defusedxml==0.7.1
+deprecated==1.2.13
+dill==0.3.4
+dlinfo==1.2.1
+dm-tree==0.1.6
+docker-pycreds==0.4.0
+docker==4.4.4
+entrypoints==0.4
+execnet==1.9.0
+executing==0.8.2
+faiss-cpu==1.7.2
+filelock==3.4.2
+fire==0.4.0
+flake8==4.0.1
+flask-compress==1.11
+flask==2.1.1
+flatbuffers==1.12
+flax==0.4.0
+fonttools==4.29.1
+frozenlist==1.3.0
+fsspec==2022.1.0
+fugashi==1.1.2
+gast==0.5.3
+gitdb==4.0.9
+gitpython==3.1.18
+google-auth-oauthlib==0.4.6
+google-auth==2.6.0
+google-pasta==0.2.0
+greenlet==1.1.2
+grpcio==1.43.0
+h5py==3.6.0
+hf-doc-builder==0.2.0
+huggingface-hub==0.4.0
+hypothesis==6.36.1
+idna==3.3
+importlib-metadata==4.10.1
+iniconfig==1.1.1
+ipadic==1.0.0
+ipdb==0.13.9
+ipykernel==6.8.0
+ipython-genutils==0.2.0
+ipython==8.0.1
+ipywidgets==7.6.5
+isodate==0.6.1
+isort==5.10.1
+itsdangerous==2.1.2
+jax==0.2.28
+jaxlib==0.1.76+cuda11.cudnn82
+jedi==0.18.1
+jinja2-time==0.2.0
+jinja2==3.0.3
+jiwer==2.3.0
+jmespath==0.10.0
+joblib==1.1.0
+json5==0.9.6
+jsonschema==4.4.0
+jupyter-client==7.1.2
+jupyter-console==6.4.0
+jupyter-core==4.9.1
+jupyter-server==1.13.5
+jupyter==1.0.0
+jupyterlab-pygments==0.1.2
+jupyterlab-server==2.10.3
+jupyterlab-widgets==1.0.2
+jupyterlab==3.2.9
+keras-preprocessing==1.1.2
+keras==2.8.0
+kiwisolver==1.3.2
+kubernetes==12.0.1
+libclang==13.0.0
+librosa==0.8.1
+llvmlite==0.38.0
+mako==1.2.0
+markdown==3.3.6
+markupsafe==2.0.1
+matplotlib-inline==0.1.3
+matplotlib==3.5.1
+mccabe==0.6.1
+mistune==0.8.4
+msgpack==1.0.3
+multidict==6.0.2
+multiprocess==0.70.12.2
+mypy-extensions==0.4.3
+nbclassic==0.3.5
+nbclient==0.5.10
+nbconvert==6.4.1
+nbformat==5.1.3
+nest-asyncio==1.5.4
+nltk==3.7
+notebook==6.4.8
+numba==0.55.1
+numpy==1.21.5
+oauthlib==3.2.0
+onnx==1.11.0
+onnxconverter-common==1.9.0
+opt-einsum==3.3.0
+optax==0.1.0
+optuna==2.10.0
+packaging==21.3
+pandas==1.4.0
+pandocfilters==1.5.0
+parameterized==0.8.1
+parso==0.8.3
+pathspec==0.9.0
+pathtools==0.1.2
+pbr==5.8.1
+pexpect==4.8.0
+phonemizer==3.0.1
+pickleshare==0.7.5
+pillow==9.0.0
+pint==0.16.1
+pip==22.0.2
+pkg-resources==0.0.0
+plac==1.3.5
+platformdirs==2.4.1
+plotly==5.6.0
+pluggy==1.0.0
+pooch==1.6.0
+portalocker==2.0.0
+poyo==0.5.0
+prettytable==3.2.0
+prometheus-client==0.13.1
+promise==2.3
+prompt-toolkit==3.0.26
+protobuf==3.19.4
+psutil==5.9.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+py-cpuinfo==8.0.0
+py==1.11.0
+pyarrow==6.0.1
+pyasn1-modules==0.2.8
+pyasn1==0.4.8
+pycodestyle==2.8.0
+pycparser==2.21
+pyctcdecode==0.3.0
+pyflakes==2.4.0
+pygments==2.11.2
+pygtrie==2.4.2
+pynvml==11.4.1
+pyopenssl==22.0.0
+pyparsing==3.0.7
+pyperclip==1.8.2
+pypng==0.0.21
+pyrsistent==0.18.1
+pytest-forked==1.4.0
+pytest-timeout==2.1.0
+pytest-xdist==2.5.0
+pytest==7.1.1
+python-dateutil==2.8.2
+python-levenshtein==0.12.2
+python-slugify==6.1.1
+pytz-deprecation-shim==0.1.0.post0
+pytz==2021.3
+pyyaml==5.4.1
+pyzmq==22.3.0
+qtconsole==5.2.2
+qtpy==2.0.1
+ray==1.11.0
+redis==4.2.2
+regex==2022.1.18
+requests-oauthlib==1.3.1
+requests==2.27.1
+resampy==0.2.2
+responses==0.18.0
+rfc3986==2.0.0
+rouge-score==0.0.4
+rsa==4.8
+s3transfer==0.3.7
+sacrebleu==1.5.1
+sacremoses==0.0.47
+scikit-learn==1.0.2
+scipy==1.7.3
+segments==2.2.0
+send2trash==1.8.0
+sentencepiece==0.1.96
+sentry-sdk==1.5.6
+setuptools==44.1.1
+shortuuid==1.0.8
+sigopt==8.3.0
+six==1.16.0
+smmap==5.0.0
+sniffio==1.2.0
+sortedcontainers==2.4.0
+soundfile==0.10.3.post1
+sqlalchemy==1.4.34
+stack-data==0.1.4
+stevedore==3.5.0
+tabulate==0.8.9
+tenacity==8.0.1
+tensorboard-data-server==0.6.1
+tensorboard-plugin-wit==1.8.1
+tensorboard==2.8.0
+tensorboardx==2.5
+tensorflow-io-gcs-filesystem==0.24.0
+tensorflow==2.8.0
+termcolor==1.1.0
+terminado==0.13.1
+testpath==0.5.0
+text-unidecode==1.3
+tf-estimator-nightly==2.8.0.dev2021122109
+tf2onnx==1.9.3
+threadpoolctl==3.1.0
+timeout-decorator==0.5.0
+timm==0.5.4
+tokenizers==0.11.4
+toml==0.10.2
+tomli==2.0.0
+toolz==0.11.2
+torch==1.10.2+cu113
+torchaudio==0.10.2+cu113
+torchvision==0.11.3
+tornado==6.1
+tqdm==4.62.3
+traitlets==5.1.1
+transformers==4.18.0.dev0
+typing-extensions==3.10.0.2
+tzdata==2022.1
+tzlocal==4.2
+unidic-lite==1.0.8
+unidic==1.1.0
+uritemplate==4.1.1
+urllib3==1.26.8
+wandb==0.12.10
+wasabi==0.9.1
+wcwidth==0.2.5
+webencodings==0.5.1
+websocket-client==1.2.3
+werkzeug==2.0.2
+wheel==0.37.1
+widgetsnbextension==3.5.2
+wrapt==1.14.0
+xxhash==2.0.2
+yarl==1.7.2
+yaspin==2.1.0
+zipp==3.7.0

