Upload 15 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: meta-llama/CodeLlama-7b-Python-hf
+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 0.14.0

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/CodeLlama-7b-Python-hf",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 2,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85666f15fcb3ad3cf19b43e51a5002e5cdb846f1b8d7ce87d5c1b6a34c979ae
+size 1583117160

added_tokens.json

@@ -0,0 +1,6 @@
+{
+  "▁<EOT>": 32003,
+  "▁<MID>": 32001,
+  "▁<PRE>": 32000,
+  "▁<SUF>": 32002
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_attn_implementation_autoset": true,
+  "_name_or_path": "meta-llama/CodeLlama-7b-Python-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 16384,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.3",
+  "use_cache": false,
+  "vocab_size": 32004
+}

latest

@@ -0,0 +1 @@
+global_step78

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eeaee95eb41662f712fca25c26e2a06c9d6fdd7064e537b44eab21b9b3e602e
+size 14512

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:687ad4a9d977747caf0a4e00af72769309d277853a0d82155aad52a91a4acad2
+size 14512

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91cf99c21f8b68b65e0192eb76e276b1bdb218fdde666d1d4a1f67e77591499d
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,85 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "suffix_first": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,579 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 12.192307692307692,
+  "eval_steps": 500,
+  "global_step": 78,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 4.947939872741699,
+      "learning_rate": 2e-05,
+      "loss": 2.7425,
+      "step": 1
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 5.395760536193848,
+      "learning_rate": 4e-05,
+      "loss": 3.0917,
+      "step": 2
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 4.972382068634033,
+      "learning_rate": 6e-05,
+      "loss": 2.5889,
+      "step": 3
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 4.1436309814453125,
+      "learning_rate": 8e-05,
+      "loss": 2.6749,
+      "step": 4
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 3.4529764652252197,
+      "learning_rate": 0.0001,
+      "loss": 3.0256,
+      "step": 5
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 3.0711050033569336,
+      "learning_rate": 0.00012,
+      "loss": 2.5193,
+      "step": 6
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 6.622050762176514,
+      "learning_rate": 0.00014,
+      "loss": 3.7169,
+      "step": 7
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 1.689590334892273,
+      "learning_rate": 0.00016,
+      "loss": 1.8293,
+      "step": 8
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 1.1921875476837158,
+      "learning_rate": 0.00018,
+      "loss": 2.1506,
+      "step": 9
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 1.3741947412490845,
+      "learning_rate": 0.0002,
+      "loss": 1.7855,
+      "step": 10
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 1.1680189371109009,
+      "learning_rate": 0.00019990989662046818,
+      "loss": 1.8602,
+      "step": 11
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 2.420065402984619,
+      "learning_rate": 0.00019963974885425266,
+      "loss": 1.6481,
+      "step": 12
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.954460144042969,
+      "learning_rate": 0.00019919004352588767,
+      "loss": 2.3852,
+      "step": 13
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 1.9217047691345215,
+      "learning_rate": 0.00019856159103477086,
+      "loss": 1.3094,
+      "step": 14
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 2.4744794368743896,
+      "learning_rate": 0.00019775552389476864,
+      "loss": 1.4755,
+      "step": 15
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 1.807592511177063,
+      "learning_rate": 0.0001967732946933499,
+      "loss": 1.2384,
+      "step": 16
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 1.5733166933059692,
+      "learning_rate": 0.00019561667347392508,
+      "loss": 1.36,
+      "step": 17
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 0.5816245079040527,
