feat: upload weights and biases for fine-tuned Mixtral (Win Rate: 80%)

adaption_mixtral_8x7b_instruct_marketing_tasks/README.md

@@ -0,0 +1,202 @@
+---
+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

adaption_mixtral_8x7b_instruct_marketing_tasks/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": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05000000074505806,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adaption_mixtral_8x7b_instruct_marketing_tasks/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e392d10289ac216e0cc787ef2c2d84eff88e848cd2de83352f9a95f0dc91505
+size 109086416

adaption_mixtral_8x7b_instruct_marketing_tasks/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 %}

adaption_mixtral_8x7b_instruct_marketing_tasks/config.json

@@ -0,0 +1,33 @@
+{
+  "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_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": false,
+  "vocab_size": 32000,
+  "torch_dtype": "bfloat16"
+}

adaption_mixtral_8x7b_instruct_marketing_tasks/special_tokens_map.json

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

adaption_mixtral_8x7b_instruct_marketing_tasks/tokenizer.model

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

adaption_mixtral_8x7b_instruct_marketing_tasks/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 32768,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

adaption_mixtral_8x7b_instruct_marketing_tasks/trainer_state.json

@@ -0,0 +1,536 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 13,
+  "global_step": 66,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 1.0258235931396484,
+      "learning_rate": 0.0,
+      "loss": 1.7783,
+      "step": 1
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 1.202452540397644,
+      "learning_rate": 7.5e-05,
+      "loss": 1.8301,
+      "step": 2
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 0.8090412616729736,
+      "learning_rate": 0.00015,
+      "loss": 1.6414,
+      "step": 3
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 0.4998999536037445,
+      "learning_rate": 0.00014991869329384914,
+      "loss": 1.5006,
+      "step": 4
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.16320624947547913,
+      "learning_rate": 0.0001496749690503733,
+      "loss": 1.4033,
+      "step": 5
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.1388137936592102,
+      "learning_rate": 0.0001492694144226227,
+      "loss": 1.3909,
+      "step": 6
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 0.16060611605644226,
+      "learning_rate": 0.00014870300642721805,
+      "loss": 1.4067,
+      "step": 7
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.15183641016483307,
+      "learning_rate": 0.00014797710959063172,
+      "loss": 1.3678,
+      "step": 8
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 0.13724304735660553,
+      "learning_rate": 0.00014709347266192408,
+      "loss": 1.3301,
+      "step": 9
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.07294932007789612,
+      "learning_rate": 0.00014605422439985388,
+      "loss": 1.1759,
+      "step": 10
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.07600562274456024,
+      "learning_rate": 0.00014486186844451184,
+      "loss": 1.2642,
+      "step": 11
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.06638158112764359,
+      "learning_rate": 0.00014351927728583242,
+      "loss": 1.2833,
+      "step": 12
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 0.08298511058092117,
+      "learning_rate": 0.00014202968534351396,
+      "loss": 1.2899,
+      "step": 13
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.08382251113653183,
+      "learning_rate": 0.00014039668117501837,
+      "loss": 1.2686,
+      "step": 14
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "eval_loss": 1.228515625,
+      "eval_runtime": 2.1791,
+      "eval_samples_per_second": 2.294,
+      "eval_steps_per_second": 0.459,
+      "step": 14
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.08143270760774612,
+      "learning_rate": 0.0001386241988304218,
+      "loss": 1.2703,
+      "step": 15
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.08548818528652191,
+      "learning_rate": 0.0001367165083749435,
+      "loss": 1.2547,
+      "step": 16
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 0.09365896135568619,
+      "learning_rate": 0.00013467820560198474,
+      "loss": 1.2056,
+      "step": 17
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.09182783216238022,
+      "learning_rate": 0.00013251420096145974,
