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 +1,202 @@
+---
+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 0.9.0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "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": 16,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "up_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94167f2c29f47d8cf78aa5e6b42114adf25de5c22f5e537da6dabf1625868b03
+size 156926880

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b28a4661b18e7d998ed4960cb4de4f5e86adb2c14d9eecbf143e0d336e4488
+size 313998650

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3424380a714d6152a0f2bc081cfef86ce96a85b8e4cd32338eefb420e3a639dc
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1016937f2c03513269c0aa2eb48e00994c84f647846b4918fd2da86df225f377
+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 sha256:05e97791a5e007260de1db7e1692e53150e08cea481e2bf25435553380c147ee
+size 17477929

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 +1,756 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8924033522573669,
+  "eval_steps": 500,
+  "global_step": 10500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.87135249376297,
+      "learning_rate": 0.00019819808452978876,
+      "loss": 2.1425,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8564028739929199,
+      "learning_rate": 0.0001963956283227154,
+      "loss": 1.8647,
+      "step": 200
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8958914875984192,
+      "learning_rate": 0.000194593172115642,
+      "loss": 1.8182,
+      "step": 300
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.8007214069366455,
+      "learning_rate": 0.00019279071590856862,
+      "loss": 1.711,
+      "step": 400
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.8793672919273376,
+      "learning_rate": 0.00019098825970149526,
+      "loss": 1.686,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.9486576318740845,
+      "learning_rate": 0.00018918580349442187,
+      "loss": 1.7068,
+      "step": 600
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.8130625486373901,
+      "learning_rate": 0.0001873833472873485,
+      "loss": 1.6457,
+      "step": 700
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.8903294801712036,
+      "learning_rate": 0.00018558089108027513,
+      "loss": 1.6285,
+      "step": 800
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9597026109695435,
+      "learning_rate": 0.0001837784348732017,
+      "loss": 1.6305,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.7700974941253662,
+      "learning_rate": 0.00018197597866612835,
+      "loss": 1.6443,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.8106345534324646,
+      "learning_rate": 0.00018017352245905497,
+      "loss": 1.5963,
+      "step": 1100
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.026309847831726,
+      "learning_rate": 0.00017837106625198158,
+      "loss": 1.5615,
+      "step": 1200
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.8697523474693298,
+      "learning_rate": 0.00017656861004490822,
+      "loss": 1.5295,
+      "step": 1300
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.2120341062545776,
+      "learning_rate": 0.00017476615383783483,
+      "loss": 1.4984,
+      "step": 1400
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.7356016039848328,
+      "learning_rate": 0.00017296369763076145,
+      "loss": 1.5311,
+      "step": 1500
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.8384151458740234,
+      "learning_rate": 0.00017116124142368809,
+      "loss": 1.5632,
+      "step": 1600
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.8941056132316589,
+      "learning_rate": 0.0001693587852166147,
+      "loss": 1.492,
+      "step": 1700
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.7094323039054871,
+      "learning_rate": 0.0001675563290095413,
+      "loss": 1.4425,
+      "step": 1800
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.7246663570404053,
+      "learning_rate": 0.00016575387280246795,
+      "loss": 1.4277,
+      "step": 1900
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.8121210932731628,
+      "learning_rate": 0.00016395141659539456,
+      "loss": 1.464,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.712011456489563,
+      "learning_rate": 0.0001621489603883212,
+      "loss": 1.4779,
+      "step": 2100
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.7419346570968628,
+      "learning_rate": 0.00016034650418124782,
+      "loss": 1.4669,
+      "step": 2200
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.0694609880447388,
+      "learning_rate": 0.0001585440479741744,
+      "loss": 1.4499,
+      "step": 2300
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 1.0339300632476807,
+      "learning_rate": 0.00015674159176710104,
+      "loss": 1.4115,
+      "step": 2400
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.1224662065505981,
+      "learning_rate": 0.00015493913556002766,
+      "loss": 1.4353,
+      "step": 2500
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.8455696702003479,
+      "learning_rate": 0.0001531366793529543,
+      "loss": 1.3991,
+      "step": 2600
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 0.8783261179924011,
+      "learning_rate": 0.0001513342231458809,
+      "loss": 1.4174,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.8644577264785767,
+      "learning_rate": 0.00014953176693880752,
+      "loss": 1.4272,
+      "step": 2800
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.804175853729248,
+      "learning_rate": 0.00014772931073173416,
+      "loss": 1.3904,
+      "step": 2900
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.8686081767082214,
+      "learning_rate": 0.00014592685452466077,
+      "loss": 1.3577,
+      "step": 3000
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 0.8131946325302124,
+      "learning_rate": 0.0001441243983175874,
+      "loss": 1.3798,
+      "step": 3100
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.9579694271087646,
