Upload 9 files

README.md

@@ -1,3 +1,202 @@
 ---
-license: apache-2.0
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+library_name: peft
 ---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.1

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": [],
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "q_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fc2b429bf7dd277d8baadbdbd24755c8589934c559337d65ab72b83048ce621
+size 218138576

chat_template.jinja

@@ -0,0 +1,24 @@
+{%- if messages[0]['role'] == 'system' %}
+    {%- set system_message = messages[0]['content'] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}
+        {{- raise_exception('After the optional system message, conversation roles must alternate user/assistant/user/assistant/...') }}
+    {%- endif %}
+    {%- if message['role'] == 'user' %}
+        {%- if loop.first and system_message is defined %}
+            {{- ' [INST] ' + system_message + '\n\n' + message['content'] + ' [/INST]' }}
+        {%- else %}
+            {{- ' [INST] ' + message['content'] + ' [/INST]' }}
+        {%- endif %}
+    {%- elif message['role'] == 'assistant' %}
+        {{- ' ' + message['content'] + eos_token}}
+    {%- else %}
+        {{- raise_exception('Only user and assistant roles are supported, with the exception of an initial optional system message!') }}
+    {%- endif %}
+{%- endfor %}

config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": null,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.10.1",
+  "use_cache": false,
+  "vocab_size": 32000,
+  "torch_dtype": "bfloat16"
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "add_prefix_space": null,
+  "additional_special_tokens": [],
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": true,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,746 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 19,
+  "global_step": 96,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.041666666666666664,
+      "grad_norm": 0.8793060183525085,
+      "learning_rate": 0.0,
+      "loss": 1.1922607421875,
+      "step": 1
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 0.9236243367195129,
+      "learning_rate": 0.0001,
+      "loss": 1.1376953125,
+      "step": 2
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 0.2843455970287323,
+      "learning_rate": 9.997539658034168e-05,
+      "loss": 0.7738800048828125,
+      "step": 3
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.26448318362236023,
+      "learning_rate": 9.990161322484486e-05,
+      "loss": 0.9853973388671875,
+      "step": 4
+    },
+    {
+      "epoch": 0.20833333333333334,
+      "grad_norm": 0.11444772034883499,
+      "learning_rate": 9.977873061452552e-05,
+      "loss": 0.9564609527587891,
+      "step": 5
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.147213876247406,
+      "learning_rate": 9.96068831197139e-05,
+      "loss": 0.93408203125,
+      "step": 6
+    },
+    {
+      "epoch": 0.2916666666666667,
+      "grad_norm": 0.1659262478351593,
+      "learning_rate": 9.938625865312251e-05,
+      "loss": 0.9327259063720703,
+      "step": 7
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.14943991601467133,
+      "learning_rate": 9.911709846436641e-05,
+      "loss": 1.0107307434082031,
+      "step": 8
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 0.10237906128168106,
+      "learning_rate": 9.879969687616027e-05,
+      "loss": 0.9565887451171875,
+      "step": 9
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.08303987234830856,
+      "learning_rate": 9.84344009624807e-05,
+      "loss": 0.8689174652099609,
+      "step": 10
+    },
+    {
+      "epoch": 0.4583333333333333,
+      "grad_norm": 0.06906509399414062,
+      "learning_rate": 9.80216101690461e-05,
+      "loss": 0.8139371871948242,
+      "step": 11
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.0893741250038147,
+      "learning_rate": 9.756177587652856e-05,
+      "loss": 0.9046802520751953,
+      "step": 12
+    },
+    {
+      "epoch": 0.5416666666666666,
+      "grad_norm": 0.0950048640370369,
