Training in progress, step 500

.ipynb_checkpoints/added_tokens-checkpoint.json

@@ -1 +0,0 @@
-{"<s>": 51, "</s>": 52}

.ipynb_checkpoints/config-checkpoint.json

@@ -1,107 +0,0 @@
-{
-  "_name_or_path": "facebook/wav2vec2-xls-r-300m",
-  "activation_dropout": 0.05,
-  "adapter_kernel_size": 3,
-  "adapter_stride": 2,
-  "add_adapter": false,
-  "apply_spec_augment": true,
-  "architectures": [
-    "Wav2Vec2ForPreTraining"
-  ],
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "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
-  ],
-  "ctc_loss_reduction": "mean",
-  "ctc_zero_infinity": false,
-  "diversity_loss_weight": 0.1,
-  "do_stable_layer_norm": true,
-  "eos_token_id": 2,
-  "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,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.0,
-  "hidden_size": 1024,
-  "initializer_range": 0.02,
-  "intermediate_size": 4096,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.0,
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.3,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.65,
-  "model_type": "wav2vec2",
-  "num_adapter_layers": 3,
-  "num_attention_heads": 16,
-  "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,
-  "output_hidden_size": 1024,
-  "pad_token_id": 50,
-  "proj_codevector_dim": 768,
-  "tdnn_dilation": [
-    1,
-    2,
-    3,
-    1,
-    1
-  ],
-  "tdnn_dim": [
-    512,
-    512,
-    512,
-    512,
-    1500
-  ],
-  "tdnn_kernel": [
-    5,
-    3,
-    3,
-    1,
-    1
-  ],
-  "torch_dtype": "float32",
-  "transformers_version": "4.17.0.dev0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 53,
-  "xvector_output_dim": 512
-}

.ipynb_checkpoints/run-checkpoint.sh

@@ -5,12 +5,12 @@ python run_speech_recognition_ctc.py \
 --cache_dir="../downloaded_data" \
 --output_dir="./" \
 --overwrite_output_dir \
---num_train_epochs="20" \
---per_device_train_batch_size="64" \
---per_device_eval_batch_size="64" \
+--num_train_epochs="15" \
+--per_device_train_batch_size="32" \
+--per_device_eval_batch_size="32" \
 --gradient_accumulation_steps="1" \
---learning_rate="1e-4" \
---warmup_steps="2000" \
+--learning_rate="2e-4" \
+--warmup_steps="1500" \
 --length_column_name="input_length" \
 --evaluation_strategy="steps" \
 --text_column_name="sentence" \
@@ -29,8 +29,7 @@ python run_speech_recognition_ctc.py \
 --gradient_checkpointing \
 --report_to="wandb" \
 --run_name="xls-r-300m-fr" \
---max_eval_samples="4500" \
---max_duration_in_seconds="10" \
+--max_duration_in_seconds="20" \
 --use_auth_token \
 --fp16 \
 --group_by_length \

.ipynb_checkpoints/special_tokens_map-checkpoint.json

@@ -1 +0,0 @@
-{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "[UNK]", "pad_token": "[PAD]", "additional_special_tokens": [{"content": "<s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, {"content": "</s>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}]}

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -1 +0,0 @@
-{"unk_token": "[UNK]", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "[PAD]", "do_lower_case": false, "word_delimiter_token": "|", "config": null, "tokenizer_type": "wav2vec2", "special_tokens_map_file": null, "tokenizer_file": null, "name_or_path": "./", "tokenizer_class": "Wav2Vec2CTCTokenizer"}

