Add files using upload-large-folder tool

SLAM-OMNI-SFT/model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c7bf2415a9979cac189f43fac5880caa8b5b3b881e31366a17fbf377badb4c3
+size 2237875274

VocalNet-1B-SFT/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /share/nlp/tuwenming/models/VocalNet/VocalNet-1B
+library_name: peft
+---
+
+# 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 0.11.1

VocalNet-1B-SFT/adapter_config.json

@@ -0,0 +1,139 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/share/nlp/tuwenming/models/VocalNet/VocalNet-1B",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.15.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

VocalNet-1B-SFT/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee92764145c96840a8024ba908b9ca0a704eec76d8430ef89127b56fd88bddd3
+size 11301520

VocalNet-1B-SFT/global_step4000/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a66b9f1348862e8efd9e5528964ec071f143531eefbcc665b6a9baabcd13d3fb
+size 2514143600

VocalNet-1B-SFT/global_step4000/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a253db835a70cf41421615e7b83f89e71f5f0fbe78fd0e94cada84d596bad224
+size 2514143600

VocalNet-1B-SFT/global_step4000/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd3166580d518db51193379ef43633074717ae153f1aa9a8251aad25f04220d
+size 2514143600

VocalNet-1B-SFT/global_step4000/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebfe77c31cf7db6672ea21ae2b249bdbcc43707b4c1aaf0fb1b27857ed90bae4
+size 2514143600

VocalNet-1B-SFT/global_step4000/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:def676d5bde1f3de9e098881ea1eb7e91041f74e7a1290626275f484fe8c22ff
+size 319625

VocalNet-1B-SFT/global_step4000/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5775e779b933f4b5858b494cab27bbbbf4378c4f8867a3f9cef558ec164c7198
+size 319497

VocalNet-1B-SFT/global_step4000/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8be12939ebac7158c78deb656007122ece0276c9634fa3d34497896321bf9c16
+size 319497

VocalNet-1B-SFT/global_step4000/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:374cd0b4f0aa71c4021b2bff5949e30728bf0d70b40fa231cd3981d74e0a6deb
+size 319497

VocalNet-1B-SFT/latest

@@ -0,0 +1 @@
+global_step4000

VocalNet-1B-SFT/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c542535ebc3563a388077447b3172171d869605d0bc9bb79e73ae8c3d3f954
+size 15024

VocalNet-1B-SFT/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4a58e3e726d2469c06952a828a34a3e921fb8a3614319e45c7199ffe5076e3d
+size 15024

VocalNet-1B-SFT/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f39e29acd8a78b823791d140d0a0ffa98c09da9116806390cb7ea7fcc546d2dc
+size 15024

VocalNet-1B-SFT/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c8c790ee36118386d343c6bf055225de534c902f051e22085388f44f499c19
+size 15024

VocalNet-1B-SFT/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:453242198831ab409dc0543bd3f47459f5cf78863e812101f396cd91d37382bb
+size 1064

VocalNet-1B-SFT/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|finetune_right_pad_id|>"
+}

VocalNet-1B-SFT/tokenizer_config.json

@@ -0,0 +1,2064 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- if strftime_now is defined %}\n        {%- set date_string = strftime_now(\"%d %b %Y\") %}\n    {%- else %}\n        {%- set date_string = \"26 Jul 2024\" %}\n    {%- endif %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n        {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n        {{- '\"parameters\": ' }}\n        {{- tool_call.arguments | tojson }}\n        {{- \"}\" }}\n        {{- \"<|eot_id|>\" }}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 4096,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

VocalNet-1B-SFT/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d04e3256f5fab7eea993343e4d944c39f256902c6363a9274a549b0289315ec9
+size 7544

VocalNet-1B-SFT/zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)

VocalNet-7B-SFT/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /share/nlp/tuwenming/models/VocalNet/VocalNet-qwen25-7B
+library_name: peft
+---
+
+# 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 0.11.1

VocalNet-7B-SFT/adapter_config.json

@@ -0,0 +1,223 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/share/nlp/tuwenming/models/VocalNet/VocalNet-qwen25-7B",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.25.mlp.down_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.20.self_attn.o_proj",
+    "model.layers.16.self_attn.q_proj",
+    "model.layers.20.self_attn.v_proj",
+    "model.layers.22.mlp.down_proj",
+    "model.layers.12.mlp.up_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.21.self_attn.o_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.12.self_attn.k_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.27.self_attn.v_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.16.mlp.up_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.13.mlp.down_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.17.self_attn.o_proj",
+    "model.layers.23.self_attn.o_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.21.self_attn.k_proj",
+    "model.layers.22.self_attn.q_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.19.self_attn.k_proj",
+    "model.layers.13.self_attn.o_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.23.self_attn.k_proj",
+    "model.layers.27.self_attn.q_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.14.self_attn.v_proj",
+    "model.layers.23.mlp.gate_proj",
+    "model.layers.17.mlp.up_proj",
+    "model.layers.19.self_attn.v_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.24.self_attn.v_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.27.self_attn.k_proj",
+    "model.layers.23.self_attn.v_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.13.self_attn.q_proj",
+    "model.layers.18.mlp.down_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.24.mlp.up_proj",
+    "model.layers.23.mlp.up_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.21.mlp.gate_proj",
+    "model.layers.18.self_attn.q_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.15.mlp.gate_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.16.self_attn.v_proj",
+    "model.layers.19.mlp.down_proj",
+    "model.layers.13.self_attn.v_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.23.mlp.down_proj",
+    "model.layers.20.self_attn.q_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.26.self_attn.v_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.14.mlp.gate_proj",
+    "model.layers.24.mlp.down_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.15.self_attn.k_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.15.self_attn.q_proj",
+    "model.layers.16.mlp.down_proj",
+    "model.layers.18.mlp.gate_proj",
+    "model.layers.19.mlp.gate_proj",
+    "model.layers.22.self_attn.o_proj",
+    "model.layers.25.self_attn.k_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.17.self_attn.k_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.26.mlp.up_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.12.self_attn.v_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.26.mlp.down_proj",
+    "model.layers.17.mlp.gate_proj",
+    "model.layers.18.mlp.up_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.27.mlp.down_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.17.mlp.down_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.23.self_attn.q_proj",
+    "model.layers.19.self_attn.o_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.13.mlp.gate_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.1.self_attn.o_proj",
+    "model.layers.22.self_attn.k_proj",
+    "model.layers.22.mlp.up_proj",
+    "model.layers.14.self_attn.q_proj",
+    "model.layers.17.self_attn.q_proj",
+    "model.layers.24.self_attn.o_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.18.self_attn.k_proj",
+    "model.layers.24.self_attn.k_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.12.mlp.down_proj",
+    "model.layers.25.self_attn.v_proj",
+    "model.layers.26.self_attn.q_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.16.self_attn.o_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.15.mlp.down_proj",
+    "model.layers.16.mlp.gate_proj",
+    "model.layers.20.mlp.up_proj",
+    "model.layers.21.self_attn.v_proj",
+    "model.layers.27.self_attn.o_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.25.mlp.gate_proj",
+    "model.layers.25.self_attn.o_proj",
+    "model.layers.26.mlp.gate_proj",
+    "model.layers.14.self_attn.o_proj",
+    "model.layers.21.mlp.up_proj",
+    "model.layers.21.self_attn.q_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.12.self_attn.q_proj",
+    "model.layers.17.self_attn.v_proj",
+    "model.layers.19.self_attn.q_proj",
+    "model.layers.15.self_attn.v_proj",
+    "model.layers.20.self_attn.k_proj",
+    "model.layers.14.self_attn.k_proj",
+    "model.layers.25.self_attn.q_proj",
+    "model.layers.27.mlp.up_proj",
+    "model.layers.18.self_attn.o_proj",
+    "model.layers.24.mlp.gate_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.24.self_attn.q_proj",
+    "model.layers.12.mlp.gate_proj",
+    "model.layers.26.self_attn.o_proj",
+    "model.layers.18.self_attn.v_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.22.mlp.gate_proj",
+    "model.layers.14.mlp.up_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.20.mlp.down_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.15.mlp.up_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.14.mlp.down_proj",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.27.mlp.gate_proj",
+    "model.layers.20.mlp.gate_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.13.mlp.up_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.26.self_attn.k_proj",
+    "model.layers.11.mlp.gate_proj",
+    "model.layers.13.self_attn.k_proj",
+    "model.layers.16.self_attn.k_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.19.mlp.up_proj",
+    "model.layers.25.mlp.up_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.15.self_attn.o_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.21.mlp.down_proj",
+    "model.layers.12.self_attn.o_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.22.self_attn.v_proj",
+    "model.layers.5.self_attn.q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

VocalNet-7B-SFT/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:601c304775e0dd5ac1444e99fe790d2e24fb118cd31aa8442fd7541fe64f3857
+size 40422208

VocalNet-7B-SFT/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

VocalNet-7B-SFT/global_step400/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:611f17bff66e5fbf4a05a28182ae2bcd55da9ff6e012ca5f963f3297f3660cf4
+size 7337277452

VocalNet-7B-SFT/global_step400/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6dccbb1f2edf5d053c03d55d6f8b205ea212d15df7a99f1ecbf151d28a95048
+size 7337277452

VocalNet-7B-SFT/global_step400/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a49172e01b3e9842f38548c1a20f863d35af4d3bb2e7d65a9de45a97b39087f0
+size 7337277452

VocalNet-7B-SFT/global_step400/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f30ca06114dd1f36dd7c56aa097f0fa733273df09b599b4de99e6f1e3a21f025
+size 7337277452

VocalNet-7B-SFT/global_step400/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa3a01d438487784ea8ec1a5673d11dcb280d56439d26760b1ccbb96ac1c91c
+size 478196

VocalNet-7B-SFT/global_step400/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f52cd1e0d5ee90db90868c29dfee441e34b258a2a4e3a77e021875a81c1e3d1
+size 478196

VocalNet-7B-SFT/global_step400/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42fb4956191524065563d453e66c425580589c0615a5832b2d5181036174a497
+size 478196

VocalNet-7B-SFT/global_step400/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6553ebb9f9a3d6b57ba3abd1d830789bd6bcb52326dde5edf6b2858188c567c9
+size 478196

VocalNet-7B-SFT/latest

@@ -0,0 +1 @@
+global_step400

VocalNet-7B-SFT/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff24f75be3b445b6d30ca43fbd2ae46e9253099eeffd67ba8473220a92f95899
+size 15024

VocalNet-7B-SFT/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59504666da22f53504b5aa2ce4b25f2dcc62605cbcbdf7733913e73af0d9f44d
+size 15024

VocalNet-7B-SFT/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd4c2bd5135429acc03c86a12ebc3a94c5a3bef4f5f0165c0252b44d100dd31b
+size 15024

VocalNet-7B-SFT/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eed580013b8033aef05d82a9fa956c40c2d306fb7adaea446f9f2b21746368e
+size 15024

VocalNet-7B-SFT/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f850f0addc3978ee095c1fe5c6bd56be53017ae3c0f95ffb63bf3c1ad02e6963
+size 1064

VocalNet-7B-SFT/special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>"
+}

