Upload 7 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: huggyllama/llama-7b
+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 0.11.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "huggyllama/llama-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": "unsloth",
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34ef2a147717b4436b3836b03a8137527cc2e469b6ff761cc92bb014557e25f3
+size 33588528

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,727 @@
+{
+  "best_metric": 0.8182997107505798,
+  "best_model_checkpoint": "outputs/checkpoint-92",
+  "epoch": 1.0,
+  "eval_steps": 23,
+  "global_step": 92,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010869565217391304,
+      "grad_norm": 0.25948596000671387,
+      "learning_rate": 0.001,
+      "loss": 2.557,
+      "step": 1
+    },
+    {
+      "epoch": 0.021739130434782608,
+      "grad_norm": 0.6524776220321655,
+      "learning_rate": 0.001,
+      "loss": 2.2351,
+      "step": 2
+    },
+    {
+      "epoch": 0.03260869565217391,
+      "grad_norm": 0.5083250403404236,
+      "learning_rate": 0.001,
+      "loss": 1.9823,
+      "step": 3
+    },
+    {
+      "epoch": 0.043478260869565216,
+      "grad_norm": 2.7111644744873047,
+      "learning_rate": 0.001,
+      "loss": 1.766,
+      "step": 4
+    },
+    {
+      "epoch": 0.05434782608695652,
+      "grad_norm": 0.5816826224327087,
+      "learning_rate": 0.001,
+      "loss": 1.5714,
+      "step": 5
+    },
+    {
+      "epoch": 0.06521739130434782,
+      "grad_norm": 0.3153815269470215,
+      "learning_rate": 0.001,
+      "loss": 1.4747,
+      "step": 6
+    },
+    {
+      "epoch": 0.07608695652173914,
+      "grad_norm": 0.23670993745326996,
+      "learning_rate": 0.001,
+      "loss": 1.4613,
+      "step": 7
+    },
+    {
+      "epoch": 0.08695652173913043,
+      "grad_norm": 0.22481270134449005,
+      "learning_rate": 0.001,
+      "loss": 1.3309,
+      "step": 8
+    },
+    {
+      "epoch": 0.09782608695652174,
+      "grad_norm": 0.19224806129932404,
+      "learning_rate": 0.001,
+      "loss": 1.2744,
+      "step": 9
+    },
+    {
+      "epoch": 0.10869565217391304,
+      "grad_norm": 0.4313323199748993,
+      "learning_rate": 0.001,
+      "loss": 1.2549,
+      "step": 10
+    },
+    {
+      "epoch": 0.11956521739130435,
+      "grad_norm": 0.21521781384944916,
+      "learning_rate": 0.001,
+      "loss": 1.2236,
+      "step": 11
+    },
+    {
+      "epoch": 0.13043478260869565,
+      "grad_norm": 0.22998858988285065,
+      "learning_rate": 0.001,
+      "loss": 1.2058,
+      "step": 12
+    },
+    {
+      "epoch": 0.14130434782608695,
+      "grad_norm": 0.912493109703064,
+      "learning_rate": 0.001,
+      "loss": 1.2498,
+      "step": 13
+    },
+    {
+      "epoch": 0.15217391304347827,
+      "grad_norm": 0.9947443008422852,
+      "learning_rate": 0.001,
+      "loss": 1.1692,
+      "step": 14
+    },
+    {
+      "epoch": 0.16304347826086957,
+      "grad_norm": 0.6725525259971619,
+      "learning_rate": 0.001,
+      "loss": 1.1741,
+      "step": 15
+    },
+    {
+      "epoch": 0.17391304347826086,
+      "grad_norm": 0.4825955927371979,
+      "learning_rate": 0.001,
+      "loss": 1.1859,
+      "step": 16
+    },
+    {
+      "epoch": 0.18478260869565216,
+      "grad_norm": 0.5571773648262024,