+      "learning_rate": 0.00019428774454610843,
+      "loss": 1.1345,
+      "step": 18
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 0.3857601583003998,
+      "learning_rate": 0.00019278890272965096,
+      "loss": 1.0873,
+      "step": 19
+    },
+    {
+      "epoch": 3.1153846153846154,
+      "grad_norm": 1.011568307876587,
+      "learning_rate": 0.0001911228490388136,
+      "loss": 1.8665,
+      "step": 20
+    },
+    {
+      "epoch": 3.269230769230769,
+      "grad_norm": 2.7151846885681152,
+      "learning_rate": 0.00018929258581495685,
+      "loss": 0.8705,
+      "step": 21
+    },
+    {
+      "epoch": 3.423076923076923,
+      "grad_norm": 0.3418419361114502,
+      "learning_rate": 0.00018730141131611882,
+      "loss": 0.6694,
+      "step": 22
+    },
+    {
+      "epoch": 3.5769230769230766,
+      "grad_norm": 0.581399142742157,
+      "learning_rate": 0.00018515291377333112,
+      "loss": 1.1754,
+      "step": 23
+    },
+    {
+      "epoch": 3.730769230769231,
+      "grad_norm": 0.3654610514640808,
+      "learning_rate": 0.00018285096492438424,
+      "loss": 0.6974,
+      "step": 24
+    },
+    {
+      "epoch": 3.8846153846153846,
+      "grad_norm": 0.3354414701461792,
+      "learning_rate": 0.00018039971303669407,
+      "loss": 0.7878,
+      "step": 25
+    },
+    {
+      "epoch": 4.076923076923077,
+      "grad_norm": 1.0409477949142456,
+      "learning_rate": 0.00017780357543184397,
+      "loss": 1.7312,
+      "step": 26
+    },
+    {
+      "epoch": 4.230769230769231,
+      "grad_norm": 0.2807375192642212,
+      "learning_rate": 0.00017506723052527242,
+      "loss": 0.6799,
+      "step": 27
+    },
+    {
+      "epoch": 4.384615384615385,
+      "grad_norm": 0.3576838970184326,
+      "learning_rate": 0.00017219560939545246,
+      "loss": 0.8706,
+      "step": 28
+    },
+    {
+      "epoch": 4.538461538461538,
+      "grad_norm": 0.28981831669807434,
+      "learning_rate": 0.00016919388689775464,
+      "loss": 0.7189,
+      "step": 29
+    },
+    {
+      "epoch": 4.6923076923076925,
+      "grad_norm": 0.258354514837265,
+      "learning_rate": 0.00016606747233900815,
+      "loss": 0.6547,
+      "step": 30
+    },
+    {
+      "epoch": 4.846153846153846,
+      "grad_norm": 0.5264655351638794,
+      "learning_rate": 0.00016282199972956425,
+      "loss": 0.7603,
+      "step": 31
+    },
+    {
+      "epoch": 5.038461538461538,
+      "grad_norm": 0.6122850179672241,
+      "learning_rate": 0.00015946331763042867,
+      "loss": 1.2304,
+      "step": 32
+    },
+    {
+      "epoch": 5.1923076923076925,
+      "grad_norm": 0.32399341464042664,
+      "learning_rate": 0.00015599747861375955,
+      "loss": 0.5769,
+      "step": 33
+    },
+    {
+      "epoch": 5.346153846153846,
+      "grad_norm": 0.36697638034820557,
+      "learning_rate": 0.00015243072835572318,
+      "loss": 0.5996,
+      "step": 34
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.2546577751636505,
+      "learning_rate": 0.00014876949438136347,
+      "loss": 0.6029,
+      "step": 35
+    },
+    {
+      "epoch": 5.653846153846154,
+      "grad_norm": 0.275869756937027,
+      "learning_rate": 0.00014502037448176734,
+      "loss": 0.7286,
+      "step": 36
+    },
+    {
+      "epoch": 5.8076923076923075,
+      "grad_norm": 0.2754996418952942,
+      "learning_rate": 0.0001411901248243993,
+      "loss": 0.5506,
+      "step": 37
+    },
+    {
+      "epoch": 5.961538461538462,
+      "grad_norm": 0.4771808683872223,
+      "learning_rate": 0.00013728564777803088,
+      "loss": 0.868,
+      "step": 38
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 0.29702961444854736,
+      "learning_rate": 0.00013331397947420576,
+      "loss": 0.5534,
+      "step": 39
+    },
+    {
+      "epoch": 6.3076923076923075,
+      "grad_norm": 0.24644634127616882,
+      "learning_rate": 0.00012928227712765504,
+      "loss": 0.5194,
+      "step": 40
+    },
+    {
+      "epoch": 6.461538461538462,
+      "grad_norm": 0.2727232277393341,
+      "learning_rate": 0.00012519780613851254,
+      "loss": 0.373,
+      "step": 41
+    },
+    {
+      "epoch": 6.615384615384615,
