Uploading OD_carDD_llava_13b model with all subfolders

README.md

@@ -0,0 +1,202 @@
+---
+base_model: liuhaotian/llava-v1.5-13b
+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 0.10.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "v_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:d6a64ab1a58abd7591f59b28d0fd6700c897ba7f2c1a69ea48600c0fd95292cb
+size 1001466944

checkpoint-144/README.md

@@ -0,0 +1,202 @@
+---
+base_model: liuhaotian/llava-v1.5-13b
+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 0.10.0

checkpoint-144/adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-144/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c50d3f3d09caab8e306e41d1a4d9e7d91e5fcd65ecb0ae109022bb0c8d298c2a
+size 1001466944

checkpoint-144/global_step144/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:bed9286a9735648844079794190472d96843a7e7dcca9227043d6abeb5c5fed3
+size 798250034

checkpoint-144/global_step144/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:a70e843c10b46b7cb7543593e721bdf0df66194f8628380d675ecaa8f4d7cc97
+size 798250034

checkpoint-144/global_step144/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:b4b283ac3280d774e37014b7436123eef42dec7fb200d92d53b2f75a0164376d
+size 798250034

checkpoint-144/global_step144/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:b957f368e3dd10a3ed631add88f173bc92096ffc82506aad44c4d65a3eb3f23a
+size 798250034

checkpoint-144/global_step144/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:947dfd1a8ac13101eabb88e9f53af40bb8c990f83174801f552494858b83eeb5
+size 798250034

checkpoint-144/global_step144/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d247281c208d23be3739eea99116cc901c3439ba13a2c036383a66bef6a5d81
+size 798250034

checkpoint-144/global_step144/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f4e26add6d3a305a7d0bf9ccaf73077203175e0d3616bf31f9e9e3f71a02db2
+size 798250034

checkpoint-144/global_step144/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edbff976d942e5a8ba1d212b6d39a5cb46696c05e7326a67f65c889e99360231
+size 798250034

checkpoint-144/global_step144/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fab5438e9bb38a215ea7a169e3c2272a474c6562f00a1d5368948aedf0bd56c4
+size 566930

checkpoint-144/global_step144/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a80a56763e897e4e514e2515f662176457fb7297838ba862b0b28a7c6cdef03
+size 566930

checkpoint-144/global_step144/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c8b51c39788f74bf82e1510f7693834279460af676bcd417806b8a4e1e1680
+size 566930

checkpoint-144/global_step144/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec47eb7feb40eaf378a396a1b61c810e49e58af5b4bb1a1bad2d7f75fcdb2f20
+size 566930

checkpoint-144/global_step144/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c99166a85edd48b78e121466ae497c7c027addbe56b5ee9a031a563bdca7aff6
+size 566930

checkpoint-144/global_step144/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:895b76bbf5de7e2b21a6e85df9c9d85bb4ad01d3bfa8db538c732c4de61810a0
+size 566930

checkpoint-144/global_step144/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:700e44f1703f9731430dc5f485786f4d9cbe1b6c758bb08f3d5b7fc58912a3cb
+size 566930

checkpoint-144/global_step144/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be8ebce2c2b631670f7f07bd0fa1c2d8dfdbe87aafe3113a3c1a51c91c36b919
+size 566930

checkpoint-144/latest

@@ -0,0 +1 @@
+global_step144

checkpoint-144/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624fad9362a44ecd50e95cb12e5de04e36fb855a0aa3b7fbcd329783d4c90868
+size 15984

checkpoint-144/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9e3837bb7238ac0c04760e6b683921653ae2c96d90d0f6c80402735f933e028
+size 15984

checkpoint-144/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1186d6f078660b3bf59fa8f7d0ac77cb88b5e99006312fb5116ce3bcdcb5493
+size 15984

checkpoint-144/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03c9891a623e05767952ef66557b98f184b4f80a747c6e2484c091212bf61a9d
+size 15984

checkpoint-144/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde50816ee8af4b7910dfa9ad55b2be7150bcc3b40dca07ca7a1653792b7127f
+size 15984

checkpoint-144/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64be10dcd5c45cc8d4463ecb1db28b8aec968be62570046debb5c875fcc84e29
+size 15984

checkpoint-144/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34865d1975e8cbdfdcbe68095ee78880946455b2dffdae3800787ed028385862
+size 15984

checkpoint-144/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abda49cd8ca4a018608d14472994ffb10edd386aa7688db341ea8d6e566cee3
+size 15984

checkpoint-144/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd1cd4916dea79332261efbf8f92d6b4921cdf4822b880695f56463917d9d3a5
+size 1064

checkpoint-144/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": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-144/tokenizer.model