+      "learning_rate": 0.00014232194211051403,
+      "loss": 1.3705,
+      "step": 3200
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 0.7878475785255432,
+      "learning_rate": 0.00014051948590344064,
+      "loss": 1.3216,
+      "step": 3300
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.9384462833404541,
+      "learning_rate": 0.00013871702969636725,
+      "loss": 1.3681,
+      "step": 3400
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.899638295173645,
+      "learning_rate": 0.0001369145734892939,
+      "loss": 1.3752,
+      "step": 3500
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.8509306907653809,
+      "learning_rate": 0.0001351121172822205,
+      "loss": 1.3253,
+      "step": 3600
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 0.712924063205719,
+      "learning_rate": 0.00013330966107514712,
+      "loss": 1.3318,
+      "step": 3700
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.8807259798049927,
+      "learning_rate": 0.00013150720486807373,
+      "loss": 1.3163,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9081091284751892,
+      "learning_rate": 0.00012970474866100034,
+      "loss": 1.3839,
+      "step": 3900
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 1.0412542819976807,
+      "learning_rate": 0.00012790229245392698,
+      "loss": 1.3057,
+      "step": 4000
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.8416357636451721,
+      "learning_rate": 0.0001260998362468536,
+      "loss": 1.2548,
+      "step": 4100
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.8973735570907593,
+      "learning_rate": 0.0001242973800397802,
+      "loss": 1.3154,
+      "step": 4200
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.7394294738769531,
+      "learning_rate": 0.00012249492383270685,
+      "loss": 1.3079,
+      "step": 4300
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 1.1180624961853027,
+      "learning_rate": 0.00012069246762563346,
+      "loss": 1.2789,
+      "step": 4400
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.8885756134986877,
+      "learning_rate": 0.00011889001141856009,
+      "loss": 1.2959,
+      "step": 4500
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 1.1742843389511108,
+      "learning_rate": 0.00011708755521148672,
+      "loss": 1.2486,
+      "step": 4600
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.9566686153411865,
+      "learning_rate": 0.00011528509900441333,
+      "loss": 1.303,
+      "step": 4700
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 1.2613877058029175,
+      "learning_rate": 0.00011348264279733996,
+      "loss": 1.301,
+      "step": 4800
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9030331969261169,
+      "learning_rate": 0.00011168018659026658,
+      "loss": 1.3338,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 1.0433690547943115,
+      "learning_rate": 0.00010987773038319318,
+      "loss": 1.3068,
+      "step": 5000
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.8587890267372131,
+      "learning_rate": 0.00010807527417611981,
+      "loss": 1.2632,
+      "step": 5100
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 1.0812350511550903,
+      "learning_rate": 0.00010627281796904642,
+      "loss": 1.278,
+      "step": 5200
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.8623504042625427,
+      "learning_rate": 0.00010447036176197305,
+      "loss": 1.2392,
+      "step": 5300
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.8327571749687195,
+      "learning_rate": 0.00010266790555489967,
+      "loss": 1.2652,
+      "step": 5400
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.958329975605011,
+      "learning_rate": 0.00010086544934782629,
+      "loss": 1.286,
+      "step": 5500
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.9664350748062134,
+      "learning_rate": 9.906299314075291e-05,
+      "loss": 1.1171,
+      "step": 5600
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.8452981114387512,
+      "learning_rate": 9.726053693367954e-05,
+      "loss": 1.0828,
+      "step": 5700
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 1.0611803531646729,
+      "learning_rate": 9.545808072660615e-05,
+      "loss": 1.1142,
+      "step": 5800
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 1.0450036525726318,
+      "learning_rate": 9.365562451953278e-05,
+      "loss": 1.1217,
+      "step": 5900
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.9196897745132446,
+      "learning_rate": 9.18531683124594e-05,
+      "loss": 1.1435,
+      "step": 6000
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.241141676902771,
+      "learning_rate": 9.005071210538602e-05,
+      "loss": 1.1174,
+      "step": 6100
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.8073747754096985,
+      "learning_rate": 8.826628046038338e-05,
+      "loss": 1.0501,
+      "step": 6200
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 0.8413310647010803,
+      "learning_rate": 8.646382425331e-05,
+      "loss": 1.1023,
+      "step": 6300
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.8178868889808655,
+      "learning_rate": 8.466136804623662e-05,
+      "loss": 1.0948,
+      "step": 6400
+    },
+    {
+      "epoch": 1.17,
+      "grad_norm": 0.9561821222305298,
+      "learning_rate": 8.285891183916323e-05,
+      "loss": 1.0936,
+      "step": 6500
+    },
+    {
+      "epoch": 1.19,
+      "grad_norm": 0.9246460199356079,
+      "learning_rate": 8.105645563208986e-05,
+      "loss": 1.0679,
+      "step": 6600
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.9705007076263428,
+      "learning_rate": 7.925399942501648e-05,
+      "loss": 1.026,
+      "step": 6700
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.9710861444473267,
+      "learning_rate": 7.74515432179431e-05,
+      "loss": 1.0543,
+      "step": 6800
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 1.0675069093704224,
+      "learning_rate": 7.564908701086972e-05,
+      "loss": 1.0987,
+      "step": 6900
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.8517453670501709,