+      "grad_norm": 0.22836743295192719,
+      "learning_rate": 0.00012106792699957263,
+      "loss": 0.4847,
+      "step": 42
+    },
+    {
+      "epoch": 6.769230769230769,
+      "grad_norm": 0.2520367205142975,
+      "learning_rate": 0.00011690008203218493,
+      "loss": 0.4785,
+      "step": 43
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 0.2718031406402588,
+      "learning_rate": 0.00011270178197468789,
+      "loss": 0.5619,
+      "step": 44
+    },
+    {
+      "epoch": 7.076923076923077,
+      "grad_norm": 0.3759967088699341,
+      "learning_rate": 0.00010848059244755093,
+      "loss": 0.6291,
+      "step": 45
+    },
+    {
+      "epoch": 7.230769230769231,
+      "grad_norm": 0.20126377046108246,
+      "learning_rate": 0.00010424412031961484,
+      "loss": 0.3597,
+      "step": 46
+    },
+    {
+      "epoch": 7.384615384615385,
+      "grad_norm": 0.2589998245239258,
+      "learning_rate": 0.0001,
+      "loss": 0.467,
+      "step": 47
+    },
+    {
+      "epoch": 7.538461538461538,
+      "grad_norm": 0.2349349856376648,
+      "learning_rate": 9.57558796803852e-05,
+      "loss": 0.4365,
+      "step": 48
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 0.22222279012203217,
+      "learning_rate": 9.151940755244912e-05,
+      "loss": 0.3549,
+      "step": 49
+    },
+    {
+      "epoch": 7.846153846153846,
+      "grad_norm": 0.222075954079628,
+      "learning_rate": 8.729821802531212e-05,
+      "loss": 0.3699,
+      "step": 50
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.3602772653102875,
+      "learning_rate": 8.309991796781511e-05,
+      "loss": 0.5873,
+      "step": 51
+    },
+    {
+      "epoch": 8.153846153846153,
+      "grad_norm": 0.22580599784851074,
+      "learning_rate": 7.89320730004274e-05,
+      "loss": 0.3826,
+      "step": 52
+    },
+    {
+      "epoch": 8.307692307692308,
+      "grad_norm": 0.25292614102363586,
+      "learning_rate": 7.48021938614875e-05,
+      "loss": 0.3367,
+      "step": 53
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 0.24913984537124634,
+      "learning_rate": 7.071772287234497e-05,
+      "loss": 0.3329,
+      "step": 54
+    },
+    {
+      "epoch": 8.615384615384615,
+      "grad_norm": 0.217300683259964,
+      "learning_rate": 6.668602052579424e-05,
+      "loss": 0.3753,
+      "step": 55
+    },
+    {
+      "epoch": 8.76923076923077,
+      "grad_norm": 0.20688268542289734,
+      "learning_rate": 6.271435222196916e-05,
+      "loss": 0.3123,
+      "step": 56
+    },
+    {
+      "epoch": 8.923076923076923,
+      "grad_norm": 0.2173534780740738,
+      "learning_rate": 5.880987517560075e-05,
+      "loss": 0.2578,
+      "step": 57
+    },
+    {
+      "epoch": 9.076923076923077,
+      "grad_norm": 0.5606672167778015,
+      "learning_rate": 5.497962551823266e-05,
+      "loss": 0.5143,
+      "step": 58
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 0.1941177397966385,
+      "learning_rate": 5.123050561863657e-05,
+      "loss": 0.2446,
+      "step": 59
+    },
+    {
+      "epoch": 9.384615384615385,
+      "grad_norm": 0.21033766865730286,
+      "learning_rate": 4.756927164427685e-05,
+      "loss": 0.313,
+      "step": 60
+    },
+    {
+      "epoch": 9.538461538461538,
+      "grad_norm": 0.24171344935894012,
+      "learning_rate": 4.4002521386240466e-05,
+      "loss": 0.3002,
+      "step": 61
+    },
+    {
+      "epoch": 9.692307692307692,
+      "grad_norm": 0.19194771349430084,
+      "learning_rate": 4.053668236957134e-05,
+      "loss": 0.2588,
+      "step": 62
+    },
+    {
+      "epoch": 9.846153846153847,
+      "grad_norm": 0.22882544994354248,
+      "learning_rate": 3.717800027043576e-05,
+      "loss": 0.2999,
+      "step": 63
+    },
+    {
+      "epoch": 10.038461538461538,
+      "grad_norm": 0.5228483080863953,
+      "learning_rate": 3.393252766099187e-05,
+      "loss": 0.5175,
+      "step": 64
+    },
+    {
+      "epoch": 10.192307692307692,
+      "grad_norm": 0.188337504863739,
+      "learning_rate": 3.080611310224539e-05,
+      "loss": 0.2212,
+      "step": 65
+    },
+    {
+      "epoch": 10.346153846153847,
+      "grad_norm": 0.22668048739433289,