.ipynb_checkpoints/vocab-checkpoint.json

@@ -1 +0,0 @@
-{"&": 1, "'": 2, "a": 3, "b": 4, "c": 5, "d": 6, "e": 7, "f": 8, "g": 9, "h": 10, "i": 11, "j": 12, "k": 13, "l": 14, "m": 15, "n": 16, "o": 17, "p": 18, "q": 19, "r": 20, "s": 21, "t": 22, "u": 23, "v": 24, "w": 25, "x": 26, "y": 27, "z": 28, "«": 29, "´": 30, "»": 31, "à": 32, "á": 33, "â": 34, "ã": 35, "ç": 36, "è": 37, "é": 38, "ê": 39, "í": 40, "ñ": 41, "ó": 42, "ô": 43, "õ": 44, "ú": 45, "ü": 46, "š": 47, "ž": 48, "|": 0, "[UNK]": 49, "[PAD]": 50}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f30fe7e0ba64aa9d4bc988cdd971720410091ba89cb29fa82dece96061fbeb
+oid sha256:48f053180e231379019d16f1ab3274e0af95430b2eec311bade84deab960a3a0
 size 1262140977

run.sh

@@ -5,12 +5,12 @@ python run_speech_recognition_ctc.py \
 --cache_dir="../downloaded_data" \
 --output_dir="./" \
 --overwrite_output_dir \
---num_train_epochs="20" \
---per_device_train_batch_size="64" \
---per_device_eval_batch_size="64" \
+--num_train_epochs="15" \
+--per_device_train_batch_size="32" \
+--per_device_eval_batch_size="32" \
 --gradient_accumulation_steps="1" \
---learning_rate="1e-4" \
---warmup_steps="2000" \
+--learning_rate="2e-4" \
+--warmup_steps="1500" \
 --length_column_name="input_length" \
 --evaluation_strategy="steps" \
 --text_column_name="sentence" \
@@ -29,8 +29,7 @@ python run_speech_recognition_ctc.py \
 --gradient_checkpointing \
 --report_to="wandb" \
 --run_name="xls-r-300m-fr" \
---max_eval_samples="4500" \
---max_duration_in_seconds="10" \
+--max_duration_in_seconds="20" \
 --use_auth_token \
 --fp16 \
 --group_by_length \

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a72b131552d7bdf4f3d9f27a7a1e0da4c0e810656b296557f72745333e7dbad
+oid sha256:5a0deb169ee87b5f7b9d6dd5712e9dca515a2ea7d385e039e5dd14ecad55b340
 size 3055

wandb/debug-internal.log

@@ -1 +1 @@
-run-20220201_214324-8dmqnlr2/logs/debug-internal.log
+run-20220201_223624-2b1hcyq3/logs/debug-internal.log

wandb/debug.log

@@ -1 +1 @@
-run-20220201_214324-8dmqnlr2/logs/debug.log
+run-20220201_223624-2b1hcyq3/logs/debug.log

wandb/latest-run

@@ -1 +1 @@
-run-20220201_214324-8dmqnlr2
+run-20220201_223624-2b1hcyq3

wandb/{run-20220201_214324-8dmqnlr2 → run-20220201_223624-2b1hcyq3}/files/config.yaml

@@ -4803,7 +4803,7 @@ _wandb:
       6:
       - 1
     python_version: 3.8.8
-    start_time: 1643751804
+    start_time: 1643754984
     t:
       1:
       - 1
@@ -4981,7 +4981,7 @@ eval_accumulation_steps:
   value: None
 eval_batch_size:
   desc: null
-  value: 64
+  value: 32
 eval_steps:
   desc: null
   value: 500
@@ -5099,7 +5099,7 @@ layerdrop:
   value: 0.0
 learning_rate:
   desc: null
-  value: 0.0001
+  value: 0.0002
 length_column_name:
   desc: null
   value: input_length
@@ -5123,7 +5123,7 @@ log_on_each_node:
   value: true
 logging_dir:
   desc: null
-  value: ./runs/Feb01_21-41-58_job-1abccd0a-3293-4ffe-8274-9e8f841f653f
+  value: ./runs/Feb01_22-34-39_job-1abccd0a-3293-4ffe-8274-9e8f841f653f
 logging_first_step:
   desc: null
   value: false
@@ -5222,7 +5222,7 @@ num_return_sequences:
   value: 1
 num_train_epochs:
   desc: null
-  value: 20.0
+  value: 15.0
 optim:
   desc: null
   value: adamw_hf
@@ -5252,10 +5252,10 @@ past_index:
   value: -1
 per_device_eval_batch_size:
   desc: null
-  value: 64
+  value: 32
 per_device_train_batch_size:
   desc: null
-  value: 64
+  value: 32
 per_gpu_eval_batch_size:
   desc: null
   value: None
@@ -5399,7 +5399,7 @@ tpu_num_cores:
   value: None
 train_batch_size:
   desc: null
-  value: 64
+  value: 32
 transformers_version:
   desc: null
   value: 4.17.0.dev0
@@ -5420,7 +5420,7 @@ warmup_ratio:
   value: 0.0
 warmup_steps:
   desc: null
-  value: 2000
+  value: 1500
 weight_decay:
   desc: null
   value: 0.0