wandb/run-20220503_171959-a6039xud/files/wandb-metadata.json

@@ -0,0 +1,57 @@
+{
+    "os": "Linux-5.11.0-1028-gcp-x86_64-with-glibc2.33",
+    "python": "3.9.5",
+    "heartbeatAt": "2022-05-03T17:20:04.283739",
+    "startedAt": "2022-05-03T17:19:59.978222",
+    "docker": null,
+    "gpu": "Tesla V100-SXM2-16GB",
+    "gpu_count": 2,
+    "cpu_count": 16,
+    "cuda": null,
+    "args": [
+        "--overwrite_output_dir",
+        "--freeze_feature_encoder",
+        "--gradient_checkpointing",
+        "--predict_with_generate",
+        "--fp16",
+        "--group_by_length",
+        "--do_train",
+        "--do_eval",
+        "--load_best_model_at_end",
+        "--push_to_hub",
+        "--use_auth_token",
+        "--eval_split_name=test",
+        "--eval_steps=500",
+        "--evaluation_strategy=steps",
+        "--generation_max_length=40",
+        "--generation_num_beams=1",
+        "--gradient_accumulation_steps=8",
+        "--greater_is_better=True",
+        "--hidden_dropout=0.06862889720223829",
+        "--language=fr.en",
+        "--learning_rate=0.0004848089062550082",
+        "--logging_steps=1",
+        "--max_duration_in_seconds=20",
+        "--metric_for_best_model=bleu",
+        "--model_name_or_path=./",
+        "--num_train_epochs=3",
+        "--output_dir=./",
+        "--per_device_eval_batch_size=4",
+        "--per_device_train_batch_size=4",
+        "--save_steps=500",
+        "--task=covost2",
+        "--warmup_steps=500"
+    ],
+    "state": "running",
+    "program": "/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/run_xtreme_s.py",
+    "codePath": "run_xtreme_s.py",
+    "git": {
+        "remote": "https://huggingface.co/sanchit-gandhi/xtreme_s_xlsr_2_bart_covost2_fr_en",
+        "commit": "c787ad4df48cedb3c1492e0593442fbabf32819f"
+    },
+    "email": "sanchit@huggingface.co",
+    "root": "/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en",
+    "host": "sanchit--v100",
+    "username": "sanchit_huggingface_co",
+    "executable": "/home/sanchit_huggingface_co/gcp/bin/python3"
+}