VocalNet-7B-SFT/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

VocalNet-7B-SFT/trainer_state.json

@@ -0,0 +1,2833 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2602049113677021,
+  "eval_steps": 500,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0006505122784192552,
+      "grad_norm": 14.9100680844527,
+      "learning_rate": 1.4388489208633094e-06,
+      "loss": 23.3662,
+      "step": 1
+    },
+    {
+      "epoch": 0.0013010245568385104,
+      "grad_norm": 14.942963467353986,
+      "learning_rate": 2.877697841726619e-06,
+      "loss": 22.9598,
+      "step": 2
+    },
+    {
+      "epoch": 0.0019515368352577655,
+      "grad_norm": 16.055673561380587,
+      "learning_rate": 4.316546762589929e-06,
+      "loss": 23.2287,
+      "step": 3
+    },
+    {
+      "epoch": 0.002602049113677021,
+      "grad_norm": 14.923160007515575,
+      "learning_rate": 5.755395683453238e-06,
+      "loss": 23.1396,
+      "step": 4
+    },
+    {
+      "epoch": 0.0032525613920962758,
+      "grad_norm": 14.149209093551988,
+      "learning_rate": 7.1942446043165465e-06,
+      "loss": 23.3855,
+      "step": 5
+    },
+    {
+      "epoch": 0.003903073670515531,
+      "grad_norm": 13.81311374536001,
+      "learning_rate": 8.633093525179858e-06,
+      "loss": 23.4155,
+      "step": 6
+    },
+    {
+      "epoch": 0.004553585948934786,
+      "grad_norm": 13.78985111130566,
+      "learning_rate": 1.0071942446043167e-05,
+      "loss": 23.8439,
+      "step": 7
+    },
+    {
+      "epoch": 0.005204098227354042,
+      "grad_norm": 17.326973949525275,
+      "learning_rate": 1.1510791366906475e-05,
+      "loss": 22.4472,
+      "step": 8
+    },
+    {
+      "epoch": 0.005854610505773296,
+      "grad_norm": 18.376682414339786,
+      "learning_rate": 1.2949640287769784e-05,
+      "loss": 22.4034,
+      "step": 9
+    },
+    {
+      "epoch": 0.0065051227841925515,
+      "grad_norm": 21.592823004213024,
+      "learning_rate": 1.4388489208633093e-05,
+      "loss": 21.4057,
+      "step": 10
+    },
+    {
+      "epoch": 0.007155635062611807,
+      "grad_norm": 22.754197129933665,
+      "learning_rate": 1.5827338129496403e-05,
+      "loss": 20.9012,
+      "step": 11
+    },
+    {
+      "epoch": 0.007806147341031062,
+      "grad_norm": 8.420903628097577,
+      "learning_rate": 1.7266187050359716e-05,
+      "loss": 20.2356,
+      "step": 12
+    },
+    {
+      "epoch": 0.008456659619450317,
+      "grad_norm": 4.820677753781494,
+      "learning_rate": 1.8705035971223024e-05,
+      "loss": 19.6071,
+      "step": 13
+    },
+    {
+      "epoch": 0.009107171897869573,
+      "grad_norm": 4.53140308347643,
+      "learning_rate": 2.0143884892086333e-05,
+      "loss": 20.1037,
+      "step": 14
+    },
+    {
+      "epoch": 0.009757684176288828,
+      "grad_norm": 4.147984474039313,
+      "learning_rate": 2.1582733812949642e-05,
+      "loss": 19.4484,
+      "step": 15
+    },
+    {
+      "epoch": 0.010408196454708083,
+      "grad_norm": 7.499669746844926,
+      "learning_rate": 2.302158273381295e-05,
+      "loss": 19.7755,
+      "step": 16
+    },
+    {
+      "epoch": 0.011058708733127337,
+      "grad_norm": 6.75188437746758,
+      "learning_rate": 2.446043165467626e-05,
+      "loss": 19.5029,
+      "step": 17
+    },
+    {
+      "epoch": 0.011709221011546592,
+      "grad_norm": 5.990476759553056,
+      "learning_rate": 2.589928057553957e-05,
+      "loss": 19.3643,
+      "step": 18
+    },
+    {
+      "epoch": 0.012359733289965848,
+      "grad_norm": 4.3136680671831105,
+      "learning_rate": 2.733812949640288e-05,
+      "loss": 19.8471,
+      "step": 19
+    },
+    {
+      "epoch": 0.013010245568385103,
+      "grad_norm": 3.616381624567815,
+      "learning_rate": 2.8776978417266186e-05,
+      "loss": 18.1306,
+      "step": 20
+    },
+    {
+      "epoch": 0.013660757846804358,
+      "grad_norm": 2.829624126368199,
+      "learning_rate": 3.0215827338129498e-05,
+      "loss": 19.28,
+      "step": 21
+    },
+    {
+      "epoch": 0.014311270125223614,
+      "grad_norm": 2.257236171790319,
+      "learning_rate": 3.165467625899281e-05,
+      "loss": 18.8043,
+      "step": 22
+    },
+    {
+      "epoch": 0.014961782403642869,
+      "grad_norm": 2.0401460122722694,
+      "learning_rate": 3.3093525179856116e-05,
+      "loss": 18.3876,
+      "step": 23
+    },
+    {
+      "epoch": 0.015612294682062124,
+      "grad_norm": 2.01144066292761,
+      "learning_rate": 3.453237410071943e-05,
+      "loss": 19.0136,
+      "step": 24
+    },
+    {
+      "epoch": 0.01626280696048138,
+      "grad_norm": 1.7074930501408525,
+      "learning_rate": 3.597122302158273e-05,
+      "loss": 18.6118,
+      "step": 25
+    },
+    {
+      "epoch": 0.016913319238900635,
+      "grad_norm": 1.5932493978633762,
+      "learning_rate": 3.741007194244605e-05,
+      "loss": 18.5584,
+      "step": 26
+    },
+    {
+      "epoch": 0.01756383151731989,
+      "grad_norm": 1.5912494999159947,
+      "learning_rate": 3.884892086330936e-05,
+      "loss": 18.8337,
+      "step": 27
+    },
+    {
+      "epoch": 0.018214343795739146,
+      "grad_norm": 1.7736768834839776,
+      "learning_rate": 4.0287769784172666e-05,
+      "loss": 19.0386,
+      "step": 28
+    },
+    {
+      "epoch": 0.0188648560741584,
+      "grad_norm": 1.630718589825753,
+      "learning_rate": 4.1726618705035975e-05,
+      "loss": 18.3971,
+      "step": 29
+    },
+    {
+      "epoch": 0.019515368352577656,
+      "grad_norm": 2.0209028189851765,
+      "learning_rate": 4.3165467625899284e-05,
+      "loss": 18.333,
+      "step": 30
+    },
+    {
+      "epoch": 0.02016588063099691,
+      "grad_norm": 1.5587597015447017,
+      "learning_rate": 4.460431654676259e-05,
+      "loss": 18.5942,
+      "step": 31
+    },
+    {
+      "epoch": 0.020816392909416167,
+      "grad_norm": 1.4887631013259133,
+      "learning_rate": 4.60431654676259e-05,
+      "loss": 18.1176,
+      "step": 32
+    },
+    {
+      "epoch": 0.02146690518783542,
+      "grad_norm": 1.3320353048467588,
+      "learning_rate": 4.748201438848921e-05,
+      "loss": 18.0518,
+      "step": 33
+    },
+    {
+      "epoch": 0.022117417466254674,
+      "grad_norm": 1.386745989169568,
+      "learning_rate": 4.892086330935252e-05,
+      "loss": 17.9244,
+      "step": 34
+    },
+    {
+      "epoch": 0.02276792974467393,
+      "grad_norm": 1.3938624818100709,
+      "learning_rate": 5.035971223021583e-05,
+      "loss": 17.6912,
+      "step": 35
+    },
+    {
+      "epoch": 0.023418442023093185,
+      "grad_norm": 1.4359883312832364,
+      "learning_rate": 5.179856115107914e-05,
+      "loss": 17.859,
+      "step": 36
+    },
+    {
+      "epoch": 0.02406895430151244,
+      "grad_norm": 1.2531536018704754,
+      "learning_rate": 5.323741007194245e-05,
+      "loss": 18.3595,
+      "step": 37
+    },
+    {
+      "epoch": 0.024719466579931695,
+      "grad_norm": 1.1810256252580864,
+      "learning_rate": 5.467625899280576e-05,
+      "loss": 17.6762,
+      "step": 38
+    },
+    {
+      "epoch": 0.02536997885835095,
+      "grad_norm": 1.3036244003466404,
+      "learning_rate": 5.611510791366906e-05,
+      "loss": 17.9837,
+      "step": 39
+    },
+    {
+      "epoch": 0.026020491136770206,
+      "grad_norm": 1.27580432265322,
+      "learning_rate": 5.755395683453237e-05,
+      "loss": 17.7984,
+      "step": 40
+    },
+    {
+      "epoch": 0.02667100341518946,
+      "grad_norm": 1.2151810682758621,
+      "learning_rate": 5.899280575539569e-05,
+      "loss": 17.7297,
+      "step": 41
+    },
+    {
+      "epoch": 0.027321515693608717,
+      "grad_norm": 1.2114570310158876,
+      "learning_rate": 6.0431654676258996e-05,
+      "loss": 17.1564,
+      "step": 42
+    },
+    {
+      "epoch": 0.027972027972027972,
+      "grad_norm": 1.2985962176451518,
+      "learning_rate": 6.187050359712231e-05,
+      "loss": 16.9317,
+      "step": 43
+    },
+    {
+      "epoch": 0.028622540250447227,
+      "grad_norm": 1.256971864348589,
+      "learning_rate": 6.330935251798561e-05,
+      "loss": 17.3788,
+      "step": 44
+    },
+    {
+      "epoch": 0.029273052528866483,
+      "grad_norm": 1.1645006927976935,
+      "learning_rate": 6.474820143884892e-05,
+      "loss": 17.2548,
+      "step": 45
+    },
+    {
+      "epoch": 0.029923564807285738,
+      "grad_norm": 1.2049086227800867,
+      "learning_rate": 6.618705035971223e-05,
+      "loss": 17.6986,
+      "step": 46
+    },
+    {
+      "epoch": 0.030574077085704993,
+      "grad_norm": 1.3076518347009005,
+      "learning_rate": 6.762589928057555e-05,
+      "loss": 17.5603,
+      "step": 47
+    },
+    {
+      "epoch": 0.03122458936412425,
+      "grad_norm": 1.1431315905764077,
+      "learning_rate": 6.906474820143886e-05,
+      "loss": 17.3651,
+      "step": 48
+    },
+    {
+      "epoch": 0.0318751016425435,
+      "grad_norm": 1.0171897272985948,
+      "learning_rate": 7.050359712230215e-05,
+      "loss": 17.7242,
+      "step": 49
+    },
+    {
+      "epoch": 0.03252561392096276,
+      "grad_norm": 1.0460517083509904,
+      "learning_rate": 7.194244604316547e-05,
+      "loss": 17.1166,
+      "step": 50
+    },
+    {
+      "epoch": 0.03317612619938201,
+      "grad_norm": 1.2619245546455962,
+      "learning_rate": 7.338129496402878e-05,
+      "loss": 17.4234,
+      "step": 51
+    },
+    {
+      "epoch": 0.03382663847780127,
+      "grad_norm": 1.1381160410526339,
+      "learning_rate": 7.48201438848921e-05,
+      "loss": 17.5279,
+      "step": 52
+    },
+    {
+      "epoch": 0.03447715075622052,
+      "grad_norm": 0.9919628998169787,
+      "learning_rate": 7.62589928057554e-05,
+      "loss": 17.4952,
+      "step": 53
+    },
+    {
+      "epoch": 0.03512766303463978,
+      "grad_norm": 1.215106894195362,
+      "learning_rate": 7.769784172661872e-05,
+      "loss": 17.3751,
+      "step": 54
+    },
+    {
+      "epoch": 0.03577817531305903,
+      "grad_norm": 1.1851060534008606,
+      "learning_rate": 7.913669064748202e-05,
+      "loss": 17.1834,
+      "step": 55
+    },
+    {
+      "epoch": 0.03642868759147829,
+      "grad_norm": 1.170836646439913,
+      "learning_rate": 8.057553956834533e-05,
+      "loss": 17.7604,
+      "step": 56
+    },
+    {
+      "epoch": 0.03707919986989754,
+      "grad_norm": 1.0570810421991996,
+      "learning_rate": 8.201438848920863e-05,
+      "loss": 17.2827,
+      "step": 57
+    },
+    {
