Training in progress, step 200, checkpoint

checkpoint-200/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+---
+
+# 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-200/adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 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": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c78b2e9086589f3a09fe34c85c267cf01e345b024791390e48e3e4789ad99f
+size 54560368

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ba826a34eb9d7ea14230e2e8747dd0c60a15348cbfa00bd413076f32e1e9b9
+size 109267450

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01c87c6e854b7bb6ec339c97d067bba2522d1fa713465e94a4d57a37ae9938a8
+size 1064

checkpoint-200/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-200/tokenizer.model

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% 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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,207 @@
+{
+  "best_metric": 0.014605735428631306,
+  "best_model_checkpoint": "./mixstral/01-04-24-Weni-WeniGPT-QA-Zephyr-7B-5.0.1-KTO_WeniGPT Experiment using KTO trainer with no collator, Mixstral model and no system prompt.-2_max_steps-262_batch_32_2024-04-01_ppid_2059/checkpoint-200",
+  "epoch": 1.5165876777251186,
+  "eval_steps": 50,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.2250428199768066,
+      "learning_rate": 0.00019133858267716535,
+      "loss": 0.3931,
+      "step": 20,
+      "train/kl": 1.2274655103683472,
+      "train/logps/chosen": -192.38479614257812,
+      "train/logps/rejected": -224.69888305664062,
+      "train/rewards/chosen": -0.14804823696613312,
+      "train/rewards/margins": 1.4835635870695114,
+      "train/rewards/rejected": -1.6316118240356445
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.3648412227630615,
+      "learning_rate": 0.00017559055118110238,
+      "loss": 0.1177,
+      "step": 40,
+      "train/kl": 0.9526737332344055,
+      "train/logps/chosen": -162.2818603515625,
+      "train/logps/rejected": -265.06201171875,
+      "train/rewards/chosen": 3.2411201000213623,
+      "train/rewards/margins": 10.128443956375122,
+      "train/rewards/rejected": -6.88732385635376
+    },
+    {
+      "epoch": 0.38,
+      "eval/kl": 0.0,
+      "eval/logps/chosen": -149.90289306640625,
+      "eval/logps/rejected": -403.8857727050781,
+      "eval/rewards/chosen": 4.500288486480713,
+      "eval/rewards/margins": 24.8637433052063,
+      "eval/rewards/rejected": -20.363454818725586,
+      "eval_loss": 0.04682931676506996,
+      "eval_runtime": 1026.2439,
+      "eval_samples_per_second": 0.476,
+      "eval_steps_per_second": 0.119,
+      "step": 50
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.3626991510391235,
+      "learning_rate": 0.00015984251968503938,
+      "loss": 0.0493,
+      "step": 60,
+      "train/kl": 0.10373685508966446,
+      "train/logps/chosen": -142.3507080078125,
+      "train/logps/rejected": -377.33282470703125,
+      "train/rewards/chosen": 5.036634922027588,
+      "train/rewards/margins": 22.215031147003174,
+      "train/rewards/rejected": -17.178396224975586
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.18376566469669342,
+      "learning_rate": 0.0001440944881889764,
+      "loss": 0.0223,
+      "step": 80,
+      "train/kl": 0.26756417751312256,
+      "train/logps/chosen": -134.23001098632812,
+      "train/logps/rejected": -367.7132263183594,
+      "train/rewards/chosen": 5.875685691833496,
+      "train/rewards/margins": 24.18467617034912,
+      "train/rewards/rejected": -18.308990478515625
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.5995637774467468,
+      "learning_rate": 0.00012834645669291338,
+      "loss": 0.0257,
+      "step": 100,
+      "train/kl": 0.0,
+      "train/logps/chosen": -145.93228149414062,
+      "train/logps/rejected": -409.9689025878906,
+      "train/rewards/chosen": 6.230437755584717,
+      "train/rewards/margins": 27.460736751556396,
