Upload 12 files

checkpoint-18000/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: ../Mixtral-8x7B-Instruct-v0.1
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+
+### Framework versions
+
+- PEFT 0.7.1

checkpoint-18000/adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "../Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-18000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16fe6b556d7ca3c2c68b8124550c0d32ab3e6c398767897284667962c85ad728
+size 13648432

checkpoint-18000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff59682ba9e4ddf7b5bfe30f2b76a266dc86fb67a1c660c52e2a0bf43869a5d
+size 27370618

checkpoint-18000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:856f0fd4b503840463c992e5d46e46ba88389b142cf55d5fa741b20f2c3e2427
+size 14244

checkpoint-18000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca809200faab02a65a95250b1dea2de62ddacf29da6f2eed76eab74c589ce629
+size 1064

checkpoint-18000/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-18000/tokenizer.model

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

checkpoint-18000/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "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-18000/trainer_state.json

@@ -0,0 +1,1101 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9271779022599962,
+  "eval_steps": 500,
+  "global_step": 18000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9996726480206315e-05,
+      "loss": 0.7422,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9986906778099784e-05,
+      "loss": 0.6673,
+      "step": 200
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9970543465279565e-05,
+      "loss": 0.6749,
+      "step": 300
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.994764082699591e-05,
+      "loss": 0.6481,
+      "step": 400
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.991820486102801e-05,
+      "loss": 0.6505,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9882243276113245e-05,
+      "loss": 0.6708,
+      "step": 600
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.983976548992841e-05,
+      "loss": 0.6596,
+      "step": 700
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9790782626623436e-05,
+      "loss": 0.6657,
+      "step": 800
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.97353075139081e-05,
+      "loss": 0.659,
+      "step": 900
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9673354679692785e-05,
+      "loss": 0.6519,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.960494034828381e-05,
+      "loss": 0.638,
+      "step": 1100
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.9530082436134614e-05,
+      "loss": 0.629,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.944880054715378e-05,
+      "loss": 0.6464,
+      "step": 1300
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.9361115967571094e-05,
+      "loss": 0.642,
+      "step": 1400
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.926705166036311e-05,
+      "loss": 0.6431,
+      "step": 1500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.916663225923953e-05,
+      "loss": 0.6465,
+      "step": 1600
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.905988406219217e-05,
+      "loss": 0.6439,
+      "step": 1700
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.8946835024607885e-05,
+      "loss": 0.652,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.8827514751947656e-05,
+      "loss": 0.6376,
+      "step": 1900
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.8701954491993426e-05,
+      "loss": 0.6357,
+      "step": 2000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.85701871266649e-05,
+      "loss": 0.6338,
+      "step": 2100
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.8432247163408365e-05,
+      "loss": 0.6591,
+      "step": 2200
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.8288170726159815e-05,
+      "loss": 0.621,
+      "step": 2300
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.8137995545884794e-05,
+      "loss": 0.6337,
+      "step": 2400
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.798176095069731e-05,
+      "loss": 0.637,
+      "step": 2500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.781950785556054e-05,
+      "loss": 0.6464,
+      "step": 2600
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.7651278751571984e-05,
+      "loss": 0.6539,
+      "step": 2700
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.747711769483576e-05,
+      "loss": 0.6233,
+      "step": 2800
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.729707029492521e-05,
+      "loss": 0.6476,
+      "step": 2900
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.711118370293852e-05,
+      "loss": 0.6302,
+      "step": 3000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.691950659915074e-05,
+      "loss": 0.632,
+      "step": 3100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.672208918026535e-05,
+      "loss": 0.6281,
+      "step": 3200
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.6518983146268604e-05,
+      "loss": 0.6514,
+      "step": 3300
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.63102416868903e-05,
+      "loss": 0.6254,
+      "step": 3400
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.609591946767437e-05,
+      "loss": 0.6412,
+      "step": 3500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.587607261566294e-05,
+      "loss": 0.6647,
+      "step": 3600
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.565075870469777e-05,
+      "loss": 0.644,
+      "step": 3700
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.542003674034263e-05,
+      "loss": 0.6328,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.5183967144430904e-05,