+      "learning_rate": 9.705540090697575e-05,
+      "loss": 0.9661464691162109,
+      "step": 13
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.09773612767457962,
+      "learning_rate": 9.650303897398232e-05,
+      "loss": 0.9238529205322266,
+      "step": 14
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.07399343699216843,
+      "learning_rate": 9.590529407721231e-05,
+      "loss": 0.9286479949951172,
+      "step": 15
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.08683284372091293,
+      "learning_rate": 9.526281984193436e-05,
+      "loss": 0.8059654235839844,
+      "step": 16
+    },
+    {
+      "epoch": 0.7083333333333334,
+      "grad_norm": 0.08106762170791626,
+      "learning_rate": 9.4576318804292e-05,
+      "loss": 0.8695812225341797,
+      "step": 17
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.07135742902755737,
+      "learning_rate": 9.384654164309083e-05,
+      "loss": 0.8596839904785156,
+      "step": 18
+    },
+    {
+      "epoch": 0.7916666666666666,
+      "grad_norm": 0.07224518060684204,
+      "learning_rate": 9.30742863589421e-05,
+      "loss": 0.8866386413574219,
+      "step": 19
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.049965087324380875,
+      "learning_rate": 9.226039740166091e-05,
+      "loss": 0.8490200042724609,
+      "step": 20
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "eval_loss": 0.70703125,
+      "eval_runtime": 2.2447,
+      "eval_samples_per_second": 2.228,
+      "eval_steps_per_second": 0.446,
+      "step": 20
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.08873027563095093,
+      "learning_rate": 9.140576474687264e-05,
+      "loss": 0.7799034118652344,
+      "step": 21
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.06065167486667633,
+      "learning_rate": 9.051132292283771e-05,
+      "loss": 0.8547039031982422,
+      "step": 22
+    },
+    {
+      "epoch": 0.9583333333333334,
+      "grad_norm": 0.07170149683952332,
+      "learning_rate": 8.957804998855866e-05,
+      "loss": 0.9889545440673828,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.06963331997394562,
+      "learning_rate": 8.860696646428693e-05,
+      "loss": 0.8532295227050781,
+      "step": 24
+    },
+    {
+      "epoch": 1.0416666666666667,
+      "grad_norm": 0.06944938749074936,
+      "learning_rate": 8.759913421559902e-05,
+      "loss": 0.8123455047607422,
+      "step": 25
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.05863318592309952,
+      "learning_rate": 8.655565529226198e-05,
+      "loss": 0.7635040283203125,
+      "step": 26
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.04687070474028587,
+      "learning_rate": 8.547767072315835e-05,
+      "loss": 0.626739501953125,
+      "step": 27
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.09054134786128998,
+      "learning_rate": 8.436635926858759e-05,
+      "loss": 0.8233604431152344,
+      "step": 28
+    },
+    {
+      "epoch": 1.2083333333333333,
+      "grad_norm": 0.052699826657772064,
+      "learning_rate": 8.322293613130917e-05,
+      "loss": 0.8357448577880859,
+      "step": 29
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.047030121088027954,
+      "learning_rate": 8.204865162773613e-05,
+      "loss": 0.81787109375,
+      "step": 30
+    },
+    {
+      "epoch": 1.2916666666666667,
+      "grad_norm": 0.052900541573762894,
+      "learning_rate": 8.084478982073247e-05,
+      "loss": 0.8191127777099609,
+      "step": 31
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.06003842130303383,
+      "learning_rate": 7.961266711550922e-05,
+      "loss": 0.8995933532714844,
+      "step": 32
+    },
+    {
+      "epoch": 1.375,
+      "grad_norm": 0.059103600680828094,
+      "learning_rate": 7.835363082015468e-05,
+      "loss": 0.8704128265380859,
+      "step": 33
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.058741144835948944,
+      "learning_rate": 7.706905767237288e-05,
+      "loss": 0.800018310546875,
+      "step": 34
+    },
+    {
+      "epoch": 1.4583333333333333,
