Upload folder using huggingface_hub

README.md

@@ -0,0 +1,58 @@
+---
+library_name: peft
+license: other
+base_model: mistralai/Mistral-7B-v0.1
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: train_2025-06-13-06-18-44
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# train_2025-06-13-06-18-44
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the math_qa dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.6.0+cu124
+- Datasets 3.6.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9a031411a375812a5322436011f448f745375e825dd0dba12b6d8870c1a0b3
+size 83945296

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "num_input_tokens_seen": 177776,
+    "total_flos": 7606997652996096.0,
+    "train_loss": 0.5502152733071141,
+    "train_runtime": 4598.4523,
+    "train_samples_per_second": 0.652,
+    "train_steps_per_second": 0.041
+}

chat_template.jinja

@@ -0,0 +1,3 @@
+{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message is defined %}{% set content = system_message + '
+
+' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + '[/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content + '</s>' }}{% endif %}{% endfor %}

checkpoint-100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-100/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05848bfa0abaf2925e5e7893d6bfb1ab05088c95c8dd042fefc5020664883085
+size 83945296

checkpoint-100/chat_template.jinja

@@ -0,0 +1,3 @@
+{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message is defined %}{% set content = system_message + '
+
+' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + '[/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content + '</s>' }}{% endif %}{% endfor %}

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1f2c52e1709fb5374e668d385b0f281122dee377348a3bb598311f315bec4e
+size 168149074

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:679986a4e07ba38279891ed38c64c49e95e56e9df70e7e3ed71db7653ad7ca1f
+size 1064

checkpoint-100/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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-100/tokenizer.model

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

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,234 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.592,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.599682807922363,
+      "learning_rate": 0.0001997790438338385,
+      "loss": 1.683,
+      "num_input_tokens_seen": 4896,
+      "step": 5,
+      "train_runtime": 118.4256,
+      "train_tokens_per_second": 41.342
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.600591659545898,
+      "learning_rate": 0.00019888308262251285,
+      "loss": 0.9406,
+      "num_input_tokens_seen": 10144,
+      "step": 10,
+      "train_runtime": 247.2151,
+      "train_tokens_per_second": 41.033
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.516849994659424,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 1.1972,
+      "num_input_tokens_seen": 14768,
+      "step": 15,
+      "train_runtime": 367.0408,
+      "train_tokens_per_second": 40.235
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.443480968475342,
+      "learning_rate": 0.0001950541548947829,
+      "loss": 0.8463,
+      "num_input_tokens_seen": 19456,
+      "step": 20,
+      "train_runtime": 488.2663,
+      "train_tokens_per_second": 39.847
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.511438846588135,
+      "learning_rate": 0.00019214762118704076,
+      "loss": 0.9397,
+      "num_input_tokens_seen": 24240,
+      "step": 25,
+      "train_runtime": 611.1324,
+      "train_tokens_per_second": 39.664
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.14411735534668,
+      "learning_rate": 0.00018860495104301345,
+      "loss": 0.8065,
+      "num_input_tokens_seen": 28928,
+      "step": 30,
+      "train_runtime": 732.2813,
+      "train_tokens_per_second": 39.504
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.8415708541870117,
+      "learning_rate": 0.0001844506011066308,
+      "loss": 1.0692,
+      "num_input_tokens_seen": 33712,
+      "step": 35,
+      "train_runtime": 854.4771,
+      "train_tokens_per_second": 39.453
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.072882175445557,
+      "learning_rate": 0.00017971325072229226,
+      "loss": 1.1197,
+      "num_input_tokens_seen": 38384,
+      "step": 40,
+      "train_runtime": 975.508,
+      "train_tokens_per_second": 39.348
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.347297191619873,
+      "learning_rate": 0.00017442560394846516,
+      "loss": 0.9444,
+      "num_input_tokens_seen": 43232,
+      "step": 45,
+      "train_runtime": 1098.6527,
+      "train_tokens_per_second": 39.35
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.867551326751709,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 1.1552,
+      "num_input_tokens_seen": 47600,
+      "step": 50,
+      "train_runtime": 1216.8692,
+      "train_tokens_per_second": 39.117
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.36644172668457,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.7799,
+      "num_input_tokens_seen": 52416,
+      "step": 55,
+      "train_runtime": 1339.2743,
+      "train_tokens_per_second": 39.138
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.242959499359131,
+      "learning_rate": 0.00015564337355766412,
+      "loss": 1.0976,
+      "num_input_tokens_seen": 57024,
+      "step": 60,
+      "train_runtime": 1460.6574,
+      "train_tokens_per_second": 39.04
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 2.891428232192993,
+      "learning_rate": 0.00014855363571801523,
+      "loss": 0.6118,
+      "num_input_tokens_seen": 61376,
+      "step": 65,
+      "train_runtime": 1571.9701,
+      "train_tokens_per_second": 39.044
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 3.863312244415283,
+      "learning_rate": 0.00014112871031306119,
+      "loss": 0.4582,
+      "num_input_tokens_seen": 65808,
+      "step": 70,
+      "train_runtime": 1688.4702,
+      "train_tokens_per_second": 38.975
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 8.035051345825195,
+      "learning_rate": 0.00013341985493931877,
+      "loss": 0.4555,
+      "num_input_tokens_seen": 70800,
+      "step": 75,
+      "train_runtime": 1816.0492,
+      "train_tokens_per_second": 38.986
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 6.827272891998291,
+      "learning_rate": 0.0001254802872894655,
+      "loss": 0.5214,
+      "num_input_tokens_seen": 75744,
+      "step": 80,
+      "train_runtime": 1941.6476,
+      "train_tokens_per_second": 39.01
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 3.403914451599121,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.396,
+      "num_input_tokens_seen": 80400,
+      "step": 85,
+      "train_runtime": 2063.1926,
+      "train_tokens_per_second": 38.969
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 5.601797103881836,
+      "learning_rate": 0.00010912947110386484,
+      "loss": 0.494,
+      "num_input_tokens_seen": 85040,
+      "step": 90,
+      "train_runtime": 2183.6375,
+      "train_tokens_per_second": 38.944
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 4.063144683837891,
+      "learning_rate": 0.00010083109959960973,
+      "loss": 0.4208,
+      "num_input_tokens_seen": 89472,
+      "step": 95,
+      "train_runtime": 2301.5727,
+      "train_tokens_per_second": 38.874
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 3.933701515197754,
+      "learning_rate": 9.252699064135758e-05,
+      "loss": 0.3598,
+      "num_input_tokens_seen": 94128,
+      "step": 100,
+      "train_runtime": 2423.5983,
+      "train_tokens_per_second": 38.838
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 94128,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4027717324505088.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270e555ab2afc03e62179b9e34a7de0d45bb5c252e90141ef2edaba214c341c8
+size 5752