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

checkpoint-144/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-144/trainer_state.json

@@ -0,0 +1,885 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.5,
+  "eval_steps": 500,
+  "global_step": 144,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 3.9159,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8e-05,
+      "loss": 3.7411,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00012,
+      "loss": 2.6559,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00016,
+      "loss": 1.0552,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 0.4381,
+      "step": 5
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019997946042345127,
+      "loss": 0.7843,
+      "step": 6
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019991785013128923,
+      "loss": 0.4278,
+      "step": 7
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001998151944325001,
+      "loss": 0.3102,
+      "step": 8
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019967153549717553,
+      "loss": 0.184,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019948693233918952,
+      "loss": 0.2193,
+      "step": 10
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019926146079195594,
+      "loss": 0.1322,
+      "step": 11
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001989952134772769,
+      "loss": 0.1299,
+      "step": 12
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019868829976729443,
+      "loss": 0.1289,
+      "step": 13
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019834084573956128,
+      "loss": 0.1078,
+      "step": 14
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00019795299412524945,
+      "loss": 0.0919,
+      "step": 15
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00019752490425051743,
+      "loss": 0.0843,
+      "step": 16
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00019705675197106016,
+      "loss": 0.0998,
+      "step": 17
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00019654872959986937,
+      "loss": 0.0729,
+      "step": 18
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001960010458282326,
+      "loss": 0.111,
+      "step": 19
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00019541392564000488,
+      "loss": 0.0915,
+      "step": 20
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00019478761021918728,
+      "loss": 0.0905,
+      "step": 21
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00019412235685085035,
+      "loss": 0.0977,
+      "step": 22
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00019341843881544372,
+      "loss": 0.0709,
+      "step": 23
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00019267614527653488,
+      "loss": 0.0959,
+      "step": 24
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00019189578116202307,
+      "loss": 0.0722,
+      "step": 25
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00019107766703887764,
+      "loss": 0.0737,
+      "step": 26
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00019022213898145176,
+      "loss": 0.0744,
+      "step": 27
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00018932954843342591,
+      "loss": 0.0663,
+      "step": 28
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00018840026206343784,
+      "loss": 0.0887,
+      "step": 29
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00018743466161445823,
+      "loss": 0.0816,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00018643314374697378,
+      "loss": 0.0705,
+      "step": 31
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00018539611987604258,
+      "loss": 0.0529,
+      "step": 32
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00018432401600228823,
+      "loss": 0.0753,
+      "step": 33
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0001832172725369024,
+      "loss": 0.0514,
+      "step": 34
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018207634412072764,
+      "loss": 0.0459,
+      "step": 35
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0523,
+      "step": 36
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001796938210212915,
+      "loss": 0.0377,
+      "step": 37
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00017845320505834175,
+      "loss": 0.0499,
+      "step": 38
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001771803611831762,
+      "loss": 0.0486,
+      "step": 39
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001758758122692791,
+      "loss": 0.0348,
+      "step": 40
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00017454009421429597,
+      "loss": 0.0407,
+      "step": 41
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00017317375571989158,
+      "loss": 0.0544,
+      "step": 42
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00017177735806634789,
+      "loss": 0.0317,
+      "step": 43
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00017035147488199482,
+      "loss": 0.0504,
+      "step": 44
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00016889669190756868,
+      "loss": 0.0592,
+      "step": 45
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00016741360675559473,
+      "loss": 0.047,
+      "step": 46
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00016590282866489319,
+      "loss": 0.0409,
+      "step": 47
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00016436497825030884,
+      "loss": 0.0341,
+      "step": 48
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00016280068724776797,
+      "loss": 0.0783,
+      "step": 49
