Add files using upload-large-folder tool

adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hpc2hdd/home/kehuitan/huggingface/hub/mistralai/Mixtral-8x22B-Instruct-v0.1",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w1",
+    "q_proj",
+    "w3",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate",
+    "w2"
+  ],
+  "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 sha256:792b37034f6456ae49a0b496a79831fadc831005bbf96b7281127286f088b060
+size 525299200

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.962025316455696,
+    "total_flos": 480077453852672.0,
+    "train_loss": 0.17797149998000544,
+    "train_runtime": 4132.2453,
+    "train_samples_per_second": 0.229,
+    "train_steps_per_second": 0.028
+}

checkpoint-117/README.md

@@ -0,0 +1,202 @@
+---
+base_model: /hpc2hdd/home/kehuitan/huggingface/hub/mistralai/Mixtral-8x22B-Instruct-v0.1
+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 0.12.0

checkpoint-117/adapter_config.json

@@ -0,0 +1,35 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/hpc2hdd/home/kehuitan/huggingface/hub/mistralai/Mixtral-8x22B-Instruct-v0.1",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "w1",
+    "q_proj",
+    "w3",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate",
+    "w2"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-117/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792b37034f6456ae49a0b496a79831fadc831005bbf96b7281127286f088b060
+size 525299200

checkpoint-117/global_step117/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141d74dd57362a918d2b063ec05439cebab2ac0f8c8b712f1764f04dd9919c42
+size 787232848

checkpoint-117/global_step117/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:c2b4a31fb47eb7f2330df08745f28aefe27f97867f6a45028651bb6041c0086b
+size 787232848

checkpoint-117/global_step117/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d490e3e59570754032f99f88eb4118001588cd905013853e9f57e5cd39b7199
+size 787232848

checkpoint-117/global_step117/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02dff4f802b16a62eeca2f945399adcb23e11eef435dbf3f5ac46d466594813c
+size 787232848

checkpoint-117/global_step117/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df16cfaffcbdfd45bac486a4bb635ee660c883269b1f30f8b18ba516916ea9e6
+size 3527910

checkpoint-117/global_step117/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b4e9ddd4cb56b84ff935193309ba00adf04438a44e0538c0d3b45a9af1905bc
+size 3527910

checkpoint-117/global_step117/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25238af3586f234f8983a1ac9216a1472938dab54012a112630a0602f2d1c430
+size 3527910

checkpoint-117/global_step117/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa92b94f66b3b0d1710c2c86c3f30f039cae519fec8159b7fe572001057323bc
+size 3527910

checkpoint-117/latest

@@ -0,0 +1 @@
+global_step117

checkpoint-117/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:308f94f9a5c24e1bad5c393d56ae7af7782600f4e791d9c6ac35b22fff2105b6
+size 15024

checkpoint-117/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b056f3c23cb32dc77a2ec9e7651e0b64e4440e21f0fdf969b86bfc56a1cbdf06
+size 15024

checkpoint-117/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3f8a05714bc528f4885a2816181652f2303b3e8150f89b56aaee6bec56aa520
+size 15024

checkpoint-117/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f755bd3c330281961e5c03af9d10ce8c1e1678619d384f6f1fd5fd7dce2ff50
+size 15024

checkpoint-117/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09557b1d4da433a4489d12bec551f7b75466f796a905598e6ba8698b633264c8
+size 1064

checkpoint-117/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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
+  }
+}

checkpoint-117/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-117/trainer_state.json