+      "learning_rate": 0.001,
+      "loss": 1.246,
+      "step": 17
+    },
+    {
+      "epoch": 0.1956521739130435,
+      "grad_norm": 0.5893177390098572,
+      "learning_rate": 0.001,
+      "loss": 1.2051,
+      "step": 18
+    },
+    {
+      "epoch": 0.20652173913043478,
+      "grad_norm": 0.3296414613723755,
+      "learning_rate": 0.001,
+      "loss": 1.1514,
+      "step": 19
+    },
+    {
+      "epoch": 0.21739130434782608,
+      "grad_norm": 192.71990966796875,
+      "learning_rate": 0.001,
+      "loss": 3.0997,
+      "step": 20
+    },
+    {
+      "epoch": 0.22826086956521738,
+      "grad_norm": 0.42136579751968384,
+      "learning_rate": 0.001,
+      "loss": 1.0657,
+      "step": 21
+    },
+    {
+      "epoch": 0.2391304347826087,
+      "grad_norm": 0.7099547982215881,
+      "learning_rate": 0.001,
+      "loss": 1.0948,
+      "step": 22
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 20.096664428710938,
+      "learning_rate": 0.001,
+      "loss": 1.2483,
+      "step": 23
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 1.2063277959823608,
+      "eval_runtime": 58.817,
+      "eval_samples_per_second": 29.855,
+      "eval_steps_per_second": 3.74,
+      "step": 23
+    },
+    {
+      "epoch": 0.2608695652173913,
+      "grad_norm": 189.78805541992188,
+      "learning_rate": 0.001,
+      "loss": 1.1614,
+      "step": 24
+    },
+    {
+      "epoch": 0.2717391304347826,
+      "grad_norm": 169.01876831054688,
+      "learning_rate": 0.001,
+      "loss": 2.2421,
+      "step": 25
+    },
+    {
+      "epoch": 0.2826086956521739,
+      "grad_norm": 3.0187716484069824,
+      "learning_rate": 0.001,
+      "loss": 1.1622,
+      "step": 26
+    },
+    {
+      "epoch": 0.29347826086956524,
+      "grad_norm": 0.2984677851200104,
+      "learning_rate": 0.001,
+      "loss": 1.1179,
+      "step": 27
+    },
+    {
+      "epoch": 0.30434782608695654,
+      "grad_norm": 0.3879133462905884,
+      "learning_rate": 0.001,
+      "loss": 1.0627,
+      "step": 28
+    },
+    {
+      "epoch": 0.31521739130434784,
+      "grad_norm": 0.3028254806995392,
+      "learning_rate": 0.001,
+      "loss": 1.0891,
+      "step": 29
+    },
+    {
+      "epoch": 0.32608695652173914,
+      "grad_norm": 0.22070440649986267,
+      "learning_rate": 0.001,
+      "loss": 1.034,
+      "step": 30
+    },
+    {
+      "epoch": 0.33695652173913043,
+      "grad_norm": 0.21481624245643616,
+      "learning_rate": 0.001,
+      "loss": 1.0961,
+      "step": 31
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.21487851440906525,
+      "learning_rate": 0.001,
+      "loss": 1.0287,
+      "step": 32
+    },
+    {
+      "epoch": 0.358695652173913,
+      "grad_norm": 0.23472800850868225,
+      "learning_rate": 0.001,
+      "loss": 0.9764,
+      "step": 33
+    },
+    {
+      "epoch": 0.3695652173913043,
+      "grad_norm": 0.2811538279056549,
+      "learning_rate": 0.001,
+      "loss": 1.0515,
+      "step": 34
+    },
+    {
+      "epoch": 0.3804347826086957,
+      "grad_norm": 0.505190908908844,
+      "learning_rate": 0.001,
+      "loss": 1.0424,
+      "step": 35
+    },
+    {
+      "epoch": 0.391304347826087,
+      "grad_norm": 0.42631781101226807,
+      "learning_rate": 0.001,
+      "loss": 1.0337,
+      "step": 36
+    },
+    {