+      "epoch": 0.0377297121483168,
+      "grad_norm": 1.0892621143468961,
+      "learning_rate": 8.345323741007195e-05,
+      "loss": 17.3127,
+      "step": 58
+    },
+    {
+      "epoch": 0.038380224426736054,
+      "grad_norm": 1.3408181015931786,
+      "learning_rate": 8.489208633093527e-05,
+      "loss": 17.2656,
+      "step": 59
+    },
+    {
+      "epoch": 0.03903073670515531,
+      "grad_norm": 1.135185398642103,
+      "learning_rate": 8.633093525179857e-05,
+      "loss": 17.8505,
+      "step": 60
+    },
+    {
+      "epoch": 0.039681248983574564,
+      "grad_norm": 1.0340370120284927,
+      "learning_rate": 8.776978417266187e-05,
+      "loss": 17.0219,
+      "step": 61
+    },
+    {
+      "epoch": 0.04033176126199382,
+      "grad_norm": 1.0054848070137998,
+      "learning_rate": 8.920863309352519e-05,
+      "loss": 16.9429,
+      "step": 62
+    },
+    {
+      "epoch": 0.040982273540413075,
+      "grad_norm": 1.1647855506468234,
+      "learning_rate": 9.06474820143885e-05,
+      "loss": 17.1581,
+      "step": 63
+    },
+    {
+      "epoch": 0.041632785818832334,
+      "grad_norm": 1.2859338036958894,
+      "learning_rate": 9.20863309352518e-05,
+      "loss": 16.9788,
+      "step": 64
+    },
+    {
+      "epoch": 0.042283298097251586,
+      "grad_norm": 1.0469321540380294,
+      "learning_rate": 9.35251798561151e-05,
+      "loss": 17.444,
+      "step": 65
+    },
+    {
+      "epoch": 0.04293381037567084,
+      "grad_norm": 1.1401833425936454,
+      "learning_rate": 9.496402877697842e-05,
+      "loss": 16.86,
+      "step": 66
+    },
+    {
+      "epoch": 0.043584322654090096,
+      "grad_norm": 1.263033456431559,
+      "learning_rate": 9.640287769784174e-05,
+      "loss": 16.5687,
+      "step": 67
+    },
+    {
+      "epoch": 0.04423483493250935,
+      "grad_norm": 1.2347980060019075,
+      "learning_rate": 9.784172661870504e-05,
+      "loss": 16.5912,
+      "step": 68
+    },
+    {
+      "epoch": 0.04488534721092861,
+      "grad_norm": 1.0791126527814534,
+      "learning_rate": 9.928057553956835e-05,
+      "loss": 16.6344,
+      "step": 69
+    },
+    {
+      "epoch": 0.04553585948934786,
+      "grad_norm": 1.3109492738424895,
+      "learning_rate": 0.00010071942446043166,
+      "loss": 17.3385,
+      "step": 70
+    },
+    {
+      "epoch": 0.04618637176776712,
+      "grad_norm": 1.1875024587318612,
+      "learning_rate": 0.00010215827338129497,
+      "loss": 17.0446,
+      "step": 71
+    },
+    {
+      "epoch": 0.04683688404618637,
+      "grad_norm": 1.214560177748547,
+      "learning_rate": 0.00010359712230215827,
+      "loss": 17.1027,
+      "step": 72
+    },
+    {
+      "epoch": 0.04748739632460563,
+      "grad_norm": 1.27365826871933,
+      "learning_rate": 0.00010503597122302158,
+      "loss": 17.0316,
+      "step": 73
+    },
+    {
+      "epoch": 0.04813790860302488,
+      "grad_norm": 1.0107531280233304,
+      "learning_rate": 0.0001064748201438849,
+      "loss": 16.6107,
+      "step": 74
+    },
+    {
+      "epoch": 0.04878842088144414,
+      "grad_norm": 1.0752979288102993,
+      "learning_rate": 0.0001079136690647482,
+      "loss": 16.8372,
+      "step": 75
+    },
+    {
+      "epoch": 0.04943893315986339,
+      "grad_norm": 1.3473200310324882,
+      "learning_rate": 0.00010935251798561152,
+      "loss": 16.2633,
+      "step": 76
+    },
+    {
+      "epoch": 0.05008944543828265,
+      "grad_norm": 0.9976750591019443,
+      "learning_rate": 0.00011079136690647482,
+      "loss": 16.5393,
+      "step": 77
+    },
+    {
+      "epoch": 0.0507399577167019,
+      "grad_norm": 1.140260855010124,
+      "learning_rate": 0.00011223021582733813,
+      "loss": 16.9728,
+      "step": 78
+    },
+    {
+      "epoch": 0.05139046999512116,
+      "grad_norm": 1.2933070425174276,
+      "learning_rate": 0.00011366906474820144,
+      "loss": 17.0574,
+      "step": 79
+    },
+    {
+      "epoch": 0.05204098227354041,
+      "grad_norm": 1.389839896336709,
+      "learning_rate": 0.00011510791366906474,
+      "loss": 17.2136,
+      "step": 80
+    },
+    {
+      "epoch": 0.05269149455195967,
+      "grad_norm": 1.3042181124245171,
+      "learning_rate": 0.00011654676258992807,
+      "loss": 17.0988,
+      "step": 81
+    },
+    {
+      "epoch": 0.05334200683037892,
+      "grad_norm": 1.2402285738075134,
+      "learning_rate": 0.00011798561151079137,
+      "loss": 16.7513,
+      "step": 82
+    },
+    {
+      "epoch": 0.05399251910879818,
+      "grad_norm": 1.1756839248485857,
+      "learning_rate": 0.00011942446043165468,
+      "loss": 16.6371,
+      "step": 83
+    },
+    {
+      "epoch": 0.05464303138721743,
+      "grad_norm": 1.1017265908030667,
+      "learning_rate": 0.00012086330935251799,
+      "loss": 16.6265,
+      "step": 84
+    },
+    {
+      "epoch": 0.05529354366563669,
+      "grad_norm": 1.0733408266004016,
+      "learning_rate": 0.0001223021582733813,
+      "loss": 16.3938,
+      "step": 85
+    },
+    {
+      "epoch": 0.055944055944055944,
+      "grad_norm": 1.2334734635103237,
+      "learning_rate": 0.00012374100719424462,
+      "loss": 17.1788,
+      "step": 86
+    },
+    {
+      "epoch": 0.056594568222475196,
+      "grad_norm": 1.3993193378681297,
+      "learning_rate": 0.00012517985611510793,
+      "loss": 17.1104,
+      "step": 87
+    },
+    {
+      "epoch": 0.057245080500894455,
+      "grad_norm": 1.123524900841842,
+      "learning_rate": 0.00012661870503597123,
+      "loss": 16.6873,
+      "step": 88
+    },
+    {
+      "epoch": 0.057895592779313707,
+      "grad_norm": 1.0866939121943058,
+      "learning_rate": 0.00012805755395683453,
+      "loss": 16.4546,
+      "step": 89
+    },
+    {
+      "epoch": 0.058546105057732965,
+      "grad_norm": 1.2002785909329639,
+      "learning_rate": 0.00012949640287769783,
+      "loss": 16.4714,
+      "step": 90
+    },
+    {
+      "epoch": 0.05919661733615222,
+      "grad_norm": 1.325598788871793,
+      "learning_rate": 0.00013093525179856116,
+      "loss": 16.7844,
+      "step": 91
+    },
+    {
+      "epoch": 0.059847129614571476,
+      "grad_norm": 1.2716044573613756,
+      "learning_rate": 0.00013237410071942446,
+      "loss": 16.7685,
+      "step": 92
+    },
+    {
+      "epoch": 0.06049764189299073,
+      "grad_norm": 1.592624541274254,
+      "learning_rate": 0.00013381294964028776,
+      "loss": 16.3279,
+      "step": 93
+    },
+    {
+      "epoch": 0.06114815417140999,
+      "grad_norm": 1.1888045611874833,
+      "learning_rate": 0.0001352517985611511,
+      "loss": 16.8773,
+      "step": 94
+    },
+    {
+      "epoch": 0.06179866644982924,
+      "grad_norm": 1.1304868799760661,
+      "learning_rate": 0.0001366906474820144,
+      "loss": 16.549,
+      "step": 95
+    },
+    {
+      "epoch": 0.0624491787282485,
+      "grad_norm": 1.281816060679092,
+      "learning_rate": 0.00013812949640287772,
+      "loss": 16.5085,
+      "step": 96
+    },
+    {
+      "epoch": 0.06309969100666775,
+      "grad_norm": 1.279734938210875,
+      "learning_rate": 0.000139568345323741,
+      "loss": 16.5126,
+      "step": 97
+    },
+    {
+      "epoch": 0.063750203285087,
+      "grad_norm": 1.344628171405415,
+      "learning_rate": 0.0001410071942446043,
+      "loss": 16.9847,
+      "step": 98
+    },
+    {
+      "epoch": 0.06440071556350627,
+      "grad_norm": 1.545187456825628,
+      "learning_rate": 0.00014244604316546763,
+      "loss": 16.1767,
+      "step": 99
+    },
+    {
+      "epoch": 0.06505122784192552,
+      "grad_norm": 1.1709031589550802,
+      "learning_rate": 0.00014388489208633093,
+      "loss": 16.6085,
+      "step": 100
+    },
+    {
+      "epoch": 0.06570174012034477,
+      "grad_norm": 1.393257097361909,
+      "learning_rate": 0.00014532374100719426,
+      "loss": 16.8053,
+      "step": 101
+    },
+    {
+      "epoch": 0.06635225239876402,
+      "grad_norm": 1.2394244999375903,
+      "learning_rate": 0.00014676258992805756,
+      "loss": 16.0928,
+      "step": 102
+    },
+    {
+      "epoch": 0.06700276467718329,
+      "grad_norm": 1.1930709723876223,
+      "learning_rate": 0.00014820143884892087,
+      "loss": 16.3948,
+      "step": 103
+    },
+    {
+      "epoch": 0.06765327695560254,
+      "grad_norm": 1.4604414423568501,
+      "learning_rate": 0.0001496402877697842,
+      "loss": 16.4568,
+      "step": 104
+    },
+    {
+      "epoch": 0.06830378923402179,
+      "grad_norm": 1.443578551786741,
+      "learning_rate": 0.00015107913669064747,
+      "loss": 16.5166,
+      "step": 105
+    },
+    {
+      "epoch": 0.06895430151244104,
+      "grad_norm": 1.1518933700116423,
+      "learning_rate": 0.0001525179856115108,
+      "loss": 16.3,
+      "step": 106
+    },
+    {
+      "epoch": 0.06960481379086031,
+      "grad_norm": 1.542483343842307,
+      "learning_rate": 0.0001539568345323741,
+      "loss": 16.9024,
+      "step": 107
+    },
+    {
+      "epoch": 0.07025532606927956,
+      "grad_norm": 1.258054075736978,
+      "learning_rate": 0.00015539568345323743,
+      "loss": 16.2683,
+      "step": 108
+    },
+    {
+      "epoch": 0.07090583834769881,
+      "grad_norm": 1.6150884165278452,
+      "learning_rate": 0.00015683453237410073,
+      "loss": 16.5888,
+      "step": 109
+    },
+    {
+      "epoch": 0.07155635062611806,
+      "grad_norm": 1.449118851982076,
+      "learning_rate": 0.00015827338129496403,
+      "loss": 16.8165,
+      "step": 110
+    },
+    {
+      "epoch": 0.07220686290453732,
+      "grad_norm": 1.128094016574892,
+      "learning_rate": 0.00015971223021582736,
+      "loss": 16.1181,
+      "step": 111
+    },
+    {
+      "epoch": 0.07285737518295658,
+      "grad_norm": 1.338715747211773,
+      "learning_rate": 0.00016115107913669067,
+      "loss": 16.2324,
+      "step": 112
+    },
+    {
+      "epoch": 0.07350788746137583,
+      "grad_norm": 1.2823514695284481,
+      "learning_rate": 0.00016258992805755397,
+      "loss": 16.6262,
+      "step": 113
+    },
+    {
+      "epoch": 0.07415839973979509,
+      "grad_norm": 1.5052281683955466,
+      "learning_rate": 0.00016402877697841727,
+      "loss": 16.8457,
+      "step": 114
+    },
+    {
+      "epoch": 0.07480891201821434,
+      "grad_norm": 1.0584967598938566,
+      "learning_rate": 0.00016546762589928057,
+      "loss": 16.2674,
+      "step": 115
+    },
+    {
+      "epoch": 0.0754594242966336,
+      "grad_norm": 1.19530515172656,