@@ -0,0 +1,852 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962025316455696,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02531645569620253,
+      "grad_norm": 0.28381249212278864,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.527,
+      "step": 1
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 0.29332876337801134,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.5152,
+      "step": 2
+    },
+    {
+      "epoch": 0.0759493670886076,
+      "grad_norm": 0.42097245913011233,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5138,
+      "step": 3
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.31373613965244807,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.4898,
+      "step": 4
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "grad_norm": 0.38811861849958174,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.4976,
+      "step": 5
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.3665975538958321,
+      "learning_rate": 5e-05,
+      "loss": 0.4886,
+      "step": 6
+    },
+    {
+      "epoch": 0.17721518987341772,
+      "grad_norm": 0.28812556883203455,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.4605,
+      "step": 7
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.3161799363224881,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4187,
+      "step": 8
+    },
+    {
+      "epoch": 0.22784810126582278,
+      "grad_norm": 0.30351099872377285,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.3898,
+      "step": 9
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.20421030715908728,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.2981,
+      "step": 10
+    },
+    {
+      "epoch": 0.27848101265822783,
+      "grad_norm": 0.2622244347847273,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 0.2359,
+      "step": 11
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.20123682547622748,
+      "learning_rate": 0.0001,
+      "loss": 0.3136,
+      "step": 12
+    },
+    {
+      "epoch": 0.3291139240506329,
+      "grad_norm": 0.19424698101984617,
+      "learning_rate": 9.997762161417517e-05,
+      "loss": 0.2814,
+      "step": 13
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.2138956216522083,
+      "learning_rate": 9.991050648838675e-05,
+      "loss": 0.2265,
+      "step": 14
+    },
+    {
+      "epoch": 0.379746835443038,
+      "grad_norm": 0.23993237439220805,
+      "learning_rate": 9.979871469976196e-05,
+      "loss": 0.2007,
+      "step": 15
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.20626020803621276,
+      "learning_rate": 9.964234631709187e-05,
+      "loss": 0.2496,
+      "step": 16
+    },
+    {
+      "epoch": 0.43037974683544306,
+      "grad_norm": 0.16885750202973263,
+      "learning_rate": 9.944154131125642e-05,
+      "loss": 0.216,
+      "step": 17
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.20604877553838427,
+      "learning_rate": 9.919647942993148e-05,
+      "loss": 0.2173,
+      "step": 18
+    },
+    {
+      "epoch": 0.4810126582278481,
+      "grad_norm": 0.17817294328866598,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.2012,
+      "step": 19
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.169371216914731,
+      "learning_rate": 9.857450191464337e-05,
+      "loss": 0.2249,
+      "step": 20
+    },
+    {
+      "epoch": 0.5316455696202531,
+      "grad_norm": 0.16863849651520665,
+      "learning_rate": 9.819814303479267e-05,
+      "loss": 0.1928,
+      "step": 21
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 0.15933923390114604,
+      "learning_rate": 9.777864028930705e-05,
+      "loss": 0.2231,
+      "step": 22
+    },
+    {
+      "epoch": 0.5822784810126582,
+      "grad_norm": 0.1578071135366508,
+      "learning_rate": 9.731636918995821e-05,
+      "loss": 0.2078,
+      "step": 23
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.14721022380875914,
+      "learning_rate": 9.681174353198687e-05,
+      "loss": 0.2151,
+      "step": 24
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 0.16015977971909204,
+      "learning_rate": 9.626521502369984e-05,
+      "loss": 0.2108,
+      "step": 25
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 0.22236247508590176,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.2015,
+      "step": 26
+    },
+    {
+      "epoch": 0.6835443037974683,
+      "grad_norm": 0.12808123195714893,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 0.1715,
+      "step": 27
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 0.14385399140847496,
+      "learning_rate": 9.437928945022771e-05,
+      "loss": 0.2256,
+      "step": 28
+    },
+    {
+      "epoch": 0.7341772151898734,
+      "grad_norm": 0.1362215128043263,
+      "learning_rate": 9.367041003085649e-05,
+      "loss": 0.1813,
+      "step": 29
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.14186669882045214,
+      "learning_rate": 9.292243968009331e-05,
+      "loss": 0.2053,
+      "step": 30
+    },
+    {
+      "epoch": 0.7848101265822784,
+      "grad_norm": 0.13378456553677073,
+      "learning_rate": 9.213604793270196e-05,
+      "loss": 0.2085,
+      "step": 31
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.14358937888813622,
+      "learning_rate": 9.131193871579975e-05,
+      "loss": 0.2008,
+      "step": 32
+    },
+    {
+      "epoch": 0.8354430379746836,
+      "grad_norm": 0.147823569949849,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2539,
+      "step": 33
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 0.13623356559268837,
+      "learning_rate": 8.955355173281708e-05,
+      "loss": 0.1863,
+      "step": 34
+    },
+    {
+      "epoch": 0.8860759493670886,
+      "grad_norm": 0.13948008252693808,
+      "learning_rate": 8.862084796122998e-05,
+      "loss": 0.1463,
+      "step": 35
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.1339429888742059,
+      "learning_rate": 8.765357330018056e-05,
+      "loss": 0.1592,
+      "step": 36
+    },
+    {
+      "epoch": 0.9367088607594937,
+      "grad_norm": 0.1602446905039844,
+      "learning_rate": 8.665259359149132e-05,
+      "loss": 0.2199,
+      "step": 37
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 0.13728548840884053,
+      "learning_rate": 8.561880484756725e-05,
+      "loss": 0.178,
+      "step": 38
+    },
+    {
+      "epoch": 0.9873417721518988,
+      "grad_norm": 0.13701462745977658,
+      "learning_rate": 8.455313244934324e-05,
+      "loss": 0.1739,
+      "step": 39
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 0.2072023638259741,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.2222,
+      "step": 40
+    },
+    {
+      "epoch": 1.0379746835443038,
+      "grad_norm": 0.15105393513368087,
