Upload trained model and tokenizer 🚀

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/mistral-7b-v0.3-bnb-4bit
+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 0.14.0

adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
+  "bias": "none",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "embed_tokens",
+    "lm_head"
+  ],
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": true
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16eac0f0d6d5a5d20813a4c87af9f2ae53822ae3a9aa8ace40b5bed426877f25
+size 2415981336

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f13a83353ec85e034d4eefacb0e041702ab9531299761b42f00b29475778bfd
+size 1227363292

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:608fccb6c056ce88cdfd5355e6be2046f4d107a24a87c6b0d2c3b200ce6bb4ea
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c74a6b0fa93948347c57c36fe43701bdf05c0a2565ee9e1a5037b8eecf5016f
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e138551ed85f2ec8ed6eccd092f891f5910f6cd2bd353e2237175c263b538db
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "[control_768]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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 sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

trainer_state.json

@@ -0,0 +1,1126 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0064,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 4.4717,
+      "step": 1
+    },
+    {
+      "epoch": 0.0128,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 3.7313,
+      "step": 2
+    },
+    {
+      "epoch": 0.0192,
+      "grad_norm": 50.09918975830078,
+      "learning_rate": 0.0,
+      "loss": 4.8819,
+      "step": 3
+    },
+    {
+      "epoch": 0.0256,
+      "grad_norm": 49.641700744628906,
+      "learning_rate": 3.125e-06,
+      "loss": 5.1502,
+      "step": 4
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 38.01877975463867,
+      "learning_rate": 6.25e-06,
+      "loss": 4.0776,
+      "step": 5
+    },
+    {
+      "epoch": 0.0384,
+      "grad_norm": 34.66939926147461,
+      "learning_rate": 9.375000000000001e-06,
+      "loss": 3.8857,
+      "step": 6
+    },
+    {
+      "epoch": 0.0448,
+      "grad_norm": 33.477439880371094,
+      "learning_rate": 1.25e-05,
+      "loss": 3.8721,
+      "step": 7
+    },
+    {
+      "epoch": 0.0512,
+      "grad_norm": 45.55080795288086,
+      "learning_rate": 1.5625e-05,
+      "loss": 3.7879,
+      "step": 8
+    },
+    {
+      "epoch": 0.0576,
+      "grad_norm": 32.00156021118164,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 3.345,
+      "step": 9
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 29.618633270263672,
+      "learning_rate": 2.1875e-05,
+      "loss": 3.1297,
+      "step": 10
+    },
+    {
+      "epoch": 0.0704,
+      "grad_norm": 32.84077453613281,
+      "learning_rate": 2.5e-05,
+      "loss": 3.3396,
+      "step": 11
+    },
+    {
+      "epoch": 0.0768,
+      "grad_norm": 31.820215225219727,
+      "learning_rate": 2.8125000000000003e-05,
+      "loss": 3.0906,
+      "step": 12
+    },
+    {
+      "epoch": 0.0832,
+      "grad_norm": 27.288164138793945,
+      "learning_rate": 3.125e-05,
+      "loss": 2.8775,
+      "step": 13
+    },
+    {
+      "epoch": 0.0896,
+      "grad_norm": 30.749038696289062,
+      "learning_rate": 3.4375e-05,
+      "loss": 3.0161,
+      "step": 14
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 25.01470184326172,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 2.8359,
+      "step": 15
+    },
+    {
+      "epoch": 0.1024,
+      "grad_norm": 24.316774368286133,
+      "learning_rate": 4.0625000000000005e-05,
+      "loss": 2.7709,
+      "step": 16
+    },
+    {
+      "epoch": 0.1088,
+      "grad_norm": 21.760366439819336,
+      "learning_rate": 4.375e-05,
+      "loss": 2.6184,