+      "loss": 0.6454,
+      "step": 3900
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.4942611739242166e-05,
+      "loss": 0.6619,
+      "step": 4000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 4.469603373131214e-05,
+      "loss": 0.6326,
+      "step": 4100
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.444429769487997e-05,
+      "loss": 0.6373,
+      "step": 4200
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.4187469554977503e-05,
+      "loss": 0.6375,
+      "step": 4300
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.392561657016472e-05,
+      "loss": 0.6181,
+      "step": 4400
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.3658807314915915e-05,
+      "loss": 0.6415,
+      "step": 4500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.338711166166135e-05,
+      "loss": 0.6235,
+      "step": 4600
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 4.3110600762488915e-05,
+      "loss": 0.643,
+      "step": 4700
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.282934703051076e-05,
+      "loss": 0.6488,
+      "step": 4800
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.2543424120899556e-05,
+      "loss": 0.6536,
+      "step": 4900
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.2252906911599646e-05,
+      "loss": 0.6396,
+      "step": 5000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.195787148371782e-05,
+      "loss": 0.6456,
+      "step": 5100
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.165839510159914e-05,
+      "loss": 0.6213,
+      "step": 5200
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.1354556192592766e-05,
+      "loss": 0.6408,
+      "step": 5300
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.1046434326513305e-05,
+      "loss": 0.6394,
+      "step": 5400
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.073411019480297e-05,
+      "loss": 0.6338,
+      "step": 5500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.041766558939991e-05,
+      "loss": 0.6271,
+      "step": 5600
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 4.009718338131851e-05,
+      "loss": 0.6269,
+      "step": 5700
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.97727474989469e-05,
+      "loss": 0.6465,
+      "step": 5800
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.944444290606768e-05,
+      "loss": 0.6372,
+      "step": 5900
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.911235557960752e-05,
+      "loss": 0.6399,
+      "step": 6000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.877657248712131e-05,
+      "loss": 0.62,
+      "step": 6100
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.844059304094324e-05,
+      "loss": 0.6468,
+      "step": 6200
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.8097717913954655e-05,
+      "loss": 0.6362,
+      "step": 6300
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.775141273585859e-05,
+      "loss": 0.6302,
+      "step": 6400
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.740176819760346e-05,
+      "loss": 0.6334,
+      "step": 6500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.704887586465459e-05,
+      "loss": 0.6507,
+      "step": 6600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.669282815301495e-05,
+      "loss": 0.6403,
+      "step": 6700
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.6333718305023066e-05,
+      "loss": 0.6407,
+      "step": 6800
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.597164036493457e-05,
+      "loss": 0.6477,
+      "step": 6900
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.560668915429376e-05,
+      "loss": 0.656,
+      "step": 7000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.5238960247101584e-05,
+      "loss": 0.6252,
+      "step": 7100
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.486854994478655e-05,
+      "loss": 0.6345,
+      "step": 7200
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.4499297670475796e-05,
+      "loss": 0.6355,
+      "step": 7300
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.412384064706181e-05,
+      "loss": 0.6468,
+      "step": 7400
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.374599425781161e-05,
+      "loss": 0.6356,
+      "step": 7500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.336585745373593e-05,
+      "loss": 0.6335,
+      "step": 7600
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.2983529785662964e-05,
+      "loss": 0.6092,
+      "step": 7700
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3.2599111378167855e-05,
+      "loss": 0.6337,
+      "step": 7800
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.221657650708416e-05,
+      "loss": 0.6455,
+      "step": 7900
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 3.182829754439824e-05,
+      "loss": 0.627,
+      "step": 8000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.143823037633881e-05,
+      "loss": 0.6272,
+      "step": 8100
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 3.104647715431351e-05,
+      "loss": 0.6337,
+      "step": 8200
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.0653140471276476e-05,
+      "loss": 0.6562,
+      "step": 8300
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3.0258323334861104e-05,
+      "loss": 0.6184,
+      "step": 8400
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.9862129140404272e-05,
+      "loss": 0.6175,
+      "step": 8500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.9464661643868984e-05,
+      "loss": 0.6489,
+      "step": 8600
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.9066024934672632e-05,
+      "loss": 0.6423,