+      "learning_rate": 8.232998006078997e-05,
+      "loss": 0.1479,
+      "step": 41
+    },
+    {
+      "epoch": 1.0632911392405062,
+      "grad_norm": 0.15569390641449965,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 0.2338,
+      "step": 42
+    },
+    {
+      "epoch": 1.0886075949367089,
+      "grad_norm": 0.16038992744587696,
+      "learning_rate": 7.999109473439569e-05,
+      "loss": 0.2465,
+      "step": 43
+    },
+    {
+      "epoch": 1.1139240506329113,
+      "grad_norm": 0.14681811778410783,
+      "learning_rate": 7.878085328428369e-05,
+      "loss": 0.1957,
+      "step": 44
+    },
+    {
+      "epoch": 1.139240506329114,
+      "grad_norm": 0.16734148603665647,
+      "learning_rate": 7.754484907260513e-05,
+      "loss": 0.2047,
+      "step": 45
+    },
+    {
+      "epoch": 1.1645569620253164,
+      "grad_norm": 0.14760531374441424,
+      "learning_rate": 7.628418849052523e-05,
+      "loss": 0.149,
+      "step": 46
+    },
+    {
+      "epoch": 1.189873417721519,
+      "grad_norm": 0.3076003175984034,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1874,
+      "step": 47
+    },
+    {
+      "epoch": 1.2151898734177216,
+      "grad_norm": 0.1342886833257913,
+      "learning_rate": 7.369343312364993e-05,
+      "loss": 0.1225,
+      "step": 48
+    },
+    {
+      "epoch": 1.240506329113924,
+      "grad_norm": 0.1565758288110148,
+      "learning_rate": 7.236565741578163e-05,
+      "loss": 0.1709,
+      "step": 49
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 0.12936285098939904,
+      "learning_rate": 7.101786141547828e-05,
+      "loss": 0.0952,
+      "step": 50
+    },
+    {
+      "epoch": 1.2911392405063291,
+      "grad_norm": 0.1651361450780901,
+      "learning_rate": 6.965125158269619e-05,
+      "loss": 0.1798,
+      "step": 51
+    },
+    {
+      "epoch": 1.3164556962025316,
+      "grad_norm": 0.18294240175450024,
+      "learning_rate": 6.826705121831976e-05,
+      "loss": 0.2146,
+      "step": 52
+    },
+    {
+      "epoch": 1.3417721518987342,
+      "grad_norm": 0.15907649925734338,
+      "learning_rate": 6.686649936914152e-05,
+      "loss": 0.1651,
+      "step": 53
+    },
+    {
+      "epoch": 1.3670886075949367,
+      "grad_norm": 0.15265125027320092,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1318,
+      "step": 54
+    },
+    {
+      "epoch": 1.3924050632911391,
+      "grad_norm": 0.15507370320317093,
+      "learning_rate": 6.402136946530014e-05,
+      "loss": 0.1396,
+      "step": 55
+    },
+    {
+      "epoch": 1.4177215189873418,
+      "grad_norm": 0.17930905252960624,
+      "learning_rate": 6.257933818722543e-05,
+      "loss": 0.1627,
+      "step": 56
+    },
+    {
+      "epoch": 1.4430379746835442,
+      "grad_norm": 0.1950350507388175,
+      "learning_rate": 6.112604669781572e-05,
+      "loss": 0.1178,
+      "step": 57
+    },
+    {
+      "epoch": 1.4683544303797469,
+      "grad_norm": 0.16629437997930713,
+      "learning_rate": 5.9662795889777666e-05,
+      "loss": 0.1708,
+      "step": 58
+    },
+    {
+      "epoch": 1.4936708860759493,
+      "grad_norm": 0.20546299378777336,
+      "learning_rate": 5.819089557075689e-05,
+      "loss": 0.1567,
+      "step": 59
+    },
+    {
+      "epoch": 1.518987341772152,
+      "grad_norm": 0.15069790201742334,
+      "learning_rate": 5.6711663290882776e-05,
+      "loss": 0.1153,
+      "step": 60
+    },
+    {
+      "epoch": 1.5443037974683544,
+      "grad_norm": 0.1819232976665009,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2024,
+      "step": 61
+    },
+    {
+      "epoch": 1.5696202531645569,
+      "grad_norm": 0.15124842383808745,
+      "learning_rate": 5.373650467932122e-05,
+      "loss": 0.1006,
+      "step": 62
+    },
+    {
+      "epoch": 1.5949367088607596,
+      "grad_norm": 0.17606437452474172,
+      "learning_rate": 5.2243241517525754e-05,
+      "loss": 0.1583,
+      "step": 63
+    },
+    {
+      "epoch": 1.620253164556962,
+      "grad_norm": 0.203467245813199,
+      "learning_rate": 5.074797035076319e-05,
+      "loss": 0.1928,
+      "step": 64
+    },
+    {
+      "epoch": 1.6455696202531644,
+      "grad_norm": 0.17192119281095727,
+      "learning_rate": 4.925202964923683e-05,
+      "loss": 0.1186,
+      "step": 65
+    },
+    {
+      "epoch": 1.6708860759493671,
+      "grad_norm": 0.16287577101677936,
+      "learning_rate": 4.775675848247427e-05,
+      "loss": 0.1179,
+      "step": 66
+    },
+    {
+      "epoch": 1.6962025316455698,
+      "grad_norm": 0.16446919781752384,
+      "learning_rate": 4.626349532067879e-05,
+      "loss": 0.1128,
+      "step": 67
+    },
+    {
+      "epoch": 1.721518987341772,
+      "grad_norm": 0.21462405849921243,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1284,
+      "step": 68
+    },
+    {
+      "epoch": 1.7468354430379747,
+      "grad_norm": 0.13999924246549017,
+      "learning_rate": 4.328833670911724e-05,
+      "loss": 0.1145,
+      "step": 69
+    },
+    {
+      "epoch": 1.7721518987341773,
+      "grad_norm": 0.18064769980074544,
+      "learning_rate": 4.180910442924312e-05,
+      "loss": 0.1655,
+      "step": 70
+    },
+    {
+      "epoch": 1.7974683544303798,
+      "grad_norm": 0.16541787975736866,
+      "learning_rate": 4.0337204110222346e-05,
+      "loss": 0.1204,
+      "step": 71
+    },
+    {
+      "epoch": 1.8227848101265822,
+      "grad_norm": 0.17309004286105295,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 0.1118,
+      "step": 72
+    },
+    {
+      "epoch": 1.8481012658227849,
+      "grad_norm": 0.17513841600341226,
+      "learning_rate": 3.742066181277458e-05,
+      "loss": 0.1424,
+      "step": 73
+    },
+    {
+      "epoch": 1.8734177215189873,
+      "grad_norm": 0.19362821096770938,
+      "learning_rate": 3.597863053469987e-05,
+      "loss": 0.1682,
+      "step": 74
+    },
+    {
+      "epoch": 1.8987341772151898,
+      "grad_norm": 0.20119249367834352,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1173,
+      "step": 75
+    },
+    {
+      "epoch": 1.9240506329113924,
+      "grad_norm": 0.2085780534303345,
+      "learning_rate": 3.313350063085851e-05,
+      "loss": 0.1657,
+      "step": 76
+    },
+    {
+      "epoch": 1.9493670886075949,
+      "grad_norm": 0.18223304941420868,
+      "learning_rate": 3.173294878168025e-05,
+      "loss": 0.1797,
+      "step": 77
+    },
+    {
+      "epoch": 1.9746835443037973,
+      "grad_norm": 0.1891158533084314,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 0.1319,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.27462058932982153,
+      "learning_rate": 2.8982138584521735e-05,
+      "loss": 0.1609,
+      "step": 79
+    },