+      "step": 17
+    },
+    {
+      "epoch": 0.1152,
+      "grad_norm": 18.646337509155273,
+      "learning_rate": 4.6875e-05,
+      "loss": 2.1646,
+      "step": 18
+    },
+    {
+      "epoch": 0.1216,
+      "grad_norm": 23.844223022460938,
+      "learning_rate": 5e-05,
+      "loss": 2.8295,
+      "step": 19
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 24.90797233581543,
+      "learning_rate": 4.9993705873562665e-05,
+      "loss": 2.9796,
+      "step": 20
+    },
+    {
+      "epoch": 0.1344,
+      "grad_norm": 23.792762756347656,
+      "learning_rate": 4.997482666353287e-05,
+      "loss": 2.9825,
+      "step": 21
+    },
+    {
+      "epoch": 0.1408,
+      "grad_norm": 21.59649658203125,
+      "learning_rate": 4.99433718761614e-05,
+      "loss": 2.496,
+      "step": 22
+    },
+    {
+      "epoch": 0.1472,
+      "grad_norm": Infinity,
+      "learning_rate": 4.989935734988098e-05,
+      "loss": 2.2942,
+      "step": 23
+    },
+    {
+      "epoch": 0.1536,
+      "grad_norm": 26.09481430053711,
+      "learning_rate": 4.989935734988098e-05,
+      "loss": 2.4601,
+      "step": 24
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": Infinity,
+      "learning_rate": 4.984280524733107e-05,
+      "loss": 2.7508,
+      "step": 25
+    },
+    {
+      "epoch": 0.1664,
+      "grad_norm": Infinity,
+      "learning_rate": 4.984280524733107e-05,
+      "loss": 3.4579,
+      "step": 26
+    },
+    {
+      "epoch": 0.1728,
+      "grad_norm": 196.4443359375,
+      "learning_rate": 4.984280524733107e-05,
+      "loss": 2.5371,
+      "step": 27
+    },
+    {
+      "epoch": 0.1792,
+      "grad_norm": 24.16455078125,
+      "learning_rate": 4.977374404419837e-05,
+      "loss": 2.4961,
+      "step": 28
+    },
+    {
+      "epoch": 0.1856,
+      "grad_norm": 20.553077697753906,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 2.0176,
+      "step": 29
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 20.222591400146484,
+      "learning_rate": 4.959823971496574e-05,
+      "loss": 2.3133,
+      "step": 30
+    },
+    {
+      "epoch": 0.1984,
+      "grad_norm": 23.096298217773438,
+      "learning_rate": 4.9491884960580894e-05,
+      "loss": 2.6822,
+      "step": 31
+    },
+    {
+      "epoch": 0.2048,
+      "grad_norm": 20.923219680786133,
+      "learning_rate": 4.937319780454559e-05,
+      "loss": 2.718,
+      "step": 32
+    },
+    {
+      "epoch": 0.2112,
+      "grad_norm": 20.68602752685547,
+      "learning_rate": 4.9242238009417175e-05,
+      "loss": 2.7881,
+      "step": 33
+    },
+    {
+      "epoch": 0.2176,
+      "grad_norm": 20.52227210998535,
+      "learning_rate": 4.909907151739633e-05,
+      "loss": 2.4548,
+      "step": 34
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 20.739513397216797,
+      "learning_rate": 4.894377041712326e-05,
+      "loss": 2.7408,
+      "step": 35
+    },
+    {
+      "epoch": 0.2304,
+      "grad_norm": 16.86931610107422,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 2.2282,
+      "step": 36
+    },
+    {
+      "epoch": 0.2368,
+      "grad_norm": 20.215930938720703,
+      "learning_rate": 4.8597083257709194e-05,
+      "loss": 2.3036,
+      "step": 37
+    },
+    {
+      "epoch": 0.2432,
+      "grad_norm": 21.190462112426758,
+      "learning_rate": 4.8405871765993433e-05,
+      "loss": 2.0958,
+      "step": 38
+    },
+    {
+      "epoch": 0.2496,
+      "grad_norm": 18.445409774780273,
+      "learning_rate": 4.820287471297598e-05,
+      "loss": 2.1603,
+      "step": 39
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 17.071805953979492,
+      "learning_rate": 4.7988194313786275e-05,
+      "loss": 2.6078,
+      "step": 40
+    },
+    {
+      "epoch": 0.2624,
+      "grad_norm": 18.929542541503906,
+      "learning_rate": 4.7761938666470403e-05,