+      "learning_rate": 0.0001669064748201439,
+      "loss": 16.3831,
+      "step": 116
+    },
+    {
+      "epoch": 0.07610993657505286,
+      "grad_norm": 1.3823269723152116,
+      "learning_rate": 0.0001683453237410072,
+      "loss": 16.0168,
+      "step": 117
+    },
+    {
+      "epoch": 0.07676044885347211,
+      "grad_norm": 1.1326747997852689,
+      "learning_rate": 0.00016978417266187053,
+      "loss": 16.5556,
+      "step": 118
+    },
+    {
+      "epoch": 0.07741096113189136,
+      "grad_norm": 1.4782960584362579,
+      "learning_rate": 0.00017122302158273383,
+      "loss": 16.1571,
+      "step": 119
+    },
+    {
+      "epoch": 0.07806147341031063,
+      "grad_norm": 1.1412483235812583,
+      "learning_rate": 0.00017266187050359714,
+      "loss": 16.7017,
+      "step": 120
+    },
+    {
+      "epoch": 0.07871198568872988,
+      "grad_norm": 1.157134336094669,
+      "learning_rate": 0.00017410071942446044,
+      "loss": 15.9355,
+      "step": 121
+    },
+    {
+      "epoch": 0.07936249796714913,
+      "grad_norm": 1.2596042075299902,
+      "learning_rate": 0.00017553956834532374,
+      "loss": 16.1794,
+      "step": 122
+    },
+    {
+      "epoch": 0.08001301024556838,
+      "grad_norm": 1.2772290231565924,
+      "learning_rate": 0.00017697841726618707,
+      "loss": 16.4033,
+      "step": 123
+    },
+    {
+      "epoch": 0.08066352252398765,
+      "grad_norm": 1.1151767474693137,
+      "learning_rate": 0.00017841726618705037,
+      "loss": 16.2436,
+      "step": 124
+    },
+    {
+      "epoch": 0.0813140348024069,
+      "grad_norm": 1.1798680876713907,
+      "learning_rate": 0.00017985611510791367,
+      "loss": 16.3236,
+      "step": 125
+    },
+    {
+      "epoch": 0.08196454708082615,
+      "grad_norm": 1.3267769421108575,
+      "learning_rate": 0.000181294964028777,
+      "loss": 16.5717,
+      "step": 126
+    },
+    {
+      "epoch": 0.0826150593592454,
+      "grad_norm": 1.1581704541921807,
+      "learning_rate": 0.0001827338129496403,
+      "loss": 16.3513,
+      "step": 127
+    },
+    {
+      "epoch": 0.08326557163766467,
+      "grad_norm": 1.1159863796317613,
+      "learning_rate": 0.0001841726618705036,
+      "loss": 16.3247,
+      "step": 128
+    },
+    {
+      "epoch": 0.08391608391608392,
+      "grad_norm": 1.382427396057904,
+      "learning_rate": 0.0001856115107913669,
+      "loss": 16.3353,
+      "step": 129
+    },
+    {
+      "epoch": 0.08456659619450317,
+      "grad_norm": 1.3108697331353616,
+      "learning_rate": 0.0001870503597122302,
+      "loss": 16.1073,
+      "step": 130
+    },
+    {
+      "epoch": 0.08521710847292242,
+      "grad_norm": 1.334059821814415,
+      "learning_rate": 0.00018848920863309354,
+      "loss": 16.6671,
+      "step": 131
+    },
+    {
+      "epoch": 0.08586762075134168,
+      "grad_norm": 1.0908085686681828,
+      "learning_rate": 0.00018992805755395684,
+      "loss": 16.0294,
+      "step": 132
+    },
+    {
+      "epoch": 0.08651813302976094,
+      "grad_norm": 1.2959343742729015,
+      "learning_rate": 0.00019136690647482017,
+      "loss": 16.223,
+      "step": 133
+    },
+    {
+      "epoch": 0.08716864530818019,
+      "grad_norm": 1.1047169830611183,
+      "learning_rate": 0.00019280575539568347,
+      "loss": 16.056,
+      "step": 134
+    },
+    {
+      "epoch": 0.08781915758659944,
+      "grad_norm": 1.1140635817897093,
+      "learning_rate": 0.00019424460431654677,
+      "loss": 16.2575,
+      "step": 135
+    },
+    {
+      "epoch": 0.0884696698650187,
+      "grad_norm": 1.04162967240226,
+      "learning_rate": 0.00019568345323741008,
+      "loss": 15.9829,
+      "step": 136
+    },
+    {
+      "epoch": 0.08912018214343796,
+      "grad_norm": 1.1761240919823441,
+      "learning_rate": 0.00019712230215827338,
+      "loss": 16.2074,
+      "step": 137
+    },
+    {
+      "epoch": 0.08977069442185721,
+      "grad_norm": 1.4060425455840306,
+      "learning_rate": 0.0001985611510791367,
+      "loss": 16.1239,
+      "step": 138
+    },
+    {
+      "epoch": 0.09042120670027647,
+      "grad_norm": 1.435373460153808,
+      "learning_rate": 0.0002,
+      "loss": 16.1211,
+      "step": 139
+    },
+    {
+      "epoch": 0.09107171897869572,
+      "grad_norm": 1.2857137989530858,
+      "learning_rate": 0.00019999997532448976,
+      "loss": 16.4245,
+      "step": 140
+    },
+    {
+      "epoch": 0.09172223125711498,
+      "grad_norm": 1.1369350028631544,
+      "learning_rate": 0.00019999990129797115,
+      "loss": 16.0879,
+      "step": 141
+    },
+    {
+      "epoch": 0.09237274353553424,
+      "grad_norm": 1.5692988291240053,
+      "learning_rate": 0.00019999977792048074,
+      "loss": 16.295,
+      "step": 142
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 1.1485054343733085,
+      "learning_rate": 0.00019999960519207944,
+      "loss": 15.9654,
+      "step": 143
+    },
+    {
+      "epoch": 0.09367376809237274,
+      "grad_norm": 1.2691183484733912,
+      "learning_rate": 0.00019999938311285242,
+      "loss": 16.1865,
+      "step": 144
+    },
+    {
+      "epoch": 0.094324280370792,
+      "grad_norm": 1.2296350651328132,
+      "learning_rate": 0.00019999911168290933,
+      "loss": 16.5049,
+      "step": 145
+    },
+    {
+      "epoch": 0.09497479264921126,
+      "grad_norm": 1.29674174881806,
+      "learning_rate": 0.00019999879090238412,
+      "loss": 16.4973,
+      "step": 146
+    },
+    {
+      "epoch": 0.09562530492763051,
+      "grad_norm": 1.2163093953815163,
+      "learning_rate": 0.00019999842077143512,
+      "loss": 16.0886,
+      "step": 147
+    },
+    {
+      "epoch": 0.09627581720604976,
+      "grad_norm": 1.102167587738724,
+      "learning_rate": 0.00019999800129024493,
+      "loss": 16.2596,
+      "step": 148
+    },
+    {
+      "epoch": 0.09692632948446903,
+      "grad_norm": 1.2962346828275186,
+      "learning_rate": 0.00019999753245902063,
+      "loss": 15.9227,
+      "step": 149
+    },
+    {
+      "epoch": 0.09757684176288828,
+      "grad_norm": 1.396967329301785,
+      "learning_rate": 0.00019999701427799354,
+      "loss": 16.4865,
+      "step": 150
+    },
+    {
+      "epoch": 0.09822735404130753,
+      "grad_norm": 1.4714923520577858,
+      "learning_rate": 0.00019999644674741944,
+      "loss": 16.9116,
+      "step": 151
+    },
+    {
+      "epoch": 0.09887786631972678,
+      "grad_norm": 1.3751033752663124,
+      "learning_rate": 0.00019999582986757842,
+      "loss": 16.2383,
+      "step": 152
+    },
+    {
+      "epoch": 0.09952837859814603,
+      "grad_norm": 1.9739150971571289,
+      "learning_rate": 0.00019999516363877482,
+      "loss": 15.9845,
+      "step": 153
+    },
+    {
+      "epoch": 0.1001788908765653,
+      "grad_norm": 1.3584998682938432,
+      "learning_rate": 0.00019999444806133754,
+      "loss": 16.8096,
+      "step": 154
+    },
+    {
+      "epoch": 0.10082940315498455,
+      "grad_norm": 1.220625597864733,
+      "learning_rate": 0.00019999368313561967,
+      "loss": 15.9965,
+      "step": 155
+    },
+    {
+      "epoch": 0.1014799154334038,
+      "grad_norm": 1.2378184674625017,
+      "learning_rate": 0.0001999928688619987,
+      "loss": 16.0512,
+      "step": 156
+    },
+    {
+      "epoch": 0.10213042771182305,
+      "grad_norm": 1.4456186669948223,
+      "learning_rate": 0.00019999200524087655,
+      "loss": 16.0118,
+      "step": 157
+    },
+    {
+      "epoch": 0.10278093999024232,
+      "grad_norm": 1.1587926959313264,
+      "learning_rate": 0.0001999910922726793,
+      "loss": 16.16,
+      "step": 158
+    },
+    {
+      "epoch": 0.10343145226866157,
+      "grad_norm": 1.382929812171896,
+      "learning_rate": 0.00019999012995785764,
+      "loss": 16.0912,
+      "step": 159
+    },
+    {
+      "epoch": 0.10408196454708082,
+      "grad_norm": 1.1829518612500756,
+      "learning_rate": 0.00019998911829688642,
+      "loss": 16.2882,
+      "step": 160
+    },
+    {
+      "epoch": 0.10473247682550008,
+      "grad_norm": 1.1657090296589478,
+      "learning_rate": 0.0001999880572902649,
+      "loss": 16.0731,
+      "step": 161
+    },
+    {
+      "epoch": 0.10538298910391934,
+      "grad_norm": 1.3431787953725638,
+      "learning_rate": 0.00019998694693851673,
+      "loss": 16.1563,
+      "step": 162
+    },
+    {
+      "epoch": 0.1060335013823386,
+      "grad_norm": 1.286415751363148,
+      "learning_rate": 0.00019998578724218986,
+      "loss": 16.223,
+      "step": 163
+    },
+    {
+      "epoch": 0.10668401366075785,
+      "grad_norm": 1.3524624224683564,
+      "learning_rate": 0.00019998457820185662,
+      "loss": 16.3742,
+      "step": 164
+    },
+    {
+      "epoch": 0.1073345259391771,
+      "grad_norm": 1.2171855476147266,
+      "learning_rate": 0.00019998331981811366,
+      "loss": 16.0179,
+      "step": 165
+    },
+    {
+      "epoch": 0.10798503821759636,
+      "grad_norm": 1.2118698328436097,
+      "learning_rate": 0.00019998201209158202,
+      "loss": 15.9204,
+      "step": 166
+    },
+    {
+      "epoch": 0.10863555049601561,
+      "grad_norm": 1.2564460601223888,
+      "learning_rate": 0.00019998065502290708,
+      "loss": 16.3139,
+      "step": 167
+    },
+    {
+      "epoch": 0.10928606277443487,
+      "grad_norm": 1.196796001472763,
+      "learning_rate": 0.00019997924861275856,
+      "loss": 15.7352,
+      "step": 168
+    },
+    {
+      "epoch": 0.10993657505285412,
+      "grad_norm": 1.1113045242286628,
+      "learning_rate": 0.00019997779286183058,
+      "loss": 15.7405,
+      "step": 169
+    },
+    {
+      "epoch": 0.11058708733127338,
+      "grad_norm": 1.3013879690365944,
+      "learning_rate": 0.0001999762877708415,
+      "loss": 16.0834,
+      "step": 170
+    },
+    {
+      "epoch": 0.11123759960969264,
+      "grad_norm": 1.07941672333022,
+      "learning_rate": 0.00019997473334053414,
+      "loss": 15.8096,
+      "step": 171
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "grad_norm": 1.2189404203154124,
+      "learning_rate": 0.0001999731295716756,
+      "loss": 15.8413,
+      "step": 172
+    },
+    {
+      "epoch": 0.11253862416653114,
+      "grad_norm": 1.1217077885714701,
+      "learning_rate": 0.0001999714764650574,
+      "loss": 15.5043,
+      "step": 173
+    },
+    {
+      "epoch": 0.11318913644495039,
+      "grad_norm": 1.513584542451282,
+      "learning_rate": 0.00019996977402149532,
