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": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_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 sha256:14d7e4993ea281e63f4c8d89d0e8454636a96a85561f40d54b3f36b1494cf2f7
+size 54560368

checkpoint-400/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b00b5c3feb90a68d16293c47a3fd89212b6ddc084b2103770edef555cba83178
+size 109267450

checkpoint-400/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
+size 14244

checkpoint-400/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bee2bad0fd064a9ed241202e2fb94709eef1173314e9f52a9615a916efcce7
+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": 0.003762652399018407,
+  "best_model_checkpoint": "./Zephyr/28-03-24-Weni-WeniGPT-QA-Zephyr-7B-4.0.1-KTO_WeniGPT Experiment using KTO trainer with no collator, Zephyr model and no system prompt.-2_max_steps-786_batch_32_2024-03-28_ppid_9/checkpoint-400",
+  "epoch": 3.0245746691871456,
+  "eval_steps": 50,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.94673752784729,
+      "kl": 0.3060356676578522,
+      "learning_rate": 0.0001666666666666667,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 1.0194,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 20
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.799897313117981,
+      "kl": 0.08012839406728745,
+      "learning_rate": 0.00019580052493438322,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.204,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 40
+    },
+    {
+      "epoch": 0.38,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -120.33751678466797,
+      "eval_logps/rejected": -405.6329345703125,
+      "eval_loss": 0.02746938355267048,
+      "eval_rewards/chosen": 5.632839202880859,
+      "eval_rewards/margins": 25.979337692260742,
+      "eval_rewards/rejected": -20.346500396728516,
+      "eval_runtime": 215.3361,
+      "eval_samples_per_second": 2.322,
+      "eval_steps_per_second": 0.58,
+      "step": 50
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.1745920479297638,
+      "kl": 0.20441873371601105,
+      "learning_rate": 0.0001905511811023622,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0962,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 60
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.8645330667495728,
+      "kl": 0.0,
+      "learning_rate": 0.00018556430446194227,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0881,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 80
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.13575485348701477,
+      "kl": 0.0,
+      "learning_rate": 0.00018031496062992125,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.073,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 100
+    },
+    {
+      "epoch": 0.76,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -118.76765441894531,
+      "eval_logps/rejected": -394.83203125,
+      "eval_loss": 0.014343788847327232,
+      "eval_rewards/chosen": 5.789826393127441,
+      "eval_rewards/margins": 25.05623435974121,
+      "eval_rewards/rejected": -19.266408920288086,
+      "eval_runtime": 215.2593,
+      "eval_samples_per_second": 2.323,
+      "eval_steps_per_second": 0.581,
+      "step": 100
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.04445016011595726,
+      "kl": 0.25088077783584595,
+      "learning_rate": 0.0001750656167979003,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0312,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 120
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 0.08600552380084991,
+      "kl": 0.0,
+      "learning_rate": 0.00016981627296587927,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0553,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 140
+    },
+    {
+      "epoch": 1.13,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -118.54534149169922,
+      "eval_logps/rejected": -501.9826354980469,
+      "eval_loss": 0.022491294890642166,
+      "eval_rewards/chosen": 5.812057018280029,
+      "eval_rewards/margins": 35.79352569580078,
+      "eval_rewards/rejected": -29.981468200683594,
+      "eval_runtime": 215.2877,
+      "eval_samples_per_second": 2.322,
+      "eval_steps_per_second": 0.581,
+      "step": 150
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 1.7538838386535645,
+      "kl": 0.08890169113874435,
+      "learning_rate": 0.00016456692913385828,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0322,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 160
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.1595699042081833,
+      "kl": 0.0,
+      "learning_rate": 0.00015931758530183726,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0108,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 180
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.2758983373641968,
+      "kl": 0.011286890134215355,
+      "learning_rate": 0.0001540682414698163,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0232,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 200
+    },
+    {
+      "epoch": 1.51,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -112.15116882324219,
