Upload 11 files

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
+---
+
+# 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 0.7.1

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mixtral-8x7B-Instruct-v0.1",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "down_proj",
+    "lm_head"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a615c34e23f694404a750aa27e64ae97a32055fc83605fb6e4a94ca3161e2f1
+size 751667752

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97e4379ad527346b08ba42132caba60161363800817204fb1677d4572592ee36
+size 454906234

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67697869eaf801839d6c56696131da5986d585bfc6e2ad7bebbbd2e858251b86
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3de361f37e2aedf3669e225c5f654e335456a6d598588cfaaeffd6f734fda5a
+size 1064

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
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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>",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,553 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 10,
+  "global_step": 389,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 2.4501470088205292e-05,
+      "loss": 1.0383,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.9290542602539062,
+      "eval_runtime": 77.6515,
+      "eval_samples_per_second": 0.245,
+      "eval_steps_per_second": 0.039,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 2.4001440086405184e-05,
+      "loss": 0.9448,
+      "step": 20
+    },
+    {
+      "epoch": 0.05,
+      "eval_loss": 0.9216130971908569,
+      "eval_runtime": 75.2278,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.04,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 2.350141008460508e-05,
+      "loss": 0.942,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "eval_loss": 0.9170966148376465,
+      "eval_runtime": 75.2167,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.04,
+      "step": 30
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 2.300138008280497e-05,
+      "loss": 0.9305,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.9177520871162415,
+      "eval_runtime": 75.2861,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 40
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 2.250135008100486e-05,
+      "loss": 0.9301,
+      "step": 50
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.9236036539077759,
+      "eval_runtime": 75.3569,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 50
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 2.200132007920475e-05,
+      "loss": 0.9412,
+      "step": 60
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 0.9281936287879944,
+      "eval_runtime": 75.2776,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 60
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 2.1501290077404645e-05,
+      "loss": 0.9534,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 0.931694507598877,
+      "eval_runtime": 75.4284,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 70
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 2.1001260075604537e-05,
+      "loss": 1.0193,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "eval_loss": 0.9383592009544373,
+      "eval_runtime": 75.2446,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.04,
+      "step": 80
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 2.050123007380443e-05,
+      "loss": 0.979,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.9449018239974976,
+      "eval_runtime": 75.2111,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.04,
+      "step": 90
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 2.000120007200432e-05,
+      "loss": 1.0321,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.9472957253456116,
+      "eval_runtime": 75.1836,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.04,
+      "step": 100
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.9501170070204212e-05,
+      "loss": 0.997,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "eval_loss": 0.9475318789482117,
+      "eval_runtime": 75.3079,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 110
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.9001140068404107e-05,
+      "loss": 0.9737,
+      "step": 120
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.9536099433898926,
+      "eval_runtime": 75.3453,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 120
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.8501110066603995e-05,
+      "loss": 1.0492,
+      "step": 130
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 0.9576209187507629,
+      "eval_runtime": 75.2609,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 130
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.8001080064803887e-05,
+      "loss": 0.9903,
+      "step": 140
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.9594760537147522,
+      "eval_runtime": 75.3588,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 140
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.750105006300378e-05,
+      "loss": 1.0525,
+      "step": 150
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 0.9673194885253906,
+      "eval_runtime": 75.2799,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 150
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.700102006120367e-05,
+      "loss": 0.9806,
+      "step": 160
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 0.9813961386680603,
+      "eval_runtime": 75.2782,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 160
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.6500990059403565e-05,
+      "loss": 1.0374,
+      "step": 170
+    },
+    {
+      "epoch": 0.44,
+      "eval_loss": 0.9768068194389343,
+      "eval_runtime": 75.2881,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 170
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.6000960057603457e-05,
+      "loss": 0.9967,
+      "step": 180
+    },
+    {
+      "epoch": 0.46,