+      "loss": 16.3455,
+      "step": 174
+    },
+    {
+      "epoch": 0.11383964872336966,
+      "grad_norm": 1.0817122117553408,
+      "learning_rate": 0.00019996802224182955,
+      "loss": 15.7012,
+      "step": 175
+    },
+    {
+      "epoch": 0.11449016100178891,
+      "grad_norm": 1.324691330326367,
+      "learning_rate": 0.0001999662211269246,
+      "loss": 15.9273,
+      "step": 176
+    },
+    {
+      "epoch": 0.11514067328020816,
+      "grad_norm": 1.3215782457245966,
+      "learning_rate": 0.00019996437067766934,
+      "loss": 16.0986,
+      "step": 177
+    },
+    {
+      "epoch": 0.11579118555862741,
+      "grad_norm": 1.4703639596592368,
+      "learning_rate": 0.00019996247089497704,
+      "loss": 16.1822,
+      "step": 178
+    },
+    {
+      "epoch": 0.11644169783704668,
+      "grad_norm": 1.2847301169754652,
+      "learning_rate": 0.00019996052177978518,
+      "loss": 15.9505,
+      "step": 179
+    },
+    {
+      "epoch": 0.11709221011546593,
+      "grad_norm": 1.0558955151390819,
+      "learning_rate": 0.00019995852333305574,
+      "loss": 15.6614,
+      "step": 180
+    },
+    {
+      "epoch": 0.11774272239388518,
+      "grad_norm": 1.31688233510127,
+      "learning_rate": 0.00019995647555577493,
+      "loss": 15.9143,
+      "step": 181
+    },
+    {
+      "epoch": 0.11839323467230443,
+      "grad_norm": 1.2061862180760066,
+      "learning_rate": 0.00019995437844895334,
+      "loss": 15.937,
+      "step": 182
+    },
+    {
+      "epoch": 0.1190437469507237,
+      "grad_norm": 1.0318962032993502,
+      "learning_rate": 0.00019995223201362596,
+      "loss": 15.7216,
+      "step": 183
+    },
+    {
+      "epoch": 0.11969425922914295,
+      "grad_norm": 1.5397925755718855,
+      "learning_rate": 0.00019995003625085205,
+      "loss": 15.9159,
+      "step": 184
+    },
+    {
+      "epoch": 0.1203447715075622,
+      "grad_norm": 1.0987925269830472,
+      "learning_rate": 0.00019994779116171523,
+      "loss": 15.7912,
+      "step": 185
+    },
+    {
+      "epoch": 0.12099528378598146,
+      "grad_norm": 1.4715941056192134,
+      "learning_rate": 0.00019994549674732346,
+      "loss": 16.129,
+      "step": 186
+    },
+    {
+      "epoch": 0.12164579606440072,
+      "grad_norm": 1.7015469371715195,
+      "learning_rate": 0.00019994315300880913,
+      "loss": 15.8515,
+      "step": 187
+    },
+    {
+      "epoch": 0.12229630834281997,
+      "grad_norm": 1.061978383849765,
+      "learning_rate": 0.00019994075994732882,
+      "loss": 15.7249,
+      "step": 188
+    },
+    {
+      "epoch": 0.12294682062123923,
+      "grad_norm": 1.5000616407143508,
+      "learning_rate": 0.00019993831756406357,
+      "loss": 16.1291,
+      "step": 189
+    },
+    {
+      "epoch": 0.12359733289965848,
+      "grad_norm": 1.7317319938917977,
+      "learning_rate": 0.00019993582586021872,
+      "loss": 16.5245,
+      "step": 190
+    },
+    {
+      "epoch": 0.12424784517807774,
+      "grad_norm": 1.4567802437539563,
+      "learning_rate": 0.00019993328483702393,
+      "loss": 16.0243,
+      "step": 191
+    },
+    {
+      "epoch": 0.124898357456497,
+      "grad_norm": 1.646019034772813,
+      "learning_rate": 0.00019993069449573327,
+      "loss": 15.8246,
+      "step": 192
+    },
+    {
+      "epoch": 0.12554886973491625,
+      "grad_norm": 1.497968977752877,
+      "learning_rate": 0.00019992805483762504,
+      "loss": 16.0007,
+      "step": 193
+    },
+    {
+      "epoch": 0.1261993820133355,
+      "grad_norm": 1.568913115134539,
+      "learning_rate": 0.00019992536586400196,
+      "loss": 16.0263,
+      "step": 194
+    },
+    {
+      "epoch": 0.12684989429175475,
+      "grad_norm": 1.2825977002652855,
+      "learning_rate": 0.0001999226275761911,
+      "loss": 16.0314,
+      "step": 195
+    },
+    {
+      "epoch": 0.127500406570174,
+      "grad_norm": 1.4853084052062375,
+      "learning_rate": 0.00019991983997554375,
+      "loss": 15.7547,
+      "step": 196
+    },
+    {
+      "epoch": 0.12815091884859325,
+      "grad_norm": 1.26181446950708,
+      "learning_rate": 0.00019991700306343574,
+      "loss": 15.5768,
+      "step": 197
+    },
+    {
+      "epoch": 0.12880143112701253,
+      "grad_norm": 1.285098535368629,
+      "learning_rate": 0.000199914116841267,
+      "loss": 15.6308,
+      "step": 198
+    },
+    {
+      "epoch": 0.12945194340543179,
+      "grad_norm": 1.4886189500776745,
+      "learning_rate": 0.00019991118131046197,
+      "loss": 15.5099,
+      "step": 199
+    },
+    {
+      "epoch": 0.13010245568385104,
+      "grad_norm": 1.0882097052065223,
+      "learning_rate": 0.00019990819647246934,
+      "loss": 15.7256,
+      "step": 200
+    },
+    {
+      "epoch": 0.1307529679622703,
+      "grad_norm": 1.451712523012117,
+      "learning_rate": 0.00019990516232876217,
+      "loss": 15.9345,
+      "step": 201
+    },
+    {
+      "epoch": 0.13140348024068954,
+      "grad_norm": 1.248174201894127,
+      "learning_rate": 0.00019990207888083785,
+      "loss": 15.6892,
+      "step": 202
+    },
+    {
+      "epoch": 0.1320539925191088,
+      "grad_norm": 1.1442774504969464,
+      "learning_rate": 0.0001998989461302181,
+      "loss": 15.966,
+      "step": 203
+    },
+    {
+      "epoch": 0.13270450479752804,
+      "grad_norm": 1.2854989485926203,
+      "learning_rate": 0.00019989576407844893,
+      "loss": 15.9851,
+      "step": 204
+    },
+    {
+      "epoch": 0.1333550170759473,
+      "grad_norm": 1.2598769052557937,
+      "learning_rate": 0.0001998925327271007,
+      "loss": 15.7369,
+      "step": 205
+    },
+    {
+      "epoch": 0.13400552935436658,
+      "grad_norm": 1.3508148889233056,
+      "learning_rate": 0.00019988925207776822,
+      "loss": 16.2724,
+      "step": 206
+    },
+    {
+      "epoch": 0.13465604163278583,
+      "grad_norm": 1.2543662968540914,
+      "learning_rate": 0.0001998859221320704,
+      "loss": 15.6903,
+      "step": 207
+    },
+    {
+      "epoch": 0.13530655391120508,
+      "grad_norm": 1.3580852914632515,
+      "learning_rate": 0.00019988254289165068,
+      "loss": 15.8562,
+      "step": 208
+    },
+    {
+      "epoch": 0.13595706618962433,
+      "grad_norm": 1.1129940569954546,
+      "learning_rate": 0.0001998791143581767,
+      "loss": 15.8507,
+      "step": 209
+    },
+    {
+      "epoch": 0.13660757846804358,
+      "grad_norm": 1.005036890256765,
+      "learning_rate": 0.00019987563653334052,
+      "loss": 15.6289,
+      "step": 210
+    },
+    {
+      "epoch": 0.13725809074646284,
+      "grad_norm": 1.509494723127827,
+      "learning_rate": 0.00019987210941885844,
+      "loss": 15.5293,
+      "step": 211
+    },
+    {
+      "epoch": 0.1379086030248821,
+      "grad_norm": 1.0933249835745373,
+      "learning_rate": 0.00019986853301647118,
+      "loss": 15.7172,
+      "step": 212
+    },
+    {
+      "epoch": 0.13855911530330134,
+      "grad_norm": 1.3233215085626935,
+      "learning_rate": 0.00019986490732794366,
+      "loss": 15.902,
+      "step": 213
+    },
+    {
+      "epoch": 0.13920962758172062,
+      "grad_norm": 1.4004958895369275,
+      "learning_rate": 0.00019986123235506527,
+      "loss": 16.1623,
+      "step": 214
+    },
+    {
+      "epoch": 0.13986013986013987,
+      "grad_norm": 1.1345262168078565,
+      "learning_rate": 0.0001998575080996496,
+      "loss": 15.8426,
+      "step": 215
+    },
+    {
+      "epoch": 0.14051065213855912,
+      "grad_norm": 1.3274606810342473,
+      "learning_rate": 0.0001998537345635346,
+      "loss": 15.7356,
+      "step": 216
+    },
+    {
+      "epoch": 0.14116116441697837,
+      "grad_norm": 1.1335953463026522,
+      "learning_rate": 0.00019984991174858257,
+      "loss": 16.0681,
+      "step": 217
+    },
+    {
+      "epoch": 0.14181167669539763,
+      "grad_norm": 1.139268993686519,
+      "learning_rate": 0.00019984603965668014,
+      "loss": 15.6382,
+      "step": 218
+    },
+    {
+      "epoch": 0.14246218897381688,
+      "grad_norm": 1.2850079050869794,
+      "learning_rate": 0.00019984211828973818,
+      "loss": 15.7931,
+      "step": 219
+    },
+    {
+      "epoch": 0.14311270125223613,
+      "grad_norm": 1.160212512429598,
+      "learning_rate": 0.0001998381476496919,
+      "loss": 15.9299,
+      "step": 220
+    },
+    {
+      "epoch": 0.14376321353065538,
+      "grad_norm": 1.1564836237836946,
+      "learning_rate": 0.00019983412773850095,
+      "loss": 15.5794,
+      "step": 221
+    },
+    {
+      "epoch": 0.14441372580907463,
+      "grad_norm": 1.3183934970924405,
+      "learning_rate": 0.0001998300585581491,
+      "loss": 15.6865,
+      "step": 222
+    },
+    {
+      "epoch": 0.1450642380874939,
+      "grad_norm": 1.1357155370384815,
+      "learning_rate": 0.00019982594011064454,
+      "loss": 15.6368,
+      "step": 223
+    },
+    {
+      "epoch": 0.14571475036591316,
+      "grad_norm": 1.2387068766768285,
+      "learning_rate": 0.00019982177239801985,
+      "loss": 15.6648,
+      "step": 224
+    },
+    {
+      "epoch": 0.14636526264433242,
+      "grad_norm": 1.1694436074329784,
+      "learning_rate": 0.00019981755542233177,
+      "loss": 15.7061,
+      "step": 225
+    },
+    {
+      "epoch": 0.14701577492275167,
+      "grad_norm": 1.3752125556000327,
+      "learning_rate": 0.0001998132891856614,
+      "loss": 15.7798,
+      "step": 226
+    },
+    {
+      "epoch": 0.14766628720117092,
+      "grad_norm": 1.1806090978543626,
+      "learning_rate": 0.0001998089736901142,
+      "loss": 15.7428,
+      "step": 227
+    },
+    {
+      "epoch": 0.14831679947959017,
+      "grad_norm": 1.0049551357886353,
+      "learning_rate": 0.00019980460893781997,
+      "loss": 15.5933,
+      "step": 228
+    },
+    {
+      "epoch": 0.14896731175800942,
+      "grad_norm": 1.5622852573666057,
+      "learning_rate": 0.00019980019493093267,
+      "loss": 15.7534,
+      "step": 229
+    },
+    {
+      "epoch": 0.14961782403642868,
+      "grad_norm": 1.1013069862391307,
+      "learning_rate": 0.0001997957316716307,
+      "loss": 15.8864,
+      "step": 230
+    },
+    {
+      "epoch": 0.15026833631484796,
+      "grad_norm": 1.4734225284779912,
+      "learning_rate": 0.0001997912191621167,
+      "loss": 15.9077,
+      "step": 231
+    },
+    {
+      "epoch": 0.1509188485932672,
+      "grad_norm": 1.399096561174609,
+      "learning_rate": 0.0001997866574046177,
+      "loss": 16.0059,