checkpoint-189/README.md

@@ -0,0 +1,202 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-189/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-189/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9a031411a375812a5322436011f448f745375e825dd0dba12b6d8870c1a0b3
+size 83945296

checkpoint-189/chat_template.jinja

@@ -0,0 +1,3 @@
+{{ '<s>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 and system_message is defined %}{% set content = system_message + '
+
+' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + '[/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content + '</s>' }}{% endif %}{% endfor %}

checkpoint-189/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab254baddef73b844c2649f399dab5bf75e72b79cf2f72aa50416be8416015f6
+size 168149074

checkpoint-189/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

checkpoint-189/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:399c207d5814a42f8b20e25df3fedb22c4b1c005b6a9c0d1622291adf032b026
+size 1064

checkpoint-189/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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-189/tokenizer.model

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

checkpoint-189/tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-189/trainer_state.json

@@ -0,0 +1,404 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.599682807922363,
+      "learning_rate": 0.0001997790438338385,
+      "loss": 1.683,
+      "num_input_tokens_seen": 4896,
+      "step": 5,
+      "train_runtime": 118.4256,
+      "train_tokens_per_second": 41.342
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.600591659545898,
+      "learning_rate": 0.00019888308262251285,
+      "loss": 0.9406,
+      "num_input_tokens_seen": 10144,
+      "step": 10,
+      "train_runtime": 247.2151,
+      "train_tokens_per_second": 41.033
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.516849994659424,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 1.1972,
+      "num_input_tokens_seen": 14768,
+      "step": 15,
+      "train_runtime": 367.0408,
+      "train_tokens_per_second": 40.235
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.443480968475342,
+      "learning_rate": 0.0001950541548947829,
+      "loss": 0.8463,
+      "num_input_tokens_seen": 19456,
+      "step": 20,
+      "train_runtime": 488.2663,
+      "train_tokens_per_second": 39.847
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.511438846588135,
+      "learning_rate": 0.00019214762118704076,
+      "loss": 0.9397,
+      "num_input_tokens_seen": 24240,
+      "step": 25,
+      "train_runtime": 611.1324,
+      "train_tokens_per_second": 39.664
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.14411735534668,
+      "learning_rate": 0.00018860495104301345,
+      "loss": 0.8065,
+      "num_input_tokens_seen": 28928,
+      "step": 30,
+      "train_runtime": 732.2813,
+      "train_tokens_per_second": 39.504
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.8415708541870117,
+      "learning_rate": 0.0001844506011066308,
+      "loss": 1.0692,
+      "num_input_tokens_seen": 33712,
+      "step": 35,
+      "train_runtime": 854.4771,
+      "train_tokens_per_second": 39.453
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.072882175445557,
+      "learning_rate": 0.00017971325072229226,
+      "loss": 1.1197,
+      "num_input_tokens_seen": 38384,
+      "step": 40,
+      "train_runtime": 975.508,
+      "train_tokens_per_second": 39.348
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.347297191619873,
+      "learning_rate": 0.00017442560394846516,
+      "loss": 0.9444,
+      "num_input_tokens_seen": 43232,
+      "step": 45,
+      "train_runtime": 1098.6527,
+      "train_tokens_per_second": 39.35
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.867551326751709,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 1.1552,
+      "num_input_tokens_seen": 47600,
+      "step": 50,
+      "train_runtime": 1216.8692,
+      "train_tokens_per_second": 39.117
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.36644172668457,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.7799,
+      "num_input_tokens_seen": 52416,
+      "step": 55,
+      "train_runtime": 1339.2743,
+      "train_tokens_per_second": 39.138
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.242959499359131,
+      "learning_rate": 0.00015564337355766412,
+      "loss": 1.0976,
+      "num_input_tokens_seen": 57024,
+      "step": 60,
+      "train_runtime": 1460.6574,
+      "train_tokens_per_second": 39.04
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 2.891428232192993,
+      "learning_rate": 0.00014855363571801523,
+      "loss": 0.6118,
+      "num_input_tokens_seen": 61376,
+      "step": 65,
+      "train_runtime": 1571.9701,
+      "train_tokens_per_second": 39.044
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 3.863312244415283,
+      "learning_rate": 0.00014112871031306119,
+      "loss": 0.4582,
+      "num_input_tokens_seen": 65808,
+      "step": 70,
+      "train_runtime": 1688.4702,
+      "train_tokens_per_second": 38.975
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 8.035051345825195,
+      "learning_rate": 0.00013341985493931877,
+      "loss": 0.4555,
+      "num_input_tokens_seen": 70800,
+      "step": 75,
+      "train_runtime": 1816.0492,
+      "train_tokens_per_second": 38.986
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 6.827272891998291,
+      "learning_rate": 0.0001254802872894655,
+      "loss": 0.5214,
+      "num_input_tokens_seen": 75744,
+      "step": 80,
+      "train_runtime": 1941.6476,
+      "train_tokens_per_second": 39.01
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 3.403914451599121,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.396,
+      "num_input_tokens_seen": 80400,
+      "step": 85,
+      "train_runtime": 2063.1926,