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001612105982547663,
+      "loss": 0.0318,
+      "step": 50
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0001595953644663957,
+      "loss": 0.05,
+      "step": 51
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.000157955649407017,
+      "loss": 0.0659,
+      "step": 52
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00015629212665768978,
+      "loss": 0.0594,
+      "step": 53
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00015460547957947104,
+      "loss": 0.0279,
+      "step": 54
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00015289640103269625,
+      "loss": 0.0731,
+      "step": 55
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00015116559309235825,
+      "loss": 0.047,
+      "step": 56
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0001494137667597006,
+      "loss": 0.0523,
+      "step": 57
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00014764164167014451,
+      "loss": 0.0604,
+      "step": 58
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00014584994579766865,
+      "loss": 0.048,
+      "step": 59
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00014403941515576344,
+      "loss": 0.0544,
+      "step": 60
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0001422107934950832,
+      "loss": 0.0493,
+      "step": 61
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00014036483199791948,
+      "loss": 0.0699,
+      "step": 62
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001385022889696218,
+      "loss": 0.0594,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013662392952709228,
+      "loss": 0.0531,
+      "step": 64
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00013473052528448201,
+      "loss": 0.0336,
+      "step": 65
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013282285403621864,
+      "loss": 0.0474,
+      "step": 66
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0288,
+      "step": 67
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00012896785068234926,
+      "loss": 0.0277,
+      "step": 68
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00012702210217947288,
+      "loss": 0.0386,
+      "step": 69
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00012506525322587207,
+      "loss": 0.023,
+      "step": 70
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00012309810767852433,
+      "loss": 0.0342,
+      "step": 71
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00012112147362416076,
+      "loss": 0.023,
+      "step": 72
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00011913616304731063,
+      "loss": 0.0242,
+      "step": 73
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00011714299149674537,
+      "loss": 0.0322,
+      "step": 74
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00011514277775045768,
+      "loss": 0.0404,
+      "step": 75
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.00011313634347931466,
+      "loss": 0.027,
+      "step": 76
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.00011112451290952237,
+      "loss": 0.0282,
+      "step": 77
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.00010910811248404065,
+      "loss": 0.0295,
+      "step": 78
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.0001070879705230873,
+      "loss": 0.0315,
+      "step": 79
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00010506491688387127,
+      "loss": 0.0301,
+      "step": 80
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0001030397826196943,
+      "loss": 0.0251,
+      "step": 81
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.00010101339963856111,
+      "loss": 0.0186,
+      "step": 82
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.898660036143893e-05,
+      "loss": 0.0238,
+      "step": 83
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 9.696021738030575e-05,
+      "loss": 0.0188,
+      "step": 84
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 9.493508311612874e-05,
+      "loss": 0.0161,
+      "step": 85
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.291202947691271e-05,
+      "loss": 0.0227,
+      "step": 86
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 9.089188751595936e-05,
+      "loss": 0.0276,
+      "step": 87
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 8.887548709047764e-05,
+      "loss": 0.035,
+      "step": 88
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 8.686365652068535e-05,
+      "loss": 0.0165,
+      "step": 89
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.485722224954237e-05,
+      "loss": 0.0225,
+      "step": 90
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.285700850325467e-05,
+      "loss": 0.0171,
+      "step": 91
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.086383695268938e-05,
+      "loss": 0.031,
+      "step": 92
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 7.887852637583926e-05,
+      "loss": 0.0291,
+      "step": 93
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 7.690189232147566e-05,
+      "loss": 0.0346,
+      "step": 94
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 7.493474677412794e-05,
+      "loss": 0.0327,
+      "step": 95
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.297789782052717e-05,
+      "loss": 0.0151,
+      "step": 96
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 7.10321493176508e-05,
+      "loss": 0.0179,
+      "step": 97
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0101,
+      "step": 98
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 6.717714596378137e-05,