+    {
+      "epoch": 2.0253164556962027,
+      "grad_norm": 0.18602374184501738,
+      "learning_rate": 2.7634342584218365e-05,
+      "loss": 0.099,
+      "step": 80
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.17573647458638603,
+      "learning_rate": 2.630656687635007e-05,
+      "loss": 0.1269,
+      "step": 81
+    },
+    {
+      "epoch": 2.0759493670886076,
+      "grad_norm": 0.170011474839188,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1492,
+      "step": 82
+    },
+    {
+      "epoch": 2.1012658227848102,
+      "grad_norm": 0.16455052655933264,
+      "learning_rate": 2.371581150947476e-05,
+      "loss": 0.086,
+      "step": 83
+    },
+    {
+      "epoch": 2.1265822784810124,
+      "grad_norm": 0.16183814372981142,
+      "learning_rate": 2.245515092739488e-05,
+      "loss": 0.0894,
+      "step": 84
+    },
+    {
+      "epoch": 2.151898734177215,
+      "grad_norm": 0.1845809186683481,
+      "learning_rate": 2.1219146715716332e-05,
+      "loss": 0.1312,
+      "step": 85
+    },
+    {
+      "epoch": 2.1772151898734178,
+      "grad_norm": 0.17513589542519134,
+      "learning_rate": 2.0008905265604316e-05,
+      "loss": 0.0934,
+      "step": 86
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.2109199799220023,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 0.093,
+      "step": 87
+    },
+    {
+      "epoch": 2.2278481012658227,
+      "grad_norm": 0.17669643474539057,
+      "learning_rate": 1.7670019939210024e-05,
+      "loss": 0.087,
+      "step": 88
+    },
+    {
+      "epoch": 2.2531645569620253,
+      "grad_norm": 0.21167114503852452,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.114,
+      "step": 89
+    },
+    {
+      "epoch": 2.278481012658228,
+      "grad_norm": 0.21139669768919672,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 0.1003,
+      "step": 90
+    },
+    {
+      "epoch": 2.3037974683544302,
+      "grad_norm": 0.17912893970040897,
+      "learning_rate": 1.438119515243277e-05,
+      "loss": 0.1023,
+      "step": 91
+    },
+    {
+      "epoch": 2.329113924050633,
+      "grad_norm": 0.19961182766357477,
+      "learning_rate": 1.3347406408508695e-05,
+      "loss": 0.0989,
+      "step": 92
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.18672908810203143,
+      "learning_rate": 1.2346426699819458e-05,
+      "loss": 0.0865,
+      "step": 93
+    },
+    {
+      "epoch": 2.379746835443038,
+      "grad_norm": 0.1970580774900479,
+      "learning_rate": 1.137915203877003e-05,
+      "loss": 0.0954,
+      "step": 94
+    },
+    {
+      "epoch": 2.4050632911392404,
+      "grad_norm": 0.15997868673482188,
+      "learning_rate": 1.0446448267182952e-05,
+      "loss": 0.0751,
+      "step": 95
+    },
+    {
+      "epoch": 2.430379746835443,
+      "grad_norm": 0.22896720413179728,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0888,
+      "step": 96
+    },
+    {
+      "epoch": 2.4556962025316453,
+      "grad_norm": 0.1837419155509244,
+      "learning_rate": 8.688061284200266e-06,
+      "loss": 0.091,
+      "step": 97
+    },
+    {
+      "epoch": 2.481012658227848,
+      "grad_norm": 0.21793351897040644,
+      "learning_rate": 7.863952067298042e-06,
+      "loss": 0.0892,
+      "step": 98
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.19632949222949325,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 0.088,
+      "step": 99
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "grad_norm": 0.21767182823620418,
+      "learning_rate": 6.329589969143518e-06,
+      "loss": 0.1415,
+      "step": 100
+    },
+    {
+      "epoch": 2.5569620253164556,
+      "grad_norm": 0.2195952213656607,
+      "learning_rate": 5.620710549772295e-06,
+      "loss": 0.1036,
+      "step": 101
+    },
+    {
+      "epoch": 2.5822784810126582,
+      "grad_norm": 0.19933172837107496,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.074,
+      "step": 102
+    },
+    {
+      "epoch": 2.607594936708861,
+      "grad_norm": 0.20549095019371302,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.087,
+      "step": 103
+    },
+    {
+      "epoch": 2.632911392405063,
+      "grad_norm": 0.19724008187075792,
+      "learning_rate": 3.734784976300165e-06,
+      "loss": 0.1255,
+      "step": 104
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.22735257344640358,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 0.1352,
+      "step": 105
+    },
+    {
+      "epoch": 2.6835443037974684,
+      "grad_norm": 0.20013828861070956,
+      "learning_rate": 2.6836308100417873e-06,
+      "loss": 0.0766,
+      "step": 106
+    },
+    {
+      "epoch": 2.708860759493671,
+      "grad_norm": 0.20899162992915188,
+      "learning_rate": 2.221359710692961e-06,
+      "loss": 0.1113,
+      "step": 107
+    },
+    {
+      "epoch": 2.7341772151898733,
+      "grad_norm": 0.22623291377890534,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 0.1064,
+      "step": 108
+    },
+    {
+      "epoch": 2.759493670886076,
+      "grad_norm": 0.24976299644855401,
+      "learning_rate": 1.4254980853566247e-06,
+      "loss": 0.109,
+      "step": 109
+    },
+    {
+      "epoch": 2.7848101265822782,
+      "grad_norm": 0.20046850962635593,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1121,
+      "step": 110
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.21161953723512844,
+      "learning_rate": 8.035205700685167e-07,
+      "loss": 0.0884,
+      "step": 111
+    },
+    {
+      "epoch": 2.8354430379746836,
+      "grad_norm": 0.23714913658575656,
+      "learning_rate": 5.584586887435739e-07,
+      "loss": 0.0868,
+      "step": 112
+    },
+    {
+      "epoch": 2.8607594936708862,
+      "grad_norm": 0.20860035989411196,
+      "learning_rate": 3.576536829081323e-07,
+      "loss": 0.0945,
+      "step": 113
+    },
+    {
+      "epoch": 2.8860759493670884,
+      "grad_norm": 0.264811602754133,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 0.1285,
+      "step": 114
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 0.21080729209863774,
+      "learning_rate": 8.949351161324227e-08,
+      "loss": 0.0733,
+      "step": 115
+    },
+    {
+      "epoch": 2.9367088607594938,
+      "grad_norm": 0.21648721660730044,
+      "learning_rate": 2.237838582483387e-08,
+      "loss": 0.106,
+      "step": 116
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.20297309807693178,
+      "learning_rate": 0.0,
+      "loss": 0.11,
+      "step": 117
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 480077453852672.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-117/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b824d808fe94c8353ba36a394d2101d1d0658f601927160facdb8532fd03fbad
+size 7352