+      "grad_norm": 0.0494692288339138,
+      "learning_rate": 7.576035233404096e-05,
+      "loss": 0.7496585845947266,
+      "step": 35
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.07651121914386749,
+      "learning_rate": 7.442894585523218e-05,
+      "loss": 0.8236103057861328,
+      "step": 36
+    },
+    {
+      "epoch": 1.5416666666666665,
+      "grad_norm": 0.07268194854259491,
+      "learning_rate": 7.307629410938363e-05,
+      "loss": 0.8843345642089844,
+      "step": 37
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.06088404729962349,
+      "learning_rate": 7.170387620131993e-05,
+      "loss": 0.8448820114135742,
+      "step": 38
+    },
+    {
+      "epoch": 1.625,
+      "grad_norm": 0.04881656914949417,
+      "learning_rate": 7.031319284987394e-05,
+      "loss": 0.8646316528320312,
+      "step": 39
+    },
+    {
+      "epoch": 1.625,
+      "eval_loss": 0.677978515625,
+      "eval_runtime": 2.2474,
+      "eval_samples_per_second": 2.225,
+      "eval_steps_per_second": 0.445,
+      "step": 39
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.06063127890229225,
+      "learning_rate": 6.890576474687263e-05,
+      "loss": 0.7459278106689453,
+      "step": 40
+    },
+    {
+      "epoch": 1.7083333333333335,
+      "grad_norm": 0.06719189882278442,
+      "learning_rate": 6.7483130894283e-05,
+      "loss": 0.8032417297363281,
+      "step": 41
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.05449753254652023,
+      "learning_rate": 6.604684692133597e-05,
+      "loss": 0.8038978576660156,
+      "step": 42
+    },
+    {
+      "epoch": 1.7916666666666665,
+      "grad_norm": 0.06328374147415161,
+      "learning_rate": 6.459848338346861e-05,
+      "loss": 0.8226470947265625,
+      "step": 43
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.04831730201840401,
+      "learning_rate": 6.313962404494496e-05,
+      "loss": 0.8016071319580078,
+      "step": 44
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 0.0738108828663826,
+      "learning_rate": 6.167186414703289e-05,
+      "loss": 0.7264728546142578,
+      "step": 45
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.05554795265197754,
+      "learning_rate": 6.019680866363139e-05,
+      "loss": 0.8036289215087891,
+      "step": 46
+    },
+    {
+      "epoch": 1.9583333333333335,
+      "grad_norm": 0.06595105677843094,
+      "learning_rate": 5.8716070546254966e-05,
+      "loss": 0.9345455169677734,
+      "step": 47
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.06640685349702835,
+      "learning_rate": 5.7231268960295e-05,
+      "loss": 0.795257568359375,
+      "step": 48
+    },
+    {
+      "epoch": 2.0416666666666665,
+      "grad_norm": 0.06418655812740326,
+      "learning_rate": 5.574402751448614e-05,
+      "loss": 0.7591991424560547,
+      "step": 49
+    },
+    {
+      "epoch": 2.0833333333333335,
+      "grad_norm": 0.06147291138768196,
+      "learning_rate": 5.425597248551387e-05,
+      "loss": 0.7209262847900391,
+      "step": 50
+    },
+    {
+      "epoch": 2.125,
+      "grad_norm": 0.04414745047688484,
+      "learning_rate": 5.2768731039705e-05,
+      "loss": 0.5957622528076172,
+      "step": 51
+    },
+    {
+      "epoch": 2.1666666666666665,
+      "grad_norm": 0.07838333398103714,
+      "learning_rate": 5.128392945374505e-05,
+      "loss": 0.765411376953125,
+      "step": 52
+    },
+    {
+      "epoch": 2.2083333333333335,
+      "grad_norm": 0.05295613780617714,
+      "learning_rate": 4.980319133636863e-05,
+      "loss": 0.8023247718811035,
+      "step": 53
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.0547562837600708,
+      "learning_rate": 4.83281358529671e-05,
+      "loss": 0.789794921875,
+      "step": 54
+    },
+    {
+      "epoch": 2.2916666666666665,
+      "grad_norm": 0.0593954473733902,
+      "learning_rate": 4.686037595505507e-05,
+      "loss": 0.7842569351196289,
+      "step": 55
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 0.06293150037527084,
+      "learning_rate": 4.54015166165314e-05,