+      "epoch": 0.40217391304347827,
+      "grad_norm": 1.035503625869751,
+      "learning_rate": 0.001,
+      "loss": 0.9914,
+      "step": 37
+    },
+    {
+      "epoch": 0.41304347826086957,
+      "grad_norm": 0.17122802138328552,
+      "learning_rate": 0.001,
+      "loss": 0.9921,
+      "step": 38
+    },
+    {
+      "epoch": 0.42391304347826086,
+      "grad_norm": 0.45569631457328796,
+      "learning_rate": 0.001,
+      "loss": 0.9887,
+      "step": 39
+    },
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.44947272539138794,
+      "learning_rate": 0.001,
+      "loss": 1.0364,
+      "step": 40
+    },
+    {
+      "epoch": 0.44565217391304346,
+      "grad_norm": 0.20161911845207214,
+      "learning_rate": 0.001,
+      "loss": 0.9919,
+      "step": 41
+    },
+    {
+      "epoch": 0.45652173913043476,
+      "grad_norm": 0.16475366055965424,
+      "learning_rate": 0.001,
+      "loss": 0.9565,
+      "step": 42
+    },
+    {
+      "epoch": 0.4673913043478261,
+      "grad_norm": 0.14725033938884735,
+      "learning_rate": 0.001,
+      "loss": 0.966,
+      "step": 43
+    },
+    {
+      "epoch": 0.4782608695652174,
+      "grad_norm": 0.14876875281333923,
+      "learning_rate": 0.001,
+      "loss": 0.9352,
+      "step": 44
+    },
+    {
+      "epoch": 0.4891304347826087,
+      "grad_norm": 0.17598117887973785,
+      "learning_rate": 0.001,
+      "loss": 0.9868,
+      "step": 45
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1724141240119934,
+      "learning_rate": 0.001,
+      "loss": 0.9633,
+      "step": 46
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.9434607028961182,
+      "eval_runtime": 58.8635,
+      "eval_samples_per_second": 29.832,
+      "eval_steps_per_second": 3.737,
+      "step": 46
+    },
+    {
+      "epoch": 0.5108695652173914,
+      "grad_norm": 0.16071145236492157,
+      "learning_rate": 0.001,
+      "loss": 0.8422,
+      "step": 47
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.15899214148521423,
+      "learning_rate": 0.001,
+      "loss": 0.8679,
+      "step": 48
+    },
+    {
+      "epoch": 0.532608695652174,
+      "grad_norm": 0.1507413685321808,
+      "learning_rate": 0.001,
+      "loss": 0.9633,
+      "step": 49
+    },
+    {
+      "epoch": 0.5434782608695652,
+      "grad_norm": 0.1445205807685852,
+      "learning_rate": 0.001,
+      "loss": 0.9291,
+      "step": 50
+    },
+    {
+      "epoch": 0.5543478260869565,
+      "grad_norm": 0.1479858011007309,
+      "learning_rate": 0.001,
+      "loss": 0.9272,
+      "step": 51
+    },
+    {
+      "epoch": 0.5652173913043478,
+      "grad_norm": 0.13822589814662933,
+      "learning_rate": 0.001,
+      "loss": 0.9729,
+      "step": 52
+    },
+    {
+      "epoch": 0.5760869565217391,
+      "grad_norm": 0.16067130863666534,
+      "learning_rate": 0.001,
+      "loss": 0.9124,
+      "step": 53
+    },
+    {
+      "epoch": 0.5869565217391305,
+      "grad_norm": 0.13832823932170868,
+      "learning_rate": 0.001,
+      "loss": 0.9292,
+      "step": 54
+    },
+    {
+      "epoch": 0.5978260869565217,
+      "grad_norm": 0.1415243297815323,
+      "learning_rate": 0.001,
+      "loss": 0.8777,
+      "step": 55
+    },
+    {
+      "epoch": 0.6086956521739131,
+      "grad_norm": 0.1511407047510147,
+      "learning_rate": 0.001,
+      "loss": 0.9124,