+      "train_tokens_per_second": 38.969
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 5.601797103881836,
+      "learning_rate": 0.00010912947110386484,
+      "loss": 0.494,
+      "num_input_tokens_seen": 85040,
+      "step": 90,
+      "train_runtime": 2183.6375,
+      "train_tokens_per_second": 38.944
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 4.063144683837891,
+      "learning_rate": 0.00010083109959960973,
+      "loss": 0.4208,
+      "num_input_tokens_seen": 89472,
+      "step": 95,
+      "train_runtime": 2301.5727,
+      "train_tokens_per_second": 38.874
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 3.933701515197754,
+      "learning_rate": 9.252699064135758e-05,
+      "loss": 0.3598,
+      "num_input_tokens_seen": 94128,
+      "step": 100,
+      "train_runtime": 2423.5983,
+      "train_tokens_per_second": 38.838
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 2.3344547748565674,
+      "learning_rate": 8.427447122476148e-05,
+      "loss": 0.3386,
+      "num_input_tokens_seen": 99120,
+      "step": 105,
+      "train_runtime": 2556.3976,
+      "train_tokens_per_second": 38.773
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 6.219064712524414,
+      "learning_rate": 7.613051219968623e-05,
+      "loss": 0.363,
+      "num_input_tokens_seen": 104224,
+      "step": 110,
+      "train_runtime": 2687.8442,
+      "train_tokens_per_second": 38.776
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 4.835460662841797,
+      "learning_rate": 6.815133497483157e-05,
+      "loss": 0.4988,
+      "num_input_tokens_seen": 108352,
+      "step": 115,
+      "train_runtime": 2797.943,
+      "train_tokens_per_second": 38.726
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 3.8654727935791016,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 0.492,
+      "num_input_tokens_seen": 113216,
+      "step": 120,
+      "train_runtime": 2921.7812,
+      "train_tokens_per_second": 38.749
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 2.8310158252716064,
+      "learning_rate": 5.290614347797802e-05,
+      "loss": 0.3521,
+      "num_input_tokens_seen": 118128,
+      "step": 125,
+      "train_runtime": 3048.0813,
+      "train_tokens_per_second": 38.755
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 2.7480006217956543,
+      "learning_rate": 4.574537361342407e-05,
+      "loss": 0.2833,
+      "num_input_tokens_seen": 121984,
+      "step": 130,
+      "train_runtime": 3150.1518,
+      "train_tokens_per_second": 38.723
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 2.6361961364746094,
+      "learning_rate": 3.89591478145437e-05,
+      "loss": 0.1752,
+      "num_input_tokens_seen": 126272,
+      "step": 135,
+      "train_runtime": 3263.6021,
+      "train_tokens_per_second": 38.691
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 2.188568115234375,
+      "learning_rate": 3.259431444746846e-05,
+      "loss": 0.1497,
+      "num_input_tokens_seen": 131184,
+      "step": 140,
+      "train_runtime": 3388.4424,
+      "train_tokens_per_second": 38.715
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 2.502239942550659,
+      "learning_rate": 2.669481281701739e-05,
+      "loss": 0.123,
+      "num_input_tokens_seen": 136256,
+      "step": 145,
+      "train_runtime": 3517.0188,
+      "train_tokens_per_second": 38.742
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 5.557635307312012,
+      "learning_rate": 2.1301369833931117e-05,
+      "loss": 0.1846,
+      "num_input_tokens_seen": 140816,
+      "step": 150,
+      "train_runtime": 3636.002,
+      "train_tokens_per_second": 38.728
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 7.517292022705078,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 0.1589,
+      "num_input_tokens_seen": 145824,
+      "step": 155,
+      "train_runtime": 3761.3932,
+      "train_tokens_per_second": 38.769
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 4.320331573486328,
+      "learning_rate": 1.2177842662977135e-05,
+      "loss": 0.2244,
+      "num_input_tokens_seen": 150720,
+      "step": 160,
+      "train_runtime": 3886.3506,
+      "train_tokens_per_second": 38.782
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 5.886272430419922,
+      "learning_rate": 8.510742282896544e-06,
+      "loss": 0.243,
+      "num_input_tokens_seen": 155408,
+      "step": 165,
+      "train_runtime": 4010.9688,
+      "train_tokens_per_second": 38.746
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 4.565557479858398,
+      "learning_rate": 5.475233360227516e-06,
+      "loss": 0.1998,
+      "num_input_tokens_seen": 159616,
+      "step": 170,
+      "train_runtime": 4124.7853,
+      "train_tokens_per_second": 38.697
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 5.315474987030029,
+      "learning_rate": 3.092271377092215e-06,
+      "loss": 0.1511,
+      "num_input_tokens_seen": 164544,
+      "step": 175,
+      "train_runtime": 4249.8174,
+      "train_tokens_per_second": 38.718
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 2.225633382797241,
+      "learning_rate": 1.378306990862177e-06,
+      "loss": 0.1868,
+      "num_input_tokens_seen": 169728,
+      "step": 180,
+      "train_runtime": 4382.478,
+      "train_tokens_per_second": 38.729
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 3.31820011138916,
+      "learning_rate": 3.451724678784518e-07,
+      "loss": 0.2023,
+      "num_input_tokens_seen": 174320,
+      "step": 185,
+      "train_runtime": 4501.8922,
+      "train_tokens_per_second": 38.721
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 177776,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7606997652996096.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-189/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270e555ab2afc03e62179b9e34a7de0d45bb5c252e90141ef2edaba214c341c8
+size 5752