wandb/{run-20220201_214324-8dmqnlr2 → run-20220201_223624-2b1hcyq3}/files/output.log

@@ -57,6 +57,7 @@
 
 
 
+  1%|█▋                                                                                                                                                                                                | 100/11670 [02:02<1:59:38,  1.61it/s]
 
 
 
@@ -87,7 +88,6 @@
 
 
 
-  1%|█▌                                                                                                                          | 99/7780 [04:08<2:17:38,  1.08s/it]
 
 
 
@@ -116,6 +116,7 @@
 
 
 
+  2%|███▎                                                                                                                                                                                              | 199/11670 [04:03<1:46:43,  1.79it/s]
 
 
 
@@ -174,9 +175,9 @@
 
 
 
+  3%|████▉                                                                                                                                                                                             | 298/11670 [06:03<1:52:10,  1.69it/s]
 
 
-  3%|███▏                                                                                                                       | 199/7780 [08:14<2:24:26,  1.14s/it]
 
 
 
@@ -234,6 +235,7 @@
 
 
 
+  3%|██████▋                                                                                                                                                                                           | 400/11670 [08:06<1:53:58,  1.65it/s]
 
 
 
@@ -266,96 +268,6 @@
 
 
 
-  4%|████▋                                                                                                                      | 300/7780 [12:19<2:14:04,  1.08s/it]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-  5%|██████▎                                                                                                                    | 399/7780 [16:35<7:56:31,  3.87s/it]
-
 
 
 
@@ -382,6 +294,11 @@
 
 
 
+  4%|████████▎                                                                                                                                                                                         | 499/11670 [10:07<1:48:23,  1.72it/s]
+  4%|████████▎                                                                                                                                                                                         | 500/11670 [10:08<1:59:55,  1.55it/s]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
+***** Running Evaluation *****
+  Num examples = 8301
+  Batch size = 32
 
 
 
@@ -446,11 +363,6 @@
 
 
 
-  6%|███████▉                                                                                                                   | 499/7780 [20:46<7:04:20,  3.50s/it]
-  6%|███████▉                                                                                                                   | 500/7780 [20:49<7:04:04,  3.50s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
-***** Running Evaluation *****
-  Num examples = 4494
-  Batch size = 64
 
 
 
@@ -520,527 +432,8 @@
 
 
 
-100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 71/71 [02:46<00:00,  1.75s/it]
+100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 260/260 [04:29<00:00,  1.58it/s]
 
 Configuration saved in ./checkpoint-500/config.json
 Model weights saved in ./checkpoint-500/pytorch_model.bin
 Configuration saved in ./checkpoint-500/preprocessor_config.json
-Configuration saved in ./preprocessor_config.json
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-  8%|█████████▍                                                                                                                 | 599/7780 [28:28<7:11:02,  3.60s/it]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-  9%|███████████                                                                                                                | 699/7780 [32:27<6:39:21,  3.38s/it]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- 10%|████████████▋                                                                                                              | 799/7780 [36:31<5:03:14,  2.61s/it]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- 12%|██████████████▏                                                                                                            | 900/7780 [40:37<5:25:44,  2.84s/it]
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- 13%|███████████████▋                                                                                                          | 1000/7780 [44:41<5:00:43,  2.66s/it]The following columns in the evaluation set  don't have a corresponding argument in `Wav2Vec2ForCTC.forward` and have been ignored: input_length.
-***** Running Evaluation *****
-  Num examples = 4494
-  Batch size = 64
-{'loss': 3.0217, 'learning_rate': 4.9850000000000006e-05, 'epoch': 2.57}
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-Configuration saved in ./checkpoint-1000/config.json
-{'eval_loss': 3.000413656234741, 'eval_wer': 0.997821071520123, 'eval_runtime': 195.2466, 'eval_samples_per_second': 23.017, 'eval_steps_per_second': 0.364, 'epoch': 2.57}
-Model weights saved in ./checkpoint-1000/pytorch_model.bin
-Configuration saved in ./checkpoint-1000/preprocessor_config.json