+      "loss": 0.0207,
+      "step": 99
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 6.526947471551798e-05,
+      "loss": 0.0093,
+      "step": 100
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 6.337607047290774e-05,
+      "loss": 0.0135,
+      "step": 101
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 6.149771103037821e-05,
+      "loss": 0.0149,
+      "step": 102
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 5.9635168002080564e-05,
+      "loss": 0.0147,
+      "step": 103
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 5.7789206504916816e-05,
+      "loss": 0.0109,
+      "step": 104
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 5.596058484423656e-05,
+      "loss": 0.0107,
+      "step": 105
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 5.415005420233141e-05,
+      "loss": 0.0099,
+      "step": 106
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 5.2358358329855516e-05,
+      "loss": 0.0172,
+      "step": 107
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 5.058623324029944e-05,
+      "loss": 0.0173,
+      "step": 108
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 4.8834406907641784e-05,
+      "loss": 0.0126,
+      "step": 109
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 4.710359896730379e-05,
+      "loss": 0.0144,
+      "step": 110
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 4.539452042052901e-05,
+      "loss": 0.012,
+      "step": 111
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 4.3707873342310254e-05,
+      "loss": 0.0146,
+      "step": 112
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 4.204435059298303e-05,
+      "loss": 0.0133,
+      "step": 113
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 4.040463553360431e-05,
+      "loss": 0.0065,
+      "step": 114
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 3.878940174523371e-05,
+      "loss": 0.0144,
+      "step": 115
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 3.719931275223205e-05,
+      "loss": 0.0066,
+      "step": 116
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 3.5635021749691166e-05,
+      "loss": 0.0168,
+      "step": 117
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 3.4097171335106824e-05,
+      "loss": 0.0151,
+      "step": 118
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 3.258639324440527e-05,
+      "loss": 0.0151,
+      "step": 119
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 3.110330809243134e-05,
+      "loss": 0.0112,
+      "step": 120
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.964852511800519e-05,
+      "loss": 0.0287,
+      "step": 121
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 2.8222641933652117e-05,
+      "loss": 0.0103,
+      "step": 122
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 2.6826244280108437e-05,
+      "loss": 0.0167,
+      "step": 123
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 2.5459905785704042e-05,
+      "loss": 0.0073,
+      "step": 124
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.4124187730720917e-05,
+      "loss": 0.0065,
+      "step": 125
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 2.2819638816823797e-05,
+      "loss": 0.0132,
+      "step": 126
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 2.154679494165829e-05,
+      "loss": 0.0032,
+      "step": 127
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.0306178978708514e-05,
+      "loss": 0.0041,
+      "step": 128
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0031,
+      "step": 129
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 1.7923655879272393e-05,
+      "loss": 0.0034,
+      "step": 130
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 1.6782727463097624e-05,
+      "loss": 0.0091,
+      "step": 131
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.5675983997711795e-05,
+      "loss": 0.0089,
+      "step": 132
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 1.4603880123957447e-05,
+      "loss": 0.0129,
+      "step": 133
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.356685625302625e-05,
+      "loss": 0.0129,
+      "step": 134
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.2565338385541792e-05,
+      "loss": 0.0032,
+      "step": 135
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 1.1599737936562149e-05,
+      "loss": 0.0118,
+      "step": 136
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 1.0670451566574102e-05,
+      "loss": 0.0062,
+      "step": 137
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 9.777861018548251e-06,
+      "loss": 0.0068,
+      "step": 138
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 8.92233296112236e-06,
+      "loss": 0.0086,
+      "step": 139
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 8.10421883797694e-06,
+      "loss": 0.0049,
+      "step": 140
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 7.32385472346514e-06,
+      "loss": 0.0103,
+      "step": 141
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 6.581561184556295e-06,
+      "loss": 0.0086,
+      "step": 142
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 5.87764314914967e-06,
+      "loss": 0.0053,
+      "step": 143
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 5.212389780812732e-06,
+      "loss": 0.007,
+      "step": 144
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 72,
+  "total_flos": 29370880622592.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-144/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:948c6c89f185a058adb744d3fe2374ac59b1bb52d76771c32abea6421dd6f8be
+size 6712