wandb/run-20220503_171959-a6039xud/logs/debug.log

@@ -0,0 +1,28 @@
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_setup.py:_flush():75] Loading settings from /home/sanchit_huggingface_co/.config/wandb/settings
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_setup.py:_flush():75] Loading settings from wandb/settings
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_setup.py:_flush():75] Loading settings from environment variables: {'entity': 'sanchit-gandhi', 'project': 'xtreme_s_xlsr_2_bart_covost2_fr_en', 'sweep_id': '39ci3gkf', 'root_dir': '/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en', 'run_id': 'a6039xud', 'sweep_param_path': '/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/sweep-39ci3gkf/config-a6039xud.yaml'}
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_setup.py:_flush():75] Inferring run settings from compute environment: {'program_relpath': 'run_xtreme_s.py', 'program': '/home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/run_xtreme_s.py'}
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_init.py:_log_setup():386] Logging user logs to /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220503_171959-a6039xud/logs/debug.log
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_init.py:_log_setup():387] Logging internal logs to /home/sanchit_huggingface_co/xtreme_s_xlsr_2_bart_covost2_fr_en/wandb/run-20220503_171959-a6039xud/logs/debug-internal.log
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_init.py:init():420] calling init triggers
+2022-05-03 17:19:59,980 INFO    MainThread:42111 [wandb_init.py:init():425] wandb.init called with sweep_config: {'eval_split_name': 'test', 'eval_steps': 500, 'evaluation_strategy': 'steps', 'generation_max_length': 40, 'generation_num_beams': 1, 'gradient_accumulation_steps': 8, 'greater_is_better': True, 'hidden_dropout': 0.06862889720223829, 'language': 'fr.en', 'learning_rate': 0.0004848089062550082, 'logging_steps': 1, 'max_duration_in_seconds': 20, 'metric_for_best_model': 'bleu', 'model_name_or_path': './', 'num_train_epochs': 3, 'output_dir': './', 'per_device_eval_batch_size': 4, 'per_device_train_batch_size': 4, 'save_steps': 500, 'task': 'covost2', 'warmup_steps': 500}
+config: {}
+2022-05-03 17:19:59,981 INFO    MainThread:42111 [wandb_init.py:init():471] starting backend
+2022-05-03 17:19:59,981 INFO    MainThread:42111 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-05-03 17:20:00,059 INFO    MainThread:42111 [backend.py:ensure_launched():219] starting backend process...
+2022-05-03 17:20:00,134 INFO    MainThread:42111 [backend.py:ensure_launched():224] started backend process with pid: 42356
+2022-05-03 17:20:00,137 INFO    MainThread:42111 [wandb_init.py:init():480] backend started and connected
+2022-05-03 17:20:00,140 INFO    MainThread:42111 [wandb_run.py:_config_callback():966] config_cb None None {'eval_split_name': 'test', 'eval_steps': 500, 'evaluation_strategy': 'steps', 'generation_max_length': 40, 'generation_num_beams': 1, 'gradient_accumulation_steps': 8, 'greater_is_better': True, 'hidden_dropout': 0.06862889720223829, 'language': 'fr.en', 'learning_rate': 0.0004848089062550082, 'logging_steps': 1, 'max_duration_in_seconds': 20, 'metric_for_best_model': 'bleu', 'model_name_or_path': './', 'num_train_epochs': 3, 'output_dir': './', 'per_device_eval_batch_size': 4, 'per_device_train_batch_size': 4, 'save_steps': 500, 'task': 'covost2', 'warmup_steps': 500}
+2022-05-03 17:20:00,155 INFO    MainThread:42111 [wandb_init.py:init():550] updated telemetry
+2022-05-03 17:20:00,359 INFO    MainThread:42111 [wandb_init.py:init():581] communicating current version
+2022-05-03 17:20:01,247 INFO    MainThread:42111 [wandb_init.py:init():586] got version response upgrade_message: "wandb version 0.12.16 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2022-05-03 17:20:01,248 INFO    MainThread:42111 [wandb_init.py:init():596] communicating run to backend with 30 second timeout
