Training in progress, step 750, checkpoint

checkpoint-750/README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: Qwen/Qwen1.5-4B-Chat
+---
+
+# 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-750/adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-4B-Chat",
+  "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": [
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-750/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234fd2d557f8ff61018ed165ee4a8d8ebcd0d09573165c11748d5ea8ec534476
+size 26235864

checkpoint-750/added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

checkpoint-750/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9e300126cb6c08994d46b23e018ce7c2b67102c0ce02613e7de7402c0d342b7
+size 52523514

checkpoint-750/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:facd8faf838df24dc1b8c65491845d86cdc829e93133132024cccae67860063d
+size 14244

checkpoint-750/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c829b2a7b27fb0ef113dfe1a7e62cbb57ba405460c789ae724e64cad2234d36
+size 1064

checkpoint-750/special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-750/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-750/trainer_state.json

@@ -0,0 +1,471 @@
+{
+  "best_metric": 2.2024943828582764,
+  "best_model_checkpoint": "./Qwen2-4B-Chat-hinglish-sft/checkpoint-750",
+  "epoch": 2.9791459781529293,
+  "eval_steps": 25,
+  "global_step": 750,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.1830133199691772,
+      "learning_rate": 0.00019999629591162656,
+      "loss": 4.7862,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 4.098670482635498,
+      "eval_runtime": 4.1063,
+      "eval_samples_per_second": 2.679,
+      "eval_steps_per_second": 2.679,
+      "step": 25
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.0619295835494995,
+      "learning_rate": 0.00019932568492674144,
+      "loss": 2.9161,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 3.1406357288360596,
+      "eval_runtime": 4.0777,
+      "eval_samples_per_second": 2.698,
+      "eval_steps_per_second": 2.698,
+      "step": 50
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.1028335094451904,
+      "learning_rate": 0.0001975064532257195,
+      "loss": 2.4282,
+      "step": 75
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 2.8003995418548584,
+      "eval_runtime": 4.076,
+      "eval_samples_per_second": 2.699,
+      "eval_steps_per_second": 2.699,
+      "step": 75
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.9855464100837708,
+      "learning_rate": 0.00019455963874271426,
+      "loss": 2.2815,
+      "step": 100
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 2.6393470764160156,
+      "eval_runtime": 4.084,
+      "eval_samples_per_second": 2.693,
+      "eval_steps_per_second": 2.693,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.154259204864502,
+      "learning_rate": 0.00019051931898913976,
+      "loss": 2.1485,
+      "step": 125
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 2.5862808227539062,
+      "eval_runtime": 4.0324,
+      "eval_samples_per_second": 2.728,
+      "eval_steps_per_second": 2.728,
+      "step": 125
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.2115691900253296,
+      "learning_rate": 0.0001854322169749827,
+      "loss": 2.0884,
+      "step": 150
+    },
+    {
+      "epoch": 0.6,
+      "eval_loss": 2.491671323776245,
+      "eval_runtime": 4.0837,
+      "eval_samples_per_second": 2.694,
+      "eval_steps_per_second": 2.694,
+      "step": 150
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.0713191032409668,
+      "learning_rate": 0.00017935716089521474,
+      "loss": 2.1055,
+      "step": 175
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 2.4541499614715576,
+      "eval_runtime": 4.0493,
+      "eval_samples_per_second": 2.717,
+      "eval_steps_per_second": 2.717,
+      "step": 175
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.1404445171356201,
+      "learning_rate": 0.00017236440382959126,
+      "loss": 2.1012,
+      "step": 200
+    },
+    {
+      "epoch": 0.79,
+      "eval_loss": 2.42814040184021,
+      "eval_runtime": 4.0309,
+      "eval_samples_per_second": 2.729,
+      "eval_steps_per_second": 2.729,