wandb/{run-20220201_214324-8dmqnlr2 → run-20220201_223624-2b1hcyq3}/files/wandb-metadata.json

@@ -1,8 +1,8 @@
 {
     "os": "Linux-4.15.0-151-generic-x86_64-with-glibc2.10",
     "python": "3.8.8",
-    "heartbeatAt": "2022-02-01T21:43:26.079203",
-    "startedAt": "2022-02-01T21:43:24.830312",
+    "heartbeatAt": "2022-02-01T22:36:25.895203",
+    "startedAt": "2022-02-01T22:36:24.635537",
     "docker": null,
     "gpu": "Tesla V100S-PCIE-32GB",
     "gpu_count": 1,
@@ -15,12 +15,12 @@
         "--cache_dir=../downloaded_data",
         "--output_dir=./",
         "--overwrite_output_dir",
-        "--num_train_epochs=20",
-        "--per_device_train_batch_size=64",
-        "--per_device_eval_batch_size=64",
+        "--num_train_epochs=15",
+        "--per_device_train_batch_size=32",
+        "--per_device_eval_batch_size=32",
         "--gradient_accumulation_steps=1",
-        "--learning_rate=1e-4",
-        "--warmup_steps=2000",
+        "--learning_rate=2e-4",
+        "--warmup_steps=1500",
         "--length_column_name=input_length",
         "--evaluation_strategy=steps",
         "--text_column_name=sentence",
@@ -39,8 +39,7 @@
         "--gradient_checkpointing",
         "--report_to=wandb",
         "--run_name=xls-r-300m-fr",
-        "--max_eval_samples=4500",
-        "--max_duration_in_seconds=10",
+        "--max_duration_in_seconds=20",
         "--use_auth_token",
         "--fp16",
         "--group_by_length",
@@ -55,7 +54,7 @@
     "codePath": "run_speech_recognition_ctc.py",
     "git": {
         "remote": "https://huggingface.co/AlexN/xls-r-300m-pt",
-        "commit": "a989482db2aaf328702b11eff59cc2151cab9001"
+        "commit": "707ec794e0dbf03ecf182f434d1a62fd1f4ddecf"
     },
     "email": "alexandrenap@hotmail.fr",
     "root": "/workspace/xls-r-300m-pt",

wandb/{run-20220201_214324-8dmqnlr2 → run-20220201_223624-2b1hcyq3}/logs/debug.log