checkpoint-117/zero_to_fp32.py

@@ -0,0 +1,604 @@
+#!/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, 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 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,
+                                               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_file, 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_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``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+    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("--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_file,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.962025316455696,
+    "total_flos": 480077453852672.0,
+    "train_loss": 0.17797149998000544,
+    "train_runtime": 4132.2453,
+    "train_samples_per_second": 0.229,
+    "train_steps_per_second": 0.028
+}

trainer_log.jsonl

@@ -0,0 +1 @@
+{"current_steps": 117, "total_steps": 117, "epoch": 2.962025316455696, "percentage": 100.0, "elapsed_time": "1:08:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,861 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.962025316455696,
+  "eval_steps": 500,
+  "global_step": 117,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02531645569620253,
+      "grad_norm": 0.28381249212278864,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.527,
+      "step": 1
+    },
+    {
+      "epoch": 0.05063291139240506,
+      "grad_norm": 0.29332876337801134,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.5152,
+      "step": 2
+    },
+    {
+      "epoch": 0.0759493670886076,
+      "grad_norm": 0.42097245913011233,
+      "learning_rate": 2.5e-05,
+      "loss": 0.5138,
+      "step": 3
+    },
+    {
+      "epoch": 0.10126582278481013,
+      "grad_norm": 0.31373613965244807,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.4898,
+      "step": 4
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "grad_norm": 0.38811861849958174,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.4976,
+      "step": 5
+    },
+    {
+      "epoch": 0.1518987341772152,
+      "grad_norm": 0.3665975538958321,
+      "learning_rate": 5e-05,
+      "loss": 0.4886,
+      "step": 6
+    },
+    {
+      "epoch": 0.17721518987341772,
+      "grad_norm": 0.28812556883203455,
+      "learning_rate": 5.833333333333334e-05,
+      "loss": 0.4605,
+      "step": 7
+    },
+    {
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.3161799363224881,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.4187,
+      "step": 8
+    },
+    {
+      "epoch": 0.22784810126582278,
+      "grad_norm": 0.30351099872377285,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.3898,
+      "step": 9
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.20421030715908728,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.2981,
+      "step": 10
+    },
+    {
+      "epoch": 0.27848101265822783,
+      "grad_norm": 0.2622244347847273,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 0.2359,
+      "step": 11
+    },
+    {
+      "epoch": 0.3037974683544304,
+      "grad_norm": 0.20123682547622748,
+      "learning_rate": 0.0001,
+      "loss": 0.3136,
+      "step": 12
+    },
+    {
+      "epoch": 0.3291139240506329,
+      "grad_norm": 0.19424698101984617,
+      "learning_rate": 9.997762161417517e-05,
+      "loss": 0.2814,
+      "step": 13
+    },
+    {
+      "epoch": 0.35443037974683544,
+      "grad_norm": 0.2138956216522083,
+      "learning_rate": 9.991050648838675e-05,
+      "loss": 0.2265,
+      "step": 14
+    },
+    {
+      "epoch": 0.379746835443038,
+      "grad_norm": 0.23993237439220805,
+      "learning_rate": 9.979871469976196e-05,
+      "loss": 0.2007,
+      "step": 15
+    },
+    {
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.20626020803621276,
+      "learning_rate": 9.964234631709187e-05,
+      "loss": 0.2496,
+      "step": 16
+    },
+    {
+      "epoch": 0.43037974683544306,
+      "grad_norm": 0.16885750202973263,
+      "learning_rate": 9.944154131125642e-05,
+      "loss": 0.216,
+      "step": 17
+    },
+    {
+      "epoch": 0.45569620253164556,
+      "grad_norm": 0.20604877553838427,
+      "learning_rate": 9.919647942993148e-05,
+      "loss": 0.2173,
+      "step": 18
+    },
+    {
+      "epoch": 0.4810126582278481,
+      "grad_norm": 0.17817294328866598,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 0.2012,
+      "step": 19
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.169371216914731,
+      "learning_rate": 9.857450191464337e-05,
+      "loss": 0.2249,
+      "step": 20
+    },
+    {
+      "epoch": 0.5316455696202531,
+      "grad_norm": 0.16863849651520665,
+      "learning_rate": 9.819814303479267e-05,
+      "loss": 0.1928,
+      "step": 21
+    },
+    {
+      "epoch": 0.5569620253164557,
+      "grad_norm": 0.15933923390114604,
+      "learning_rate": 9.777864028930705e-05,
+      "loss": 0.2231,
+      "step": 22
+    },
+    {
+      "epoch": 0.5822784810126582,
+      "grad_norm": 0.1578071135366508,
+      "learning_rate": 9.731636918995821e-05,
+      "loss": 0.2078,
+      "step": 23
+    },
+    {
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.14721022380875914,
+      "learning_rate": 9.681174353198687e-05,
+      "loss": 0.2151,
+      "step": 24
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 0.16015977971909204,
+      "learning_rate": 9.626521502369984e-05,
+      "loss": 0.2108,
+      "step": 25
+    },
+    {
+      "epoch": 0.6582278481012658,
