checkpoints/best (main-tree mirror)

checkpoints/best/audio_heads.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a85fd3a4dc4caa6e3edfe857cb3f0c39dc2ae54ec89c6ce86f4d9c6f0efd94
+size 8390277

checkpoints/best/depth_decoder.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8ced80136b340190d881f62e7e07e0a2d0d3d6099cbcb13b8ffaf25f4979597
+size 1428745845

checkpoints/best/metadata.json

@@ -0,0 +1,148 @@
+{
+  "step": 62750,
+  "best_val_loss": 2.9048058986663814,
+  "config": {
+    "backend": "tpu",
+    "data": {
+      "train_split": "/mnt/data/splits/train.jsonl",
+      "val_split": "/mnt/data/splits/val.jsonl",
+      "encoded_dir": "/mnt/data/encoded",
+      "max_frames": 300,
+      "bucket_frames": null,
+      "audio_frame_rate": 12.5,
+      "num_workers": 32,
+      "pin_memory": false
+    },
+    "train": {
+      "num_codebooks": 8,
+      "batch_size": 8,
+      "grad_accum": 1,
+      "max_steps": 110463,
+      "warmup_steps": 1100,
+      "min_lr_ratio": 0.0,
+      "depth_chunk_size": 100,
+      "precision": "bfloat16",
+      "max_grad_norm": 1.0,
+      "seed": 42,
+      "scheduler_total_steps": null,
+      "per_chip_batch": 2,
+      "schedule": "wsd",
+      "wsd_anneal_steps": 11000,
+      "wsd_anneal_frac": 0.1,
+      "weight_decay": 0.01,
+      "adam_beta1": 0.9,
+      "adam_beta2": 0.999,
+      "adam_eps": 1e-08,
+      "allow_fresh_optimizer": false,
+      "use_scan_layers": true,
+      "xla_grad_checkpoint": true,
+      "compile_warmup_steps": 1,
+      "debug_input_sharding": false,
+      "early_stop_patience": 10,
+      "enable_clip_grad_norm": true,
+      "clip_grad_norm": 1.0,
+      "log_grad_norm": true,
+      "fsdp_barrier_hook": false,
+      "micro_mark_step": true,
+      "final_canonical_save": true
+    },
+    "loss": {
+      "text_weight": 0.2,
+      "audio_weight": 1.0,
+      "text_weight_curriculum_frac": 0.0,
+      "composite_text_w": 0.4,
+      "composite_audio_w": 0.6,
+      "text_padding_weight": 0.01,
+      "zero_padding_weight": 0.0,
+      "label_smoothing": 0.1,
+      "per_codebook_multipliers": [
+        1.0,
+        1.0,
+        1.5,
+        1.5,
+        2.0,
+        2.0,
+        2.0,
+        2.0
+      ],
+      "progressive_unmask_fraction": 0.1,
+      "unmask_k0": 1
+    },
+    "optim": {
+      "lr_lora": 0.0001716,
+      "lr_full_ft": 5e-05,
+      "lr_projection": 0.0005,
+      "lr_depth": 0.0001,
+      "lr_audio_embed": 0.0005,
+      "lr_text_embed": 0.0005,
+      "lr_depth_blocks": 1e-05
+    },
+    "logging": {
+      "log_every": 25,
+      "save_every": 1000,
+      "audio_every": 5000,
+      "audio_ar_frames": 50,
+      "val_every": 250,
+      "val_max_batches": 25,
+      "val_on_tpu": true,
+      "val_per_chip_batch": 8,
+      "tpu_telemetry_every": 250,
+      "save_dir": "gs://tinyaya-stage2-eu/checkpoints/stage2-v6e16-mh-v03-r2",
+      "log_spaced_saves": true,
+      "save_at_steps": null,
+      "async_checkpoint_upload": true,
+      "wandb_project": "tinyaya-stage2-tpu",
+      "wandb_run_name": "v0.3-long-horizon-mh-r2",
+      "use_wandb": true,
+      "wandb_tags": [
+        "v0.3",
+        "multi-host",
+        "wsd"
+      ],
+      "push_to_hub": true,
+      "hub_repo_id": "tiny-aya-translate/tr-hi-s2st-v0.3",
+      "hub_private": true,
+      "diag_metrics": true,
+      "keep_last_n": 0,
+      "keep_local_checkpoints": false
+    },
+    "perf": {
+      "enabled": true,
+      "warmup_skip_steps": 25,
+      "xprof_trace_labels": false
+    },
+    "lora": {
+      "r": 32,
+      "alpha": 64,
+      "dropout": 0.05,
+      "use_rslora": true,
+      "target_modules": [
+        "q_proj",
+        "k_proj",
+        "v_proj",
+        "o_proj",
+        "gate_proj",
+        "up_proj",
+        "down_proj",
+        "embed_tokens"
+      ],
+      "lora_exclude_top": 0,
+      "num_full_ft_layers": 0,
+      "depth_unfreeze_blocks": 0
+    }
+  },
+  "wandb_run_id": "xzcb60bl",
+  "files": {
+    "rng.pt": 6605,
+    "depth_decoder.pt": 1428745845,
+    "text_embed.pt": 1090668924,
+    "scheduler.pt": 1401,
+    "projection.pt": 16778814,
+    "optimizer.pt": 768419326,
+    "model_audio_embed.pt": 8394415,
+    "audio_heads.pt": 8390277,
+    "peft_adapter/adapter_config.json": 1122,
+    "peft_adapter/README.md": 5202,
+    "peft_adapter/adapter_model.safetensors": 1220179520
+  }
+}

checkpoints/best/model_audio_embed.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb4d0cf9710d6f557d42b03fcd7c5ff05b776e0bba9f0dc2ca70eb9bbf74194b
+size 8394415

checkpoints/best/peft_adapter/README.md

@@ -0,0 +1,207 @@
+---
+base_model: CohereLabs/tiny-aya-base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:CohereLabs/tiny-aya-base
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.19.1

checkpoints/best/peft_adapter/adapter_config.json

@@ -0,0 +1,49 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "CohereLabs/tiny-aya-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "gate_proj",
+    "v_proj",
+    "embed_tokens",
+    "q_proj",
+    "down_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": true
+}

checkpoints/best/peft_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6645a1258da4856e3a67e42d4dea435cfe07f29ad0f6bd81ca195460cb935786
+size 1220179520

checkpoints/best/projection.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:069ab56a118e82bb3d51f6015b332048697143fe7e9b5e0c82a94ca36006213a
+size 16778814

checkpoints/best/text_embed.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2af4db9373aa383e53250beb2da5521cf149a121a2b37bd709389c0f91aea2a4
+size 1090668924