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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "num_input_tokens_seen": 177776,
+    "total_flos": 7606997652996096.0,
+    "train_loss": 0.5502152733071141,
+    "train_runtime": 4598.4523,
+    "train_samples_per_second": 0.652,
+    "train_steps_per_second": 0.041
+}

trainer_log.jsonl

@@ -0,0 +1,38 @@
+{"current_steps": 5, "total_steps": 189, "loss": 1.683, "lr": 0.0001997790438338385, "epoch": 0.08, "percentage": 2.65, "elapsed_time": "0:01:58", "remaining_time": "1:12:37", "throughput": 41.34, "total_tokens": 4896}
+{"current_steps": 10, "total_steps": 189, "loss": 0.9406, "lr": 0.00019888308262251285, "epoch": 0.16, "percentage": 5.29, "elapsed_time": "0:04:07", "remaining_time": "1:13:45", "throughput": 41.03, "total_tokens": 10144}
+{"current_steps": 15, "total_steps": 189, "loss": 1.1972, "lr": 0.00019730448705798239, "epoch": 0.24, "percentage": 7.94, "elapsed_time": "0:06:07", "remaining_time": "1:10:57", "throughput": 40.24, "total_tokens": 14768}
+{"current_steps": 20, "total_steps": 189, "loss": 0.8463, "lr": 0.0001950541548947829, "epoch": 0.32, "percentage": 10.58, "elapsed_time": "0:08:08", "remaining_time": "1:08:45", "throughput": 39.85, "total_tokens": 19456}
+{"current_steps": 25, "total_steps": 189, "loss": 0.9397, "lr": 0.00019214762118704076, "epoch": 0.4, "percentage": 13.23, "elapsed_time": "0:10:11", "remaining_time": "1:06:49", "throughput": 39.66, "total_tokens": 24240}
+{"current_steps": 30, "total_steps": 189, "loss": 0.8065, "lr": 0.00018860495104301345, "epoch": 0.48, "percentage": 15.87, "elapsed_time": "0:12:12", "remaining_time": "1:04:41", "throughput": 39.5, "total_tokens": 28928}
+{"current_steps": 35, "total_steps": 189, "loss": 1.0692, "lr": 0.0001844506011066308, "epoch": 0.56, "percentage": 18.52, "elapsed_time": "0:14:14", "remaining_time": "1:02:39", "throughput": 39.45, "total_tokens": 33712}
+{"current_steps": 40, "total_steps": 189, "loss": 1.1197, "lr": 0.00017971325072229226, "epoch": 0.64, "percentage": 21.16, "elapsed_time": "0:16:15", "remaining_time": "1:00:33", "throughput": 39.35, "total_tokens": 38384}
+{"current_steps": 45, "total_steps": 189, "loss": 0.9444, "lr": 0.00017442560394846516, "epoch": 0.72, "percentage": 23.81, "elapsed_time": "0:18:18", "remaining_time": "0:58:35", "throughput": 39.35, "total_tokens": 43232}
+{"current_steps": 50, "total_steps": 189, "loss": 1.1552, "lr": 0.0001686241637868734, "epoch": 0.8, "percentage": 26.46, "elapsed_time": "0:20:16", "remaining_time": "0:56:22", "throughput": 39.12, "total_tokens": 47600}
+{"current_steps": 55, "total_steps": 189, "loss": 0.7799, "lr": 0.00016234898018587337, "epoch": 0.88, "percentage": 29.1, "elapsed_time": "0:22:19", "remaining_time": "0:54:22", "throughput": 39.14, "total_tokens": 52416}
+{"current_steps": 60, "total_steps": 189, "loss": 1.0976, "lr": 0.00015564337355766412, "epoch": 0.96, "percentage": 31.75, "elapsed_time": "0:24:20", "remaining_time": "0:52:20", "throughput": 39.04, "total_tokens": 57024}
+{"current_steps": 65, "total_steps": 189, "loss": 0.6118, "lr": 0.00014855363571801523, "epoch": 1.032, "percentage": 34.39, "elapsed_time": "0:26:11", "remaining_time": "0:49:58", "throughput": 39.04, "total_tokens": 61376}
+{"current_steps": 70, "total_steps": 189, "loss": 0.4582, "lr": 0.00014112871031306119, "epoch": 1.112, "percentage": 37.04, "elapsed_time": "0:28:08", "remaining_time": "0:47:50", "throughput": 38.98, "total_tokens": 65808}
+{"current_steps": 75, "total_steps": 189, "loss": 0.4555, "lr": 0.00013341985493931877, "epoch": 1.192, "percentage": 39.68, "elapsed_time": "0:30:16", "remaining_time": "0:46:00", "throughput": 38.99, "total_tokens": 70800}
+{"current_steps": 80, "total_steps": 189, "loss": 0.5214, "lr": 0.0001254802872894655, "epoch": 1.272, "percentage": 42.33, "elapsed_time": "0:32:21", "remaining_time": "0:44:05", "throughput": 39.01, "total_tokens": 75744}
+{"current_steps": 85, "total_steps": 189, "loss": 0.396, "lr": 0.00011736481776669306, "epoch": 1.3519999999999999, "percentage": 44.97, "elapsed_time": "0:34:23", "remaining_time": "0:42:04", "throughput": 38.97, "total_tokens": 80400}
+{"current_steps": 90, "total_steps": 189, "loss": 0.494, "lr": 0.00010912947110386484, "epoch": 1.432, "percentage": 47.62, "elapsed_time": "0:36:23", "remaining_time": "0:40:01", "throughput": 38.94, "total_tokens": 85040}