checkpoint-144/zero_to_fp32.py

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

config.json

@@ -0,0 +1,49 @@
+{
+  "_name_or_path": "liuhaotian/llava-v1.5-13b",
+  "architectures": [
+    "LlavaLlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "freeze_mm_mlp_adapter": false,
+  "freeze_mm_vision_resampler": false,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "image_aspect_ratio": "pad",
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_length": 4096,
+  "max_position_embeddings": 4096,
+  "mm_hidden_size": 1024,
+  "mm_patch_merge_type": "flat",
+  "mm_projector_lr": 2e-05,
+  "mm_projector_type": "mlp2x_gelu",
+  "mm_resampler_type": null,
+  "mm_use_im_patch_token": false,
+  "mm_use_im_start_end": false,
+  "mm_vision_select_feature": "patch",
+  "mm_vision_select_layer": -2,
+  "mm_vision_tower": "openai/clip-vit-large-patch14-336",
+  "model_type": "llava_llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "tokenizer_model_max_length": 2048,
+  "tokenizer_padding_side": "right",
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "tune_mm_mlp_adapter": false,
+  "tune_mm_vision_resampler": false,
+  "unfreeze_mm_vision_tower": false,
+  "use_cache": true,
+  "use_mm_proj": true,
+  "vocab_size": 32000
+}

non_lora_trainables.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af36f979a14f7668a6d2685e0e2086c7128e671ec869f15f8a40999652a0528
+size 62937264