+      "loss": 0.8622207641601562,
+      "step": 56
+    },
+    {
+      "epoch": 2.375,
+      "grad_norm": 0.06123076751828194,
+      "learning_rate": 4.395315307866405e-05,
+      "loss": 0.8332023620605469,
+      "step": 57
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "grad_norm": 0.05895160138607025,
+      "learning_rate": 4.2516869105717004e-05,
+      "loss": 0.7705469131469727,
+      "step": 58
+    },
+    {
+      "epoch": 2.4166666666666665,
+      "eval_loss": 0.669921875,
+      "eval_runtime": 2.2514,
+      "eval_samples_per_second": 2.221,
+      "eval_steps_per_second": 0.444,
+      "step": 58
+    },
+    {
+      "epoch": 2.4583333333333335,
+      "grad_norm": 0.051167454570531845,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.7212095260620117,
+      "step": 59
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.08035021275281906,
+      "learning_rate": 3.968680715012606e-05,
+      "loss": 0.7839260101318359,
+      "step": 60
+    },
+    {
+      "epoch": 2.5416666666666665,
+      "grad_norm": 0.07387541979551315,
+      "learning_rate": 3.829612379868006e-05,
+      "loss": 0.8469581604003906,
+      "step": 61
+    },
+    {
+      "epoch": 2.5833333333333335,
+      "grad_norm": 0.06478056311607361,
+      "learning_rate": 3.692370589061639e-05,
+      "loss": 0.8108558654785156,
+      "step": 62
+    },
+    {
+      "epoch": 2.625,
+      "grad_norm": 0.054633643478155136,
+      "learning_rate": 3.557105414476782e-05,
+      "loss": 0.841090202331543,
+      "step": 63
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.06919875741004944,
+      "learning_rate": 3.423964766595906e-05,
+      "loss": 0.7162876129150391,
+      "step": 64
+    },
+    {
+      "epoch": 2.7083333333333335,
+      "grad_norm": 0.06721208989620209,
+      "learning_rate": 3.293094232762715e-05,
+      "loss": 0.7694759368896484,
+      "step": 65
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.0583014115691185,
+      "learning_rate": 3.164636917984534e-05,
+      "loss": 0.7788715362548828,
+      "step": 66
+    },
+    {
+      "epoch": 2.7916666666666665,
+      "grad_norm": 0.06786876916885376,
+      "learning_rate": 3.0387332884490805e-05,
+      "loss": 0.7926368713378906,
+      "step": 67
+    },
+    {
+      "epoch": 2.8333333333333335,
+      "grad_norm": 0.0554044283926487,
+      "learning_rate": 2.9155210179267546e-05,
+      "loss": 0.7786502838134766,
+      "step": 68
+    },
+    {
+      "epoch": 2.875,
+      "grad_norm": 0.08045743405818939,
+      "learning_rate": 2.7951348372263875e-05,
+      "loss": 0.6959114074707031,
+      "step": 69
+    },
+    {
+      "epoch": 2.9166666666666665,
+      "grad_norm": 0.06203767657279968,
+      "learning_rate": 2.677706386869083e-05,
+      "loss": 0.7776670455932617,
+      "step": 70
+    },
+    {
+      "epoch": 2.9583333333333335,
+      "grad_norm": 0.07093246281147003,
+      "learning_rate": 2.5633640731412412e-05,
+      "loss": 0.9026947021484375,
+      "step": 71
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.07025361061096191,
+      "learning_rate": 2.4522329276841663e-05,
+      "loss": 0.7677774429321289,
+      "step": 72
+    },
+    {
+      "epoch": 3.0416666666666665,
+      "grad_norm": 0.0708354264497757,
+      "learning_rate": 2.3444344707738015e-05,
+      "loss": 0.7287693023681641,
+      "step": 73
+    },
+    {
+      "epoch": 3.0833333333333335,
+      "grad_norm": 0.06829249858856201,
+      "learning_rate": 2.2400865784401e-05,
+      "loss": 0.6977443695068359,
+      "step": 74
+    },
+    {
+      "epoch": 3.125,
+      "grad_norm": 0.04968668892979622,
+      "learning_rate": 2.1393033535713093e-05,
+      "loss": 0.5820121765136719,
+      "step": 75
+    },
+    {
+      "epoch": 3.1666666666666665,
+      "grad_norm": 0.08538515865802765,
+      "learning_rate": 2.0421950011441354e-05,
+      "loss": 0.7337074279785156,
+      "step": 76
+    },
+    {
+      "epoch": 3.2083333333333335,
+      "grad_norm": 0.057816021144390106,
+      "learning_rate": 1.9488677077162295e-05,