+      "grad_norm": 0.22236247508590176,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 0.2015,
+      "step": 26
+    },
+    {
+      "epoch": 0.6835443037974683,
+      "grad_norm": 0.12808123195714893,
+      "learning_rate": 9.504844339512095e-05,
+      "loss": 0.1715,
+      "step": 27
+    },
+    {
+      "epoch": 0.7088607594936709,
+      "grad_norm": 0.14385399140847496,
+      "learning_rate": 9.437928945022771e-05,
+      "loss": 0.2256,
+      "step": 28
+    },
+    {
+      "epoch": 0.7341772151898734,
+      "grad_norm": 0.1362215128043263,
+      "learning_rate": 9.367041003085649e-05,
+      "loss": 0.1813,
+      "step": 29
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.14186669882045214,
+      "learning_rate": 9.292243968009331e-05,
+      "loss": 0.2053,
+      "step": 30
+    },
+    {
+      "epoch": 0.7848101265822784,
+      "grad_norm": 0.13378456553677073,
+      "learning_rate": 9.213604793270196e-05,
+      "loss": 0.2085,
+      "step": 31
+    },
+    {
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.14358937888813622,
+      "learning_rate": 9.131193871579975e-05,
+      "loss": 0.2008,
+      "step": 32
+    },
+    {
+      "epoch": 0.8354430379746836,
+      "grad_norm": 0.147823569949849,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2539,
+      "step": 33
+    },
+    {
+      "epoch": 0.8607594936708861,
+      "grad_norm": 0.13623356559268837,
+      "learning_rate": 8.955355173281708e-05,
+      "loss": 0.1863,
+      "step": 34
+    },
+    {
+      "epoch": 0.8860759493670886,
+      "grad_norm": 0.13948008252693808,
+      "learning_rate": 8.862084796122998e-05,
+      "loss": 0.1463,
+      "step": 35
+    },
+    {
+      "epoch": 0.9113924050632911,
+      "grad_norm": 0.1339429888742059,
+      "learning_rate": 8.765357330018056e-05,
+      "loss": 0.1592,
+      "step": 36
+    },
+    {
+      "epoch": 0.9367088607594937,
+      "grad_norm": 0.1602446905039844,
+      "learning_rate": 8.665259359149132e-05,
+      "loss": 0.2199,
+      "step": 37
+    },
+    {
+      "epoch": 0.9620253164556962,
+      "grad_norm": 0.13728548840884053,
+      "learning_rate": 8.561880484756725e-05,
+      "loss": 0.178,
+      "step": 38
+    },
+    {
+      "epoch": 0.9873417721518988,
+      "grad_norm": 0.13701462745977658,
+      "learning_rate": 8.455313244934324e-05,
+      "loss": 0.1739,
+      "step": 39
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 0.2072023638259741,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 0.2222,
+      "step": 40
+    },
+    {
+      "epoch": 1.0379746835443038,
+      "grad_norm": 0.15105393513368087,
+      "learning_rate": 8.232998006078997e-05,
+      "loss": 0.1479,
+      "step": 41
+    },
+    {
+      "epoch": 1.0632911392405062,
+      "grad_norm": 0.15569390641449965,
+      "learning_rate": 8.117449009293668e-05,
+      "loss": 0.2338,
+      "step": 42
+    },
+    {
+      "epoch": 1.0886075949367089,
+      "grad_norm": 0.16038992744587696,
+      "learning_rate": 7.999109473439569e-05,
+      "loss": 0.2465,
+      "step": 43
+    },
+    {
+      "epoch": 1.1139240506329113,
+      "grad_norm": 0.14681811778410783,
+      "learning_rate": 7.878085328428369e-05,
+      "loss": 0.1957,
+      "step": 44
+    },
+    {
+      "epoch": 1.139240506329114,
+      "grad_norm": 0.16734148603665647,
+      "learning_rate": 7.754484907260513e-05,
+      "loss": 0.2047,
+      "step": 45
+    },
+    {
+      "epoch": 1.1645569620253164,
+      "grad_norm": 0.14760531374441424,
+      "learning_rate": 7.628418849052523e-05,
+      "loss": 0.149,
+      "step": 46
+    },
+    {
+      "epoch": 1.189873417721519,
+      "grad_norm": 0.3076003175984034,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 0.1874,
+      "step": 47
+    },
+    {
+      "epoch": 1.2151898734177216,
+      "grad_norm": 0.1342886833257913,
+      "learning_rate": 7.369343312364993e-05,
+      "loss": 0.1225,
+      "step": 48
+    },
+    {
+      "epoch": 1.240506329113924,
+      "grad_norm": 0.1565758288110148,
+      "learning_rate": 7.236565741578163e-05,
+      "loss": 0.1709,
+      "step": 49
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 0.12936285098939904,
+      "learning_rate": 7.101786141547828e-05,
+      "loss": 0.0952,
+      "step": 50
+    },
+    {
+      "epoch": 1.2911392405063291,
+      "grad_norm": 0.1651361450780901,
+      "learning_rate": 6.965125158269619e-05,
+      "loss": 0.1798,
+      "step": 51
+    },
+    {
+      "epoch": 1.3164556962025316,
+      "grad_norm": 0.18294240175450024,
+      "learning_rate": 6.826705121831976e-05,
+      "loss": 0.2146,
+      "step": 52
+    },
+    {
+      "epoch": 1.3417721518987342,
+      "grad_norm": 0.15907649925734338,
+      "learning_rate": 6.686649936914152e-05,
+      "loss": 0.1651,
+      "step": 53
+    },
+    {
+      "epoch": 1.3670886075949367,
+      "grad_norm": 0.15265125027320092,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.1318,
+      "step": 54
+    },
+    {
+      "epoch": 1.3924050632911391,
+      "grad_norm": 0.15507370320317093,
+      "learning_rate": 6.402136946530014e-05,
+      "loss": 0.1396,
+      "step": 55
+    },
+    {
+      "epoch": 1.4177215189873418,
+      "grad_norm": 0.17930905252960624,
+      "learning_rate": 6.257933818722543e-05,
+      "loss": 0.1627,
+      "step": 56
+    },
+    {
+      "epoch": 1.4430379746835442,
+      "grad_norm": 0.1950350507388175,
+      "learning_rate": 6.112604669781572e-05,
+      "loss": 0.1178,
