Training in progress, step 300, checkpoint

checkpoint-300/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-300/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": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-300/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3813e840cc4f4cf5621fb061ce03217d9fb789ae82d38f3b1d1f6d39c1d2d96e
+size 54560368

checkpoint-300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7eb079ddeb679e642eda295a234c72dfa7a4d261d0a7d4c3236390dc78313f4
+size 109267450

checkpoint-300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
+size 14244

checkpoint-300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f26aa64b3ff3e4403aee73e58c0a9e57560bf06899628428f63c70fa82adcfdb
+size 1064

checkpoint-300/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-300/tokenizer.model

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

checkpoint-300/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-300/trainer_state.json

@@ -0,0 +1,300 @@
+{
+  "best_metric": 0.016069181263446808,
+  "best_model_checkpoint": "./Zephyr/28-03-24-Weni-WeniGPT-QA-Zephyr-7B-5.0.0-KTO_WeniGPT Experiment using KTO trainer with no collator, Mixstral model and random system prompt.-2_max_steps-786_batch_32_2024-03-28_ppid_9/checkpoint-300",
+  "epoch": 2.2813688212927756,
+  "eval_steps": 50,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 3.2390341758728027,
+      "kl": 1.4365953207015991,
+      "learning_rate": 0.0001666666666666667,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 1.2323,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.6226775050163269,
+      "kl": 0.1346512734889984,
+      "learning_rate": 0.00019580052493438322,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.1437,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "eval_kl": 0.0960722267627716,
+      "eval_logps/chosen": -158.278564453125,
+      "eval_logps/rejected": -400.1436767578125,
+      "eval_loss": 0.028233768418431282,
+      "eval_rewards/chosen": 5.2842488288879395,
+      "eval_rewards/margins": 25.394336700439453,
+      "eval_rewards/rejected": -20.11008644104004,
+      "eval_runtime": 214.1148,
+      "eval_samples_per_second": 2.232,
+      "eval_steps_per_second": 0.56,
+      "step": 50
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 1.9644193649291992,
+      "kl": 0.026479745283722878,
+      "learning_rate": 0.0001905511811023622,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.1405,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 60
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.28626948595046997,
+      "kl": 0.018679404631257057,
+      "learning_rate": 0.00018530183727034121,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.1041,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 80
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.0979766920208931,
+      "kl": 0.0,
+      "learning_rate": 0.00018005249343832022,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0615,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 100
+    },
+    {
+      "epoch": 0.76,
+      "eval_kl": 0.5886130928993225,
+      "eval_logps/chosen": -153.61863708496094,
+      "eval_logps/rejected": -383.54296875,
+      "eval_loss": 0.022206587716937065,
+      "eval_rewards/chosen": 5.750241756439209,
+      "eval_rewards/margins": 24.20025062561035,
+      "eval_rewards/rejected": -18.450010299682617,
+      "eval_runtime": 213.9917,
+      "eval_samples_per_second": 2.234,
+      "eval_steps_per_second": 0.561,
+      "step": 100
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.3924414813518524,
+      "kl": 0.0,
+      "learning_rate": 0.00017480314960629923,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0396,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 120
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.0917697548866272,
+      "kl": 0.2697001099586487,
+      "learning_rate": 0.00016955380577427821,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0346,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 140
+    },
+    {
+      "epoch": 1.14,
+      "eval_kl": 0.3035987615585327,
+      "eval_logps/chosen": -162.28248596191406,
+      "eval_logps/rejected": -612.7335205078125,
+      "eval_loss": 0.03983871266245842,
+      "eval_rewards/chosen": 4.883855819702148,
+      "eval_rewards/margins": 46.25292205810547,
+      "eval_rewards/rejected": -41.36906814575195,
+      "eval_runtime": 214.0091,
+      "eval_samples_per_second": 2.234,
+      "eval_steps_per_second": 0.561,
+      "step": 150
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 0.16112379729747772,
+      "kl": 0.2598298192024231,
+      "learning_rate": 0.00016430446194225722,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0437,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 160
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.04856234788894653,
+      "kl": 0.09709737449884415,
+      "learning_rate": 0.00015958005249343832,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0288,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 180
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.5220792889595032,
+      "kl": 0.055810533463954926,
+      "learning_rate": 0.00015433070866141733,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0563,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 200
+    },
+    {
+      "epoch": 1.52,
+      "eval_kl": 0.15839433670043945,
+      "eval_logps/chosen": -149.37533569335938,
+      "eval_logps/rejected": -463.8907165527344,
+      "eval_loss": 0.021165071055293083,
+      "eval_rewards/chosen": 6.174570083618164,
+      "eval_rewards/margins": 32.65935134887695,
+      "eval_rewards/rejected": -26.48478126525879,
+      "eval_runtime": 214.0155,
+      "eval_samples_per_second": 2.233,
+      "eval_steps_per_second": 0.561,
+      "step": 200
+    },
+    {
+      "epoch": 1.67,
+      "grad_norm": 0.05050266534090042,
+      "kl": 0.0,
+      "learning_rate": 0.00014908136482939634,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0298,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 220
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 1.530806064605713,
+      "kl": 0.0,
+      "learning_rate": 0.00014383202099737535,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0533,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 240
+    },
+    {
+      "epoch": 1.9,
+      "eval_kl": 0.4594874680042267,
+      "eval_logps/chosen": -149.20762634277344,
+      "eval_logps/rejected": -489.6085205078125,
+      "eval_loss": 0.013410959392786026,
+      "eval_rewards/chosen": 6.191342353820801,
+      "eval_rewards/margins": 35.24790573120117,
+      "eval_rewards/rejected": -29.056562423706055,
+      "eval_runtime": 214.0202,
+      "eval_samples_per_second": 2.233,
+      "eval_steps_per_second": 0.561,
+      "step": 250
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 0.017549920827150345,
+      "kl": 0.0,
+      "learning_rate": 0.00013858267716535433,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0461,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 260
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.021922318264842033,
+      "kl": 0.4756055772304535,
+      "learning_rate": 0.00013333333333333334,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.013,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 280
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.02235027775168419,
+      "kl": 0.16024529933929443,
+      "learning_rate": 0.00012808398950131235,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0076,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 300
+    },
+    {
+      "epoch": 2.28,
+      "eval_kl": 0.6192654967308044,
+      "eval_logps/chosen": -147.9675750732422,
+      "eval_logps/rejected": -453.9040222167969,
+      "eval_loss": 0.016069181263446808,
+      "eval_rewards/chosen": 6.315345764160156,
+      "eval_rewards/margins": 31.80146026611328,
+      "eval_rewards/rejected": -25.486116409301758,
+      "eval_runtime": 214.0005,
+      "eval_samples_per_second": 2.234,
+      "eval_steps_per_second": 0.561,
+      "step": 300
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 786,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 100,
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2143b63cfb768928620763e12d44a1780f6206ec9bca22cf2aab4ebe0626cbeb
+size 5752