+      "loss": 2.0112,
+      "step": 41
+    },
+    {
+      "epoch": 0.2688,
+      "grad_norm": 17.4970645904541,
+      "learning_rate": 4.752422169756048e-05,
+      "loss": 2.6611,
+      "step": 42
+    },
+    {
+      "epoch": 0.2752,
+      "grad_norm": 19.641874313354492,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 2.369,
+      "step": 43
+    },
+    {
+      "epoch": 0.2816,
+      "grad_norm": 18.337270736694336,
+      "learning_rate": 4.701488829641845e-05,
+      "loss": 2.744,
+      "step": 44
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 17.220279693603516,
+      "learning_rate": 4.674352832889239e-05,
+      "loss": 2.3373,
+      "step": 45
+    },
+    {
+      "epoch": 0.2944,
+      "grad_norm": 13.7833251953125,
+      "learning_rate": 4.6461219840046654e-05,
+      "loss": 2.1818,
+      "step": 46
+    },
+    {
+      "epoch": 0.3008,
+      "grad_norm": 19.681421279907227,
+      "learning_rate": 4.6168104980707107e-05,
+      "loss": 2.846,
+      "step": 47
+    },
+    {
+      "epoch": 0.3072,
+      "grad_norm": 17.642488479614258,
+      "learning_rate": 4.586433134303257e-05,
+      "loss": 2.6217,
+      "step": 48
+    },
+    {
+      "epoch": 0.3136,
+      "grad_norm": 15.780743598937988,
+      "learning_rate": 4.5550051886197754e-05,
+      "loss": 2.0978,
+      "step": 49
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 18.60186004638672,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 2.8495,
+      "step": 50
+    },
+    {
+      "epoch": 0.3264,
+      "grad_norm": 16.284923553466797,
+      "learning_rate": 4.489061372204453e-05,
+      "loss": 1.9968,
+      "step": 51
+    },
+    {
+      "epoch": 0.3328,
+      "grad_norm": 18.098651885986328,
+      "learning_rate": 4.454578706170075e-05,
+      "loss": 2.8142,
+      "step": 52
+    },
+    {
+      "epoch": 0.3392,
+      "grad_norm": 23.010522842407227,
+      "learning_rate": 4.419111850895028e-05,
+      "loss": 2.848,
+      "step": 53
+    },
+    {
+      "epoch": 0.3456,
+      "grad_norm": 21.82461166381836,
+      "learning_rate": 4.382678665009028e-05,
+      "loss": 2.3738,
+      "step": 54
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 20.080095291137695,
+      "learning_rate": 4.345297493718352e-05,
+      "loss": 2.55,
+      "step": 55
+    },
+    {
+      "epoch": 0.3584,
+      "grad_norm": 16.38557243347168,
+      "learning_rate": 4.306987159568479e-05,
+      "loss": 2.2054,
+      "step": 56
+    },
+    {
+      "epoch": 0.3648,
+      "grad_norm": 16.24085235595703,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 2.2092,
+      "step": 57
+    },
+    {
+      "epoch": 0.3712,
+      "grad_norm": 17.953500747680664,
+      "learning_rate": 4.227656622467162e-05,
+      "loss": 2.6697,
+      "step": 58
+    },
+    {
+      "epoch": 0.3776,
+      "grad_norm": 16.460187911987305,
+      "learning_rate": 4.186676364830186e-05,
+      "loss": 2.2483,
+      "step": 59
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 15.681517601013184,
+      "learning_rate": 4.144846814849282e-05,
+      "loss": 2.4484,
+      "step": 60
+    },
+    {
+      "epoch": 0.3904,
+      "grad_norm": 18.890939712524414,
+      "learning_rate": 4.10218903496256e-05,
+      "loss": 2.3774,
+      "step": 61
+    },
+    {
+      "epoch": 0.3968,
+      "grad_norm": 15.988091468811035,
+      "learning_rate": 4.058724504646834e-05,
+      "loss": 2.1949,
+      "step": 62
+    },
+    {
+      "epoch": 0.4032,
+      "grad_norm": 12.159764289855957,
+      "learning_rate": 4.01447510960205e-05,
+      "loss": 2.0308,
+      "step": 63
+    },
+    {
+      "epoch": 0.4096,
+      "grad_norm": 16.4202938079834,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 2.1106,
+      "step": 64
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 16.02802276611328,