+{"current_steps": 95, "total_steps": 189, "loss": 0.4208, "lr": 0.00010083109959960973, "epoch": 1.512, "percentage": 50.26, "elapsed_time": "0:38:21", "remaining_time": "0:37:57", "throughput": 38.87, "total_tokens": 89472}
+{"current_steps": 100, "total_steps": 189, "loss": 0.3598, "lr": 9.252699064135758e-05, "epoch": 1.592, "percentage": 52.91, "elapsed_time": "0:40:23", "remaining_time": "0:35:56", "throughput": 38.84, "total_tokens": 94128}
+{"current_steps": 105, "total_steps": 189, "loss": 0.3386, "lr": 8.427447122476148e-05, "epoch": 1.6720000000000002, "percentage": 55.56, "elapsed_time": "0:42:36", "remaining_time": "0:34:05", "throughput": 38.77, "total_tokens": 99120}
+{"current_steps": 110, "total_steps": 189, "loss": 0.363, "lr": 7.613051219968623e-05, "epoch": 1.752, "percentage": 58.2, "elapsed_time": "0:44:47", "remaining_time": "0:32:10", "throughput": 38.78, "total_tokens": 104224}
+{"current_steps": 115, "total_steps": 189, "loss": 0.4988, "lr": 6.815133497483157e-05, "epoch": 1.8319999999999999, "percentage": 60.85, "elapsed_time": "0:46:37", "remaining_time": "0:30:00", "throughput": 38.73, "total_tokens": 108352}
+{"current_steps": 120, "total_steps": 189, "loss": 0.492, "lr": 6.039202339608432e-05, "epoch": 1.912, "percentage": 63.49, "elapsed_time": "0:48:41", "remaining_time": "0:28:00", "throughput": 38.75, "total_tokens": 113216}
+{"current_steps": 125, "total_steps": 189, "loss": 0.3521, "lr": 5.290614347797802e-05, "epoch": 1.992, "percentage": 66.14, "elapsed_time": "0:50:48", "remaining_time": "0:26:00", "throughput": 38.75, "total_tokens": 118128}
+{"current_steps": 130, "total_steps": 189, "loss": 0.2833, "lr": 4.574537361342407e-05, "epoch": 2.064, "percentage": 68.78, "elapsed_time": "0:52:30", "remaining_time": "0:23:49", "throughput": 38.72, "total_tokens": 121984}
+{"current_steps": 135, "total_steps": 189, "loss": 0.1752, "lr": 3.89591478145437e-05, "epoch": 2.144, "percentage": 71.43, "elapsed_time": "0:54:23", "remaining_time": "0:21:45", "throughput": 38.69, "total_tokens": 126272}
+{"current_steps": 140, "total_steps": 189, "loss": 0.1497, "lr": 3.259431444746846e-05, "epoch": 2.224, "percentage": 74.07, "elapsed_time": "0:56:28", "remaining_time": "0:19:45", "throughput": 38.72, "total_tokens": 131184}
+{"current_steps": 145, "total_steps": 189, "loss": 0.123, "lr": 2.669481281701739e-05, "epoch": 2.304, "percentage": 76.72, "elapsed_time": "0:58:37", "remaining_time": "0:17:47", "throughput": 38.74, "total_tokens": 136256}
+{"current_steps": 150, "total_steps": 189, "loss": 0.1846, "lr": 2.1301369833931117e-05, "epoch": 2.384, "percentage": 79.37, "elapsed_time": "1:00:35", "remaining_time": "0:15:45", "throughput": 38.73, "total_tokens": 140816}
+{"current_steps": 155, "total_steps": 189, "loss": 0.1589, "lr": 1.6451218858706374e-05, "epoch": 2.464, "percentage": 82.01, "elapsed_time": "1:02:41", "remaining_time": "0:13:45", "throughput": 38.77, "total_tokens": 145824}
+{"current_steps": 160, "total_steps": 189, "loss": 0.2244, "lr": 1.2177842662977135e-05, "epoch": 2.544, "percentage": 84.66, "elapsed_time": "1:04:46", "remaining_time": "0:11:44", "throughput": 38.78, "total_tokens": 150720}
+{"current_steps": 165, "total_steps": 189, "loss": 0.243, "lr": 8.510742282896544e-06, "epoch": 2.624, "percentage": 87.3, "elapsed_time": "1:06:50", "remaining_time": "0:09:43", "throughput": 38.75, "total_tokens": 155408}
+{"current_steps": 170, "total_steps": 189, "loss": 0.1998, "lr": 5.475233360227516e-06, "epoch": 2.7039999999999997, "percentage": 89.95, "elapsed_time": "1:08:44", "remaining_time": "0:07:41", "throughput": 38.7, "total_tokens": 159616}
+{"current_steps": 175, "total_steps": 189, "loss": 0.1511, "lr": 3.092271377092215e-06, "epoch": 2.784, "percentage": 92.59, "elapsed_time": "1:10:49", "remaining_time": "0:05:39", "throughput": 38.72, "total_tokens": 164544}
+{"current_steps": 180, "total_steps": 189, "loss": 0.1868, "lr": 1.378306990862177e-06, "epoch": 2.864, "percentage": 95.24, "elapsed_time": "1:13:02", "remaining_time": "0:03:39", "throughput": 38.73, "total_tokens": 169728}
+{"current_steps": 185, "total_steps": 189, "loss": 0.2023, "lr": 3.451724678784518e-07, "epoch": 2.944, "percentage": 97.88, "elapsed_time": "1:15:01", "remaining_time": "0:01:37", "throughput": 38.72, "total_tokens": 174320}
+{"current_steps": 189, "total_steps": 189, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:16:38", "remaining_time": "0:00:00", "throughput": 38.66, "total_tokens": 177776}