+      "eval_logps/rejected": -478.0784912109375,
+      "eval_loss": 0.0047710007056593895,
+      "eval_rewards/chosen": 6.451474189758301,
+      "eval_rewards/margins": 34.04253005981445,
+      "eval_rewards/rejected": -27.591054916381836,
+      "eval_runtime": 215.2869,
+      "eval_samples_per_second": 2.322,
+      "eval_steps_per_second": 0.581,
+      "step": 200
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.04578682407736778,
+      "kl": 0.08650239557027817,
+      "learning_rate": 0.00014881889763779528,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0095,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 220
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 4.036252498626709,
+      "kl": 0.0,
+      "learning_rate": 0.0001435695538057743,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0519,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 240
+    },
+    {
+      "epoch": 1.89,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -111.8521728515625,
+      "eval_logps/rejected": -507.0782470703125,
+      "eval_loss": 0.008064903318881989,
+      "eval_rewards/chosen": 6.481375217437744,
+      "eval_rewards/margins": 36.97240447998047,
+      "eval_rewards/rejected": -30.491031646728516,
+      "eval_runtime": 215.2836,
+      "eval_samples_per_second": 2.323,
+      "eval_steps_per_second": 0.581,
+      "step": 250
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.027836302295327187,
+      "kl": 0.10306696593761444,
+      "learning_rate": 0.00013832020997375327,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0103,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 260
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.5005787014961243,
+      "kl": 0.0,
+      "learning_rate": 0.0001330708661417323,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0185,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 280
+    },
+    {
+      "epoch": 2.27,
+      "grad_norm": 0.010965784080326557,
+      "kl": 0.008135443553328514,
+      "learning_rate": 0.0001278215223097113,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0095,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 300
+    },
+    {
+      "epoch": 2.27,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -112.58515930175781,
+      "eval_logps/rejected": -541.0062866210938,
+      "eval_loss": 0.0153852179646492,
+      "eval_rewards/chosen": 6.408076286315918,
+      "eval_rewards/margins": 40.29190444946289,
+      "eval_rewards/rejected": -33.88383102416992,
+      "eval_runtime": 215.4103,
+      "eval_samples_per_second": 2.321,
+      "eval_steps_per_second": 0.58,
+      "step": 300
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.03853553906083107,
+      "kl": 0.09816194325685501,
+      "learning_rate": 0.0001225721784776903,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0074,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 320
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.019064167514443398,
+      "kl": 0.0,
+      "learning_rate": 0.00011732283464566928,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0098,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 340
+    },
+    {
+      "epoch": 2.65,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -110.7034683227539,
+      "eval_logps/rejected": -614.9013671875,
+      "eval_loss": 0.005230295471847057,
+      "eval_rewards/chosen": 6.596245288848877,
+      "eval_rewards/margins": 47.869590759277344,
+      "eval_rewards/rejected": -41.27334213256836,
+      "eval_runtime": 215.26,
+      "eval_samples_per_second": 2.323,
+      "eval_steps_per_second": 0.581,
+      "step": 350
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.011980261653661728,
+      "kl": 0.0,
+      "learning_rate": 0.0001120734908136483,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0147,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 360
+    },
+    {
+      "epoch": 2.87,
+      "grad_norm": 0.02171475999057293,
+      "kl": 0.0,
+      "learning_rate": 0.0001068241469816273,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0066,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 380
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 0.013751395046710968,
+      "kl": 0.0,
+      "learning_rate": 0.0001015748031496063,
+      "logps/chosen": NaN,
+      "logps/rejected": NaN,
+      "loss": 0.0038,
+      "rewards/chosen": NaN,
+      "rewards/margins": NaN,
+      "rewards/rejected": NaN,
+      "step": 400
+    },
+    {
+      "epoch": 3.02,
+      "eval_kl": 0.0,
+      "eval_logps/chosen": -111.44074249267578,
+      "eval_logps/rejected": -539.215576171875,
+      "eval_loss": 0.003762652399018407,
+      "eval_rewards/chosen": 6.522518157958984,
+      "eval_rewards/margins": 40.22727966308594,
+      "eval_rewards/rejected": -33.70476531982422,
+      "eval_runtime": 215.2203,
+      "eval_samples_per_second": 2.323,
+      "eval_steps_per_second": 0.581,
+      "step": 400
+    }
+  ],
+  "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-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f2155a0ae7749da9e171490498968b99b2aaa26988e17c08597261b3e802373
+size 5688