+      "step": 200
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 1.1801480054855347,
+      "learning_rate": 0.00016453481132295506,
+      "loss": 1.9956,
+      "step": 225
+    },
+    {
+      "epoch": 0.89,
+      "eval_loss": 2.3967058658599854,
+      "eval_runtime": 4.0145,
+      "eval_samples_per_second": 2.74,
+      "eval_steps_per_second": 2.74,
+      "step": 225
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.2651640176773071,
+      "learning_rate": 0.00015595892624101765,
+      "loss": 1.9931,
+      "step": 250
+    },
+    {
+      "epoch": 0.99,
+      "eval_loss": 2.3804991245269775,
+      "eval_runtime": 4.0509,
+      "eval_samples_per_second": 2.715,
+      "eval_steps_per_second": 2.715,
+      "step": 250
+    },
+    {
+      "epoch": 1.09,
+      "grad_norm": 1.2018358707427979,
+      "learning_rate": 0.00014673592171580025,
+      "loss": 1.7605,
+      "step": 275
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.358070135116577,
+      "eval_runtime": 4.0302,
+      "eval_samples_per_second": 2.729,
+      "eval_steps_per_second": 2.729,
+      "step": 275
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 1.2622418403625488,
+      "learning_rate": 0.00013697245428906732,
+      "loss": 1.9231,
+      "step": 300
+    },
+    {
+      "epoch": 1.19,
+      "eval_loss": 2.3286843299865723,
+      "eval_runtime": 4.0327,
+      "eval_samples_per_second": 2.728,
+      "eval_steps_per_second": 2.728,
+      "step": 300
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 1.324831247329712,
+      "learning_rate": 0.00012678143051621742,
+      "loss": 1.8805,
+      "step": 325
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 2.3032760620117188,
+      "eval_runtime": 4.0494,
+      "eval_samples_per_second": 2.716,
+      "eval_steps_per_second": 2.716,
+      "step": 325
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.242129921913147,
+      "learning_rate": 0.00011628070129385169,
+      "loss": 1.8475,
+      "step": 350
+    },
+    {
+      "epoch": 1.39,
+      "eval_loss": 2.2904257774353027,
+      "eval_runtime": 4.0806,
+      "eval_samples_per_second": 2.696,
+      "eval_steps_per_second": 2.696,
+      "step": 350
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 1.2501651048660278,
+      "learning_rate": 0.00010559169901006034,
+      "loss": 1.8282,
+      "step": 375
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 2.2831265926361084,
+      "eval_runtime": 4.0586,
+      "eval_samples_per_second": 2.71,
+      "eval_steps_per_second": 2.71,
+      "step": 375
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.2264453172683716,
+      "learning_rate": 9.483803327767462e-05,
+      "loss": 1.8311,
+      "step": 400
+    },
+    {
+      "epoch": 1.59,
+      "eval_loss": 2.2586615085601807,
+      "eval_runtime": 4.0884,
+      "eval_samples_per_second": 2.691,
+      "eval_steps_per_second": 2.691,
+      "step": 400
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.2421507835388184,
+      "learning_rate": 8.414406148968657e-05,
+      "loss": 1.8051,
+      "step": 425
+    },
+    {
+      "epoch": 1.69,
+      "eval_loss": 2.2608296871185303,
+      "eval_runtime": 4.0277,
+      "eval_samples_per_second": 2.731,
+      "eval_steps_per_second": 2.731,
+      "step": 425
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.4312422275543213,
+      "learning_rate": 7.363345072719929e-05,
+      "loss": 1.8093,
+      "step": 450
+    },
+    {
+      "epoch": 1.79,
+      "eval_loss": 2.249046564102173,
+      "eval_runtime": 4.1182,
+      "eval_samples_per_second": 2.671,
+      "eval_steps_per_second": 2.671,
+      "step": 450
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.3606431484222412,
+      "learning_rate": 6.342774765027309e-05,
+      "loss": 1.6944,
+      "step": 475
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 2.2398183345794678,
+      "eval_runtime": 4.0501,
+      "eval_samples_per_second": 2.716,
+      "eval_steps_per_second": 2.716,
+      "step": 475
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 1.4951516389846802,
+      "learning_rate": 5.3644972909714906e-05,
+      "loss": 1.7418,