trainer_state.json

@@ -0,0 +1,414 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 189,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "grad_norm": 5.599682807922363,
+      "learning_rate": 0.0001997790438338385,
+      "loss": 1.683,
+      "num_input_tokens_seen": 4896,
+      "step": 5,
+      "train_runtime": 118.4256,
+      "train_tokens_per_second": 41.342
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.600591659545898,
+      "learning_rate": 0.00019888308262251285,
+      "loss": 0.9406,
+      "num_input_tokens_seen": 10144,
+      "step": 10,
+      "train_runtime": 247.2151,
+      "train_tokens_per_second": 41.033
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.516849994659424,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 1.1972,
+      "num_input_tokens_seen": 14768,
+      "step": 15,
+      "train_runtime": 367.0408,
+      "train_tokens_per_second": 40.235
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 4.443480968475342,
+      "learning_rate": 0.0001950541548947829,
+      "loss": 0.8463,
+      "num_input_tokens_seen": 19456,
+      "step": 20,
+      "train_runtime": 488.2663,
+      "train_tokens_per_second": 39.847
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.511438846588135,
+      "learning_rate": 0.00019214762118704076,
+      "loss": 0.9397,
+      "num_input_tokens_seen": 24240,
+      "step": 25,
+      "train_runtime": 611.1324,
+      "train_tokens_per_second": 39.664
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.14411735534668,
+      "learning_rate": 0.00018860495104301345,
+      "loss": 0.8065,
+      "num_input_tokens_seen": 28928,
+      "step": 30,
+      "train_runtime": 732.2813,
+      "train_tokens_per_second": 39.504
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 3.8415708541870117,
+      "learning_rate": 0.0001844506011066308,
+      "loss": 1.0692,
+      "num_input_tokens_seen": 33712,
+      "step": 35,
+      "train_runtime": 854.4771,
+      "train_tokens_per_second": 39.453
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.072882175445557,
+      "learning_rate": 0.00017971325072229226,
+      "loss": 1.1197,
+      "num_input_tokens_seen": 38384,
+      "step": 40,
+      "train_runtime": 975.508,
+      "train_tokens_per_second": 39.348
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.347297191619873,
+      "learning_rate": 0.00017442560394846516,
+      "loss": 0.9444,
+      "num_input_tokens_seen": 43232,
+      "step": 45,
+      "train_runtime": 1098.6527,
+      "train_tokens_per_second": 39.35
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 4.867551326751709,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 1.1552,
+      "num_input_tokens_seen": 47600,
+      "step": 50,
+      "train_runtime": 1216.8692,
+      "train_tokens_per_second": 39.117
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.36644172668457,
+      "learning_rate": 0.00016234898018587337,
+      "loss": 0.7799,
+      "num_input_tokens_seen": 52416,
+      "step": 55,
+      "train_runtime": 1339.2743,
+      "train_tokens_per_second": 39.138
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 5.242959499359131,
+      "learning_rate": 0.00015564337355766412,
+      "loss": 1.0976,
+      "num_input_tokens_seen": 57024,
+      "step": 60,
+      "train_runtime": 1460.6574,
+      "train_tokens_per_second": 39.04
+    },
+    {
+      "epoch": 1.032,
+      "grad_norm": 2.891428232192993,
+      "learning_rate": 0.00014855363571801523,
+      "loss": 0.6118,
+      "num_input_tokens_seen": 61376,
+      "step": 65,
+      "train_runtime": 1571.9701,
+      "train_tokens_per_second": 39.044
+    },
+    {
