Upload 11 files

README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-v0.1
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.18.1

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45a1406b146fbb26c8e7e69a970142356ff2bbf979551ab848ccb2bdb6d6ab5a
+size 551634040

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a16342584d17efac5145c50d9165bab082754d70c4cd11f889d638874f06af9
+size 109130618

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d09ce2b6e37a9d9c8c7d4e22f7a724d231f482b130612876f5faa0f15ebb3de9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a9b3bb4e458b1d27f96bde8ed8a0ace6ffbcd98ee8a8b1000c43f4118d5a30e
+size 1064

special_tokens_map.json

@@ -0,0 +1,54 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|think|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|/think|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|story|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    },
+    {
+      "content": "<|/story|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "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_config.json

@@ -0,0 +1,81 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|think|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|/think|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|story|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|/story|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|think|>",
+    "<|/think|>",
+    "<|story|>",
+    "<|/story|>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,594 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.992414100847836,
+  "eval_steps": 500,
+  "global_step": 2800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.6259768772125245,
+      "epoch": 0.0892458723784025,
+      "grad_norm": 0.9921875,
+      "learning_rate": 9.702970297029703e-05,
+      "loss": 1.5974,
+      "mean_token_accuracy": 0.6319892483949662,
+      "num_tokens": 204800.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.1296514749526978,
+      "epoch": 0.178491744756805,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.00019603960396039606,
+      "loss": 1.095,
+      "mean_token_accuracy": 0.7227028369903564,
+      "num_tokens": 409600.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.0354267311096192,
+      "epoch": 0.2677376171352075,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.0001998929698787665,
+      "loss": 1.0001,
+      "mean_token_accuracy": 0.738949174284935,
+      "num_tokens": 614400.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.9883857735991478,
+      "epoch": 0.35698348951361,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019955410749920795,
+      "loss": 0.9576,
+      "mean_token_accuracy": 0.7486803528666496,
+      "num_tokens": 819200.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.9801795700192452,
+      "epoch": 0.4462293618920125,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00019898401407651969,
+      "loss": 0.9485,
+      "mean_token_accuracy": 0.7502834811806679,
+      "num_tokens": 1024000.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.976861891746521,
+      "epoch": 0.535475234270415,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00019818401374789826,
+      "loss": 0.942,
+      "mean_token_accuracy": 0.7504301071166992,
+      "num_tokens": 1228800.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.9461924117803574,
+      "epoch": 0.6247211066488175,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.00019715596464773042,
+      "loss": 0.9121,
+      "mean_token_accuracy": 0.7569012671709061,
+      "num_tokens": 1433600.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.9457061448693276,
+      "epoch": 0.71396697902722,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00019590225459176582,
+      "loss": 0.9115,
+      "mean_token_accuracy": 0.7561534664034844,
+      "num_tokens": 1638400.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.9444361236691475,
+      "epoch": 0.8032128514056225,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.00019442579553101584,
+      "loss": 0.9109,
+      "mean_token_accuracy": 0.7562658813595772,
+      "num_tokens": 1843200.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.9286397603154183,
+      "epoch": 0.892458723784025,
+      "grad_norm": 0.60546875,
+      "learning_rate": 0.00019273001678826114,
+      "loss": 0.8951,
+      "mean_token_accuracy": 0.7600635370612144,
+      "num_tokens": 2048000.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.9270413678884506,