+2022-05-03 17:20:01,757 INFO    MainThread:42111 [wandb_init.py:init():624] starting run threads in backend
+2022-05-03 17:20:04,342 INFO    MainThread:42111 [wandb_run.py:_console_start():1827] atexit reg
+2022-05-03 17:20:04,342 INFO    MainThread:42111 [wandb_run.py:_redirect():1701] redirect: SettingsConsole.REDIRECT
+2022-05-03 17:20:04,343 INFO    MainThread:42111 [wandb_run.py:_redirect():1706] Redirecting console.
+2022-05-03 17:20:04,345 INFO    MainThread:42111 [wandb_run.py:_redirect():1762] Redirects installed.
+2022-05-03 17:20:04,345 INFO    MainThread:42111 [wandb_init.py:init():651] run started, returning control to user process
+2022-05-03 17:20:04,348 INFO    MainThread:42111 [wandb_run.py:_config_callback():966] config_cb None None {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'torch.float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': False, 'is_encoder_decoder': True, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 40, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'architectures': ['SpeechEncoderDecoderModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': None, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 0, 'task_specific_params': None, 'problem_type': None, '_name_or_path': './', 'transformers_version': None, 'decoder': {'vocab_size': 50265, 'max_position_embeddings': 1024, 'd_model': 1024, 'encoder_ffn_dim': 4096, 'encoder_layers': 12, 'encoder_attention_heads': 16, 'decoder_ffn_dim': 4096, 'decoder_layers': 12, 'decoder_attention_heads': 16, 'dropout': 0.1, 'attention_dropout': 0.1, 'activation_dropout': 0.1, 'activation_function': 'gelu', 'init_std': 0.02, 'encoder_layerdrop': 0.0, 'decoder_layerdrop': 0.0, 'classifier_dropout': 0.0, 'use_cache': True, 'num_hidden_layers': 12, 'scale_embedding': False, 'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': None, 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': True, 'cross_attention_hidden_size': None, 'add_cross_attention': True, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': True, 'num_beams': 4, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 3, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': 0, 'forced_eos_token_id': 2, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'architectures': ['BartModel'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1', 2: 'LABEL_2'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1, 'LABEL_2': 2}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 0, 'pad_token_id': 1, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': 2, 'task_specific_params': {'summarization': {'length_penalty': 1.0, 'max_length': 128, 'min_length': 12, 'num_beams': 4}, 'summarization_cnn': {'length_penalty': 2.0, 'max_length': 142, 'min_length': 56, 'num_beams': 4}, 'summarization_xsum': {'length_penalty': 1.0, 'max_length': 62, 'min_length': 11, 'num_beams': 6}}, 'problem_type': None, '_name_or_path': 'facebook/bart-large', 'transformers_version': '4.19.0.dev0', 'add_bias_logits': False, 'add_final_layer_norm': False, 'classif_dropout': 0.1, 'gradient_checkpointing': False, 'normalize_before': False, 'model_type': 'bart'}, 'encoder': {'return_dict': True, 'output_hidden_states': False, 'output_attentions': False, 'torchscript': False, 'torch_dtype': 'float32', 'use_bfloat16': False, 'pruned_heads': {}, 'tie_word_embeddings': True, 'is_encoder_decoder': False, 'is_decoder': False, 'cross_attention_hidden_size': None, 'add_cross_attention': False, 'tie_encoder_decoder': False, 'max_length': 20, 'min_length': 0, 'do_sample': False, 'early_stopping': False, 'num_beams': 1, 'num_beam_groups': 1, 'diversity_penalty': 0.0, 'temperature': 1.0, 'top_k': 50, 'top_p': 1.0, 'typical_p': 1.0, 'repetition_penalty': 1.0, 'length_penalty': 1.0, 'no_repeat_ngram_size': 0, 'encoder_no_repeat_ngram_size': 0, 'bad_words_ids': None, 'num_return_sequences': 1, 'chunk_size_feed_forward': 0, 'output_scores': False, 