+      "loss": 1.1533,
+      "step": 18
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 0.06191667914390564,
+      "learning_rate": 0.00013022970773009194,
+      "loss": 1.2125,
+      "step": 19
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.0696016401052475,
+      "learning_rate": 0.00012783022945217373,
+      "loss": 1.2048,
+      "step": 20
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 0.05720340460538864,
+      "learning_rate": 0.00012532154668104607,
+      "loss": 1.2362,
+      "step": 21
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0652061328291893,
+      "learning_rate": 0.00012270970305323925,
+      "loss": 1.2246,
+      "step": 22
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 0.0560685396194458,
+      "learning_rate": 0.00012000099072882315,
+      "loss": 1.1885,
+      "step": 23
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.052994053810834885,
+      "learning_rate": 0.00011720193523304244,
+      "loss": 1.1813,
+      "step": 24
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.05800238996744156,
+      "learning_rate": 0.00011431927973575484,
+      "loss": 1.212,
+      "step": 25
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.0640348345041275,
+      "learning_rate": 0.00011135996880654404,
+      "loss": 1.2127,
+      "step": 26
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 0.05417352542281151,
+      "learning_rate": 0.00010833113168464354,
+      "loss": 1.2063,
+      "step": 27
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "eval_loss": 1.170654296875,
+      "eval_runtime": 2.1739,
+      "eval_samples_per_second": 2.3,
+      "eval_steps_per_second": 0.46,
+      "step": 27
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.05252690985798836,
+      "learning_rate": 0.00010524006510397484,
+      "loss": 1.1968,
+      "step": 28
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 0.04840606823563576,
+      "learning_rate": 0.00010209421571467619,
+      "loss": 1.215,
+      "step": 29
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.047674886882305145,
+      "learning_rate": 9.890116214347032e-05,
+      "loss": 1.1918,
+      "step": 30
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 0.0701334998011589,
+      "learning_rate": 9.566859673608866e-05,
+      "loss": 1.1545,
+      "step": 31
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.04426707699894905,
+      "learning_rate": 9.24043070257369e-05,
+      "loss": 1.0649,
+      "step": 32
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.05895956605672836,
+      "learning_rate": 8.911615697224536e-05,
+      "loss": 1.1316,
+      "step": 33
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.04725153371691704,
+      "learning_rate": 8.581206801710071e-05,
+      "loss": 1.1628,
+      "step": 34
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.04187237471342087,
+      "learning_rate": 8.25e-05,
+      "loss": 1.1827,
+      "step": 35
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.043725937604904175,
+      "learning_rate": 7.918793198289929e-05,
+      "loss": 1.1655,
+      "step": 36
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 0.05090896040201187,
+      "learning_rate": 7.588384302775465e-05,
+      "loss": 1.1709,
+      "step": 37
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.045376256108284,
+      "learning_rate": 7.259569297426307e-05,
+      "loss": 1.1649,
+      "step": 38
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 0.06016011908650398,
+      "learning_rate": 6.933140326391134e-05,
+      "loss": 1.1117,
+      "step": 39
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 0.05998160317540169,
+      "learning_rate": 6.609883785652968e-05,
+      "loss": 1.0663,
+      "step": 40
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "eval_loss": 1.13623046875,
+      "eval_runtime": 2.1725,
+      "eval_samples_per_second": 2.301,
+      "eval_steps_per_second": 0.46,
+      "step": 40
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 0.05060423165559769,
+      "learning_rate": 6.29057842853238e-05,
+      "loss": 1.1395,
+      "step": 41
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.05058607459068298,
+      "learning_rate": 5.9759934896025146e-05,
+      "loss": 1.1261,
+      "step": 42
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 0.04361967369914055,
+      "learning_rate": 5.666886831535644e-05,
+      "loss": 1.1704,
+      "step": 43
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.05158119276165962,