+      "epoch": 0.9817045961624274,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00019081885709287667,
+      "loss": 0.8924,
+      "mean_token_accuracy": 0.7599315717816353,
+      "num_tokens": 2252800.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.871931555307456,
+      "epoch": 1.069611780455154,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00018869675543247482,
+      "loss": 0.8402,
+      "mean_token_accuracy": 0.7711419060750662,
+      "num_tokens": 2454528.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.866090109050274,
+      "epoch": 1.1588576528335564,
+      "grad_norm": 0.640625,
+      "learning_rate": 0.00018636864074261523,
+      "loss": 0.8309,
+      "mean_token_accuracy": 0.7731769263744355,
+      "num_tokens": 2659328.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.8680649262666702,
+      "epoch": 1.248103525211959,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018383992045852872,
+      "loss": 0.8363,
+      "mean_token_accuracy": 0.7720087966322899,
+      "num_tokens": 2864128.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.8708215129375457,
+      "epoch": 1.3373493975903614,
+      "grad_norm": 0.578125,
+      "learning_rate": 0.0001811164679554457,
+      "loss": 0.8353,
+      "mean_token_accuracy": 0.7726930573582649,
+      "num_tokens": 3068928.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.8597633948922158,
+      "epoch": 1.426595269968764,
+      "grad_norm": 0.5703125,
+      "learning_rate": 0.0001782046089067012,
+      "loss": 0.8265,
+      "mean_token_accuracy": 0.7739687168598175,
+      "num_tokens": 3273728.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.85432891279459,
+      "epoch": 1.5158411423471665,
+      "grad_norm": 0.59375,
+      "learning_rate": 0.000175111106591302,
+      "loss": 0.8231,
+      "mean_token_accuracy": 0.7762707683444023,
+      "num_tokens": 3478528.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.8619935244321824,
+      "epoch": 1.605087014725569,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.00017184314618508148,
+      "loss": 0.8254,
+      "mean_token_accuracy": 0.7741544449329376,
+      "num_tokens": 3683328.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.8650275564193726,
+      "epoch": 1.6943328871039713,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00016840831807192854,
+      "loss": 0.8275,
+      "mean_token_accuracy": 0.7748044946789742,
+      "num_tokens": 3888128.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.860476321876049,
+      "epoch": 1.783578759482374,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00016481460021385323,
+      "loss": 0.8255,
+      "mean_token_accuracy": 0.7732942277193069,
+      "num_tokens": 4092928.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.8491663599014282,
+      "epoch": 1.8728246318607764,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.0001610703396208375,
+      "loss": 0.8172,
+      "mean_token_accuracy": 0.7759139758348464,
+      "num_tokens": 4297728.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.8503634676337242,
+      "epoch": 1.962070504239179,
+      "grad_norm": 0.58203125,
+      "learning_rate": 0.0001571842329635102,
+      "loss": 0.8165,
+      "mean_token_accuracy": 0.7770869982242584,
+      "num_tokens": 4502528.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.7979691500591143,
+      "epoch": 2.0499776885319054,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00015316530637367708,
+      "loss": 0.7612,
+      "mean_token_accuracy": 0.7890002040693602,
+      "num_tokens": 4704256.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.7788776361942291,
+      "epoch": 2.139223560910308,
+      "grad_norm": 0.62890625,
+      "learning_rate": 0.00014902289447962187,
+      "loss": 0.7431,
+      "mean_token_accuracy": 0.7926588499546051,
+      "num_tokens": 4909056.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.7778185418248177,
+      "epoch": 2.2284694332887103,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.0001447666187248731,
+      "loss": 0.7431,
+      "mean_token_accuracy": 0.7919403752684593,
+      "num_tokens": 5113856.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.7770297473669052,
+      "epoch": 2.3177153056671127,
+      "grad_norm": 0.671875,
+      "learning_rate": 0.00014040636502079434,
+      "loss": 0.7421,
+      "mean_token_accuracy": 0.7937096789479255,