+      "step": 56
+    },
+    {
+      "epoch": 0.6195652173913043,
+      "grad_norm": 0.13163386285305023,
+      "learning_rate": 0.001,
+      "loss": 0.9266,
+      "step": 57
+    },
+    {
+      "epoch": 0.6304347826086957,
+      "grad_norm": 0.1511267125606537,
+      "learning_rate": 0.001,
+      "loss": 0.8583,
+      "step": 58
+    },
+    {
+      "epoch": 0.6413043478260869,
+      "grad_norm": 0.1495072990655899,
+      "learning_rate": 0.001,
+      "loss": 0.9624,
+      "step": 59
+    },
+    {
+      "epoch": 0.6521739130434783,
+      "grad_norm": 0.13261999189853668,
+      "learning_rate": 0.001,
+      "loss": 0.8063,
+      "step": 60
+    },
+    {
+      "epoch": 0.6630434782608695,
+      "grad_norm": 0.14297187328338623,
+      "learning_rate": 0.001,
+      "loss": 0.8697,
+      "step": 61
+    },
+    {
+      "epoch": 0.6739130434782609,
+      "grad_norm": 0.12715451419353485,
+      "learning_rate": 0.001,
+      "loss": 0.922,
+      "step": 62
+    },
+    {
+      "epoch": 0.6847826086956522,
+      "grad_norm": 0.13431622087955475,
+      "learning_rate": 0.001,
+      "loss": 0.9276,
+      "step": 63
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.1349351555109024,
+      "learning_rate": 0.001,
+      "loss": 0.8976,
+      "step": 64
+    },
+    {
+      "epoch": 0.7065217391304348,
+      "grad_norm": 0.1352081298828125,
+      "learning_rate": 0.001,
+      "loss": 0.8791,
+      "step": 65
+    },
+    {
+      "epoch": 0.717391304347826,
+      "grad_norm": 0.14080628752708435,
+      "learning_rate": 0.001,
+      "loss": 0.9413,
+      "step": 66
+    },
+    {
+      "epoch": 0.7282608695652174,
+      "grad_norm": 0.13674688339233398,
+      "learning_rate": 0.001,
+      "loss": 0.7708,
+      "step": 67
+    },
+    {
+      "epoch": 0.7391304347826086,
+      "grad_norm": 0.14996537566184998,
+      "learning_rate": 0.001,
+      "loss": 0.8691,
+      "step": 68
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.1501636952161789,
+      "learning_rate": 0.001,
+      "loss": 0.9026,
+      "step": 69
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.864105761051178,
+      "eval_runtime": 58.719,
+      "eval_samples_per_second": 29.905,
+      "eval_steps_per_second": 3.747,
+      "step": 69
+    },
+    {
+      "epoch": 0.7608695652173914,
+      "grad_norm": 0.1360858827829361,
+      "learning_rate": 0.001,
+      "loss": 0.8336,
+      "step": 70
+    },
+    {
+      "epoch": 0.7717391304347826,
+      "grad_norm": 0.1359189748764038,
+      "learning_rate": 0.001,
+      "loss": 0.8056,
+      "step": 71
+    },
+    {
+      "epoch": 0.782608695652174,
+      "grad_norm": 0.13545744121074677,
+      "learning_rate": 0.001,
+      "loss": 0.9322,
+      "step": 72
+    },
+    {
+      "epoch": 0.7934782608695652,
+      "grad_norm": 0.13769179582595825,
+      "learning_rate": 0.001,
+      "loss": 0.8573,
+      "step": 73
+    },
+    {
+      "epoch": 0.8043478260869565,
+      "grad_norm": 0.13420400023460388,
+      "learning_rate": 0.001,
+      "loss": 0.8809,
+      "step": 74
+    },
+    {
+      "epoch": 0.8152173913043478,
+      "grad_norm": 0.13306210935115814,
+      "learning_rate": 0.001,
+      "loss": 0.9157,
+      "step": 75
+    },
+    {
+      "epoch": 0.8260869565217391,
+      "grad_norm": 0.13138633966445923,