+      "learning_rate": 2.7804390604547557e-05,
+      "loss": 0.2561,
+      "step": 66
+    },
+    {
+      "epoch": 10.5,
+      "grad_norm": 0.2146831899881363,
+      "learning_rate": 2.493276947472756e-05,
+      "loss": 0.259,
+      "step": 67
+    },
+    {
+      "epoch": 10.653846153846153,
+      "grad_norm": 0.20940867066383362,
+      "learning_rate": 2.2196424568156073e-05,
+      "loss": 0.2535,
+      "step": 68
+    },
+    {
+      "epoch": 10.807692307692308,
+      "grad_norm": 0.19297531247138977,
+      "learning_rate": 1.9600286963305957e-05,
+      "loss": 0.2409,
+      "step": 69
+    },
+    {
+      "epoch": 10.961538461538462,
+      "grad_norm": 0.4436163604259491,
+      "learning_rate": 1.7149035075615794e-05,
+      "loss": 0.4615,
+      "step": 70
+    },
+    {
+      "epoch": 11.115384615384615,
+      "grad_norm": 0.2383939027786255,
+      "learning_rate": 1.4847086226668872e-05,
+      "loss": 0.2431,
+      "step": 71
+    },
+    {
+      "epoch": 11.26923076923077,
+      "grad_norm": 0.2192695140838623,
+      "learning_rate": 1.2698588683881186e-05,
+      "loss": 0.2613,
+      "step": 72
+    },
+    {
+      "epoch": 11.423076923076923,
+      "grad_norm": 0.19706690311431885,
+      "learning_rate": 1.0707414185043163e-05,
+      "loss": 0.2265,
+      "step": 73
+    },
+    {
+      "epoch": 11.576923076923077,
+      "grad_norm": 0.2416417896747589,
+      "learning_rate": 8.87715096118642e-06,
+      "loss": 0.2464,
+      "step": 74
+    },
+    {
+      "epoch": 11.73076923076923,
+      "grad_norm": 0.18953856825828552,
+      "learning_rate": 7.211097270349066e-06,
+      "loss": 0.1902,
+      "step": 75
+    },
+    {
+      "epoch": 11.884615384615385,
+      "grad_norm": 0.24142511188983917,
+      "learning_rate": 5.71225545389158e-06,
+      "loss": 0.2684,
+      "step": 76
+    },
+    {
+      "epoch": 12.038461538461538,
+      "grad_norm": 0.38491952419281006,
+      "learning_rate": 4.383326526074916e-06,
+      "loss": 0.417,
+      "step": 77
+    },
+    {
+      "epoch": 12.192307692307692,
+      "grad_norm": 0.22990219295024872,
+      "learning_rate": 3.226705306650113e-06,
+      "loss": 0.273,
+      "step": 78
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 84,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 14,
+  "save_steps": 6,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 160914305187840.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de0b95876ca715c9d5c31196abc0f99724956d090feb6959113c626ce34a242
+size 8504

zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/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 . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+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, exclude_frozen_parameters):
+    """
+    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,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+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 _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+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() if _has_callable(shape, 'numel') else math.prod(shape)
+            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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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 tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        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,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _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, exclude_frozen_parameters=False):
+    """
+    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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    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, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    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_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+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_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    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("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    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_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)