+      "num_tokens": 5318656.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.774446559548378,
+      "epoch": 2.4069611780455156,
+      "grad_norm": 0.69921875,
+      "learning_rate": 0.00013595226078490395,
+      "loss": 0.7405,
+      "mean_token_accuracy": 0.7925708714127541,
+      "num_tokens": 5523456.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.7771885851025582,
+      "epoch": 2.496207050423918,
+      "grad_norm": 0.61328125,
+      "learning_rate": 0.00013141465141825603,
+      "loss": 0.7402,
+      "mean_token_accuracy": 0.7931915977597237,
+      "num_tokens": 5728256.0,
+      "step": 1400
+    },
+    {
+      "entropy": 0.7688560289144516,
+      "epoch": 2.5854529228023204,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.0001268040762765189,
+      "loss": 0.7369,
+      "mean_token_accuracy": 0.7952443835139275,
+      "num_tokens": 5933056.0,
+      "step": 1450
+    },
+    {
+      "entropy": 0.78252092897892,
+      "epoch": 2.674698795180723,
+      "grad_norm": 0.70703125,
+      "learning_rate": 0.00012213124419056074,
+      "loss": 0.7474,
+      "mean_token_accuracy": 0.7915493679046631,
+      "num_tokens": 6137856.0,
+      "step": 1500
+    },
+    {
+      "entropy": 0.7763542786240578,
+      "epoch": 2.7639446675591253,
+      "grad_norm": 0.625,
+      "learning_rate": 0.00011740700859340161,
+      "loss": 0.7383,
+      "mean_token_accuracy": 0.7942082145810128,
+      "num_tokens": 6342656.0,
+      "step": 1550
+    },
+    {
+      "entropy": 0.7749826022982598,
+      "epoch": 2.853190539937528,
+      "grad_norm": 0.6796875,
+      "learning_rate": 0.00011264234231130209,
+      "loss": 0.7394,
+      "mean_token_accuracy": 0.794452593922615,
+      "num_tokens": 6547456.0,
+      "step": 1600
+    },
+    {
+      "entropy": 0.7712367391586303,
+      "epoch": 2.9424364123159306,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00010784831207754171,
+      "loss": 0.7352,
+      "mean_token_accuracy": 0.793088955283165,
+      "num_tokens": 6752256.0,
+      "step": 1650
+    },
+    {
+      "entropy": 0.7491341354278138,
+      "epoch": 3.030343596608657,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00010303605282808242,
+      "loss": 0.7141,
+      "mean_token_accuracy": 0.7993410486860324,
+      "num_tokens": 6953984.0,
+      "step": 1700
+    },
+    {
+      "entropy": 0.7142950230836869,
+      "epoch": 3.1195894689870594,
+      "grad_norm": 0.66796875,
+      "learning_rate": 9.821674183881982e-05,
+      "loss": 0.6733,
+      "mean_token_accuracy": 0.809511242210865,
+      "num_tokens": 7158784.0,
+      "step": 1750
+    },
+    {
+      "entropy": 0.7075088465213776,
+      "epoch": 3.208835341365462,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.34015727644931e-05,
+      "loss": 0.6705,
+      "mean_token_accuracy": 0.80923753708601,
+      "num_tokens": 7363584.0,
+      "step": 1800
+    },
+    {
+      "entropy": 0.7165163627266884,
+      "epoch": 3.298081213743864,
+      "grad_norm": 0.734375,
+      "learning_rate": 8.860172963955215e-05,
+      "loss": 0.683,
+      "mean_token_accuracy": 0.8069452607631683,
+      "num_tokens": 7568384.0,
+      "step": 1850
+    },
+    {
+      "entropy": 0.7122274199128151,
+      "epoch": 3.3873270861222666,
+      "grad_norm": 0.75390625,
+      "learning_rate": 8.382836090136962e-05,
+      "loss": 0.6751,
+      "mean_token_accuracy": 0.8079178902506828,
+      "num_tokens": 7773184.0,
+      "step": 1900
+    },
+    {
+      "entropy": 0.7034698343276977,
+      "epoch": 3.4765729585006695,
+      "grad_norm": 0.6953125,
+      "learning_rate": 7.909255349613283e-05,
+      "loss": 0.6673,
+      "mean_token_accuracy": 0.8113440865278244,
+      "num_tokens": 7977984.0,
+      "step": 1950
+    },
+    {
+      "entropy": 0.7057863634824753,
+      "epoch": 3.565818830879072,
+      "grad_norm": 0.76171875,
+      "learning_rate": 7.440530712755951e-05,
+      "loss": 0.6688,
+      "mean_token_accuracy": 0.8105962842702865,
+      "num_tokens": 8182784.0,
+      "step": 2000
+    },
+    {
+      "entropy": 0.7125656777620315,
+      "epoch": 3.6550647032574743,
+      "grad_norm": 0.76953125,
+      "learning_rate": 6.977750870824863e-05,
+      "loss": 0.6761,
+      "mean_token_accuracy": 0.8088660803437233,
+      "num_tokens": 8387584.0,
+      "step": 2050
+    },
+    {
+      "entropy": 0.70076868891716,
+      "epoch": 3.7443105756358768,
+      "grad_norm": 0.765625,
+      "learning_rate": 6.521990707300736e-05,
