Training in progress, step 400, checkpoint

checkpoint-400/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: HuggingFaceH4/zephyr-7b-beta
+---
+
+# 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-400/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-400/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39f6e40abe652c2034fbeef6ba673f34ac878c8706c5bd79c6bf7582b6bc7847
+size 54560368

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38595797c3f597a87ab18a44e887d4c3aff26774eb4a760b41b7fb169179d65e
+size 109267450

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d245e05e72192c132e0f2edb6fdcae0c578c890f0fe912f17ec7b0bba2d38cc3
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0036d82f2e21e3394011d2fd21cbbd9af467f37a026201c919dae62d508ef9ba
+size 1064

checkpoint-400/special_tokens_map.json

@@ -0,0 +1,29 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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-400/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

checkpoint-400/tokenizer_config.json

@@ -0,0 +1,50 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_lenght": 8192,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "padding": true,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

checkpoint-400/trainer_state.json

@@ -0,0 +1,393 @@
+{
+  "best_metric": 0.020107893273234367,
+  "best_model_checkpoint": "./Zephyr/27-03-24-Weni-WeniGPT-QA-Zephyr-7B-4.0.0-KTO_WeniGPT Experiment using KTO trainer with no collator-2_max_steps-786_batch_16_2024-03-27_ppid_9/checkpoint-400",
+  "epoch": 1.510146295422369,
+  "eval_steps": 50,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.2820355892181396,
+      "kl": 0.7391773462295532,
+      "learning_rate": 0.0001666666666666667,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 785.5091,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 20
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": NaN,
+      "kl": 1.364301085472107,
+      "learning_rate": 0.00019606299212598428,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 124.9389,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 40
+    },
+    {
+      "epoch": 0.19,
+      "eval_kl": 3.282975673675537,
+      "eval_logps/chosen": -132.00738525390625,
+      "eval_logps/rejected": -237.69239807128906,
+      "eval_loss": 0.09803511947393417,
+      "eval_rewards/chosen": 4.3711838722229,
+      "eval_rewards/margins": 8.833364486694336,
+      "eval_rewards/rejected": -4.462180137634277,
+      "eval_runtime": 474.8108,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.535,
+      "step": 50
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1073336601257324,
+      "kl": 0.8054396510124207,
+      "learning_rate": 0.00019107611548556432,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 91.2134,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 60
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.4274377226829529,
+      "kl": 0.38704636693000793,
+      "learning_rate": 0.00018582677165354333,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 26.9569,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 80
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.5270018577575684,
+      "kl": 0.47709473967552185,
+      "learning_rate": 0.0001805774278215223,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 10.8269,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 100
+    },
+    {
+      "epoch": 0.38,
+      "eval_kl": 0.762260377407074,
+      "eval_logps/chosen": -135.4526824951172,
+      "eval_logps/rejected": -541.3764038085938,
+      "eval_loss": 0.039932698011398315,
+      "eval_rewards/chosen": 4.026655197143555,
+      "eval_rewards/margins": 38.857234954833984,
+      "eval_rewards/rejected": -34.83057403564453,
+      "eval_runtime": 474.2877,
+      "eval_samples_per_second": 1.071,
+      "eval_steps_per_second": 0.536,
+      "step": 100
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.19858050346374512,
+      "kl": 1.8940637111663818,
+      "learning_rate": 0.00017532808398950132,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 34.2088,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 120
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 2.615041971206665,
+      "kl": 1.40102219581604,
+      "learning_rate": 0.00017007874015748033,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 276.3512,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 140
+    },
+    {
+      "epoch": 0.57,
+      "eval_kl": 1.686139702796936,
+      "eval_logps/chosen": -127.73213195800781,
+      "eval_logps/rejected": -397.8934631347656,
+      "eval_loss": 0.02803400717675686,
+      "eval_rewards/chosen": 4.798709869384766,
+      "eval_rewards/margins": 25.2810001373291,
+      "eval_rewards/rejected": -20.482288360595703,
+      "eval_runtime": 474.6717,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.535,
+      "step": 150
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.31603240966796875,
+      "kl": 0.7387570738792419,
+      "learning_rate": 0.00016482939632545934,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 216.0894,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 160
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.3982734978199005,
+      "kl": 1.4841536283493042,
+      "learning_rate": 0.00015958005249343832,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 8.0994,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 180
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 2.1777164936065674,