+      "learning_rate": 5.364003119345597e-05,
+      "loss": 1.1434,
+      "step": 44
+    },
+    {
+      "epoch": 2.0454545454545454,
+      "grad_norm": 0.048779308795928955,
+      "learning_rate": 5.0680720264245154e-05,
+      "loss": 1.1225,
+      "step": 45
+    },
+    {
+      "epoch": 2.090909090909091,
+      "grad_norm": 0.049742817878723145,
+      "learning_rate": 4.7798064766957536e-05,
+      "loss": 1.1177,
+      "step": 46
+    },
+    {
+      "epoch": 2.1363636363636362,
+      "grad_norm": 0.04239320382475853,
+      "learning_rate": 4.4999009271176865e-05,
+      "loss": 1.1578,
+      "step": 47
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 0.04660114645957947,
+      "learning_rate": 4.229029694676075e-05,
+      "loss": 1.1572,
+      "step": 48
+    },
+    {
+      "epoch": 2.227272727272727,
+      "grad_norm": 0.042004574090242386,
+      "learning_rate": 3.967845331895394e-05,
+      "loss": 1.1531,
+      "step": 49
+    },
+    {
+      "epoch": 2.2727272727272725,
+      "grad_norm": 0.04568534344434738,
+      "learning_rate": 3.716977054782625e-05,
+      "loss": 1.1451,
+      "step": 50
+    },
+    {
+      "epoch": 2.3181818181818183,
+      "grad_norm": 0.046037498861551285,
+      "learning_rate": 3.4770292269908044e-05,
+      "loss": 1.1727,
+      "step": 51
+    },
+    {
+      "epoch": 2.3636363636363638,
+      "grad_norm": 0.04487365856766701,
+      "learning_rate": 3.2485799038540274e-05,
+      "loss": 1.1504,
+      "step": 52
+    },
+    {
+      "epoch": 2.409090909090909,
+      "grad_norm": 0.06776122003793716,
+      "learning_rate": 3.032179439801525e-05,
+      "loss": 1.0966,
+      "step": 53
+    },
+    {
+      "epoch": 2.409090909090909,
+      "eval_loss": 1.125,
+      "eval_runtime": 2.1711,
+      "eval_samples_per_second": 2.303,
+      "eval_steps_per_second": 0.461,
+      "step": 53
+    },
+    {
+      "epoch": 2.4545454545454546,
+      "grad_norm": 0.040834926068782806,
+      "learning_rate": 2.8283491625056474e-05,
+      "loss": 1.0332,
+      "step": 54
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.059045545756816864,
+      "learning_rate": 2.6375801169578187e-05,
+      "loss": 1.0847,
+      "step": 55
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.046077560633420944,
+      "learning_rate": 2.460331882498164e-05,
+      "loss": 1.1277,
+      "step": 56
+    },
+    {
+      "epoch": 2.590909090909091,
+      "grad_norm": 0.03946666419506073,
+      "learning_rate": 2.2970314656486043e-05,
+      "loss": 1.149,
+      "step": 57
+    },
+    {
+      "epoch": 2.6363636363636362,
+      "grad_norm": 0.04094894975423813,
+      "learning_rate": 2.1480722714167575e-05,
+      "loss": 1.1356,
+      "step": 58
+    },
+    {
+      "epoch": 2.6818181818181817,
+      "grad_norm": 0.04413091018795967,
+      "learning_rate": 2.0138131555488145e-05,
+      "loss": 1.1443,
+      "step": 59
+    },
+    {
+      "epoch": 2.7272727272727275,
+      "grad_norm": 0.04297490417957306,
+      "learning_rate": 1.89457756001461e-05,
+      "loss": 1.1403,
+      "step": 60
+    },
+    {
+      "epoch": 2.7727272727272725,
+      "grad_norm": 0.05426976457238197,
+      "learning_rate": 1.7906527338075904e-05,
+      "loss": 1.0807,
+      "step": 61
+    },
+    {
+      "epoch": 2.8181818181818183,
+      "grad_norm": 0.05803615599870682,
+      "learning_rate": 1.702289040936828e-05,
+      "loss": 1.037,
+      "step": 62
+    },
+    {
+      "epoch": 2.8636363636363638,
+      "grad_norm": 0.041255880147218704,
+      "learning_rate": 1.6296993572781945e-05,
+      "loss": 1.1188,
+      "step": 63
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": 0.05099846050143242,
+      "learning_rate": 1.573058557737728e-05,
+      "loss": 1.1008,
+      "step": 64
+    },
+    {
+      "epoch": 2.9545454545454546,
+      "grad_norm": 0.03938554227352142,
+      "learning_rate": 1.5325030949626715e-05,
+      "loss": 1.1512,
+      "step": 65
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.04949432983994484,
+      "learning_rate": 1.5081306706150862e-05,
+      "loss": 1.1215,
+      "step": 66
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.1177978515625,
+      "eval_runtime": 2.1575,
+      "eval_samples_per_second": 2.317,
+      "eval_steps_per_second": 0.463,
+      "step": 66
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 66,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 2.5242364182685286e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}