+      "learning_rate": 3.92371123292113e-05,
+      "loss": 2.2022,
+      "step": 65
+    },
+    {
+      "epoch": 0.4224,
+      "grad_norm": 15.44360065460205,
+      "learning_rate": 3.8772424536302564e-05,
+      "loss": 2.0292,
+      "step": 66
+    },
+    {
+      "epoch": 0.4288,
+      "grad_norm": 16.987598419189453,
+      "learning_rate": 3.830080191288342e-05,
+      "loss": 2.3518,
+      "step": 67
+    },
+    {
+      "epoch": 0.4352,
+      "grad_norm": 16.269733428955078,
+      "learning_rate": 3.782248193514766e-05,
+      "loss": 2.7523,
+      "step": 68
+    },
+    {
+      "epoch": 0.4416,
+      "grad_norm": 15.051939964294434,
+      "learning_rate": 3.7337705451608674e-05,
+      "loss": 2.2994,
+      "step": 69
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 16.779054641723633,
+      "learning_rate": 3.6846716561824965e-05,
+      "loss": 2.299,
+      "step": 70
+    },
+    {
+      "epoch": 0.4544,
+      "grad_norm": 20.661670684814453,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 2.5077,
+      "step": 71
+    },
+    {
+      "epoch": 0.4608,
+      "grad_norm": 17.521690368652344,
+      "learning_rate": 3.5847093477938956e-05,
+      "loss": 2.3761,
+      "step": 72
+    },
+    {
+      "epoch": 0.4672,
+      "grad_norm": 13.472983360290527,
+      "learning_rate": 3.533896262416302e-05,
+      "loss": 1.6423,
+      "step": 73
+    },
+    {
+      "epoch": 0.4736,
+      "grad_norm": 15.794869422912598,
+      "learning_rate": 3.4825625791348096e-05,
+      "loss": 2.3065,
+      "step": 74
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 14.395452499389648,
+      "learning_rate": 3.4307341460048633e-05,
+      "loss": 1.9287,
+      "step": 75
+    },
+    {
+      "epoch": 0.4864,
+      "grad_norm": 14.031108856201172,
+      "learning_rate": 3.378437060203357e-05,
+      "loss": 1.7176,
+      "step": 76
+    },
+    {
+      "epoch": 0.4928,
+      "grad_norm": 14.45324420928955,
+      "learning_rate": 3.3256976548879184e-05,
+      "loss": 1.7939,
+      "step": 77
+    },
+    {
+      "epoch": 0.4992,
+      "grad_norm": 16.889461517333984,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 2.3255,
+      "step": 78
+    },
+    {
+      "epoch": 0.5056,
+      "grad_norm": 17.210290908813477,
+      "learning_rate": 3.218998318580043e-05,
+      "loss": 2.413,
+      "step": 79
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 16.81619644165039,
+      "learning_rate": 3.165092113916688e-05,
+      "loss": 2.0536,
+      "step": 80
+    },
+    {
+      "epoch": 0.5184,
+      "grad_norm": 17.692567825317383,
+      "learning_rate": 3.110851015344735e-05,
+      "loss": 2.4001,
+      "step": 81
+    },
+    {
+      "epoch": 0.5248,
+      "grad_norm": 17.277616500854492,
+      "learning_rate": 3.056302334890786e-05,
+      "loss": 2.4519,
+      "step": 82
+    },
+    {
+      "epoch": 0.5312,
+      "grad_norm": 13.526611328125,
+      "learning_rate": 3.0014735394581823e-05,
+      "loss": 2.5048,
+      "step": 83
+    },
+    {
+      "epoch": 0.5376,
+      "grad_norm": 12.37924575805664,
+      "learning_rate": 2.9463922369965917e-05,
+      "loss": 2.1537,
+      "step": 84
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 12.96046257019043,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 2.039,
+      "step": 85
+    },
+    {
+      "epoch": 0.5504,
+      "grad_norm": 14.766209602355957,
+      "learning_rate": 2.8355831645441388e-05,
+      "loss": 1.8841,
+      "step": 86
+    },
+    {
+      "epoch": 0.5568,
+      "grad_norm": 15.26258659362793,
+      "learning_rate": 2.7799111902582696e-05,
+      "loss": 1.9104,
+      "step": 87
+    },
+    {
+      "epoch": 0.5632,
+      "grad_norm": 17.1923770904541,
+      "learning_rate": 2.724098272258584e-05,