'return_dict_in_generate': False, 'forced_bos_token_id': None, 'forced_eos_token_id': None, 'remove_invalid_values': False, 'exponential_decay_length_penalty': None, 'architectures': ['Wav2Vec2ForPreTraining'], 'finetuning_task': None, 'id2label': {0: 'LABEL_0', 1: 'LABEL_1'}, 'label2id': {'LABEL_0': 0, 'LABEL_1': 1}, 'tokenizer_class': None, 'prefix': None, 'bos_token_id': 1, 'pad_token_id': 0, 'eos_token_id': 2, 'sep_token_id': None, 'decoder_start_token_id': None, 'task_specific_params': None, 'problem_type': None, '_name_or_path': 'facebook/wav2vec2-xls-r-300m', 'transformers_version': '4.19.0.dev0', 'feat_extract_dropout': 0.0, 'gradient_checkpointing': False, 'num_feat_extract_layers': 7, 'hidden_size': 1024, 'feat_extract_norm': 'layer', 'feat_extract_activation': 'gelu', 'conv_dim': [512, 512, 512, 512, 512, 512, 512], 'conv_stride': [5, 2, 2, 2, 2, 2, 2], 'conv_kernel': [10, 3, 3, 3, 3, 2, 2], 'conv_bias': True, 'num_conv_pos_embeddings': 128, 'num_conv_pos_embedding_groups': 16, 'num_hidden_layers': 24, 'intermediate_size': 4096, 'hidden_act': 'gelu', 'num_attention_heads': 16, 'hidden_dropout': 0.06862889720223829, 'attention_dropout': 0.1, 'activation_dropout': 0.0, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 32, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.1, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.0, 'mask_feature_length': 10, 'mask_feature_min_masks': 0, 'num_codevectors_per_group': 320, 'num_codevector_groups': 2, 'contrastive_logits_temperature': 0.1, 'feat_quantizer_dropout': 0.0, 'num_negatives': 100, 'codevector_dim': 768, 'proj_codevector_dim': 768, 'diversity_loss_weight': 0.1, 'ctc_loss_reduction': 'sum', 'ctc_zero_infinity': False, 'add_adapter': True, 'adapter_kernel_size': 3, 'adapter_stride': 2, 'num_adapter_layers': 3, 'output_hidden_size': 1024, 'classifier_proj_size': 256, 'tdnn_dim': [512, 512, 512, 512, 1500], 'tdnn_kernel': [5, 3, 3, 1, 1], 'tdnn_dilation': [1, 2, 3, 1, 1], 'xvector_output_dim': 512, 'model_type': 'wav2vec2'}, 'model_type': 'speech-encoder-decoder', 'processor_class': 'Wav2Vec2Processor', 'use_cache': False, 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'prediction_loss_only': False, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'eval_accumulation_steps': 'None', 'eval_delay': 0, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/May03_17-15-22_sanchit--v100', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_total_limit': 'None', 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, 'data_seed': 'None', 'bf16': False, 'fp16': True, 'fp16_opt_level': 'O1', 'half_precision_backend': 'amp', 'bf16_full_eval': False, 'fp16_full_eval': False, 'tf32': 'None', 'local_rank': -1, 'xpu_backend': 'None', 'tpu_num_cores': 'None', 'tpu_metrics_debug': False, 'debug': '[]', 'dataloader_drop_last': False, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': './', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'ignore_data_skip': False, 'sharded_ddp': '[]', 'deepspeed': 'None', 'label_smoothing_factor': 0.0, 'optim': 'adamw_hf', 'adafactor': False, 'group_by_length': True, 'length_column_name': 'length', 'report_to': "['tensorboard', 'wandb', 'codecarbon']", 'ddp_find_unused_parameters': 'None', 'ddp_bucket_cap_mb': 'None', 'dataloader_pin_memory': True, 'skip_memory_metrics': True, 'use_legacy_prediction_loop': False, 'push_to_hub': True, 'resume_from_checkpoint': 'None', 'hub_model_id': 'None', 'hub_strategy': 'every_save', 'hub_token': '<HUB_TOKEN>', 'hub_private_repo': False, 'gradient_checkpointing': True, 'include_inputs_for_metrics': False, 'fp16_backend': 'auto', 'push_to_hub_model_id': 'None', 'push_to_hub_organization': 'None', 'push_to_hub_token': '<PUSH_TO_HUB_TOKEN>', '_n_gpu': 1, 'mp_parameters': '', 'sortish_sampler': False, 'predict_with_generate': True, 'train_batch_size': 4, 'eval_batch_size': 4}
+2022-05-03 17:20:04,351 INFO    MainThread:42111 [wandb_watch.py:watch():43] Watching