+      "step": 57
+    },
+    {
+      "epoch": 1.4683544303797469,
+      "grad_norm": 0.16629437997930713,
+      "learning_rate": 5.9662795889777666e-05,
+      "loss": 0.1708,
+      "step": 58
+    },
+    {
+      "epoch": 1.4936708860759493,
+      "grad_norm": 0.20546299378777336,
+      "learning_rate": 5.819089557075689e-05,
+      "loss": 0.1567,
+      "step": 59
+    },
+    {
+      "epoch": 1.518987341772152,
+      "grad_norm": 0.15069790201742334,
+      "learning_rate": 5.6711663290882776e-05,
+      "loss": 0.1153,
+      "step": 60
+    },
+    {
+      "epoch": 1.5443037974683544,
+      "grad_norm": 0.1819232976665009,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.2024,
+      "step": 61
+    },
+    {
+      "epoch": 1.5696202531645569,
+      "grad_norm": 0.15124842383808745,
+      "learning_rate": 5.373650467932122e-05,
+      "loss": 0.1006,
+      "step": 62
+    },
+    {
+      "epoch": 1.5949367088607596,
+      "grad_norm": 0.17606437452474172,
+      "learning_rate": 5.2243241517525754e-05,
+      "loss": 0.1583,
+      "step": 63
+    },
+    {
+      "epoch": 1.620253164556962,
+      "grad_norm": 0.203467245813199,
+      "learning_rate": 5.074797035076319e-05,
+      "loss": 0.1928,
+      "step": 64
+    },
+    {
+      "epoch": 1.6455696202531644,
+      "grad_norm": 0.17192119281095727,
+      "learning_rate": 4.925202964923683e-05,
+      "loss": 0.1186,
+      "step": 65
+    },
+    {
+      "epoch": 1.6708860759493671,
+      "grad_norm": 0.16287577101677936,
+      "learning_rate": 4.775675848247427e-05,
+      "loss": 0.1179,
+      "step": 66
+    },
+    {
+      "epoch": 1.6962025316455698,
+      "grad_norm": 0.16446919781752384,
+      "learning_rate": 4.626349532067879e-05,
+      "loss": 0.1128,
+      "step": 67
+    },
+    {
+      "epoch": 1.721518987341772,
+      "grad_norm": 0.21462405849921243,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.1284,
+      "step": 68
+    },
+    {
+      "epoch": 1.7468354430379747,
+      "grad_norm": 0.13999924246549017,
+      "learning_rate": 4.328833670911724e-05,
+      "loss": 0.1145,
+      "step": 69
+    },
+    {
+      "epoch": 1.7721518987341773,
+      "grad_norm": 0.18064769980074544,
+      "learning_rate": 4.180910442924312e-05,
+      "loss": 0.1655,
+      "step": 70
+    },
+    {
+      "epoch": 1.7974683544303798,
+      "grad_norm": 0.16541787975736866,
+      "learning_rate": 4.0337204110222346e-05,
+      "loss": 0.1204,
+      "step": 71
+    },
+    {
+      "epoch": 1.8227848101265822,
+      "grad_norm": 0.17309004286105295,
+      "learning_rate": 3.887395330218429e-05,
+      "loss": 0.1118,
+      "step": 72
+    },
+    {
+      "epoch": 1.8481012658227849,
+      "grad_norm": 0.17513841600341226,
+      "learning_rate": 3.742066181277458e-05,
+      "loss": 0.1424,
+      "step": 73
+    },
+    {
+      "epoch": 1.8734177215189873,
+      "grad_norm": 0.19362821096770938,
+      "learning_rate": 3.597863053469987e-05,
+      "loss": 0.1682,
+      "step": 74
+    },
+    {
+      "epoch": 1.8987341772151898,
+      "grad_norm": 0.20119249367834352,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.1173,
+      "step": 75
+    },
+    {
+      "epoch": 1.9240506329113924,
+      "grad_norm": 0.2085780534303345,
+      "learning_rate": 3.313350063085851e-05,
+      "loss": 0.1657,
+      "step": 76
+    },
+    {
+      "epoch": 1.9493670886075949,
+      "grad_norm": 0.18223304941420868,
+      "learning_rate": 3.173294878168025e-05,
+      "loss": 0.1797,
+      "step": 77
+    },
+    {
+      "epoch": 1.9746835443037973,
+      "grad_norm": 0.1891158533084314,
+      "learning_rate": 3.0348748417303823e-05,
+      "loss": 0.1319,
+      "step": 78
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.27462058932982153,
+      "learning_rate": 2.8982138584521735e-05,
+      "loss": 0.1609,
+      "step": 79
+    },
+    {
+      "epoch": 2.0253164556962027,
+      "grad_norm": 0.18602374184501738,
+      "learning_rate": 2.7634342584218365e-05,
+      "loss": 0.099,
+      "step": 80
+    },
+    {
+      "epoch": 2.050632911392405,
+      "grad_norm": 0.17573647458638603,
+      "learning_rate": 2.630656687635007e-05,
+      "loss": 0.1269,
+      "step": 81
+    },
+    {
+      "epoch": 2.0759493670886076,
+      "grad_norm": 0.170011474839188,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1492,
+      "step": 82
+    },
+    {
+      "epoch": 2.1012658227848102,
+      "grad_norm": 0.16455052655933264,
+      "learning_rate": 2.371581150947476e-05,
+      "loss": 0.086,
+      "step": 83
+    },
+    {
+      "epoch": 2.1265822784810124,
+      "grad_norm": 0.16183814372981142,
+      "learning_rate": 2.245515092739488e-05,
+      "loss": 0.0894,
+      "step": 84
+    },
+    {
+      "epoch": 2.151898734177215,
+      "grad_norm": 0.1845809186683481,
+      "learning_rate": 2.1219146715716332e-05,
+      "loss": 0.1312,
+      "step": 85
+    },
+    {
+      "epoch": 2.1772151898734178,
+      "grad_norm": 0.17513589542519134,
+      "learning_rate": 2.0008905265604316e-05,
+      "loss": 0.0934,
+      "step": 86
+    },
+    {
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.2109199799220023,
+      "learning_rate": 1.8825509907063327e-05,
+      "loss": 0.093,
+      "step": 87
+    },
+    {
+      "epoch": 2.2278481012658227,
+      "grad_norm": 0.17669643474539057,
+      "learning_rate": 1.7670019939210024e-05,
+      "loss": 0.087,
+      "step": 88
+    },
+    {
+      "epoch": 2.2531645569620253,