trainer_state.json

@@ -0,0 +1,990 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4e-05,
+      "loss": 3.9159,
+      "step": 1
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 8e-05,
+      "loss": 3.7411,
+      "step": 2
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00012,
+      "loss": 2.6559,
+      "step": 3
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.00016,
+      "loss": 1.0552,
+      "step": 4
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002,
+      "loss": 0.4381,
+      "step": 5
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.00019997946042345127,
+      "loss": 0.7843,
+      "step": 6
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.00019991785013128923,
+      "loss": 0.4278,
+      "step": 7
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0001998151944325001,
+      "loss": 0.3102,
+      "step": 8
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00019967153549717553,
+      "loss": 0.184,
+      "step": 9
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00019948693233918952,
+      "loss": 0.2193,
+      "step": 10
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00019926146079195594,
+      "loss": 0.1322,
+      "step": 11
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0001989952134772769,
+      "loss": 0.1299,
+      "step": 12
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00019868829976729443,
+      "loss": 0.1289,
+      "step": 13
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00019834084573956128,
+      "loss": 0.1078,
+      "step": 14
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00019795299412524945,
+      "loss": 0.0919,
+      "step": 15
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00019752490425051743,
+      "loss": 0.0843,
+      "step": 16
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00019705675197106016,
+      "loss": 0.0998,
+      "step": 17
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00019654872959986937,
+      "loss": 0.0729,
+      "step": 18
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001960010458282326,
+      "loss": 0.111,
+      "step": 19
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00019541392564000488,
+      "loss": 0.0915,
+      "step": 20
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00019478761021918728,
+      "loss": 0.0905,
+      "step": 21
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00019412235685085035,
+      "loss": 0.0977,
+      "step": 22
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00019341843881544372,
+      "loss": 0.0709,
+      "step": 23
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00019267614527653488,
+      "loss": 0.0959,
+      "step": 24
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00019189578116202307,
+      "loss": 0.0722,
+      "step": 25
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00019107766703887764,
+      "loss": 0.0737,
+      "step": 26
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00019022213898145176,
+      "loss": 0.0744,
+      "step": 27
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.00018932954843342591,
+      "loss": 0.0663,
+      "step": 28
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 0.00018840026206343784,
+      "loss": 0.0887,
+      "step": 29
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.00018743466161445823,
+      "loss": 0.0816,
+      "step": 30
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 0.00018643314374697378,
+      "loss": 0.0705,
+      "step": 31
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.00018539611987604258,
+      "loss": 0.0529,
+      "step": 32
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.00018432401600228823,
+      "loss": 0.0753,
+      "step": 33
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.0001832172725369024,
+      "loss": 0.0514,
+      "step": 34
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.00018207634412072764,
+      "loss": 0.0459,
+      "step": 35
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.0523,
+      "step": 36
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001796938210212915,
+      "loss": 0.0377,
+      "step": 37
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00017845320505834175,
+      "loss": 0.0499,
+      "step": 38
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 0.0001771803611831762,
+      "loss": 0.0486,
+      "step": 39
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.0001758758122692791,
+      "loss": 0.0348,
+      "step": 40
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 0.00017454009421429597,
+      "loss": 0.0407,
+      "step": 41
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00017317375571989158,
+      "loss": 0.0544,
+      "step": 42
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.00017177735806634789,
+      "loss": 0.0317,
+      "step": 43
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00017035147488199482,
+      "loss": 0.0504,
+      "step": 44
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 0.00016889669190756868,
+      "loss": 0.0592,
+      "step": 45
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.00016741360675559473,
+      "loss": 0.047,
+      "step": 46
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 0.00016590282866489319,
+      "loss": 0.0409,
+      "step": 47
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 0.00016436497825030884,
+      "loss": 0.0341,
+      "step": 48
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.00016280068724776797,
+      "loss": 0.0783,
+      "step": 49
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 0.0001612105982547663,
+      "loss": 0.0318,
+      "step": 50
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 0.0001595953644663957,
+      "loss": 0.05,
+      "step": 51
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 0.000157955649407017,
+      "loss": 0.0659,
+      "step": 52
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 0.00015629212665768978,
+      "loss": 0.0594,
+      "step": 53
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.00015460547957947104,
+      "loss": 0.0279,
+      "step": 54
+    },
+    {
+      "epoch": 1.72,
+      "learning_rate": 0.00015289640103269625,
+      "loss": 0.0731,
+      "step": 55
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00015116559309235825,