+      "eval_loss": 0.991325855255127,
+      "eval_runtime": 75.311,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 180
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.550093005580335e-05,
+      "loss": 1.047,
+      "step": 190
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 1.0070654153823853,
+      "eval_runtime": 75.2469,
+      "eval_samples_per_second": 0.253,
+      "eval_steps_per_second": 0.04,
+      "step": 190
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 1.5000900054003238e-05,
+      "loss": 1.0366,
+      "step": 200
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 1.0217609405517578,
+      "eval_runtime": 75.3156,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 200
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 1.4500870052203133e-05,
+      "loss": 0.9782,
+      "step": 210
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 1.0349949598312378,
+      "eval_runtime": 75.3478,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 210
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 1.4000840050403025e-05,
+      "loss": 1.1381,
+      "step": 220
+    },
+    {
+      "epoch": 0.57,
+      "eval_loss": 1.05660080909729,
+      "eval_runtime": 75.403,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 220
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.3500810048602917e-05,
+      "loss": 1.1266,
+      "step": 230
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.0543776750564575,
+      "eval_runtime": 75.3395,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 230
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.3000780046802807e-05,
+      "loss": 1.1131,
+      "step": 240
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 1.0707024335861206,
+      "eval_runtime": 75.2946,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 240
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.2500750045002698e-05,
+      "loss": 1.0625,
+      "step": 250
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 1.0837984085083008,
+      "eval_runtime": 75.3303,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 250
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.2000720043202592e-05,
+      "loss": 1.0762,
+      "step": 260
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.0885578393936157,
+      "eval_runtime": 75.2812,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 260
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.1500690041402485e-05,
+      "loss": 1.1995,
+      "step": 270
+    },
+    {
+      "epoch": 0.69,
+      "eval_loss": 1.1089729070663452,
+      "eval_runtime": 75.3209,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 270
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.1000660039602375e-05,
+      "loss": 1.115,
+      "step": 280
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 1.1146286725997925,
+      "eval_runtime": 75.3791,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 280
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.0500630037802268e-05,
+      "loss": 0.9881,
+      "step": 290
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 1.1138123273849487,
+      "eval_runtime": 75.3832,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 290
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.000060003600216e-05,
+      "loss": 1.2121,
+      "step": 300
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 1.1398226022720337,
+      "eval_runtime": 75.307,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 300
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 9.500570034202053e-06,
+      "loss": 1.1354,
+      "step": 310
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 1.1480103731155396,
+      "eval_runtime": 75.3962,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 310
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.000540032401943e-06,
+      "loss": 1.1815,
+      "step": 320
+    },
+    {
+      "epoch": 0.82,
+      "eval_loss": 1.1434487104415894,
+      "eval_runtime": 75.3053,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 320
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 8.500510030601835e-06,
+      "loss": 1.3204,
+      "step": 330
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 1.142481803894043,
+      "eval_runtime": 75.2776,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 330
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.000480028801728e-06,
+      "loss": 1.2111,
+      "step": 340
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 1.1574183702468872,
+      "eval_runtime": 75.3414,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 340
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.500450027001619e-06,
+      "loss": 1.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 1.1606627702713013,
+      "eval_runtime": 75.3801,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 350
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 7.0004200252015126e-06,
+      "loss": 1.2455,
+      "step": 360
+    },
+    {
+      "epoch": 0.93,
+      "eval_loss": 1.1685103178024292,
+      "eval_runtime": 75.2747,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 360
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 6.500390023401403e-06,
+      "loss": 1.2436,
+      "step": 370
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.179547667503357,
+      "eval_runtime": 75.3915,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 370
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 6.000360021601296e-06,
+      "loss": 1.2619,
+      "step": 380
+    },
+    {
+      "epoch": 0.98,
+      "eval_loss": 1.1883246898651123,
+      "eval_runtime": 75.3375,
+      "eval_samples_per_second": 0.252,
+      "eval_steps_per_second": 0.04,
+      "step": 380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 3.9179178565632e+18,
+  "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 sha256:1c496ea01c1fd98e40d1c2d4c2bbda1e68925a92d869ade1c1729e4f875f03bb
+size 4664