+      "step": 232
+    },
+    {
+      "epoch": 0.15156936087168646,
+      "grad_norm": 1.2481511742493503,
+      "learning_rate": 0.0001997820464013849,
+      "loss": 15.2446,
+      "step": 233
+    },
+    {
+      "epoch": 0.1522198731501057,
+      "grad_norm": 1.6450876422634797,
+      "learning_rate": 0.0001997773861546939,
+      "loss": 16.0028,
+      "step": 234
+    },
+    {
+      "epoch": 0.15287038542852496,
+      "grad_norm": 1.0380768921041443,
+      "learning_rate": 0.00019977267666684457,
+      "loss": 15.3622,
+      "step": 235
+    },
+    {
+      "epoch": 0.15352089770694421,
+      "grad_norm": 1.2565913626851373,
+      "learning_rate": 0.00019976791794016117,
+      "loss": 15.775,
+      "step": 236
+    },
+    {
+      "epoch": 0.15417140998536347,
+      "grad_norm": 1.398698374732754,
+      "learning_rate": 0.00019976310997699205,
+      "loss": 15.8167,
+      "step": 237
+    },
+    {
+      "epoch": 0.15482192226378272,
+      "grad_norm": 1.1787392685770026,
+      "learning_rate": 0.0001997582527797101,
+      "loss": 15.8554,
+      "step": 238
+    },
+    {
+      "epoch": 0.15547243454220197,
+      "grad_norm": 1.3270571453839568,
+      "learning_rate": 0.00019975334635071232,
+      "loss": 15.7601,
+      "step": 239
+    },
+    {
+      "epoch": 0.15612294682062125,
+      "grad_norm": 1.2295651996201515,
+      "learning_rate": 0.00019974839069242015,
+      "loss": 15.6391,
+      "step": 240
+    },
+    {
+      "epoch": 0.1567734590990405,
+      "grad_norm": 1.0502031908208234,
+      "learning_rate": 0.0001997433858072792,
+      "loss": 15.8405,
+      "step": 241
+    },
+    {
+      "epoch": 0.15742397137745975,
+      "grad_norm": 1.1796601461857301,
+      "learning_rate": 0.00019973833169775946,
+      "loss": 15.5497,
+      "step": 242
+    },
+    {
+      "epoch": 0.158074483655879,
+      "grad_norm": 1.1033706215539105,
+      "learning_rate": 0.00019973322836635518,
+      "loss": 15.2697,
+      "step": 243
+    },
+    {
+      "epoch": 0.15872499593429826,
+      "grad_norm": 1.180610347776812,
+      "learning_rate": 0.0001997280758155849,
+      "loss": 15.4631,
+      "step": 244
+    },
+    {
+      "epoch": 0.1593755082127175,
+      "grad_norm": 1.0436311275513237,
+      "learning_rate": 0.00019972287404799145,
+      "loss": 15.7433,
+      "step": 245
+    },
+    {
+      "epoch": 0.16002602049113676,
+      "grad_norm": 1.0450076005845481,
+      "learning_rate": 0.000199717623066142,
+      "loss": 15.6038,
+      "step": 246
+    },
+    {
+      "epoch": 0.160676532769556,
+      "grad_norm": 1.165903104531965,
+      "learning_rate": 0.00019971232287262791,
+      "loss": 15.5662,
+      "step": 247
+    },
+    {
+      "epoch": 0.1613270450479753,
+      "grad_norm": 1.186296885036838,
+      "learning_rate": 0.0001997069734700649,
+      "loss": 15.4763,
+      "step": 248
+    },
+    {
+      "epoch": 0.16197755732639454,
+      "grad_norm": 1.1539223101931702,
+      "learning_rate": 0.00019970157486109296,
+      "loss": 15.7241,
+      "step": 249
+    },
+    {
+      "epoch": 0.1626280696048138,
+      "grad_norm": 1.2132859734806392,
+      "learning_rate": 0.00019969612704837637,
+      "loss": 16.0917,
+      "step": 250
+    },
+    {
+      "epoch": 0.16327858188323305,
+      "grad_norm": 1.0821830202131588,
+      "learning_rate": 0.00019969063003460365,
+      "loss": 15.5398,
+      "step": 251
+    },
+    {
+      "epoch": 0.1639290941616523,
+      "grad_norm": 1.244868666859934,
+      "learning_rate": 0.00019968508382248764,
+      "loss": 15.5666,
+      "step": 252
+    },
+    {
+      "epoch": 0.16457960644007155,
+      "grad_norm": 2.263981258987727,
+      "learning_rate": 0.00019967948841476547,
+      "loss": 15.7368,
+      "step": 253
+    },
+    {
+      "epoch": 0.1652301187184908,
+      "grad_norm": 1.1565365134953118,
+      "learning_rate": 0.0001996738438141985,
+      "loss": 15.5713,
+      "step": 254
+    },
+    {
+      "epoch": 0.16588063099691006,
+      "grad_norm": 1.1165211977873781,
+      "learning_rate": 0.0001996681500235724,
+      "loss": 15.6568,
+      "step": 255
+    },
+    {
+      "epoch": 0.16653114327532934,
+      "grad_norm": 0.9788467313445461,
+      "learning_rate": 0.0001996624070456972,
+      "loss": 15.5042,
+      "step": 256
+    },
+    {
+      "epoch": 0.1671816555537486,
+      "grad_norm": 0.9826896223207806,
+      "learning_rate": 0.000199656614883407,
+      "loss": 15.4805,
+      "step": 257
+    },
+    {
+      "epoch": 0.16783216783216784,
+      "grad_norm": 1.0905115389162074,
+      "learning_rate": 0.00019965077353956037,
+      "loss": 15.3941,
+      "step": 258
+    },
+    {
+      "epoch": 0.1684826801105871,
+      "grad_norm": 0.98546216373064,
+      "learning_rate": 0.00019964488301704004,
+      "loss": 15.4301,
+      "step": 259
+    },
+    {
+      "epoch": 0.16913319238900634,
+      "grad_norm": 1.1256941726193515,
+      "learning_rate": 0.000199638943318753,
+      "loss": 15.7414,
+      "step": 260
+    },
+    {
+      "epoch": 0.1697837046674256,
+      "grad_norm": 1.3308895328622432,
+      "learning_rate": 0.00019963295444763067,
+      "loss": 15.7021,
+      "step": 261
+    },
+    {
+      "epoch": 0.17043421694584485,
+      "grad_norm": 1.0648758361297501,
+      "learning_rate": 0.00019962691640662848,
+      "loss": 15.6834,
+      "step": 262
+    },
+    {
+      "epoch": 0.1710847292242641,
+      "grad_norm": 1.1217280323593837,
+      "learning_rate": 0.0001996208291987264,
+      "loss": 15.299,
+      "step": 263
+    },
+    {
+      "epoch": 0.17173524150268335,
+      "grad_norm": 1.0777338529064635,
+      "learning_rate": 0.00019961469282692843,
+      "loss": 15.7405,
+      "step": 264
+    },
+    {
+      "epoch": 0.17238575378110263,
+      "grad_norm": 1.0921171125112286,
+      "learning_rate": 0.00019960850729426296,
+      "loss": 15.8917,
+      "step": 265
+    },
+    {
+      "epoch": 0.17303626605952188,
+      "grad_norm": 1.0636232587607821,
+      "learning_rate": 0.00019960227260378262,
+      "loss": 15.5672,
+      "step": 266
+    },
+    {
+      "epoch": 0.17368677833794113,
+      "grad_norm": 0.9709478105073301,
+      "learning_rate": 0.00019959598875856428,
+      "loss": 15.4767,
+      "step": 267
+    },
+    {
+      "epoch": 0.17433729061636039,
+      "grad_norm": 0.9225604495203942,
+      "learning_rate": 0.00019958965576170908,
+      "loss": 15.3612,
+      "step": 268
+    },
+    {
+      "epoch": 0.17498780289477964,
+      "grad_norm": 1.2829510178625863,
+      "learning_rate": 0.00019958327361634248,
+      "loss": 15.8089,
+      "step": 269
+    },
+    {
+      "epoch": 0.1756383151731989,
+      "grad_norm": 1.0061809674752291,
+      "learning_rate": 0.00019957684232561407,
+      "loss": 16.0094,
+      "step": 270
+    },
+    {
+      "epoch": 0.17628882745161814,
+      "grad_norm": 1.0911515570358572,
+      "learning_rate": 0.00019957036189269776,
+      "loss": 15.6031,
+      "step": 271
+    },
+    {
+      "epoch": 0.1769393397300374,
+      "grad_norm": 1.0647175528581065,
+      "learning_rate": 0.00019956383232079173,
+      "loss": 15.3612,
+      "step": 272
+    },
+    {
+      "epoch": 0.17758985200845667,
+      "grad_norm": 0.9314507267522828,
+      "learning_rate": 0.00019955725361311835,
+      "loss": 15.4872,
+      "step": 273
+    },
+    {
+      "epoch": 0.17824036428687592,
+      "grad_norm": 0.9745800587898155,
+      "learning_rate": 0.00019955062577292436,
+      "loss": 15.6846,
+      "step": 274
+    },
+    {
+      "epoch": 0.17889087656529518,
+      "grad_norm": 0.9322809006250521,
+      "learning_rate": 0.0001995439488034806,
+      "loss": 15.5122,
+      "step": 275
+    },
+    {
+      "epoch": 0.17954138884371443,
+      "grad_norm": 1.1374216946678781,
+      "learning_rate": 0.00019953722270808224,
+      "loss": 15.7092,
+      "step": 276
+    },
+    {
+      "epoch": 0.18019190112213368,
+      "grad_norm": 0.9874955156623716,
+      "learning_rate": 0.0001995304474900487,
+      "loss": 15.6445,
+      "step": 277
+    },
+    {
+      "epoch": 0.18084241340055293,
+      "grad_norm": 1.129401416897606,
+      "learning_rate": 0.00019952362315272355,
+      "loss": 16.0622,
+      "step": 278
+    },
+    {
+      "epoch": 0.18149292567897218,
+      "grad_norm": 0.9952226967332999,
+      "learning_rate": 0.00019951674969947476,
+      "loss": 15.3702,
+      "step": 279
+    },
+    {
+      "epoch": 0.18214343795739144,
+      "grad_norm": 1.0805351875193883,
+      "learning_rate": 0.00019950982713369436,
+      "loss": 15.6949,
+      "step": 280
+    },
+    {
+      "epoch": 0.1827939502358107,
+      "grad_norm": 1.479211550334586,
+      "learning_rate": 0.0001995028554587988,
+      "loss": 15.6463,
+      "step": 281
+    },
+    {
+      "epoch": 0.18344446251422997,
+      "grad_norm": 1.1907443194761225,
+      "learning_rate": 0.0001994958346782286,
+      "loss": 15.5587,
+      "step": 282
+    },
+    {
+      "epoch": 0.18409497479264922,
+      "grad_norm": 1.288994990161614,
+      "learning_rate": 0.00019948876479544865,
+      "loss": 15.3665,
+      "step": 283
+    },
+    {
+      "epoch": 0.18474548707106847,
+      "grad_norm": 1.059949796221308,
+      "learning_rate": 0.00019948164581394794,
+      "loss": 15.5551,
+      "step": 284
+    },
+    {
+      "epoch": 0.18539599934948772,
+      "grad_norm": 1.0406627346471329,
+      "learning_rate": 0.0001994744777372398,
+      "loss": 15.6003,
+      "step": 285
+    },
+    {
+      "epoch": 0.18604651162790697,
+      "grad_norm": 1.2391745874247917,
+      "learning_rate": 0.00019946726056886173,
+      "loss": 15.4255,
+      "step": 286
+    },
+    {
+      "epoch": 0.18669702390632623,
+      "grad_norm": 1.0469637594333425,
+      "learning_rate": 0.0001994599943123755,
+      "loss": 15.6554,
+      "step": 287
+    },
+    {
+      "epoch": 0.18734753618474548,
+      "grad_norm": 0.9959039455851394,
+      "learning_rate": 0.00019945267897136706,
+      "loss": 15.4941,
+      "step": 288
+    },
+    {
+      "epoch": 0.18799804846316473,
+      "grad_norm": 1.0776449949330023,
+      "learning_rate": 0.00019944531454944663,
+      "loss": 15.4861,
+      "step": 289
+    },
+    {
+      "epoch": 0.188648560741584,
+      "grad_norm": 1.1197322613582776,
+      "learning_rate": 0.0001994379010502486,
+      "loss": 15.6993,
+      "step": 290