+      "kl": 0.3081069588661194,
+      "learning_rate": 0.00015433070866141733,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 5.7214,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 200
+    },
+    {
+      "epoch": 0.76,
+      "eval_kl": 1.5452415943145752,
+      "eval_logps/chosen": -125.70950317382812,
+      "eval_logps/rejected": -412.7599182128906,
+      "eval_loss": 0.029857149347662926,
+      "eval_rewards/chosen": 5.000972270965576,
+      "eval_rewards/margins": 26.969900131225586,
+      "eval_rewards/rejected": -21.96892738342285,
+      "eval_runtime": 474.8305,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.535,
+      "step": 200
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 0.08603761345148087,
+      "kl": 1.142593264579773,
+      "learning_rate": 0.00014908136482939634,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 22.8407,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 220
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 5.5862650871276855,
+      "kl": 0.40408754348754883,
+      "learning_rate": 0.00014383202099737535,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 207.9747,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 240
+    },
+    {
+      "epoch": 0.94,
+      "eval_kl": 1.182385802268982,
+      "eval_logps/chosen": -127.54723358154297,
+      "eval_logps/rejected": -806.224853515625,
+      "eval_loss": 0.026166189461946487,
+      "eval_rewards/chosen": 4.817198276519775,
+      "eval_rewards/margins": 66.13262176513672,
+      "eval_rewards/rejected": -61.315425872802734,
+      "eval_runtime": 474.7526,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.535,
+      "step": 250
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 0.39546045660972595,
+      "kl": 0.7778356671333313,
+      "learning_rate": 0.00013858267716535433,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 720.8411,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 260
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.1680106222629547,
+      "kl": 1.798954963684082,
+      "learning_rate": 0.00013333333333333334,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 756.123,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 280
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.13731369376182556,
+      "kl": 1.9178543090820312,
+      "learning_rate": 0.00012808398950131235,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 25.0348,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 300
+    },
+    {
+      "epoch": 1.13,
+      "eval_kl": 1.4845337867736816,
+      "eval_logps/chosen": -125.86082458496094,
+      "eval_logps/rejected": -901.4517211914062,
+      "eval_loss": 0.020615577697753906,
+      "eval_rewards/chosen": 4.985838890075684,
+      "eval_rewards/margins": 75.82396697998047,
+      "eval_rewards/rejected": -70.83811950683594,
+      "eval_runtime": 474.4234,
+      "eval_samples_per_second": 1.071,
+      "eval_steps_per_second": 0.535,
+      "step": 300
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.35939568281173706,
+      "kl": 0.7613407373428345,
+      "learning_rate": 0.00012283464566929136,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 10.9288,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 320
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.0034766767639666796,
+      "kl": 0.3800249993801117,
+      "learning_rate": 0.00011758530183727034,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 3.1951,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 340
+    },
+    {
+      "epoch": 1.32,
+      "eval_kl": 0.6363816261291504,
+      "eval_logps/chosen": -128.82322692871094,
+      "eval_logps/rejected": -1020.8375244140625,
+      "eval_loss": 0.026503143832087517,
+      "eval_rewards/chosen": 4.689598560333252,
+      "eval_rewards/margins": 87.4662857055664,
+      "eval_rewards/rejected": -82.77667999267578,
+      "eval_runtime": 474.6086,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.535,
+      "step": 350
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.1018553972244263,
+      "kl": 0.1121591106057167,
+      "learning_rate": 0.00011233595800524934,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 3.5301,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 360
+    },
+    {
+      "epoch": 1.43,
+      "grad_norm": 0.6937451958656311,
+      "kl": 1.0412858724594116,
+      "learning_rate": 0.00010708661417322836,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 2.2977,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 380
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.25449952483177185,
+      "kl": 0.832425594329834,
+      "learning_rate": 0.00010183727034120735,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 68.7248,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 400
+    },
+    {
+      "epoch": 1.51,
+      "eval_kl": 1.2176250219345093,
+      "eval_logps/chosen": -125.15269470214844,
+      "eval_logps/rejected": -730.7761840820312,
+      "eval_loss": 0.020107893273234367,
+      "eval_rewards/chosen": 5.056652545928955,
+      "eval_rewards/margins": 58.827205657958984,
+      "eval_rewards/rejected": -53.77055358886719,
+      "eval_runtime": 474.7959,
+      "eval_samples_per_second": 1.07,
+      "eval_steps_per_second": 0.535,
+      "step": 400
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 786,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f8de63f7251b421ab779a91afa135a4e3d7a01d6fc2bbf75c6244ae559c699
+size 5624