+      "epoch": 1.112,
+      "grad_norm": 3.863312244415283,
+      "learning_rate": 0.00014112871031306119,
+      "loss": 0.4582,
+      "num_input_tokens_seen": 65808,
+      "step": 70,
+      "train_runtime": 1688.4702,
+      "train_tokens_per_second": 38.975
+    },
+    {
+      "epoch": 1.192,
+      "grad_norm": 8.035051345825195,
+      "learning_rate": 0.00013341985493931877,
+      "loss": 0.4555,
+      "num_input_tokens_seen": 70800,
+      "step": 75,
+      "train_runtime": 1816.0492,
+      "train_tokens_per_second": 38.986
+    },
+    {
+      "epoch": 1.272,
+      "grad_norm": 6.827272891998291,
+      "learning_rate": 0.0001254802872894655,
+      "loss": 0.5214,
+      "num_input_tokens_seen": 75744,
+      "step": 80,
+      "train_runtime": 1941.6476,
+      "train_tokens_per_second": 39.01
+    },
+    {
+      "epoch": 1.3519999999999999,
+      "grad_norm": 3.403914451599121,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 0.396,
+      "num_input_tokens_seen": 80400,
+      "step": 85,
+      "train_runtime": 2063.1926,
+      "train_tokens_per_second": 38.969
+    },
+    {
+      "epoch": 1.432,
+      "grad_norm": 5.601797103881836,
+      "learning_rate": 0.00010912947110386484,
+      "loss": 0.494,
+      "num_input_tokens_seen": 85040,
+      "step": 90,
+      "train_runtime": 2183.6375,
+      "train_tokens_per_second": 38.944
+    },
+    {
+      "epoch": 1.512,
+      "grad_norm": 4.063144683837891,
+      "learning_rate": 0.00010083109959960973,
+      "loss": 0.4208,
+      "num_input_tokens_seen": 89472,
+      "step": 95,
+      "train_runtime": 2301.5727,
+      "train_tokens_per_second": 38.874
+    },
+    {
+      "epoch": 1.592,
+      "grad_norm": 3.933701515197754,
+      "learning_rate": 9.252699064135758e-05,
+      "loss": 0.3598,
+      "num_input_tokens_seen": 94128,
+      "step": 100,
+      "train_runtime": 2423.5983,
+      "train_tokens_per_second": 38.838
+    },
+    {
+      "epoch": 1.6720000000000002,
+      "grad_norm": 2.3344547748565674,
+      "learning_rate": 8.427447122476148e-05,
+      "loss": 0.3386,
+      "num_input_tokens_seen": 99120,
+      "step": 105,
+      "train_runtime": 2556.3976,
+      "train_tokens_per_second": 38.773
+    },
+    {
+      "epoch": 1.752,
+      "grad_norm": 6.219064712524414,
+      "learning_rate": 7.613051219968623e-05,
+      "loss": 0.363,
+      "num_input_tokens_seen": 104224,
+      "step": 110,
+      "train_runtime": 2687.8442,
+      "train_tokens_per_second": 38.776
+    },
+    {
+      "epoch": 1.8319999999999999,
+      "grad_norm": 4.835460662841797,
+      "learning_rate": 6.815133497483157e-05,
+      "loss": 0.4988,
+      "num_input_tokens_seen": 108352,
+      "step": 115,
+      "train_runtime": 2797.943,
+      "train_tokens_per_second": 38.726
+    },
+    {
+      "epoch": 1.912,
+      "grad_norm": 3.8654727935791016,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 0.492,
+      "num_input_tokens_seen": 113216,
+      "step": 120,
+      "train_runtime": 2921.7812,
+      "train_tokens_per_second": 38.749
+    },
+    {
+      "epoch": 1.992,
+      "grad_norm": 2.8310158252716064,
+      "learning_rate": 5.290614347797802e-05,
+      "loss": 0.3521,
+      "num_input_tokens_seen": 118128,
+      "step": 125,
+      "train_runtime": 3048.0813,
+      "train_tokens_per_second": 38.755
+    },
+    {
+      "epoch": 2.064,
+      "grad_norm": 2.7480006217956543,
+      "learning_rate": 4.574537361342407e-05,
+      "loss": 0.2833,
+      "num_input_tokens_seen": 121984,
+      "step": 130,
+      "train_runtime": 3150.1518,
+      "train_tokens_per_second": 38.723
+    },
+    {