+    },
+    {
+      "epoch": 0.18929907302000326,
+      "grad_norm": 1.0686488594196952,
+      "learning_rate": 0.00019943043847743164,
+      "loss": 15.54,
+      "step": 291
+    },
+    {
+      "epoch": 0.1899495852984225,
+      "grad_norm": 0.9617912923122541,
+      "learning_rate": 0.00019942292683467855,
+      "loss": 15.4895,
+      "step": 292
+    },
+    {
+      "epoch": 0.19060009757684176,
+      "grad_norm": 1.0579923780511618,
+      "learning_rate": 0.00019941536612569648,
+      "loss": 15.2509,
+      "step": 293
+    },
+    {
+      "epoch": 0.19125060985526102,
+      "grad_norm": 1.4058152085853566,
+      "learning_rate": 0.00019940775635421667,
+      "loss": 15.3219,
+      "step": 294
+    },
+    {
+      "epoch": 0.19190112213368027,
+      "grad_norm": 0.9739768600771829,
+      "learning_rate": 0.0001994000975239946,
+      "loss": 15.3109,
+      "step": 295
+    },
+    {
+      "epoch": 0.19255163441209952,
+      "grad_norm": 1.0197135876111694,
+      "learning_rate": 0.00019939238963881002,
+      "loss": 15.2957,
+      "step": 296
+    },
+    {
+      "epoch": 0.19320214669051877,
+      "grad_norm": 1.0921071471931543,
+      "learning_rate": 0.00019938463270246682,
+      "loss": 15.3264,
+      "step": 297
+    },
+    {
+      "epoch": 0.19385265896893805,
+      "grad_norm": 1.1034846857134457,
+      "learning_rate": 0.00019937682671879316,
+      "loss": 15.51,
+      "step": 298
+    },
+    {
+      "epoch": 0.1945031712473573,
+      "grad_norm": 0.9561675342652609,
+      "learning_rate": 0.00019936897169164138,
+      "loss": 15.6254,
+      "step": 299
+    },
+    {
+      "epoch": 0.19515368352577656,
+      "grad_norm": 1.2844658924189631,
+      "learning_rate": 0.00019936106762488795,
+      "loss": 15.8538,
+      "step": 300
+    },
+    {
+      "epoch": 0.1958041958041958,
+      "grad_norm": 1.219208771817354,
+      "learning_rate": 0.00019935311452243365,
+      "loss": 15.5888,
+      "step": 301
+    },
+    {
+      "epoch": 0.19645470808261506,
+      "grad_norm": 1.4780700110332101,
+      "learning_rate": 0.00019934511238820345,
+      "loss": 15.7201,
+      "step": 302
+    },
+    {
+      "epoch": 0.1971052203610343,
+      "grad_norm": 1.0226754230294317,
+      "learning_rate": 0.00019933706122614645,
+      "loss": 15.6698,
+      "step": 303
+    },
+    {
+      "epoch": 0.19775573263945356,
+      "grad_norm": 1.1673393340798441,
+      "learning_rate": 0.00019932896104023592,
+      "loss": 15.6362,
+      "step": 304
+    },
+    {
+      "epoch": 0.19840624491787281,
+      "grad_norm": 1.0500020017182747,
+      "learning_rate": 0.0001993208118344695,
+      "loss": 15.2421,
+      "step": 305
+    },
+    {
+      "epoch": 0.19905675719629207,
+      "grad_norm": 0.9516756189471272,
+      "learning_rate": 0.00019931261361286887,
+      "loss": 15.2946,
+      "step": 306
+    },
+    {
+      "epoch": 0.19970726947471135,
+      "grad_norm": 1.02866943504753,
+      "learning_rate": 0.0001993043663794799,
+      "loss": 15.4989,
+      "step": 307
+    },
+    {
+      "epoch": 0.2003577817531306,
+      "grad_norm": 1.3247623799513832,
+      "learning_rate": 0.0001992960701383727,
+      "loss": 15.6004,
+      "step": 308
+    },
+    {
+      "epoch": 0.20100829403154985,
+      "grad_norm": 1.014994705190656,
+      "learning_rate": 0.0001992877248936415,
+      "loss": 15.5882,
+      "step": 309
+    },
+    {
+      "epoch": 0.2016588063099691,
+      "grad_norm": 1.1512880658057882,
+      "learning_rate": 0.00019927933064940487,
+      "loss": 15.2568,
+      "step": 310
+    },
+    {
+      "epoch": 0.20230931858838835,
+      "grad_norm": 1.133724973553669,
+      "learning_rate": 0.0001992708874098054,
+      "loss": 15.5901,
+      "step": 311
+    },
+    {
+      "epoch": 0.2029598308668076,
+      "grad_norm": 1.100340775367923,
+      "learning_rate": 0.00019926239517900992,
+      "loss": 15.6415,
+      "step": 312
+    },
+    {
+      "epoch": 0.20361034314522686,
+      "grad_norm": 1.2702289352009604,
+      "learning_rate": 0.00019925385396120943,
+      "loss": 15.4393,
+      "step": 313
+    },
+    {
+      "epoch": 0.2042608554236461,
+      "grad_norm": 1.0558384251128954,
+      "learning_rate": 0.00019924526376061908,
+      "loss": 15.449,
+      "step": 314
+    },
+    {
+      "epoch": 0.2049113677020654,
+      "grad_norm": 1.3530845016889854,
+      "learning_rate": 0.00019923662458147827,
+      "loss": 15.3951,
+      "step": 315
+    },
+    {
+      "epoch": 0.20556187998048464,
+      "grad_norm": 1.0981783069702051,
+      "learning_rate": 0.00019922793642805048,
+      "loss": 15.2,
+      "step": 316
+    },
+    {
+      "epoch": 0.2062123922589039,
+      "grad_norm": 1.2607434820315395,
+      "learning_rate": 0.00019921919930462347,
+      "loss": 15.1069,
+      "step": 317
+    },
+    {
+      "epoch": 0.20686290453732314,
+      "grad_norm": 1.2780343827255076,
+      "learning_rate": 0.000199210413215509,
+      "loss": 15.633,
+      "step": 318
+    },
+    {
+      "epoch": 0.2075134168157424,
+      "grad_norm": 0.9237804036426049,
+      "learning_rate": 0.0001992015781650432,
+      "loss": 15.4932,
+      "step": 319
+    },
+    {
+      "epoch": 0.20816392909416165,
+      "grad_norm": 1.396597776170188,
+      "learning_rate": 0.00019919269415758618,
+      "loss": 15.6599,
+      "step": 320
+    },
+    {
+      "epoch": 0.2088144413725809,
+      "grad_norm": 1.2029166071149413,
+      "learning_rate": 0.0001991837611975223,
+      "loss": 15.3281,
+      "step": 321
+    },
+    {
+      "epoch": 0.20946495365100015,
+      "grad_norm": 1.2331513916624601,
+      "learning_rate": 0.00019917477928926006,
+      "loss": 15.7713,
+      "step": 322
+    },
+    {
+      "epoch": 0.21011546592941943,
+      "grad_norm": 1.2590206259766967,
+      "learning_rate": 0.0001991657484372322,
+      "loss": 15.8647,
+      "step": 323
+    },
+    {
+      "epoch": 0.21076597820783868,
+      "grad_norm": 1.072611159564735,
+      "learning_rate": 0.00019915666864589544,
+      "loss": 15.5129,
+      "step": 324
+    },
+    {
+      "epoch": 0.21141649048625794,
+      "grad_norm": 1.1296896872490385,
+      "learning_rate": 0.00019914753991973083,
+      "loss": 15.6121,
+      "step": 325
+    },
+    {
+      "epoch": 0.2120670027646772,
+      "grad_norm": 1.1548367034777456,
+      "learning_rate": 0.00019913836226324343,
+      "loss": 15.3771,
+      "step": 326
+    },
+    {
+      "epoch": 0.21271751504309644,
+      "grad_norm": 1.0966526022612149,
+      "learning_rate": 0.00019912913568096252,
+      "loss": 15.3385,
+      "step": 327
+    },
+    {
+      "epoch": 0.2133680273215157,
+      "grad_norm": 1.0675846388162014,
+      "learning_rate": 0.00019911986017744153,
+      "loss": 15.4027,
+      "step": 328
+    },
+    {
+      "epoch": 0.21401853959993494,
+      "grad_norm": 1.0071752901359756,
+      "learning_rate": 0.000199110535757258,
+      "loss": 15.3179,
+      "step": 329
+    },
+    {
+      "epoch": 0.2146690518783542,
+      "grad_norm": 1.1402039001403672,
+      "learning_rate": 0.00019910116242501366,
+      "loss": 15.4543,
+      "step": 330
+    },
+    {
+      "epoch": 0.21531956415677345,
+      "grad_norm": 1.1075176343582083,
+      "learning_rate": 0.00019909174018533428,
+      "loss": 15.541,
+      "step": 331
+    },
+    {
+      "epoch": 0.21597007643519273,
+      "grad_norm": 1.0601612541490757,
+      "learning_rate": 0.00019908226904286988,
+      "loss": 15.5842,
+      "step": 332
+    },
+    {
+      "epoch": 0.21662058871361198,
+      "grad_norm": 1.1460416909714721,
+      "learning_rate": 0.00019907274900229457,
+      "loss": 15.564,
+      "step": 333
+    },
+    {
+      "epoch": 0.21727110099203123,
+      "grad_norm": 1.0420985322567373,
+      "learning_rate": 0.00019906318006830657,
+      "loss": 15.5506,
+      "step": 334
+    },
+    {
+      "epoch": 0.21792161327045048,
+      "grad_norm": 1.1947263883313544,
+      "learning_rate": 0.00019905356224562824,
+      "loss": 15.3196,
+      "step": 335
+    },
+    {
+      "epoch": 0.21857212554886973,
+      "grad_norm": 1.1326856846789986,
+      "learning_rate": 0.00019904389553900608,
+      "loss": 15.5284,
+      "step": 336
+    },
+    {
+      "epoch": 0.21922263782728899,
+      "grad_norm": 1.2450039564587716,
+      "learning_rate": 0.00019903417995321073,
+      "loss": 15.5915,
+      "step": 337
+    },
+    {
+      "epoch": 0.21987315010570824,
+      "grad_norm": 1.1345580146566845,
+      "learning_rate": 0.00019902441549303688,
+      "loss": 15.6607,
+      "step": 338
+    },
+    {
+      "epoch": 0.2205236623841275,
+      "grad_norm": 1.1600830598867455,
+      "learning_rate": 0.00019901460216330342,
+      "loss": 15.6153,
+      "step": 339
+    },
+    {
+      "epoch": 0.22117417466254677,
+      "grad_norm": 1.1501072938150543,
+      "learning_rate": 0.00019900473996885336,
+      "loss": 15.7367,
+      "step": 340
+    },
+    {
+      "epoch": 0.22182468694096602,
+      "grad_norm": 1.3090376133580883,
+      "learning_rate": 0.00019899482891455378,
+      "loss": 15.291,
+      "step": 341
+    },
+    {
+      "epoch": 0.22247519921938527,
+      "grad_norm": 1.1506758942762603,
+      "learning_rate": 0.00019898486900529581,
+      "loss": 15.4926,
+      "step": 342
+    },
+    {
+      "epoch": 0.22312571149780452,
+      "grad_norm": 1.3248180727207008,
+      "learning_rate": 0.00019897486024599486,
+      "loss": 15.516,
+      "step": 343
+    },
+    {
+      "epoch": 0.22377622377622378,
+      "grad_norm": 0.942857595499073,
+      "learning_rate": 0.00019896480264159033,
+      "loss": 15.3871,
+      "step": 344
+    },
+    {
+      "epoch": 0.22442673605464303,
+      "grad_norm": 1.0068793232557849,
+      "learning_rate": 0.00019895469619704575,
+      "loss": 15.4752,
+      "step": 345
+    },
+    {
+      "epoch": 0.22507724833306228,
+      "grad_norm": 1.066650007487764,
+      "learning_rate": 0.00019894454091734873,
+      "loss": 15.2991,
+      "step": 346
+    },
+    {
+      "epoch": 0.22572776061148153,
+      "grad_norm": 1.0384564653893773,
+      "learning_rate": 0.00019893433680751103,
+      "loss": 15.5022,
+      "step": 347
+    },
+    {
+      "epoch": 0.22637827288990078,
+      "grad_norm": 1.137808663553188,
+      "learning_rate": 0.00019892408387256846,
+      "loss": 15.4736,
+      "step": 348
+    },
+    {