+      "loss": 2.2466,
+      "step": 88
+    },
+    {
+      "epoch": 0.5696,
+      "grad_norm": 14.253467559814453,
+      "learning_rate": 2.6681725140300997e-05,
+      "loss": 1.9563,
+      "step": 89
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 15.101798057556152,
+      "learning_rate": 2.6121620758762877e-05,
+      "loss": 2.0253,
+      "step": 90
+    },
+    {
+      "epoch": 0.5824,
+      "grad_norm": 13.99666976928711,
+      "learning_rate": 2.556095160739513e-05,
+      "loss": 2.1236,
+      "step": 91
+    },
+    {
+      "epoch": 0.5888,
+      "grad_norm": 12.746740341186523,
+      "learning_rate": 2.5e-05,
+      "loss": 1.6476,
+      "step": 92
+    },
+    {
+      "epoch": 0.5952,
+      "grad_norm": 19.76336097717285,
+      "learning_rate": 2.443904839260488e-05,
+      "loss": 2.0452,
+      "step": 93
+    },
+    {
+      "epoch": 0.6016,
+      "grad_norm": 25.369564056396484,
+      "learning_rate": 2.3878379241237136e-05,
+      "loss": 2.1431,
+      "step": 94
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 17.740018844604492,
+      "learning_rate": 2.331827485969901e-05,
+      "loss": 2.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.6144,
+      "grad_norm": 15.30899715423584,
+      "learning_rate": 2.2759017277414166e-05,
+      "loss": 2.1131,
+      "step": 96
+    },
+    {
+      "epoch": 0.6208,
+      "grad_norm": 14.119115829467773,
+      "learning_rate": 2.2200888097417307e-05,
+      "loss": 1.7113,
+      "step": 97
+    },
+    {
+      "epoch": 0.6272,
+      "grad_norm": 12.78761100769043,
+      "learning_rate": 2.164416835455862e-05,
+      "loss": 1.7024,
+      "step": 98
+    },
+    {
+      "epoch": 0.6336,
+      "grad_norm": 14.637947082519531,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 1.999,
+      "step": 99
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 12.557490348815918,
+      "learning_rate": 2.0536077630034086e-05,
+      "loss": 1.9154,
+      "step": 100
+    },
+    {
+      "epoch": 0.6464,
+      "grad_norm": 13.05916690826416,
+      "learning_rate": 1.9985264605418183e-05,
+      "loss": 2.1664,
+      "step": 101
+    },
+    {
+      "epoch": 0.6528,
+      "grad_norm": 13.55716609954834,
+      "learning_rate": 1.9436976651092144e-05,
+      "loss": 2.1371,
+      "step": 102
+    },
+    {
+      "epoch": 0.6592,
+      "grad_norm": 13.797104835510254,
+      "learning_rate": 1.8891489846552646e-05,
+      "loss": 2.0145,
+      "step": 103
+    },
+    {
+      "epoch": 0.6656,
+      "grad_norm": 17.893796920776367,
+      "learning_rate": 1.8349078860833123e-05,
+      "loss": 2.5387,
+      "step": 104
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 13.919113159179688,
+      "learning_rate": 1.781001681419957e-05,
+      "loss": 1.8043,
+      "step": 105
+    },
+    {
+      "epoch": 0.6784,
+      "grad_norm": 18.958742141723633,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 1.8813,
+      "step": 106
+    },
+    {
+      "epoch": 0.6848,
+      "grad_norm": 14.358981132507324,
+      "learning_rate": 1.6743023451120832e-05,
+      "loss": 2.2653,
+      "step": 107
+    },
+    {
+      "epoch": 0.6912,
+      "grad_norm": 16.244213104248047,
+      "learning_rate": 1.621562939796643e-05,
+      "loss": 1.8594,
+      "step": 108
+    },
+    {
+      "epoch": 0.6976,
+      "grad_norm": 10.932610511779785,
+      "learning_rate": 1.5692658539951372e-05,
+      "loss": 1.5337,
+      "step": 109
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 13.12227725982666,
+      "learning_rate": 1.5174374208651912e-05,
+      "loss": 1.7683,
+      "step": 110
+    },
+    {
+      "epoch": 0.7104,
+      "grad_norm": 14.502724647521973,
+      "learning_rate": 1.466103737583699e-05,
+      "loss": 1.9204,
+      "step": 111
+    },
+    {