+      "epoch": 2.144,
+      "grad_norm": 2.6361961364746094,
+      "learning_rate": 3.89591478145437e-05,
+      "loss": 0.1752,
+      "num_input_tokens_seen": 126272,
+      "step": 135,
+      "train_runtime": 3263.6021,
+      "train_tokens_per_second": 38.691
+    },
+    {
+      "epoch": 2.224,
+      "grad_norm": 2.188568115234375,
+      "learning_rate": 3.259431444746846e-05,
+      "loss": 0.1497,
+      "num_input_tokens_seen": 131184,
+      "step": 140,
+      "train_runtime": 3388.4424,
+      "train_tokens_per_second": 38.715
+    },
+    {
+      "epoch": 2.304,
+      "grad_norm": 2.502239942550659,
+      "learning_rate": 2.669481281701739e-05,
+      "loss": 0.123,
+      "num_input_tokens_seen": 136256,
+      "step": 145,
+      "train_runtime": 3517.0188,
+      "train_tokens_per_second": 38.742
+    },
+    {
+      "epoch": 2.384,
+      "grad_norm": 5.557635307312012,
+      "learning_rate": 2.1301369833931117e-05,
+      "loss": 0.1846,
+      "num_input_tokens_seen": 140816,
+      "step": 150,
+      "train_runtime": 3636.002,
+      "train_tokens_per_second": 38.728
+    },
+    {
+      "epoch": 2.464,
+      "grad_norm": 7.517292022705078,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 0.1589,
+      "num_input_tokens_seen": 145824,
+      "step": 155,
+      "train_runtime": 3761.3932,
+      "train_tokens_per_second": 38.769
+    },
+    {
+      "epoch": 2.544,
+      "grad_norm": 4.320331573486328,
+      "learning_rate": 1.2177842662977135e-05,
+      "loss": 0.2244,
+      "num_input_tokens_seen": 150720,
+      "step": 160,
+      "train_runtime": 3886.3506,
+      "train_tokens_per_second": 38.782
+    },
+    {
+      "epoch": 2.624,
+      "grad_norm": 5.886272430419922,
+      "learning_rate": 8.510742282896544e-06,
+      "loss": 0.243,
+      "num_input_tokens_seen": 155408,
+      "step": 165,
+      "train_runtime": 4010.9688,
+      "train_tokens_per_second": 38.746
+    },
+    {
+      "epoch": 2.7039999999999997,
+      "grad_norm": 4.565557479858398,
+      "learning_rate": 5.475233360227516e-06,
+      "loss": 0.1998,
+      "num_input_tokens_seen": 159616,
+      "step": 170,
+      "train_runtime": 4124.7853,
+      "train_tokens_per_second": 38.697
+    },
+    {
+      "epoch": 2.784,
+      "grad_norm": 5.315474987030029,
+      "learning_rate": 3.092271377092215e-06,
+      "loss": 0.1511,
+      "num_input_tokens_seen": 164544,
+      "step": 175,
+      "train_runtime": 4249.8174,
+      "train_tokens_per_second": 38.718
+    },
+    {
+      "epoch": 2.864,
+      "grad_norm": 2.225633382797241,
+      "learning_rate": 1.378306990862177e-06,
+      "loss": 0.1868,
+      "num_input_tokens_seen": 169728,
+      "step": 180,
+      "train_runtime": 4382.478,
+      "train_tokens_per_second": 38.729
+    },
+    {
+      "epoch": 2.944,
+      "grad_norm": 3.31820011138916,
+      "learning_rate": 3.451724678784518e-07,
+      "loss": 0.2023,
+      "num_input_tokens_seen": 174320,
+      "step": 185,
+      "train_runtime": 4501.8922,
+      "train_tokens_per_second": 38.721
+    },
+    {
+      "epoch": 3.0,
+      "num_input_tokens_seen": 177776,
+      "step": 189,
+      "total_flos": 7606997652996096.0,
+      "train_loss": 0.5502152733071141,
+      "train_runtime": 4598.4523,
+      "train_samples_per_second": 0.652,
+      "train_steps_per_second": 0.041
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 189,
+  "num_input_tokens_seen": 177776,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7606997652996096.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270e555ab2afc03e62179b9e34a7de0d45bb5c252e90141ef2edaba214c341c8
+size 5752