+      "loss": 0.047,
+      "step": 56
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.0001494137667597006,
+      "loss": 0.0523,
+      "step": 57
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 0.00014764164167014451,
+      "loss": 0.0604,
+      "step": 58
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00014584994579766865,
+      "loss": 0.048,
+      "step": 59
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 0.00014403941515576344,
+      "loss": 0.0544,
+      "step": 60
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 0.0001422107934950832,
+      "loss": 0.0493,
+      "step": 61
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00014036483199791948,
+      "loss": 0.0699,
+      "step": 62
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001385022889696218,
+      "loss": 0.0594,
+      "step": 63
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.00013662392952709228,
+      "loss": 0.0531,
+      "step": 64
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00013473052528448201,
+      "loss": 0.0336,
+      "step": 65
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013282285403621864,
+      "loss": 0.0474,
+      "step": 66
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0288,
+      "step": 67
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 0.00012896785068234926,
+      "loss": 0.0277,
+      "step": 68
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00012702210217947288,
+      "loss": 0.0386,
+      "step": 69
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 0.00012506525322587207,
+      "loss": 0.023,
+      "step": 70
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 0.00012309810767852433,
+      "loss": 0.0342,
+      "step": 71
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 0.00012112147362416076,
+      "loss": 0.023,
+      "step": 72
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 0.00011913616304731063,
+      "loss": 0.0242,
+      "step": 73
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 0.00011714299149674537,
+      "loss": 0.0322,
+      "step": 74
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 0.00011514277775045768,
+      "loss": 0.0404,
+      "step": 75
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 0.00011313634347931466,
+      "loss": 0.027,
+      "step": 76
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 0.00011112451290952237,
+      "loss": 0.0282,
+      "step": 77
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 0.00010910811248404065,
+      "loss": 0.0295,
+      "step": 78
+    },
+    {
+      "epoch": 2.47,
+      "learning_rate": 0.0001070879705230873,
+      "loss": 0.0315,
+      "step": 79
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.00010506491688387127,
+      "loss": 0.0301,
+      "step": 80
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 0.0001030397826196943,
+      "loss": 0.0251,
+      "step": 81
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.00010101339963856111,
+      "loss": 0.0186,
+      "step": 82
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 9.898660036143893e-05,
+      "loss": 0.0238,
+      "step": 83
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 9.696021738030575e-05,
+      "loss": 0.0188,
+      "step": 84
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 9.493508311612874e-05,
+      "loss": 0.0161,
+      "step": 85
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 9.291202947691271e-05,
+      "loss": 0.0227,
+      "step": 86
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 9.089188751595936e-05,
+      "loss": 0.0276,
+      "step": 87
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 8.887548709047764e-05,
+      "loss": 0.035,
+      "step": 88
+    },
+    {
+      "epoch": 2.78,
+      "learning_rate": 8.686365652068535e-05,
+      "loss": 0.0165,
+      "step": 89
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 8.485722224954237e-05,
+      "loss": 0.0225,
+      "step": 90
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 8.285700850325467e-05,
+      "loss": 0.0171,
+      "step": 91
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 8.086383695268938e-05,
+      "loss": 0.031,
+      "step": 92
+    },
+    {
+      "epoch": 2.91,
+      "learning_rate": 7.887852637583926e-05,
+      "loss": 0.0291,
+      "step": 93
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 7.690189232147566e-05,
+      "loss": 0.0346,
+      "step": 94
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 7.493474677412794e-05,
+      "loss": 0.0327,
+      "step": 95
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.297789782052717e-05,
+      "loss": 0.0151,
+      "step": 96
+    },
+    {
+      "epoch": 3.03,
+      "learning_rate": 7.10321493176508e-05,
+      "loss": 0.0179,
+      "step": 97
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.0101,
+      "step": 98
+    },
+    {
+      "epoch": 3.09,
+      "learning_rate": 6.717714596378137e-05,
+      "loss": 0.0207,
+      "step": 99
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 6.526947471551798e-05,
+      "loss": 0.0093,
+      "step": 100
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 6.337607047290774e-05,
+      "loss": 0.0135,
+      "step": 101
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 6.149771103037821e-05,
+      "loss": 0.0149,
+      "step": 102
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 5.9635168002080564e-05,
+      "loss": 0.0147,
+      "step": 103
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 5.7789206504916816e-05,
+      "loss": 0.0109,
+      "step": 104
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 5.596058484423656e-05,
+      "loss": 0.0107,
+      "step": 105
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 5.415005420233141e-05,
+      "loss": 0.0099,
+      "step": 106
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 5.2358358329855516e-05,
+      "loss": 0.0172,
+      "step": 107
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 5.058623324029944e-05,
+      "loss": 0.0173,
+      "step": 108
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 4.8834406907641784e-05,
+      "loss": 0.0126,
+      "step": 109
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 4.710359896730379e-05,
+      "loss": 0.0144,
+      "step": 110
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 4.539452042052901e-05,