+      "step": 8700
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.866632340842786e-05,
+      "loss": 0.6127,
+      "step": 8800
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.8265661739603277e-05,
+      "loss": 0.6247,
+      "step": 8900
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.7864144854111168e-05,
+      "loss": 0.6307,
+      "step": 9000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7461877901829303e-05,
+      "loss": 0.6231,
+      "step": 9100
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.7058966229064143e-05,
+      "loss": 0.6304,
+      "step": 9200
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6655515350962545e-05,
+      "loss": 0.6408,
+      "step": 9300
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.625163092387934e-05,
+      "loss": 0.6198,
+      "step": 9400
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.584741871770784e-05,
+      "loss": 0.6378,
+      "step": 9500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.5442984588180657e-05,
+      "loss": 0.6303,
+      "step": 9600
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.5038434449148057e-05,
+      "loss": 0.6297,
+      "step": 9700
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.463387424484106e-05,
+      "loss": 0.6258,
+      "step": 9800
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4229409922126572e-05,
+      "loss": 0.6349,
+      "step": 9900
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.382514740276191e-05,
+      "loss": 0.6259,
+      "step": 10000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.3421192555655785e-05,
+      "loss": 0.6067,
+      "step": 10100
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3017651169143217e-05,
+      "loss": 0.6316,
+      "step": 10200
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.2614628923281524e-05,
+      "loss": 0.6402,
+      "step": 10300
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.2212231362174614e-05,
+      "loss": 0.6211,
+      "step": 10400
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.1810563866332996e-05,
+      "loss": 0.6315,
+      "step": 10500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1409731625076533e-05,
+      "loss": 0.6206,
+      "step": 10600
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.1009839608987253e-05,
+      "loss": 0.6201,
+      "step": 10700
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.0610992542419582e-05,
+      "loss": 0.6489,
+      "step": 10800
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2.0213294876074866e-05,
+      "loss": 0.6381,
+      "step": 10900
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9816850759647733e-05,
+      "loss": 0.6321,
+      "step": 11000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.9421764014551165e-05,
+      "loss": 0.6222,
+      "step": 11100
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.902813810672756e-05,
+      "loss": 0.6275,
+      "step": 11200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 1.8636076119553e-05,
+      "loss": 0.6281,
+      "step": 11300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.824568072684148e-05,
+      "loss": 0.6345,
+      "step": 11400
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.7857054165956648e-05,
+      "loss": 0.621,
+      "step": 11500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7470298211037665e-05,
+      "loss": 0.5951,
+      "step": 11600
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 1.7085514146346415e-05,
+      "loss": 0.6293,
+      "step": 11700
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6702802739743083e-05,
+      "loss": 0.626,
+      "step": 11800
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.6322264216296822e-05,
+      "loss": 0.6376,
+      "step": 11900
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.594399823203876e-05,
+      "loss": 0.643,
+      "step": 12000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.5568103847863835e-05,
+      "loss": 0.6274,
+      "step": 12100
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.5194679503588585e-05,
+      "loss": 0.6421,
+      "step": 12200
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.4823822992171621e-05,
+      "loss": 0.6202,
+      "step": 12300
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.445563143410339e-05,
+      "loss": 0.6156,
+      "step": 12400
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.4090201251972163e-05,
+      "loss": 0.6159,
+      "step": 12500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.3727628145212673e-05,
+      "loss": 0.6285,
+      "step": 12600
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.3368007065044269e-05,
+      "loss": 0.6356,
+      "step": 12700
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.3011432189604872e-05,
+      "loss": 0.6285,
+      "step": 12800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 1.2657996899287505e-05,
+      "loss": 0.6319,
+      "step": 12900
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2307793752285665e-05,
+      "loss": 0.6166,
+      "step": 13000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.1960914460354017e-05,
+      "loss": 0.6316,
+      "step": 13100
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.1617449864790823e-05,
+      "loss": 0.6124,
+      "step": 13200
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1277489912648251e-05,
+      "loss": 0.6318,
+      "step": 13300
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.0944469217262731e-05,
+      "loss": 0.6409,
+      "step": 13400
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0615056158497555e-05,
+      "loss": 0.6244,