+      "epoch": 0.7168,
+      "grad_norm": 13.592811584472656,
+      "learning_rate": 1.4152906522061048e-05,
+      "loss": 1.9949,
+      "step": 112
+    },
+    {
+      "epoch": 0.7232,
+      "grad_norm": 12.350465774536133,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 1.7721,
+      "step": 113
+    },
+    {
+      "epoch": 0.7296,
+      "grad_norm": 16.48741912841797,
+      "learning_rate": 1.3153283438175034e-05,
+      "loss": 2.2935,
+      "step": 114
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 15.990097045898438,
+      "learning_rate": 1.2662294548391328e-05,
+      "loss": 2.0732,
+      "step": 115
+    },
+    {
+      "epoch": 0.7424,
+      "grad_norm": 13.479302406311035,
+      "learning_rate": 1.217751806485235e-05,
+      "loss": 1.7489,
+      "step": 116
+    },
+    {
+      "epoch": 0.7488,
+      "grad_norm": 14.067448616027832,
+      "learning_rate": 1.1699198087116589e-05,
+      "loss": 1.7152,
+      "step": 117
+    },
+    {
+      "epoch": 0.7552,
+      "grad_norm": 14.49460220336914,
+      "learning_rate": 1.122757546369744e-05,
+      "loss": 1.7153,
+      "step": 118
+    },
+    {
+      "epoch": 0.7616,
+      "grad_norm": 13.666254997253418,
+      "learning_rate": 1.0762887670788702e-05,
+      "loss": 2.0473,
+      "step": 119
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 14.832523345947266,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 1.8324,
+      "step": 120
+    },
+    {
+      "epoch": 0.7744,
+      "grad_norm": 12.877457618713379,
+      "learning_rate": 9.855248903979506e-06,
+      "loss": 1.8216,
+      "step": 121
+    },
+    {
+      "epoch": 0.7808,
+      "grad_norm": 29.62076187133789,
+      "learning_rate": 9.412754953531663e-06,
+      "loss": 2.3434,
+      "step": 122
+    },
+    {
+      "epoch": 0.7872,
+      "grad_norm": 16.266117095947266,
+      "learning_rate": 8.978109650374397e-06,
+      "loss": 2.2554,
+      "step": 123
+    },
+    {
+      "epoch": 0.7936,
+      "grad_norm": 14.676825523376465,
+      "learning_rate": 8.551531851507186e-06,
+      "loss": 1.9236,
+      "step": 124
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 15.351411819458008,
+      "learning_rate": 8.133236351698143e-06,
+      "loss": 2.2928,
+      "step": 125
+    },
+    {
+      "epoch": 0.8064,
+      "grad_norm": 15.592199325561523,
+      "learning_rate": 7.723433775328384e-06,
+      "loss": 1.8252,
+      "step": 126
+    },
+    {
+      "epoch": 0.8128,
+      "grad_norm": 13.63974666595459,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 1.863,
+      "step": 127
+    },
+    {
+      "epoch": 0.8192,
+      "grad_norm": 14.163743019104004,
+      "learning_rate": 6.930128404315214e-06,
+      "loss": 2.1451,
+      "step": 128
+    },
+    {
+      "epoch": 0.8256,
+      "grad_norm": 12.641812324523926,
+      "learning_rate": 6.547025062816486e-06,
+      "loss": 1.5801,
+      "step": 129
+    },
+    {
+      "epoch": 0.832,
+      "grad_norm": 12.196229934692383,
+      "learning_rate": 6.173213349909729e-06,
+      "loss": 1.6599,
+      "step": 130
+    },
+    {
+      "epoch": 0.8384,
+      "grad_norm": 14.172977447509766,
+      "learning_rate": 5.808881491049723e-06,
+      "loss": 1.4121,
+      "step": 131
+    },
+    {
+      "epoch": 0.8448,
+      "grad_norm": 15.83859920501709,
+      "learning_rate": 5.454212938299255e-06,
+      "loss": 2.1285,
+      "step": 132
+    },
+    {
+      "epoch": 0.8512,
+      "grad_norm": 15.493228912353516,
+      "learning_rate": 5.1093862779554776e-06,
+      "loss": 1.8166,
+      "step": 133
+    },
+    {
+      "epoch": 0.8576,
+      "grad_norm": 12.775120735168457,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 1.797,
+      "step": 134
+    },
+    {
+      "epoch": 0.864,
+      "grad_norm": 16.07529640197754,