+      "learning_rate": 7.384663080379635e-05,
+      "loss": 1.0693,
+      "step": 7000
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.901584267616272,
+      "learning_rate": 7.204417459672296e-05,
+      "loss": 1.0685,
+      "step": 7100
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 1.0663121938705444,
+      "learning_rate": 7.024171838964957e-05,
+      "loss": 1.0802,
+      "step": 7200
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 1.0489306449890137,
+      "learning_rate": 6.84392621825762e-05,
+      "loss": 1.1116,
+      "step": 7300
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 0.8096909523010254,
+      "learning_rate": 6.663680597550283e-05,
+      "loss": 1.0675,
+      "step": 7400
+    },
+    {
+      "epoch": 1.35,
+      "grad_norm": 1.0951379537582397,
+      "learning_rate": 6.483434976842945e-05,
+      "loss": 1.0631,
+      "step": 7500
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 1.08359956741333,
+      "learning_rate": 6.303189356135607e-05,
+      "loss": 1.0522,
+      "step": 7600
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 1.22184419631958,
+      "learning_rate": 6.122943735428269e-05,
+      "loss": 1.0878,
+      "step": 7700
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 1.087251901626587,
+      "learning_rate": 5.9426981147209305e-05,
+      "loss": 1.0659,
+      "step": 7800
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.020251750946045,
+      "learning_rate": 5.7624524940135925e-05,
+      "loss": 1.0668,
+      "step": 7900
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.9591791033744812,
+      "learning_rate": 5.582206873306255e-05,
+      "loss": 1.0702,
+      "step": 8000
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 1.0169813632965088,
+      "learning_rate": 5.401961252598917e-05,
+      "loss": 1.0375,
+      "step": 8100
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.044224739074707,
+      "learning_rate": 5.22171563189158e-05,
+      "loss": 1.0777,
+      "step": 8200
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 1.0525567531585693,
+      "learning_rate": 5.041470011184242e-05,
+      "loss": 0.9967,
+      "step": 8300
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 0.9581038951873779,
+      "learning_rate": 4.861224390476904e-05,
+      "loss": 1.0595,
+      "step": 8400
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.0464085340499878,
+      "learning_rate": 4.6809787697695656e-05,
+      "loss": 1.0423,
+      "step": 8500
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.982803225517273,
+      "learning_rate": 4.5007331490622276e-05,
+      "loss": 1.0683,
+      "step": 8600
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 1.1214386224746704,
+      "learning_rate": 4.3204875283548896e-05,
+      "loss": 1.0984,
+      "step": 8700
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.0456256866455078,
+      "learning_rate": 4.1402419076475515e-05,
+      "loss": 1.0549,
+      "step": 8800
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.0025187730789185,
+      "learning_rate": 3.959996286940214e-05,
+      "loss": 1.024,
+      "step": 8900
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 1.2760844230651855,
+      "learning_rate": 3.7797506662328755e-05,
+      "loss": 1.0313,
+      "step": 9000
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 0.9632763862609863,
+      "learning_rate": 3.599505045525538e-05,
+      "loss": 1.0263,
+      "step": 9100
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.01961088180542,
+      "learning_rate": 3.4192594248182e-05,
+      "loss": 1.0503,
+      "step": 9200
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.9579876065254211,
+      "learning_rate": 3.239013804110862e-05,
+      "loss": 1.03,
+      "step": 9300
+    },
+    {
+      "epoch": 1.69,
+      "grad_norm": 1.400282859802246,
+      "learning_rate": 3.058768183403524e-05,
+      "loss": 1.0481,
+      "step": 9400
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 1.1665406227111816,
+      "learning_rate": 2.8785225626961863e-05,
+      "loss": 1.0585,
+      "step": 9500
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 1.1331160068511963,
+      "learning_rate": 2.6982769419888486e-05,
+      "loss": 0.9992,
+      "step": 9600
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 1.0598838329315186,
+      "learning_rate": 2.5180313212815106e-05,
+      "loss": 1.0663,
+      "step": 9700
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.0826873779296875,
+      "learning_rate": 2.3377857005741726e-05,
+      "loss": 0.9844,
+      "step": 9800
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.9529953002929688,
+      "learning_rate": 2.1575400798668345e-05,
+      "loss": 1.0349,
+      "step": 9900
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 1.0949389934539795,
+      "learning_rate": 1.977294459159497e-05,
+      "loss": 1.0473,
+      "step": 10000
+    },
+    {
+      "epoch": 1.82,
+      "grad_norm": 1.0248372554779053,
+      "learning_rate": 1.7970488384521588e-05,
+      "loss": 1.0382,
+      "step": 10100
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.9931679368019104,
+      "learning_rate": 1.616803217744821e-05,
+      "loss": 1.017,
+      "step": 10200
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.9561355710029602,
+      "learning_rate": 1.436557597037483e-05,
+      "loss": 1.0577,
+      "step": 10300
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.2075040340423584,
+      "learning_rate": 1.2563119763301454e-05,
+      "loss": 1.0493,
+      "step": 10400
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.1561285257339478,
+      "learning_rate": 1.0760663556228073e-05,
+      "loss": 0.9947,
+      "step": 10500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 11096,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 3.714097560675041e+17,
+  "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 sha256:29aca760a61dcbe73bb67d5d61058070185a2b1ab3a47b8129db6a5b07e0e729
+size 4856