+      "step": 13500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.0286064299421735e-05,
+      "loss": 0.6529,
+      "step": 13600
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.964157780320574e-06,
+      "loss": 0.6174,
+      "step": 13700
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.642917883925478e-06,
+      "loss": 0.6359,
+      "step": 13800
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.325699724512796e-06,
+      "loss": 0.6289,
+      "step": 13900
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 9.012586375676443e-06,
+      "loss": 0.6221,
+      "step": 14000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.70365983603603e-06,
+      "loss": 0.6368,
+      "step": 14100
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 8.399001007762921e-06,
+      "loss": 0.6225,
+      "step": 14200
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 8.098689675393509e-06,
+      "loss": 0.6258,
+      "step": 14300
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 7.802804484935048e-06,
+      "loss": 0.6212,
+      "step": 14400
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.511422923269759e-06,
+      "loss": 0.6354,
+      "step": 14500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.224621297862396e-06,
+      "loss": 0.6396,
+      "step": 14600
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.9424747167767785e-06,
+      "loss": 0.6066,
+      "step": 14700
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 6.665057069006344e-06,
+      "loss": 0.6273,
+      "step": 14800
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.39244100512397e-06,
+      "loss": 0.6264,
+      "step": 14900
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 6.124697918256153e-06,
+      "loss": 0.6335,
+      "step": 15000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.8618979253864585e-06,
+      "loss": 0.6205,
+      "step": 15100
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 5.604109848993158e-06,
+      "loss": 0.6349,
+      "step": 15200
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.35140119902591e-06,
+      "loss": 0.6134,
+      "step": 15300
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 5.103838155226118e-06,
+      "loss": 0.6275,
+      "step": 15400
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.861485549795722e-06,
+      "loss": 0.6228,
+      "step": 15500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.6244068504187835e-06,
+      "loss": 0.6288,
+      "step": 15600
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.392664143640512e-06,
+      "loss": 0.625,
+      "step": 15700
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.166318118607923e-06,
+      "loss": 0.6322,
+      "step": 15800
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.945428051176472e-06,
+      "loss": 0.6477,
+      "step": 15900
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.7300517883868015e-06,
+      "loss": 0.6406,
+      "step": 16000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.5202457333156443e-06,
+      "loss": 0.6277,
+      "step": 16100
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 3.3160648303049353e-06,
+      "loss": 0.6412,
+      "step": 16200
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.1175625505728834e-06,
+      "loss": 0.6361,
+      "step": 16300
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.9247908782108202e-06,
+      "loss": 0.6044,
+      "step": 16400
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 2.7378002965695594e-06,
+      "loss": 0.6183,
+      "step": 16500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.5566397750387215e-06,
+      "loss": 0.6328,
+      "step": 16600
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 2.3813567562225524e-06,
+      "loss": 0.6175,
+      "step": 16700
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.2119971435155873e-06,
+      "loss": 0.6272,
+      "step": 16800
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 2.048605289081365e-06,
+      "loss": 0.6404,
+      "step": 16900
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.8912239822374695e-06,
+      "loss": 0.6259,
+      "step": 17000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.7398944382497424e-06,
+      "loss": 0.6254,
+      "step": 17100
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.5946562875387927e-06,
+      "loss": 0.6249,
+      "step": 17200
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 1.4555475653015127e-06,
+      "loss": 0.6199,
+      "step": 17300
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.3226047015503646e-06,
+      "loss": 0.6249,
+      "step": 17400
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 1.1958625115730232e-06,
+      "loss": 0.6212,
+      "step": 17500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.0753541868148835e-06,
+      "loss": 0.6162,
+      "step": 17600
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 9.611112861868693e-07,
+      "loss": 0.6213,
+      "step": 17700
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 8.53163727800696e-07,
+      "loss": 0.6089,
+      "step": 17800
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 7.515397811338892e-07,
+      "loss": 0.6347,
+      "step": 17900
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 6.562660596265202e-07,
+      "loss": 0.6209,
+      "step": 18000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 19413,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "total_flos": 4.082470834290347e+19,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-18000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d478a4b43de7b19064a77e4740036edd604501f17a30e1008e6ef525fefdc95e
+size 4856