+      "learning_rate": 4.4499481138022544e-06,
+      "loss": 2.4226,
+      "step": 135
+    },
+    {
+      "epoch": 0.8704,
+      "grad_norm": 17.667911529541016,
+      "learning_rate": 4.135668656967434e-06,
+      "loss": 2.4773,
+      "step": 136
+    },
+    {
+      "epoch": 0.8768,
+      "grad_norm": 11.440982818603516,
+      "learning_rate": 3.831895019292897e-06,
+      "loss": 1.9243,
+      "step": 137
+    },
+    {
+      "epoch": 0.8832,
+      "grad_norm": 11.593207359313965,
+      "learning_rate": 3.5387801599533475e-06,
+      "loss": 1.8069,
+      "step": 138
+    },
+    {
+      "epoch": 0.8896,
+      "grad_norm": 12.516495704650879,
+      "learning_rate": 3.2564716711076167e-06,
+      "loss": 2.0035,
+      "step": 139
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 13.478569030761719,
+      "learning_rate": 2.98511170358155e-06,
+      "loss": 1.8373,
+      "step": 140
+    },
+    {
+      "epoch": 0.9024,
+      "grad_norm": 13.340173721313477,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 1.8686,
+      "step": 141
+    },
+    {
+      "epoch": 0.9088,
+      "grad_norm": 14.038780212402344,
+      "learning_rate": 2.475778302439524e-06,
+      "loss": 1.788,
+      "step": 142
+    },
+    {
+      "epoch": 0.9152,
+      "grad_norm": 12.520078659057617,
+      "learning_rate": 2.2380613335296036e-06,
+      "loss": 1.5771,
+      "step": 143
+    },
+    {
+      "epoch": 0.9216,
+      "grad_norm": 14.458097457885742,
+      "learning_rate": 2.0118056862137357e-06,
+      "loss": 1.7918,
+      "step": 144
+    },
+    {
+      "epoch": 0.928,
+      "grad_norm": 11.08523941040039,
+      "learning_rate": 1.7971252870240291e-06,
+      "loss": 1.2751,
+      "step": 145
+    },
+    {
+      "epoch": 0.9344,
+      "grad_norm": 16.677467346191406,
+      "learning_rate": 1.59412823400657e-06,
+      "loss": 1.7166,
+      "step": 146
+    },
+    {
+      "epoch": 0.9408,
+      "grad_norm": 11.89140796661377,
+      "learning_rate": 1.4029167422908107e-06,
+      "loss": 1.2959,
+      "step": 147
+    },
+    {
+      "epoch": 0.9472,
+      "grad_norm": 12.096765518188477,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 2.0022,
+      "step": 148
+    },
+    {
+      "epoch": 0.9536,
+      "grad_norm": 16.47886085510254,
+      "learning_rate": 1.0562295828767387e-06,
+      "loss": 1.8419,
+      "step": 149
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 14.262722969055176,
+      "learning_rate": 9.009284826036691e-07,
+      "loss": 2.0822,
+      "step": 150
+    },
+    {
+      "epoch": 0.9664,
+      "grad_norm": 12.945296287536621,
+      "learning_rate": 7.577619905828282e-07,
+      "loss": 1.6891,
+      "step": 151
+    },
+    {
+      "epoch": 0.9728,
+      "grad_norm": 13.680462837219238,
+      "learning_rate": 6.268021954544096e-07,
+      "loss": 1.8831,
+      "step": 152
+    },
+    {
+      "epoch": 0.9792,
+      "grad_norm": 12.656660079956055,
+      "learning_rate": 5.08115039419113e-07,
+      "loss": 1.5704,
+      "step": 153
+    },
+    {
+      "epoch": 0.9856,
+      "grad_norm": 13.578558921813965,
+      "learning_rate": 4.0176028503425835e-07,
+      "loss": 1.7809,
+      "step": 154
+    },
+    {
+      "epoch": 0.992,
+      "grad_norm": 12.945449829101562,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 1.9945,
+      "step": 155
+    },
+    {
+      "epoch": 0.9984,
+      "grad_norm": 13.290226936340332,
+      "learning_rate": 2.262559558016325e-07,
+      "loss": 2.065,
+      "step": 156
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 156,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3164804878614528.0,
+  "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 sha256:4cac4dccb92be3c2e06e78c30f6ddde97392699967093a005743160494168034
+size 5560