+      "step": 500
+    },
+    {
+      "epoch": 1.99,
+      "eval_loss": 2.2147467136383057,
+      "eval_runtime": 4.0963,
+      "eval_samples_per_second": 2.685,
+      "eval_steps_per_second": 2.685,
+      "step": 500
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.3656489849090576,
+      "learning_rate": 4.439825633429557e-05,
+      "loss": 1.741,
+      "step": 525
+    },
+    {
+      "epoch": 2.09,
+      "eval_loss": 2.20865797996521,
+      "eval_runtime": 4.08,
+      "eval_samples_per_second": 2.696,
+      "eval_steps_per_second": 2.696,
+      "step": 525
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 1.3683630228042603,
+      "learning_rate": 3.579452867634364e-05,
+      "loss": 1.6561,
+      "step": 550
+    },
+    {
+      "epoch": 2.18,
+      "eval_loss": 2.2086095809936523,
+      "eval_runtime": 4.0702,
+      "eval_samples_per_second": 2.703,
+      "eval_steps_per_second": 2.703,
+      "step": 550
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 1.668961524963379,
+      "learning_rate": 2.793328504461391e-05,
+      "loss": 1.6894,
+      "step": 575
+    },
+    {
+      "epoch": 2.28,
+      "eval_loss": 2.2114932537078857,
+      "eval_runtime": 4.085,
+      "eval_samples_per_second": 2.693,
+      "eval_steps_per_second": 2.693,
+      "step": 575
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 1.3654729127883911,
+      "learning_rate": 2.0905434324322283e-05,
+      "loss": 1.5617,
+      "step": 600
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 2.2105047702789307,
+      "eval_runtime": 4.0226,
+      "eval_samples_per_second": 2.735,
+      "eval_steps_per_second": 2.735,
+      "step": 600
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.1611803770065308,
+      "learning_rate": 1.4792247889869071e-05,
+      "loss": 1.6809,
+      "step": 625
+    },
+    {
+      "epoch": 2.48,
+      "eval_loss": 2.2049694061279297,
+      "eval_runtime": 4.0427,
+      "eval_samples_per_second": 2.721,
+      "eval_steps_per_second": 2.721,
+      "step": 625
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 1.6043980121612549,
+      "learning_rate": 9.664419767531564e-06,
+      "loss": 1.7355,
+      "step": 650
+    },
+    {
+      "epoch": 2.58,
+      "eval_loss": 2.2034003734588623,
+      "eval_runtime": 4.0162,
+      "eval_samples_per_second": 2.739,
+      "eval_steps_per_second": 2.739,
+      "step": 650
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 1.660874843597412,
+      "learning_rate": 5.5812491165800675e-06,
+      "loss": 1.595,
+      "step": 675
+    },
+    {
+      "epoch": 2.68,
+      "eval_loss": 2.2044949531555176,
+      "eval_runtime": 4.0854,
+      "eval_samples_per_second": 2.693,
+      "eval_steps_per_second": 2.693,
+      "step": 675
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 1.597719430923462,
+      "learning_rate": 2.58995448275795e-06,
+      "loss": 1.6264,
+      "step": 700
+    },
+    {
+      "epoch": 2.78,
+      "eval_loss": 2.203244924545288,
+      "eval_runtime": 4.0166,
+      "eval_samples_per_second": 2.739,
+      "eval_steps_per_second": 2.739,
+      "step": 700
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 1.3414063453674316,
+      "learning_rate": 7.251277542259849e-07,
+      "loss": 1.6195,
+      "step": 725
+    },
+    {
+      "epoch": 2.88,
+      "eval_loss": 2.2025506496429443,
+      "eval_runtime": 4.0553,
+      "eval_samples_per_second": 2.712,
+      "eval_steps_per_second": 2.712,
+      "step": 725
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 1.5819138288497925,
+      "learning_rate": 8.334134526211124e-09,
+      "loss": 1.5556,
+      "step": 750
+    },
+    {
+      "epoch": 2.98,
+      "eval_loss": 2.2024943828582764,
+      "eval_runtime": 4.0737,
+      "eval_samples_per_second": 2.7,
+      "eval_steps_per_second": 2.7,
+      "step": 750
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 753,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 25,
+  "total_flos": 5355974746460160.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-750/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:788436dae15eaa59cb0aad969fe709cabdaa4997e955ddb605dac6d71d60cdac
+size 5048