+      "loss": 0.7847037315368652,
+      "step": 77
+    },
+    {
+      "epoch": 3.2083333333333335,
+      "eval_loss": 0.666259765625,
+      "eval_runtime": 2.2514,
+      "eval_samples_per_second": 2.221,
+      "eval_steps_per_second": 0.444,
+      "step": 77
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.05465561896562576,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.7744140625,
+      "step": 78
+    },
+    {
+      "epoch": 3.2916666666666665,
+      "grad_norm": 0.06246788054704666,
+      "learning_rate": 1.77396025983391e-05,
+      "loss": 0.7656393051147461,
+      "step": 79
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.06507856398820877,
+      "learning_rate": 1.6925713641057904e-05,
+      "loss": 0.8431224822998047,
+      "step": 80
+    },
+    {
+      "epoch": 3.375,
+      "grad_norm": 0.06495018303394318,
+      "learning_rate": 1.6153458356909176e-05,
+      "loss": 0.8185300827026367,
+      "step": 81
+    },
+    {
+      "epoch": 3.4166666666666665,
+      "grad_norm": 0.06756020337343216,
+      "learning_rate": 1.5423681195707997e-05,
+      "loss": 0.7545089721679688,
+      "step": 82
+    },
+    {
+      "epoch": 3.4583333333333335,
+      "grad_norm": 0.05611558258533478,
+      "learning_rate": 1.4737180158065644e-05,
+      "loss": 0.7109222412109375,
+      "step": 83
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.08344320207834244,
+      "learning_rate": 1.4094705922787687e-05,
+      "loss": 0.7583560943603516,
+      "step": 84
+    },
+    {
+      "epoch": 3.5416666666666665,
+      "grad_norm": 0.06930051743984222,
+      "learning_rate": 1.3496961026017687e-05,
+      "loss": 0.8253993988037109,
+      "step": 85
+    },
+    {
+      "epoch": 3.5833333333333335,
+      "grad_norm": 0.06819939613342285,
+      "learning_rate": 1.2944599093024267e-05,
+      "loss": 0.7947092056274414,
+      "step": 86
+    },
+    {
+      "epoch": 3.625,
+      "grad_norm": 0.05748283118009567,
+      "learning_rate": 1.2438224123471442e-05,
+      "loss": 0.8298521041870117,
+      "step": 87
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 0.06575058400630951,
+      "learning_rate": 1.1978389830953907e-05,
+      "loss": 0.7025308609008789,
+      "step": 88
+    },
+    {
+      "epoch": 3.7083333333333335,
+      "grad_norm": 0.06751663237810135,
+      "learning_rate": 1.1565599037519316e-05,
+      "loss": 0.7523231506347656,
+      "step": 89
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.05522964894771576,
+      "learning_rate": 1.1200303123839742e-05,
+      "loss": 0.7666292190551758,
+      "step": 90
+    },
+    {
+      "epoch": 3.7916666666666665,
+      "grad_norm": 0.06846830993890762,
+      "learning_rate": 1.088290153563358e-05,
+      "loss": 0.7798595428466797,
+      "step": 91
+    },
+    {
+      "epoch": 3.8333333333333335,
+      "grad_norm": 0.050051383674144745,
+      "learning_rate": 1.0613741346877497e-05,
+      "loss": 0.7688732147216797,
+      "step": 92
+    },
+    {
+      "epoch": 3.875,
+      "grad_norm": 0.0775798112154007,
+      "learning_rate": 1.0393116880286118e-05,
+      "loss": 0.6811847686767578,
+      "step": 93
+    },
+    {
+      "epoch": 3.9166666666666665,
+      "grad_norm": 0.0615241639316082,
+      "learning_rate": 1.0221269385474488e-05,
+      "loss": 0.7659130096435547,
+      "step": 94
+    },
+    {
+      "epoch": 3.9583333333333335,
+      "grad_norm": 0.07225687056779861,
+      "learning_rate": 1.0098386775155147e-05,
+      "loss": 0.8869800567626953,
+      "step": 95
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.06342313438653946,
+      "learning_rate": 1.0024603419658329e-05,
+      "loss": 0.7511405944824219,
+      "step": 96
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.662353515625,
+      "eval_runtime": 2.227,
+      "eval_samples_per_second": 2.245,
+      "eval_steps_per_second": 0.449,
+      "step": 96
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.592497924128375e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}