+      "epoch": 0.22702878516832006,
+      "grad_norm": 0.9756935784966156,
+      "learning_rate": 0.00019891378211758096,
+      "loss": 15.5336,
+      "step": 349
+    },
+    {
+      "epoch": 0.22767929744673931,
+      "grad_norm": 1.0269182816812015,
+      "learning_rate": 0.0001989034315476326,
+      "loss": 15.5185,
+      "step": 350
+    },
+    {
+      "epoch": 0.22832980972515857,
+      "grad_norm": 1.0133021516659033,
+      "learning_rate": 0.00019889303216783137,
+      "loss": 15.3182,
+      "step": 351
+    },
+    {
+      "epoch": 0.22898032200357782,
+      "grad_norm": 1.2121506190997846,
+      "learning_rate": 0.0001988825839833096,
+      "loss": 15.6925,
+      "step": 352
+    },
+    {
+      "epoch": 0.22963083428199707,
+      "grad_norm": 0.979419476768741,
+      "learning_rate": 0.00019887208699922347,
+      "loss": 15.1412,
+      "step": 353
+    },
+    {
+      "epoch": 0.23028134656041632,
+      "grad_norm": 1.1245551432663146,
+      "learning_rate": 0.00019886154122075343,
+      "loss": 15.2789,
+      "step": 354
+    },
+    {
+      "epoch": 0.23093185883883557,
+      "grad_norm": 0.9817601584905314,
+      "learning_rate": 0.0001988509466531039,
+      "loss": 14.9862,
+      "step": 355
+    },
+    {
+      "epoch": 0.23158237111725483,
+      "grad_norm": 1.041626869090874,
+      "learning_rate": 0.0001988403033015034,
+      "loss": 15.3616,
+      "step": 356
+    },
+    {
+      "epoch": 0.2322328833956741,
+      "grad_norm": 0.9772021758138455,
+      "learning_rate": 0.00019882961117120452,
+      "loss": 15.1276,
+      "step": 357
+    },
+    {
+      "epoch": 0.23288339567409336,
+      "grad_norm": 1.0484472876795092,
+      "learning_rate": 0.000198818870267484,
+      "loss": 15.4899,
+      "step": 358
+    },
+    {
+      "epoch": 0.2335339079525126,
+      "grad_norm": 1.1019800428949198,
+      "learning_rate": 0.0001988080805956425,
+      "loss": 15.1505,
+      "step": 359
+    },
+    {
+      "epoch": 0.23418442023093186,
+      "grad_norm": 0.9618593616384191,
+      "learning_rate": 0.00019879724216100486,
+      "loss": 15.4749,
+      "step": 360
+    },
+    {
+      "epoch": 0.2348349325093511,
+      "grad_norm": 1.009477496014846,
+      "learning_rate": 0.00019878635496891998,
+      "loss": 15.6077,
+      "step": 361
+    },
+    {
+      "epoch": 0.23548544478777036,
+      "grad_norm": 1.1354336479992044,
+      "learning_rate": 0.00019877541902476082,
+      "loss": 15.5084,
+      "step": 362
+    },
+    {
+      "epoch": 0.23613595706618962,
+      "grad_norm": 0.9862755330388426,
+      "learning_rate": 0.00019876443433392433,
+      "loss": 15.4841,
+      "step": 363
+    },
+    {
+      "epoch": 0.23678646934460887,
+      "grad_norm": 1.0803946912682927,
+      "learning_rate": 0.00019875340090183156,
+      "loss": 15.2087,
+      "step": 364
+    },
+    {
+      "epoch": 0.23743698162302815,
+      "grad_norm": 0.9882793719972407,
+      "learning_rate": 0.00019874231873392767,
+      "loss": 15.3001,
+      "step": 365
+    },
+    {
+      "epoch": 0.2380874939014474,
+      "grad_norm": 0.9991426400802365,
+      "learning_rate": 0.00019873118783568183,
+      "loss": 15.6463,
+      "step": 366
+    },
+    {
+      "epoch": 0.23873800617986665,
+      "grad_norm": 1.1562392396317087,
+      "learning_rate": 0.0001987200082125872,
+      "loss": 15.0874,
+      "step": 367
+    },
+    {
+      "epoch": 0.2393885184582859,
+      "grad_norm": 1.072694971436447,
+      "learning_rate": 0.00019870877987016107,
+      "loss": 15.448,
+      "step": 368
+    },
+    {
+      "epoch": 0.24003903073670516,
+      "grad_norm": 1.1289182327449039,
+      "learning_rate": 0.0001986975028139447,
+      "loss": 15.375,
+      "step": 369
+    },
+    {
+      "epoch": 0.2406895430151244,
+      "grad_norm": 1.0728142914579006,
+      "learning_rate": 0.00019868617704950353,
+      "loss": 15.6778,
+      "step": 370
+    },
+    {
+      "epoch": 0.24134005529354366,
+      "grad_norm": 1.1105133827363844,
+      "learning_rate": 0.00019867480258242682,
+      "loss": 15.0283,
+      "step": 371
+    },
+    {
+      "epoch": 0.2419905675719629,
+      "grad_norm": 1.048884764881789,
+      "learning_rate": 0.00019866337941832805,
+      "loss": 15.1392,
+      "step": 372
+    },
+    {
+      "epoch": 0.24264107985038216,
+      "grad_norm": 0.969346843399204,
+      "learning_rate": 0.00019865190756284467,
+      "loss": 15.301,
+      "step": 373
+    },
+    {
+      "epoch": 0.24329159212880144,
+      "grad_norm": 1.0022234533683179,
+      "learning_rate": 0.00019864038702163814,
+      "loss": 15.2589,
+      "step": 374
+    },
+    {
+      "epoch": 0.2439421044072207,
+      "grad_norm": 1.0438820209950932,
+      "learning_rate": 0.00019862881780039398,
+      "loss": 15.3574,
+      "step": 375
+    },
+    {
+      "epoch": 0.24459261668563995,
+      "grad_norm": 1.1448486480366853,
+      "learning_rate": 0.0001986171999048217,
+      "loss": 15.5114,
+      "step": 376
+    },
+    {
+      "epoch": 0.2452431289640592,
+      "grad_norm": 1.0375452062556725,
+      "learning_rate": 0.00019860553334065487,
+      "loss": 15.3407,
+      "step": 377
+    },
+    {
+      "epoch": 0.24589364124247845,
+      "grad_norm": 1.0353720233451702,
+      "learning_rate": 0.00019859381811365104,
+      "loss": 15.0777,
+      "step": 378
+    },
+    {
+      "epoch": 0.2465441535208977,
+      "grad_norm": 1.1144223040857477,
+      "learning_rate": 0.0001985820542295918,
+      "loss": 15.4713,
+      "step": 379
+    },
+    {
+      "epoch": 0.24719466579931695,
+      "grad_norm": 0.9654600959683474,
+      "learning_rate": 0.00019857024169428277,
+      "loss": 15.344,
+      "step": 380
+    },
+    {
+      "epoch": 0.2478451780777362,
+      "grad_norm": 1.0002266183167974,
+      "learning_rate": 0.00019855838051355352,
+      "loss": 15.4414,
+      "step": 381
+    },
+    {
+      "epoch": 0.24849569035615549,
+      "grad_norm": 0.9919388456697362,
+      "learning_rate": 0.0001985464706932577,
+      "loss": 15.1953,
+      "step": 382
+    },
+    {
+      "epoch": 0.24914620263457474,
+      "grad_norm": 1.0978303367366844,
+      "learning_rate": 0.0001985345122392729,
+      "loss": 15.5149,
+      "step": 383
+    },
+    {
+      "epoch": 0.249796714912994,
+      "grad_norm": 0.983278915055748,
+      "learning_rate": 0.00019852250515750076,
+      "loss": 15.4114,
+      "step": 384
+    },
+    {
+      "epoch": 0.2504472271914132,
+      "grad_norm": 0.9998714923932541,
+      "learning_rate": 0.00019851044945386686,
+      "loss": 15.2377,
+      "step": 385
+    },
+    {
+      "epoch": 0.2510977394698325,
+      "grad_norm": 0.9858604954752316,
+      "learning_rate": 0.00019849834513432083,
+      "loss": 15.2794,
+      "step": 386
+    },
+    {
+      "epoch": 0.2517482517482518,
+      "grad_norm": 1.111525717749651,
+      "learning_rate": 0.0001984861922048363,
+      "loss": 15.3766,
+      "step": 387
+    },
+    {
+      "epoch": 0.252398764026671,
+      "grad_norm": 1.0274923332899235,
+      "learning_rate": 0.00019847399067141085,
+      "loss": 15.3851,
+      "step": 388
+    },
+    {
+      "epoch": 0.2530492763050903,
+      "grad_norm": 1.1626724083211757,
+      "learning_rate": 0.00019846174054006607,
+      "loss": 15.4801,
+      "step": 389
+    },
+    {
+      "epoch": 0.2536997885835095,
+      "grad_norm": 0.9632821913709411,
+      "learning_rate": 0.00019844944181684747,
+      "loss": 15.3021,
+      "step": 390
+    },
+    {
+      "epoch": 0.2543503008619288,
+      "grad_norm": 0.9108025537407232,
+      "learning_rate": 0.00019843709450782467,
+      "loss": 15.2892,
+      "step": 391
+    },
+    {
+      "epoch": 0.255000813140348,
+      "grad_norm": 1.0008096653913836,
+      "learning_rate": 0.00019842469861909118,
+      "loss": 15.4147,
+      "step": 392
+    },
+    {
+      "epoch": 0.2556513254187673,
+      "grad_norm": 1.011160251884873,
+      "learning_rate": 0.00019841225415676445,
+      "loss": 15.2152,
+      "step": 393
+    },
+    {
+      "epoch": 0.2563018376971865,
+      "grad_norm": 0.996522820669572,
+      "learning_rate": 0.000198399761126986,
+      "loss": 15.5902,
+      "step": 394
+    },
+    {
+      "epoch": 0.2569523499756058,
+      "grad_norm": 0.9888799579465212,
+      "learning_rate": 0.00019838721953592124,
+      "loss": 15.4606,
+      "step": 395
+    },
+    {
+      "epoch": 0.25760286225402507,
+      "grad_norm": 0.9576273348453226,
+      "learning_rate": 0.00019837462938975957,
+      "loss": 15.3974,
+      "step": 396
+    },
+    {
+      "epoch": 0.2582533745324443,
+      "grad_norm": 0.961083185695473,
+      "learning_rate": 0.00019836199069471437,
+      "loss": 15.1486,
+      "step": 397
+    },
+    {
+      "epoch": 0.25890388681086357,
+      "grad_norm": 1.0420444913934237,
+      "learning_rate": 0.00019834930345702297,
+      "loss": 15.1948,
+      "step": 398
+    },
+    {
+      "epoch": 0.2595543990892828,
+      "grad_norm": 0.9583662458167513,
+      "learning_rate": 0.00019833656768294662,
+      "loss": 15.2982,
+      "step": 399
+    },
+    {
+      "epoch": 0.2602049113677021,
+      "grad_norm": 1.1089670686833482,
+      "learning_rate": 0.0001983237833787706,
+      "loss": 15.3789,
+      "step": 400
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 4611,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 163141420056576.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

VocalNet-7B-SFT/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8a4941b46c3fa3d811768cb38965cce6966b85fe0ec534c5bcc3c3a0c6a2352
+size 7608

VocalNet-7B-SFT/zero_to_fp32.py

@@ -0,0 +1,587 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example: python zero_to_fp32.py . pytorch_model.bin
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel()
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in param_shapes.items():
+
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+    print(f"Saving fp32 state dict to {output_file}")
+    torch.save(state_dict, output_file)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument(
+        "output_file",
+        type=str,
+        help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)

VocalNet-8B-SFT/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /share/nlp/tuwenming/models/VocalNet/VocalNet-8B
+library_name: peft
+---
+
+# 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 0.11.1