+      "train/rewards/rejected": -21.23029899597168
+    },
+    {
+      "epoch": 0.76,
+      "eval/kl": 0.2827310264110565,
+      "eval/logps/chosen": -131.14064025878906,
+      "eval/logps/rejected": -441.502197265625,
+      "eval/rewards/chosen": 6.376513957977295,
+      "eval/rewards/margins": 30.501620769500732,
+      "eval/rewards/rejected": -24.125106811523438,
+      "eval_loss": 0.023628102615475655,
+      "eval_runtime": 1026.1735,
+      "eval_samples_per_second": 0.476,
+      "eval_steps_per_second": 0.119,
+      "step": 100
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.21339461207389832,
+      "learning_rate": 0.0001125984251968504,
+      "loss": 0.0155,
+      "step": 120,
+      "train/kl": 0.0014267921214923263,
+      "train/logps/chosen": -127.95144653320312,
+      "train/logps/rejected": -475.267578125,
+      "train/rewards/chosen": 6.43417501449585,
+      "train/rewards/margins": 34.42128324508667,
+      "train/rewards/rejected": -27.98710823059082
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.476151704788208,
+      "learning_rate": 9.68503937007874e-05,
+      "loss": 0.0141,
+      "step": 140,
+      "train/kl": 0.03115321323275566,
+      "train/logps/chosen": -141.92579650878906,
+      "train/logps/rejected": -525.6384887695312,
+      "train/rewards/chosen": 6.3095011711120605,
+      "train/rewards/margins": 38.23302602767944,
+      "train/rewards/rejected": -31.923524856567383
+    },
+    {
+      "epoch": 1.14,
+      "eval/kl": 0.36410796642303467,
+      "eval/logps/chosen": -133.6990509033203,
+      "eval/logps/rejected": -478.2293701171875,
+      "eval/rewards/chosen": 6.120672225952148,
+      "eval/rewards/margins": 33.91848945617676,
+      "eval/rewards/rejected": -27.79781723022461,
+      "eval_loss": 0.02185995876789093,
+      "eval_runtime": 1027.1824,
+      "eval_samples_per_second": 0.475,
+      "eval_steps_per_second": 0.119,
+      "step": 150
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.37682458758354187,
+      "learning_rate": 8.110236220472441e-05,
+      "loss": 0.0098,
+      "step": 160,
+      "train/kl": 0.07081340253353119,
+      "train/logps/chosen": -122.0663070678711,
+      "train/logps/rejected": -478.622802734375,
+      "train/rewards/chosen": 6.860583305358887,
+      "train/rewards/margins": 34.60832691192627,
+      "train/rewards/rejected": -27.747743606567383
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.48077917098999023,
+      "learning_rate": 6.535433070866141e-05,
+      "loss": 0.013,
+      "step": 180,
+      "train/kl": 0.11124138534069061,
+      "train/logps/chosen": -130.82872009277344,
+      "train/logps/rejected": -483.7926330566406,
+      "train/rewards/chosen": 6.531792640686035,
+      "train/rewards/margins": 35.301690101623535,
+      "train/rewards/rejected": -28.7698974609375
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.030962228775024414,
+      "learning_rate": 4.960629921259843e-05,
+      "loss": 0.0103,
+      "step": 200,
+      "train/kl": 0.4774416983127594,
+      "train/logps/chosen": -121.02245330810547,
+      "train/logps/rejected": -501.03900146484375,
+      "train/rewards/chosen": 6.950838088989258,
+      "train/rewards/margins": 36.22991943359375,
+      "train/rewards/rejected": -29.279081344604492
+    },
+    {
+      "epoch": 1.52,
+      "eval/kl": 0.25049710273742676,
+      "eval/logps/chosen": -129.4441375732422,
+      "eval/logps/rejected": -508.0271301269531,
+      "eval/rewards/chosen": 6.546164512634277,
+      "eval/rewards/margins": 37.32375621795654,
+      "eval/rewards/rejected": -30.777591705322266,
+      "eval_loss": 0.014605735428631306,
+      "eval_runtime": 1029.2443,
+      "eval_samples_per_second": 0.474,
+      "eval_steps_per_second": 0.119,
+      "step": 200
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 262,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc7a109417f9d2496872f991edde5dd167c9ce013858d32ca7605999cd93bdc2
+size 5752