+      "loss": 0.6634,
+      "mean_token_accuracy": 0.8110703819990158,
+      "num_tokens": 8592384.0,
+      "step": 2100
+    },
+    {
+      "entropy": 0.700417303442955,
+      "epoch": 3.833556448014279,
+      "grad_norm": 0.73828125,
+      "learning_rate": 6.074308801288713e-05,
+      "loss": 0.6631,
+      "mean_token_accuracy": 0.8109530797600746,
+      "num_tokens": 8797184.0,
+      "step": 2150
+    },
+    {
+      "entropy": 0.7015222778916359,
+      "epoch": 3.922802320392682,
+      "grad_norm": 0.77734375,
+      "learning_rate": 5.6357449687915386e-05,
+      "loss": 0.6665,
+      "mean_token_accuracy": 0.8110703811049461,
+      "num_tokens": 9001984.0,
+      "step": 2200
+    },
+    {
+      "entropy": 0.7122828648780203,
+      "epoch": 4.010709504685408,
+      "grad_norm": 0.703125,
+      "learning_rate": 5.207317847563248e-05,
+      "loss": 0.6758,
+      "mean_token_accuracy": 0.8095082153523634,
+      "num_tokens": 9203712.0,
+      "step": 2250
+    },
+    {
+      "entropy": 0.6674378645420075,
+      "epoch": 4.099955377063811,
+      "grad_norm": 0.74609375,
+      "learning_rate": 4.7900225311528094e-05,
+      "loss": 0.6269,
+      "mean_token_accuracy": 0.8208357748389244,
+      "num_tokens": 9408512.0,
+      "step": 2300
+    },
+    {
+      "entropy": 0.6730345389246941,
+      "epoch": 4.189201249442213,
+      "grad_norm": 0.75390625,
+      "learning_rate": 4.384828257633177e-05,
+      "loss": 0.6365,
+      "mean_token_accuracy": 0.8188856270909309,
+      "num_tokens": 9613312.0,
+      "step": 2350
+    },
+    {
+      "entropy": 0.6662819012999535,
+      "epoch": 4.278447121820616,
+      "grad_norm": 0.8515625,
+      "learning_rate": 3.992676158383957e-05,
+      "loss": 0.6271,
+      "mean_token_accuracy": 0.8203372398018837,
+      "num_tokens": 9818112.0,
+      "step": 2400
+    },
+    {
+      "entropy": 0.664862583577633,
+      "epoch": 4.367692994199018,
+      "grad_norm": 0.80078125,
+      "learning_rate": 3.6144770721565844e-05,
+      "loss": 0.6261,
+      "mean_token_accuracy": 0.8207477974891663,
+      "num_tokens": 10022912.0,
+      "step": 2450
+    },
+    {
+      "entropy": 0.6621513772010803,
+      "epoch": 4.4569388665774206,
+      "grad_norm": 0.77734375,
+      "learning_rate": 3.251109429499194e-05,
+      "loss": 0.6238,
+      "mean_token_accuracy": 0.8212072286009788,
+      "num_tokens": 10227712.0,
+      "step": 2500
+    },
+    {
+      "entropy": 0.6667330291867256,
+      "epoch": 4.546184738955823,
+      "grad_norm": 0.77734375,
+      "learning_rate": 2.9034172124549263e-05,
+      "loss": 0.6275,
+      "mean_token_accuracy": 0.8213147559762001,
+      "num_tokens": 10432512.0,
+      "step": 2550
+    },
+    {
+      "entropy": 0.6676543334126472,
+      "epoch": 4.635430611334225,
+      "grad_norm": 0.78125,
+      "learning_rate": 2.5722079942726964e-05,
+      "loss": 0.6295,
+      "mean_token_accuracy": 0.8205034193396569,
+      "num_tokens": 10637312.0,
+      "step": 2600
+    },
+    {
+      "entropy": 0.6684669059514999,
+      "epoch": 4.724676483712628,
+      "grad_norm": 0.796875,
+      "learning_rate": 2.2582510636834064e-05,
+      "loss": 0.6347,
+      "mean_token_accuracy": 0.8190029296278953,
+      "num_tokens": 10842112.0,
+      "step": 2650
+    },
+    {
+      "entropy": 0.6723845577239991,
+      "epoch": 4.813922356091031,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.9622756380983887e-05,
+      "loss": 0.6353,
+      "mean_token_accuracy": 0.8182209166884422,
+      "num_tokens": 11046912.0,
+      "step": 2700
+    },
+    {
+      "entropy": 0.6706709080934524,
+      "epoch": 4.903168228469434,
+      "grad_norm": 0.75390625,
+      "learning_rate": 1.684969169880165e-05,
+      "loss": 0.6291,
+      "mean_token_accuracy": 0.8204301059246063,
+      "num_tokens": 11251712.0,
+      "step": 2750
+    },
+    {
+      "entropy": 0.6609847331047058,
+      "epoch": 4.992414100847836,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.4269757496194991e-05,
+      "loss": 0.6283,
+      "mean_token_accuracy": 0.8204398784041405,
+      "num_tokens": 11456512.0,
+      "step": 2800
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 3360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 560,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.897183183625257e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5aef2ef2aa5e0492e3c844c5919533b1d735a9a2341f5ae411c844a57e691a3b
+size 5816