@@ -1,25 +1,25 @@
-2022-02-01 21:43:24,834 INFO    MainThread:16367 [wandb_setup.py:_flush():71] setting env: {}
-2022-02-01 21:43:24,834 INFO    MainThread:16367 [wandb_setup.py:_flush():71] setting login settings: {}
-2022-02-01 21:43:24,835 INFO    MainThread:16367 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-pt/wandb/run-20220201_214324-8dmqnlr2/logs/debug.log
-2022-02-01 21:43:24,835 INFO    MainThread:16367 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-pt/wandb/run-20220201_214324-8dmqnlr2/logs/debug-internal.log
-2022-02-01 21:43:24,835 INFO    MainThread:16367 [wandb_init.py:init():404] calling init triggers
-2022-02-01 21:43:24,835 INFO    MainThread:16367 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
+2022-02-01 22:36:24,639 INFO    MainThread:37310 [wandb_setup.py:_flush():71] setting env: {}
+2022-02-01 22:36:24,639 INFO    MainThread:37310 [wandb_setup.py:_flush():71] setting login settings: {}
+2022-02-01 22:36:24,640 INFO    MainThread:37310 [wandb_init.py:_log_setup():371] Logging user logs to /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/logs/debug.log
+2022-02-01 22:36:24,640 INFO    MainThread:37310 [wandb_init.py:_log_setup():372] Logging internal logs to /workspace/xls-r-300m-pt/wandb/run-20220201_223624-2b1hcyq3/logs/debug-internal.log
+2022-02-01 22:36:24,640 INFO    MainThread:37310 [wandb_init.py:init():404] calling init triggers
+2022-02-01 22:36:24,640 INFO    MainThread:37310 [wandb_init.py:init():409] wandb.init called with sweep_config: {}
 config: {}
-2022-02-01 21:43:24,835 INFO    MainThread:16367 [wandb_init.py:init():460] starting backend
-2022-02-01 21:43:24,835 INFO    MainThread:16367 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
-2022-02-01 21:43:24,898 INFO    MainThread:16367 [backend.py:ensure_launched():216] starting backend process...
-2022-02-01 21:43:24,959 INFO    MainThread:16367 [backend.py:ensure_launched():221] started backend process with pid: 17074
-2022-02-01 21:43:24,963 INFO    MainThread:16367 [wandb_init.py:init():469] backend started and connected
-2022-02-01 21:43:24,972 INFO    MainThread:16367 [wandb_init.py:init():533] updated telemetry
-2022-02-01 21:43:25,120 INFO    MainThread:16367 [wandb_init.py:init():563] communicating current version
-2022-02-01 21:43:25,868 INFO    MainThread:16367 [wandb_init.py:init():568] got version response upgrade_message: "wandb version 0.12.10 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+2022-02-01 22:36:24,640 INFO    MainThread:37310 [wandb_init.py:init():460] starting backend
+2022-02-01 22:36:24,640 INFO    MainThread:37310 [backend.py:_multiprocessing_setup():99] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2022-02-01 22:36:24,721 INFO    MainThread:37310 [backend.py:ensure_launched():216] starting backend process...
+2022-02-01 22:36:24,797 INFO    MainThread:37310 [backend.py:ensure_launched():221] started backend process with pid: 38198
+2022-02-01 22:36:24,800 INFO    MainThread:37310 [wandb_init.py:init():469] backend started and connected
+2022-02-01 22:36:24,809 INFO    MainThread:37310 [wandb_init.py:init():533] updated telemetry
+2022-02-01 22:36:24,979 INFO    MainThread:37310 [wandb_init.py:init():563] communicating current version
+2022-02-01 22:36:25,688 INFO    MainThread:37310 [wandb_init.py:init():568] got version response upgrade_message: "wandb version 0.12.10 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
 