+      "loss": 0.012,
+      "step": 111
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 4.3707873342310254e-05,
+      "loss": 0.0146,
+      "step": 112
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 4.204435059298303e-05,
+      "loss": 0.0133,
+      "step": 113
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 4.040463553360431e-05,
+      "loss": 0.0065,
+      "step": 114
+    },
+    {
+      "epoch": 3.59,
+      "learning_rate": 3.878940174523371e-05,
+      "loss": 0.0144,
+      "step": 115
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 3.719931275223205e-05,
+      "loss": 0.0066,
+      "step": 116
+    },
+    {
+      "epoch": 3.66,
+      "learning_rate": 3.5635021749691166e-05,
+      "loss": 0.0168,
+      "step": 117
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 3.4097171335106824e-05,
+      "loss": 0.0151,
+      "step": 118
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 3.258639324440527e-05,
+      "loss": 0.0151,
+      "step": 119
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 3.110330809243134e-05,
+      "loss": 0.0112,
+      "step": 120
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.964852511800519e-05,
+      "loss": 0.0287,
+      "step": 121
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 2.8222641933652117e-05,
+      "loss": 0.0103,
+      "step": 122
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 2.6826244280108437e-05,
+      "loss": 0.0167,
+      "step": 123
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 2.5459905785704042e-05,
+      "loss": 0.0073,
+      "step": 124
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 2.4124187730720917e-05,
+      "loss": 0.0065,
+      "step": 125
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 2.2819638816823797e-05,
+      "loss": 0.0132,
+      "step": 126
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 2.154679494165829e-05,
+      "loss": 0.0032,
+      "step": 127
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.0306178978708514e-05,
+      "loss": 0.0041,
+      "step": 128
+    },
+    {
+      "epoch": 4.03,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0031,
+      "step": 129
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 1.7923655879272393e-05,
+      "loss": 0.0034,
+      "step": 130
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 1.6782727463097624e-05,
+      "loss": 0.0091,
+      "step": 131
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 1.5675983997711795e-05,
+      "loss": 0.0089,
+      "step": 132
+    },
+    {
+      "epoch": 4.16,
+      "learning_rate": 1.4603880123957447e-05,
+      "loss": 0.0129,
+      "step": 133
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 1.356685625302625e-05,
+      "loss": 0.0129,
+      "step": 134
+    },
+    {
+      "epoch": 4.22,
+      "learning_rate": 1.2565338385541792e-05,
+      "loss": 0.0032,
+      "step": 135
+    },
+    {
+      "epoch": 4.25,
+      "learning_rate": 1.1599737936562149e-05,
+      "loss": 0.0118,
+      "step": 136
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 1.0670451566574102e-05,
+      "loss": 0.0062,
+      "step": 137
+    },
+    {
+      "epoch": 4.31,
+      "learning_rate": 9.777861018548251e-06,
+      "loss": 0.0068,
+      "step": 138
+    },
+    {
+      "epoch": 4.34,
+      "learning_rate": 8.92233296112236e-06,
+      "loss": 0.0086,
+      "step": 139
+    },
+    {
+      "epoch": 4.38,
+      "learning_rate": 8.10421883797694e-06,
+      "loss": 0.0049,
+      "step": 140
+    },
+    {
+      "epoch": 4.41,
+      "learning_rate": 7.32385472346514e-06,
+      "loss": 0.0103,
+      "step": 141
+    },
+    {
+      "epoch": 4.44,
+      "learning_rate": 6.581561184556295e-06,
+      "loss": 0.0086,
+      "step": 142
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 5.87764314914967e-06,
+      "loss": 0.0053,
+      "step": 143
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 5.212389780812732e-06,
+      "loss": 0.007,
+      "step": 144
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 4.586074359995119e-06,
+      "loss": 0.0064,
+      "step": 145
+    },
+    {
+      "epoch": 4.56,
+      "learning_rate": 3.998954171767422e-06,
+      "loss": 0.0023,
+      "step": 146
+    },
+    {
+      "epoch": 4.59,
+      "learning_rate": 3.451270400130646e-06,
+      "loss": 0.0045,
+      "step": 147
+    },
+    {
+      "epoch": 4.62,
+      "learning_rate": 2.943248028939838e-06,
+      "loss": 0.0035,
+      "step": 148
+    },
+    {
+      "epoch": 4.66,
+      "learning_rate": 2.4750957494826033e-06,
+      "loss": 0.005,
+      "step": 149
+    },
+    {
+      "epoch": 4.69,
+      "learning_rate": 2.0470058747505516e-06,
+      "loss": 0.0124,
+      "step": 150
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 1.6591542604387445e-06,
+      "loss": 0.0027,
+      "step": 151
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 1.3117002327055927e-06,
+      "loss": 0.0055,
+      "step": 152
+    },
+    {
+      "epoch": 4.78,
+      "learning_rate": 1.004786522723089e-06,
+      "loss": 0.002,
+      "step": 153
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 7.385392080440534e-07,
+      "loss": 0.0038,
+      "step": 154
+    },
+    {
+      "epoch": 4.84,
+      "learning_rate": 5.130676608104845e-07,
+      "loss": 0.013,
+      "step": 155
+    },
+    {
+      "epoch": 4.88,
+      "learning_rate": 3.2846450282447703e-07,
+      "loss": 0.0073,
+      "step": 156
+    },
+    {
+      "epoch": 4.91,
+      "learning_rate": 1.8480556749991274e-07,
+      "loss": 0.0113,
+      "step": 157
+    },
+    {
+      "epoch": 4.94,
+      "learning_rate": 8.214986871076802e-08,
+      "loss": 0.0066,
+      "step": 158
+    },
+    {
+      "epoch": 4.97,
+      "learning_rate": 2.0539576548717076e-08,
+      "loss": 0.0031,
+      "step": 159
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.003,
+      "step": 160
+    },
+    {
+      "epoch": 5.0,
+      "step": 160,
+      "total_flos": 32634127908864.0,
+      "train_loss": 0.11789017441187752,
+      "train_runtime": 1826.6084,
+      "train_samples_per_second": 10.949,
+      "train_steps_per_second": 0.088
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 72,
+  "total_flos": 32634127908864.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}