Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: google/gemma-2b-it
+---
+
+# 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 0.8.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b-it",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f77d629c269f64aeff3e57ce4f324725c3abbdad2d5a715334ecaa39afb0588
+size 313820248

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6ab6cf30f0b5091dc71c5a20ab1ee3edadd146a29f68cdae43cbe971e18b6ed
+size 157498564

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd36cce8b72b577a4c7d9179f1a786b9ff70f5cd4a9426e2d3ecaaa942f64a09
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044ad72f93425b036b02b17c04cefc9ba180dbb590ec5d40ae3918445a8957ec
+size 1064

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce19157ce6b457736a0015a2a4fb06c966c6ff252ec9d1950777eec6598abf6d
+size 17478028

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
+size 4241003

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<start_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<end_of_turn>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% 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'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '<start_of_turn>' + role + '\n' + message['content'] | trim + '<end_of_turn>\n' }}{% endfor %}{% if add_generation_prompt %}{{'<start_of_turn>model\n'}}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,476 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999238327366897,
+  "eval_steps": 500,
+  "global_step": 1641,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.1792221069335938,
+      "learning_rate": 0.0001,
+      "loss": 2.5047,
+      "step": 25
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 2.049243450164795,
+      "learning_rate": 0.0002,
+      "loss": 1.7337,
+      "step": 50
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.6915027499198914,
+      "learning_rate": 0.00019987817926617305,
+      "loss": 1.4443,
+      "step": 75
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0553752183914185,
+      "learning_rate": 0.00019951301387051594,
+      "loss": 1.301,
+      "step": 100
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6525191068649292,
+      "learning_rate": 0.0001989053935073581,
+      "loss": 1.3456,
+      "step": 125
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.9781862497329712,
+      "learning_rate": 0.00019805679859187002,
+      "loss": 1.2399,
+      "step": 150
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.7136988639831543,
+      "learning_rate": 0.00019696929665315825,
+      "loss": 1.3334,
+      "step": 175
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.0748471021652222,
+      "learning_rate": 0.000195645537296907,
+      "loss": 1.2078,
+      "step": 200
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.675721287727356,
+      "learning_rate": 0.00019408874574984014,
+      "loss": 1.2188,
+      "step": 225
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.605181336402893,
+      "learning_rate": 0.00019230271500173118,
+      "loss": 1.2026,
+      "step": 250
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.6624833345413208,
+      "learning_rate": 0.00019029179656410757,
+      "loss": 1.3039,
+      "step": 275
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 1.0530612468719482,
+      "learning_rate": 0.00018806088986816409,
+      "loss": 1.0913,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.6656801104545593,
+      "learning_rate": 0.00018561543032771672,
+      "loss": 1.2577,
+      "step": 325
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.8555144667625427,
+      "learning_rate": 0.00018296137609628062,
+      "loss": 1.1595,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.6359805464744568,
+      "learning_rate": 0.0001801051935505377,
+      "loss": 1.172,
+      "step": 375
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.8485956788063049,
+      "learning_rate": 0.0001770538415355612,
+      "loss": 1.145,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.6363926529884338,
+      "learning_rate": 0.00017381475441018376,
+      "loss": 1.2087,
+      "step": 425
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.7381790280342102,
+      "learning_rate": 0.0001703958239338162,
+      "loss": 1.1513,
+      "step": 450
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.653822124004364,
+      "learning_rate": 0.0001668053800388492,
+      "loss": 1.178,
+      "step": 475
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.0420897006988525,
+      "learning_rate": 0.00016305217053548375,
+      "loss": 1.1011,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.6513336300849915,
+      "learning_rate": 0.00015914533979843803,
+      "loss": 1.2081,
+      "step": 525
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 1.0648120641708374,
+      "learning_rate": 0.00015509440648745848,
+      "loss": 1.0635,
+      "step": 550
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5697813034057617,
+      "learning_rate": 0.00015090924035591767,
+      "loss": 1.1934,
+      "step": 575
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.7637466192245483,
+      "learning_rate": 0.0001466000382040022,
+      "loss": 1.0347,
+      "step": 600
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.649547278881073,
+      "learning_rate": 0.00014217729903507926,
+      "loss": 1.103,
+      "step": 625
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7465949058532715,
+      "learning_rate": 0.00013765179847577042,
+      "loss": 1.0162,
+      "step": 650
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 0.5898458361625671,
+      "learning_rate": 0.00013303456252205717,
+      "loss": 1.1759,
+      "step": 675
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 0.7913366556167603,
+      "learning_rate": 0.00012833684067538212,
+      "loss": 1.0818,
+      "step": 700
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.6705911755561829,
+      "learning_rate": 0.0001235700785341988,
+      "loss": 1.1397,