-2022-02-01 21:43:25,869 INFO    MainThread:16367 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
-2022-02-01 21:43:26,073 INFO    MainThread:16367 [wandb_init.py:init():606] starting run threads in backend
-2022-02-01 21:43:26,673 INFO    MainThread:16367 [wandb_run.py:_console_start():1810] atexit reg
-2022-02-01 21:43:26,674 INFO    MainThread:16367 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
-2022-02-01 21:43:26,675 INFO    MainThread:16367 [wandb_run.py:_redirect():1689] Redirecting console.
-2022-02-01 21:43:26,681 INFO    MainThread:16367 [wandb_run.py:_redirect():1745] Redirects installed.
-2022-02-01 21:43:26,681 INFO    MainThread:16367 [wandb_init.py:init():633] run started, returning control to user process
-2022-02-01 21:43:26,683 INFO    MainThread:16367 [wandb_run.py:_config_callback():956] config_cb None None {'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, '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, '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': 50, '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': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', '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': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.05, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 53, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.65, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.3, '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': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, '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, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 64, 'per_device_eval_batch_size': 64, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0001, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 20.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 2000, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Feb01_21-41-58_job-1abccd0a-3293-4ffe-8274-9e8f841f653f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 3, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, '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, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'xls-r-300m-fr', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, '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': 'input_length', 'report_to': "['wandb']", '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>', 'gradient_checkpointing': True, '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': '', 'train_batch_size': 64, 'eval_batch_size': 64}
-2022-02-01 21:43:26,687 INFO    MainThread:16367 [wandb_watch.py:watch():43] Watching
+2022-02-01 22:36:25,688 INFO    MainThread:37310 [wandb_init.py:init():578] communicating run to backend with 30 second timeout
+2022-02-01 22:36:25,885 INFO    MainThread:37310 [wandb_init.py:init():606] starting run threads in backend
+2022-02-01 22:36:26,492 INFO    MainThread:37310 [wandb_run.py:_console_start():1810] atexit reg
+2022-02-01 22:36:26,493 INFO    MainThread:37310 [wandb_run.py:_redirect():1684] redirect: SettingsConsole.REDIRECT
+2022-02-01 22:36:26,494 INFO    MainThread:37310 [wandb_run.py:_redirect():1689] Redirecting console.
+2022-02-01 22:36:26,500 INFO    MainThread:37310 [wandb_run.py:_redirect():1745] Redirects installed.
+2022-02-01 22:36:26,500 INFO    MainThread:37310 [wandb_init.py:init():633] run started, returning control to user process
+2022-02-01 22:36:26,504 INFO    MainThread:37310 [wandb_run.py:_config_callback():956] config_cb None None {'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, '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, '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': 50, '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': '4.17.0.dev0', 'feat_extract_dropout': 0.0, 'model_type': 'wav2vec2', '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': 0.0, 'attention_dropout': 0.0, 'activation_dropout': 0.05, 'feat_proj_dropout': 0.0, 'final_dropout': 0.0, 'layerdrop': 0.0, 'layer_norm_eps': 1e-05, 'initializer_range': 0.02, 'vocab_size': 53, 'do_stable_layer_norm': True, 'use_weighted_layer_sum': False, 'apply_spec_augment': True, 'mask_time_prob': 0.65, 'mask_time_length': 10, 'mask_time_min_masks': 2, 'mask_feature_prob': 0.3, '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': 'mean', 'ctc_zero_infinity': False, 'add_adapter': False, '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, 'output_dir': './', 'overwrite_output_dir': True, 'do_train': True, 'do_eval': True, 'do_predict': False, 'evaluation_strategy': 'steps', 'prediction_loss_only': False, 'per_device_train_batch_size': 32, 'per_device_eval_batch_size': 32, 'per_gpu_train_batch_size': 'None', 'per_gpu_eval_batch_size': 'None', 'gradient_accumulation_steps': 1, 'eval_accumulation_steps': 'None', 'learning_rate': 0.0002, 'weight_decay': 0.0, 'adam_beta1': 0.9, 'adam_beta2': 0.999, 'adam_epsilon': 1e-08, 'max_grad_norm': 1.0, 'num_train_epochs': 15.0, 'max_steps': -1, 'lr_scheduler_type': 'linear', 'warmup_ratio': 0.0, 'warmup_steps': 1500, 'log_level': -1, 'log_level_replica': -1, 'log_on_each_node': True, 'logging_dir': './runs/Feb01_22-34-39_job-1abccd0a-3293-4ffe-8274-9e8f841f653f', 'logging_strategy': 'steps', 'logging_first_step': False, 'logging_steps': 100, 'logging_nan_inf_filter': True, 'save_strategy': 'steps', 'save_steps': 500, 'save_total_limit': 3, 'save_on_each_node': False, 'no_cuda': False, 'seed': 42, '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, 'eval_steps': 500, 'dataloader_num_workers': 0, 'past_index': -1, 'run_name': 'xls-r-300m-fr', 'disable_tqdm': False, 'remove_unused_columns': True, 'label_names': 'None', 'load_best_model_at_end': True, 'metric_for_best_model': 'loss', 'greater_is_better': False, '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': 'input_length', 'report_to': "['wandb']", '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>', 'gradient_checkpointing': True, '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': '', 'train_batch_size': 32, 'eval_batch_size': 32}
+2022-02-01 22:36:26,509 INFO    MainThread:37310 [wandb_watch.py:watch():43] Watching