Saving train state of step 100000

checkpoint-100000-epoch-7/config.json

@@ -0,0 +1,278 @@
+{
+  "architectures": [
+    "ParlerTTSForConditionalGeneration"
+  ],
+  "audio_encoder": {
+    "_name_or_path": "parler-tts/dac_44khZ_8kbps",
+    "add_cross_attention": false,
+    "architectures": [
+      "DACModel"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "codebook_size": 1024,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": null,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "frame_rate": 86,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "latent_dim": 1024,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_bitrate": 8,
+    "model_type": "dac",
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sampling_rate": 44100,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false
+  },
+  "decoder": {
+    "_name_or_path": "./parler-tts-untrained-600M/decoder",
+    "activation_dropout": 0.0,
+    "activation_function": "gelu",
+    "add_cross_attention": true,
+    "architectures": [
+      "ParlerTTSForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1025,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1024,
+    "exponential_decay_length_penalty": null,
+    "ffn_dim": 4096,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 0.02,
+    "is_decoder": true,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layerdrop": 0.0,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 4096,
+    "min_length": 0,
+    "model_type": "parler_tts_decoder",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 16,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_codebooks": 9,
+    "num_hidden_layers": 24,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 1024,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rope_embeddings": true,
+    "rope_theta": 10000.0,
+    "scale_embedding": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 1088
+  },
+  "decoder_start_token_id": 1025,
+  "is_encoder_decoder": true,
+  "model_type": "parler_tts",
+  "pad_token_id": 1024,
+  "prompt_cross_attention": true,
+  "text_encoder": {
+    "_name_or_path": "google/flan-t5-base",
+    "add_cross_attention": false,
+    "architectures": [
+      "T5ForConditionalGeneration"
+    ],
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": null,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": 0.0,
+    "cross_attention_hidden_size": null,
+    "d_ff": 2048,
+    "d_kv": 64,
+    "d_model": 768,
+    "decoder_start_token_id": 0,
+    "dense_act_fn": "gelu_new",
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "dropout_rate": 0.1,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 1,
+    "exponential_decay_length_penalty": null,
+    "feed_forward_proj": "gated-gelu",
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_factor": 1.0,
+    "is_decoder": false,
+    "is_encoder_decoder": true,
+    "is_gated_act": true,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_epsilon": 1e-06,
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "min_length": 0,
+    "model_type": "t5",
+    "n_positions": 512,
+    "no_repeat_ngram_size": 0,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_decoder_layers": 12,
+    "num_heads": 12,
+    "num_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_past": true,
+    "output_scores": false,
+    "pad_token_id": 0,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "relative_attention_max_distance": 128,
+    "relative_attention_num_buckets": 32,
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": {
+      "summarization": {
+        "early_stopping": true,
+        "length_penalty": 2.0,
+        "max_length": 200,
+        "min_length": 30,
+        "no_repeat_ngram_size": 3,
+        "num_beams": 4,
+        "prefix": "summarize: "
+      },
+      "translation_en_to_de": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to German: "
+      },
+      "translation_en_to_fr": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to French: "
+      },
+      "translation_en_to_ro": {
+        "early_stopping": true,
+        "max_length": 300,
+        "num_beams": 4,
+        "prefix": "translate English to Romanian: "
+      }
+    },
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": null,
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32128
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "vocab_size": 32128
+}

checkpoint-100000-epoch-7/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1025,
+  "decoder_start_token_id": 1025,
+  "do_sample": true,
+  "eos_token_id": 1024,
+  "guidance_scale": 1,
+  "key": 10,
+  "max_length": 2580,
+  "pad_token_id": 1024,
+  "transformers_version": "4.40.2"
+}

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d85a6ebcfaea697deb81a9f43cf52b763722cc63c52559be99475194f3b1740
+oid sha256:bd37cc366fd3dc7555761b2c4d533acc24cb5167887b515a05d967039b2f69d8
 size 3652769047

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64ed77445bae74c0a44de014644335672082db652c167e03307f5aa69f497029
+oid sha256:9db954269aa6e14821889cf86751cb2a2693837e4705f87775e0a6b776e788f6
 size 2588465818

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_0.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bee040cadf66c07cc28951d8b63f5309317c467c935239899967dedde236356
+oid sha256:57b6a57da4e90aadee26add0d1940caf830055df727b7e047239ef3bcba77630
 size 16100

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_1.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac2984f6c11e0d6baba6e153c36e02cf7d8849f435a8e1d10db3db9422a5e14f
+oid sha256:d5e88440e3ee1b8018ff64f89d448a619241d0b4b676b8e34b9f549c7afc8e72
 size 16100

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_2.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0328ba0db514b5427f0cf5728abf82349345bec8a02097c30900ec57f433da11
-size 16100
+oid sha256:3a5fcd6c888c9e5901ac26aad83314ecdbcbcb367c36a1dd9aaa74906a828499
+size 16164

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_3.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:668cc4578435da562a838c3860a81ef62a34fdfed1920ccebb7657eb586c14cb
+oid sha256:fa5905fef467ea687474a5c7f35dec4589cea510fd59e642b6422ec369272b7c
 size 16100

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_4.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c856097a2b0832cc85eba37f9cd1be76e0d395fe4b2c99ef3153199386dae5e5
+oid sha256:8640abdce1b93fe30861ef6cafda4aff5358cc1b8c797bee1c1234130bc29bd6
 size 16100

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_5.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d11b3bb1f3959f58be8c638fb21de1e89e54c13aa716a178687cb1fc51ac99
+oid sha256:31dcb2e53bea6b530f0bf502156bf8caa89a3f3c661e26d16851700d150720e4
 size 16100

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_6.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18447190b31cbfd6ac8565a46dfbdc82123f510bef0eb0a72313d1150001b8f4
-size 16100
+oid sha256:29cdf8fe14f6759fa66900041f0ce6225dd045ea5ec44307b00daa1098d87698
+size 16036

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/random_states_7.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025b2bf49a9a6fe2a6fd8cb7a98ba98f4eb439e04b5aa68fd3285c8c109bdc4f
+oid sha256:60377d5c46fac6088fdbec90f53e2ea7337f1ca7aff123378e91aef819b6c3ed
 size 16100

{checkpoint-80000-epoch-5 → checkpoint-100000-epoch-7}/scheduler.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd55300ad4b9da07287969193b88215d1af9b5d03f7bf3a833f1b260aa6434c4
+oid sha256:1955e1bc00d0764fc047ce931f4a5f0afafefd63fe1863cc6f5a39adf18dee02
 size 1000