+      "grad_norm": 0.21167114503852452,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.114,
+      "step": 89
+    },
+    {
+      "epoch": 2.278481012658228,
+      "grad_norm": 0.21139669768919672,
+      "learning_rate": 1.544686755065677e-05,
+      "loss": 0.1003,
+      "step": 90
+    },
+    {
+      "epoch": 2.3037974683544302,
+      "grad_norm": 0.17912893970040897,
+      "learning_rate": 1.438119515243277e-05,
+      "loss": 0.1023,
+      "step": 91
+    },
+    {
+      "epoch": 2.329113924050633,
+      "grad_norm": 0.19961182766357477,
+      "learning_rate": 1.3347406408508695e-05,
+      "loss": 0.0989,
+      "step": 92
+    },
+    {
+      "epoch": 2.3544303797468356,
+      "grad_norm": 0.18672908810203143,
+      "learning_rate": 1.2346426699819458e-05,
+      "loss": 0.0865,
+      "step": 93
+    },
+    {
+      "epoch": 2.379746835443038,
+      "grad_norm": 0.1970580774900479,
+      "learning_rate": 1.137915203877003e-05,
+      "loss": 0.0954,
+      "step": 94
+    },
+    {
+      "epoch": 2.4050632911392404,
+      "grad_norm": 0.15997868673482188,
+      "learning_rate": 1.0446448267182952e-05,
+      "loss": 0.0751,
+      "step": 95
+    },
+    {
+      "epoch": 2.430379746835443,
+      "grad_norm": 0.22896720413179728,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0888,
+      "step": 96
+    },
+    {
+      "epoch": 2.4556962025316453,
+      "grad_norm": 0.1837419155509244,
+      "learning_rate": 8.688061284200266e-06,
+      "loss": 0.091,
+      "step": 97
+    },
+    {
+      "epoch": 2.481012658227848,
+      "grad_norm": 0.21793351897040644,
+      "learning_rate": 7.863952067298042e-06,
+      "loss": 0.0892,
+      "step": 98
+    },
+    {
+      "epoch": 2.5063291139240507,
+      "grad_norm": 0.19632949222949325,
+      "learning_rate": 7.077560319906695e-06,
+      "loss": 0.088,
+      "step": 99
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "grad_norm": 0.21767182823620418,
+      "learning_rate": 6.329589969143518e-06,
+      "loss": 0.1415,
+      "step": 100
+    },
+    {
+      "epoch": 2.5569620253164556,
+      "grad_norm": 0.2195952213656607,
+      "learning_rate": 5.620710549772295e-06,
+      "loss": 0.1036,
+      "step": 101
+    },
+    {
+      "epoch": 2.5822784810126582,
+      "grad_norm": 0.19933172837107496,
+      "learning_rate": 4.951556604879048e-06,
+      "loss": 0.074,
+      "step": 102
+    },
+    {
+      "epoch": 2.607594936708861,
+      "grad_norm": 0.20549095019371302,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.087,
+      "step": 103
+    },
+    {
+      "epoch": 2.632911392405063,
+      "grad_norm": 0.19724008187075792,
+      "learning_rate": 3.734784976300165e-06,
+      "loss": 0.1255,
+      "step": 104
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.22735257344640358,
+      "learning_rate": 3.18825646801314e-06,
+      "loss": 0.1352,
+      "step": 105
+    },
+    {
+      "epoch": 2.6835443037974684,
+      "grad_norm": 0.20013828861070956,
+      "learning_rate": 2.6836308100417873e-06,
+      "loss": 0.0766,
+      "step": 106
+    },
+    {
+      "epoch": 2.708860759493671,
+      "grad_norm": 0.20899162992915188,
+      "learning_rate": 2.221359710692961e-06,
+      "loss": 0.1113,
+      "step": 107
+    },
+    {
+      "epoch": 2.7341772151898733,
+      "grad_norm": 0.22623291377890534,
+      "learning_rate": 1.8018569652073381e-06,
+      "loss": 0.1064,
+      "step": 108
+    },
+    {
+      "epoch": 2.759493670886076,
+      "grad_norm": 0.24976299644855401,
+      "learning_rate": 1.4254980853566247e-06,
+      "loss": 0.109,
+      "step": 109
+    },
+    {
+      "epoch": 2.7848101265822782,
+      "grad_norm": 0.20046850962635593,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.1121,
+      "step": 110
+    },
+    {
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.21161953723512844,
+      "learning_rate": 8.035205700685167e-07,
+      "loss": 0.0884,
+      "step": 111
+    },
+    {
+      "epoch": 2.8354430379746836,
+      "grad_norm": 0.23714913658575656,
+      "learning_rate": 5.584586887435739e-07,
+      "loss": 0.0868,
+      "step": 112
+    },
+    {
+      "epoch": 2.8607594936708862,
+      "grad_norm": 0.20860035989411196,
+      "learning_rate": 3.576536829081323e-07,
+      "loss": 0.0945,
+      "step": 113
+    },
+    {
+      "epoch": 2.8860759493670884,
+      "grad_norm": 0.264811602754133,
+      "learning_rate": 2.012853002380466e-07,
+      "loss": 0.1285,
+      "step": 114
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 0.21080729209863774,
+      "learning_rate": 8.949351161324227e-08,
+      "loss": 0.0733,
+      "step": 115
+    },
+    {
+      "epoch": 2.9367088607594938,
+      "grad_norm": 0.21648721660730044,
+      "learning_rate": 2.237838582483387e-08,
+      "loss": 0.106,
+      "step": 116
+    },
+    {
+      "epoch": 2.962025316455696,
+      "grad_norm": 0.20297309807693178,
+      "learning_rate": 0.0,
+      "loss": 0.11,
+      "step": 117
+    },
+    {
+      "epoch": 2.962025316455696,
+      "step": 117,
+      "total_flos": 480077453852672.0,
+      "train_loss": 0.17797149998000544,
+      "train_runtime": 4132.2453,
+      "train_samples_per_second": 0.229,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 117,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 480077453852672.0,
+  "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:b824d808fe94c8353ba36a394d2101d1d0658f601927160facdb8532fd03fbad
+size 7352