+      "step": 725
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 0.7381651997566223,
+      "learning_rate": 0.00011874588990774754,
+      "loss": 1.001,
+      "step": 750
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.6801482439041138,
+      "learning_rate": 0.00011387602852000028,
+      "loss": 1.1462,
+      "step": 775
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.7729134559631348,
+      "learning_rate": 0.00010897235937271481,
+      "loss": 0.9932,
+      "step": 800
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.7287363409996033,
+      "learning_rate": 0.0001040468298373705,
+      "loss": 1.0931,
+      "step": 825
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.8064184188842773,
+      "learning_rate": 9.911144054641694e-05,
+      "loss": 0.9767,
+      "step": 850
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.643425703048706,
+      "learning_rate": 9.417821615475708e-05,
+      "loss": 1.1155,
+      "step": 875
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.8285993337631226,
+      "learning_rate": 8.925917604270138e-05,
+      "loss": 0.9891,
+      "step": 900
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.6666772961616516,
+      "learning_rate": 8.436630503177338e-05,
+      "loss": 1.0477,
+      "step": 925
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.1137924194335938,
+      "learning_rate": 7.951152418471452e-05,
+      "loss": 1.0774,
+      "step": 950
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.6717397570610046,
+      "learning_rate": 7.470666176083192e-05,
+      "loss": 1.1127,
+      "step": 975
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.7843099236488342,
+      "learning_rate": 6.996342439745391e-05,
+      "loss": 1.027,
+      "step": 1000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.6149559020996094,
+      "learning_rate": 6.529336858770693e-05,
+      "loss": 1.1219,
+      "step": 1025
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.8785507082939148,
+      "learning_rate": 6.070787252410613e-05,
+      "loss": 0.9512,
+      "step": 1050
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.654931902885437,
+      "learning_rate": 5.621810837656001e-05,
+      "loss": 1.1221,
+      "step": 1075
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.8063294887542725,
+      "learning_rate": 5.183501507233191e-05,
+      "loss": 1.0177,
+      "step": 1100
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.68848717212677,
+      "learning_rate": 4.756927164427685e-05,
+      "loss": 1.113,
+      "step": 1125
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.8536142706871033,
+      "learning_rate": 4.3431271212289306e-05,
+      "loss": 0.9812,
+      "step": 1150
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.6890403032302856,
+      "learning_rate": 3.9431095661353346e-05,
+      "loss": 1.1406,
+      "step": 1175
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.9814476370811462,
+      "learning_rate": 3.5578491077889945e-05,
+      "loss": 0.953,
+      "step": 1200
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6605543494224548,
+      "learning_rate": 3.188284400424919e-05,
+      "loss": 1.057,
+      "step": 1225
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.816616952419281,
+      "learning_rate": 2.8353158569200577e-05,
+      "loss": 1.0338,
+      "step": 1250
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.6390181183815002,
+      "learning_rate": 2.499803455014167e-05,
+      "loss": 1.0166,
+      "step": 1275
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.8337960243225098,
+      "learning_rate": 2.1825646420474066e-05,
+      "loss": 1.0925,
+      "step": 1300
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.7009729743003845,
+      "learning_rate": 1.8843723433196614e-05,
+      "loss": 1.0227,
+      "step": 1325
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.7410553693771362,
+      "learning_rate": 1.6059530789239797e-05,
+      "loss": 0.9625,
+      "step": 1350
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.5852776169776917,
+      "learning_rate": 1.3479851936423648e-05,
+      "loss": 1.1237,
+      "step": 1375
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.7892405986785889,
+      "learning_rate": 1.1110972042165957e-05,
+      "loss": 0.9894,
+      "step": 1400
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.7052353024482727,
+      "learning_rate": 8.95866268020803e-06,
+      "loss": 1.0971,
+      "step": 1425
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.843733012676239,
+      "learning_rate": 7.028167768667815e-06,
+      "loss": 0.9854,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.6242654919624329,
+      "learning_rate": 5.324190793680772e-06,
+      "loss": 1.042,
+      "step": 1475
+    },
+    {
+      "epoch": 0.91,
+      "grad_norm": 0.795802652835846,
+      "learning_rate": 3.850883349757217e-06,
+      "loss": 0.965,
+      "step": 1500
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 0.6372144818305969,
+      "learning_rate": 2.61183502477661e-06,
+      "loss": 1.0566,
+      "step": 1525
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.8181334137916565,
+      "learning_rate": 1.610064654262866e-06,
+      "loss": 0.9948,
+      "step": 1550
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6644455790519714,
+      "learning_rate": 8.480129662492231e-07,
+      "loss": 1.0306,
+      "step": 1575
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.7101704478263855,
+      "learning_rate": 3.275366346526476e-07,
+      "loss": 0.9945,
+      "step": 1600
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.5538750886917114,
+      "learning_rate": 4.990375564620786e-08,
+      "loss": 1.0422,
+      "step": 1625
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1641,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.584234844535194e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40597a41ac735a12fee9fdba5d11ca884fee16841b8a9930aff34a7981ee6e53
+size 4856