wandb/run-20220503_171959-a6039xud/run-a6039xud.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d3034118c3e235104590124be355a3a0b9fcb07d29b2485f05cfac95b555bf
+size 54318872

wandb/sweep-39ci3gkf/config-a6039xud.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.06862889720223829
+language:
+  value: fr.en
+learning_rate:
+  value: 0.0004848089062550082
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./
+per_device_eval_batch_size:
+  value: 4
+per_device_train_batch_size:
+  value: 4
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500

wandb/sweep-y3ak427l/config-irggvkgd.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.1875094322808032
+language:
+  value: fr.en
+learning_rate:
+  value: 0.00024438201183496223
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./output_dir
+per_device_eval_batch_size:
+  value: 4
+per_device_train_batch_size:
+  value: 4
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500

wandb/sweep-y3ak427l/config-ldsojzle.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.055722391000930585
+language:
+  value: fr.en
+learning_rate:
+  value: 0.0006457481677728278
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./output_dir
+per_device_eval_batch_size:
+  value: 4
+per_device_train_batch_size:
+  value: 4
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500

wandb/sweep-y3ak427l/config-qv3vjr6j.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.056807662149569525
+language:
+  value: fr.en
+learning_rate:
+  value: 0.0005558468401613797
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./output_dir
+per_device_eval_batch_size:
+  value: 4
+per_device_train_batch_size:
+  value: 4
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500

wandb/sweep-y3ak427l/config-vz5ppd75.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.036619638921206475
+language:
+  value: fr.en
+learning_rate:
+  value: 0.00024391819705381628
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./output_dir
+per_device_eval_batch_size:
+  value: 4
+per_device_train_batch_size:
+  value: 4
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500

wandb/sweep-y3ak427l/config-xur584bd.yaml

@@ -0,0 +1,44 @@
+wandb_version: 1
+
+eval_split_name:
+  value: test
+eval_steps:
+  value: 500
+evaluation_strategy:
+  value: steps
+generation_max_length:
+  value: 40
+generation_num_beams:
+  value: 1
+gradient_accumulation_steps:
+  value: 8
+greater_is_better:
+  value: true
+hidden_dropout:
+  value: 0.03413483050532159
+language:
+  value: fr.en
+learning_rate:
+  value: 0.00022086866790135088
+logging_steps:
+  value: 1
+max_duration_in_seconds:
+  value: 20
+metric_for_best_model:
+  value: bleu
+model_name_or_path:
+  value: ./
+num_train_epochs:
+  value: 3
+output_dir:
+  value: ./output_dir
+per_device_eval_batch_size:
+  value: 4
+per_device_train_batch_size:
+  value: 4
+save_steps:
+  value: 500
+task:
+  value: covost2
+warmup_steps:
+  value: 500