Training in progress, step 5, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "/home/ubuntu/whisper-large-v3-praxy-fr",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "apply_spec_augment": false,
+  "architectures": [
+    "WhisperForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "classifier_proj_size": 256,
+  "d_model": 1280,
+  "decoder_attention_heads": 20,
+  "decoder_ffn_dim": 5120,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 32,
+  "decoder_start_token_id": 50258,
+  "dropout": 0.0,
+  "encoder_attention_heads": 20,
+  "encoder_ffn_dim": 5120,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 32,
+  "eos_token_id": 50257,
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.05,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "max_length": 448,
+  "max_source_positions": 1500,
+  "max_target_positions": 448,
+  "median_filter_width": 7,
+  "model_type": "whisper",
+  "num_hidden_layers": 32,
+  "num_mel_bins": 128,
+  "pad_token_id": 50256,
+  "scale_embedding": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 51866
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "begin_suppress_tokens": [
+    220,
+    50257
+  ],
+  "bos_token_id": 50257,
+  "decoder_start_token_id": 50258,
+  "eos_token_id": 50257,
+  "max_length": 448,
+  "pad_token_id": 50256,
+  "transformers_version": "4.44.2"
+}

last-checkpoint/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae1df5dd89685564d18b95f94eafc56ee767d829b2656f10dd98a3c86204f8e
+size 4993448880

last-checkpoint/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0417511e1068133a9847e813d1b44752eacb893edce1e5f9ed1e3fa173f283
+size 1180663192

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11b175638d183fff91e19e6e715f3cdfb271e97fd6b0b8d0cd2cbca94bae719e
+size 12333660476

last-checkpoint/preprocessor_config.json

@@ -0,0 +1,14 @@
+{
+  "chunk_length": 30,
+  "feature_extractor_type": "WhisperFeatureExtractor",
+  "feature_size": 128,
+  "hop_length": 160,
+  "n_fft": 400,
+  "n_samples": 480000,
+  "nb_max_frames": 3000,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "processor_class": "WhisperProcessor",
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26420d0b671d327bab461c54783c75b8b78d7f1f0cdc89b12a2714ea41a32456
+size 15984

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14581072dd1c58a34c134e320872f680f8eef49fbea678b198d574e8a3fe6659
+size 15984

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ac47944303985f0095a7b87e35a5f146edd5c17bbe764630e646901a717b04b
+size 15984

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d293ed67e54ddd72c9dbd4b89d42aaec630f294695c73a65ae50c6cc2f4c5cef
+size 15984

last-checkpoint/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb73775b33aa7ed953e15ed92187b06c59b5e0ae3d7bc198ad085927dd0c1daa
+size 15984

last-checkpoint/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9b1eb7016305b6071d0f8d663d5e0a346f6637993b668bf99c9a7ec9c83b25
+size 15984

last-checkpoint/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4b7b9bc852a1f39c6cea3e347663af0ee6245b784841714ef90f8c845820f4
+size 15984

last-checkpoint/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88ffde7826ffb4eb506dac5aba403f2b07c59002ebe1e8fc99ef5a843e15e17
+size 15984

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c6815a247a59cc771fe631cb7e4fe6ea61917e06fbb1da84aad9abeb500fa27
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": 10.464989785409928,
+  "best_model_checkpoint": "./whisper-large-v3-praxy-fr-30k-teeeest-final/checkpoint-5",
+  "epoch": 0.14814814814814814,
+  "eval_steps": 5,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02962962962962963,
+      "grad_norm": 0.7531973123550415,
+      "learning_rate": 2e-08,
+      "loss": 0.0613,
+      "step": 1
+    },
+    {
+      "epoch": 0.05925925925925926,
+      "grad_norm": 0.6711551547050476,
+      "learning_rate": 4e-08,
+      "loss": 0.0599,
+      "step": 2
+    },
+    {
+      "epoch": 0.08888888888888889,
+      "grad_norm": 0.8161910772323608,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 0.0514,
+      "step": 3
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.783392071723938,
+      "learning_rate": 8e-08,
+      "loss": 0.0656,
+      "step": 4
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.6716492176055908,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 0.0505,
+      "step": 5
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "eval_MediaSpeech_loss": 0.3272668123245239,
+      "eval_MediaSpeech_runtime": 65.3379,
+      "eval_MediaSpeech_samples_per_second": 1.913,
+      "eval_MediaSpeech_steps_per_second": 0.061,
+      "eval_MediaSpeech_wer": 13.706183536825522,
+      "step": 5
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "eval_Pxcorpus_loss": 0.19093938171863556,
+      "eval_Pxcorpus_runtime": 30.7203,
+      "eval_Pxcorpus_samples_per_second": 1.302,
+      "eval_Pxcorpus_steps_per_second": 0.065,
+      "eval_Pxcorpus_wer": 7.223796033994335,
+      "step": 5
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 5,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.01
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1743988336544973e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef0ee7f56988a560d7d0b7d389284d63b441b798ea81d224e78ddaa18d325cee
+size 5432