+      "learning_rate": 0.001,
+      "loss": 0.9247,
+      "step": 76
+    },
+    {
+      "epoch": 0.8369565217391305,
+      "grad_norm": 0.14224551618099213,
+      "learning_rate": 0.001,
+      "loss": 0.8511,
+      "step": 77
+    },
+    {
+      "epoch": 0.8478260869565217,
+      "grad_norm": 0.13072927296161652,
+      "learning_rate": 0.001,
+      "loss": 0.8806,
+      "step": 78
+    },
+    {
+      "epoch": 0.8586956521739131,
+      "grad_norm": 0.12070866674184799,
+      "learning_rate": 0.001,
+      "loss": 0.8334,
+      "step": 79
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.12449181079864502,
+      "learning_rate": 0.001,
+      "loss": 0.8746,
+      "step": 80
+    },
+    {
+      "epoch": 0.8804347826086957,
+      "grad_norm": 0.13722895085811615,
+      "learning_rate": 0.001,
+      "loss": 0.837,
+      "step": 81
+    },
+    {
+      "epoch": 0.8913043478260869,
+      "grad_norm": 0.128278911113739,
+      "learning_rate": 0.001,
+      "loss": 0.8383,
+      "step": 82
+    },
+    {
+      "epoch": 0.9021739130434783,
+      "grad_norm": 0.14108207821846008,
+      "learning_rate": 0.001,
+      "loss": 0.8355,
+      "step": 83
+    },
+    {
+      "epoch": 0.9130434782608695,
+      "grad_norm": 0.12417194992303848,
+      "learning_rate": 0.001,
+      "loss": 0.8296,
+      "step": 84
+    },
+    {
+      "epoch": 0.9239130434782609,
+      "grad_norm": 0.1307547390460968,
+      "learning_rate": 0.001,
+      "loss": 0.7873,
+      "step": 85
+    },
+    {
+      "epoch": 0.9347826086956522,
+      "grad_norm": 0.15271253883838654,
+      "learning_rate": 0.001,
+      "loss": 0.8745,
+      "step": 86
+    },
+    {
+      "epoch": 0.9456521739130435,
+      "grad_norm": 0.12832346558570862,
+      "learning_rate": 0.001,
+      "loss": 0.7989,
+      "step": 87
+    },
+    {
+      "epoch": 0.9565217391304348,
+      "grad_norm": 0.1639142632484436,
+      "learning_rate": 0.001,
+      "loss": 0.8138,
+      "step": 88
+    },
+    {
+      "epoch": 0.967391304347826,
+      "grad_norm": 0.17407165467739105,
+      "learning_rate": 0.001,
+      "loss": 0.8698,
+      "step": 89
+    },
+    {
+      "epoch": 0.9782608695652174,
+      "grad_norm": 0.14874844253063202,
+      "learning_rate": 0.001,
+      "loss": 0.8261,
+      "step": 90
+    },
+    {
+      "epoch": 0.9891304347826086,
+      "grad_norm": 0.1823408007621765,
+      "learning_rate": 0.001,
+      "loss": 0.8961,
+      "step": 91
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.18705643713474274,
+      "learning_rate": 0.001,
+      "loss": 0.8455,
+      "step": 92
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.8182997107505798,
+      "eval_runtime": 58.7326,
+      "eval_samples_per_second": 29.898,
+      "eval_steps_per_second": 3.746,
+      "step": 92
+    },
+    {
+      "epoch": 1.0,
+      "step": 92,
+      "total_flos": 2.3790723506425037e+17,
+      "train_loss": 1.0809093979389772,
+      "train_runtime": 1602.5337,
+      "train_samples_per_second": 7.305,
+      "train_steps_per_second": 0.057
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 92,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 23,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3790723506425037e+17,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}