Upload 13 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Phi-3.5-mini-instruct
+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 0.14.0

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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,
+  "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",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "up_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:b3cfb88c9ab603f184109f35cb7d8e2a8720b67faeb3fe6ef0caf5c8abb164c2
+size 478211024

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0380e9502b324a5a09fcc85c887783244752775c8d28de2b30dccc87a697dd23
+size 956679634

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b66e3cc7c452b707ddac5caf0aa17618afb9bc1a0333600a22c4afb353f3165
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7392808863791abafe0e77a6cbc565b015a343b12273c8eea4e5a055257bc02
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|placeholder6|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,132 @@
+{
+  "add_bos_token": false,
+  "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": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|placeholder6|>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,558 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 15000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02666666666666667,
+      "grad_norm": 1.8224557638168335,
+      "learning_rate": 0.00019895986131484198,
+      "loss": 0.5652,
+      "step": 200
+    },
+    {
+      "epoch": 0.05333333333333334,
+      "grad_norm": 1.010162353515625,
+      "learning_rate": 0.00019789305240698761,
+      "loss": 0.5615,
+      "step": 400
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.7284229397773743,
+      "learning_rate": 0.00019682624349913323,
+      "loss": 0.5847,
+      "step": 600
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.9393308758735657,
+      "learning_rate": 0.00019575943459127886,
+      "loss": 0.5545,
+      "step": 800
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.915951669216156,
+      "learning_rate": 0.00019469262568342445,
+      "loss": 0.5794,
+      "step": 1000
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.9032522439956665,
+      "learning_rate": 0.0001936258167755701,
+      "loss": 0.6067,
+      "step": 1200
+    },
+    {
+      "epoch": 0.18666666666666668,
+      "grad_norm": 0.6736401915550232,
+      "learning_rate": 0.0001925590078677157,
+      "loss": 0.5701,
+      "step": 1400
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.775130271911621,
+      "learning_rate": 0.0001914921989598613,
+      "loss": 0.5895,
+      "step": 1600
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1148632764816284,
+      "learning_rate": 0.00019042539005200695,
+      "loss": 0.6095,
+      "step": 1800
+    },
+    {
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.9489474296569824,
+      "learning_rate": 0.00018935858114415256,
+      "loss": 0.6109,
+      "step": 2000
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.783237874507904,
+      "learning_rate": 0.0001882917722362982,
+      "loss": 0.5866,
+      "step": 2200
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.6665730476379395,
+      "learning_rate": 0.00018722496332844378,
+      "loss": 0.5762,
+      "step": 2400
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 1.291765570640564,
+      "learning_rate": 0.00018615815442058942,
+      "loss": 0.6123,
+      "step": 2600
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 1.536110520362854,
+      "learning_rate": 0.00018509134551273503,
+      "loss": 0.5878,
+      "step": 2800
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.170196771621704,
+      "learning_rate": 0.00018402453660488067,
+      "loss": 0.5954,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.9499145150184631,
+      "learning_rate": 0.00018295772769702628,
+      "loss": 0.6159,
+      "step": 3200
+    },
+    {
+      "epoch": 0.4533333333333333,
+      "grad_norm": 1.2118113040924072,
+      "learning_rate": 0.0001818909187891719,
+      "loss": 0.639,
+      "step": 3400
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9366052150726318,
+      "learning_rate": 0.00018082410988131753,
+      "loss": 0.6232,
+      "step": 3600
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "grad_norm": 1.1474961042404175,
+      "learning_rate": 0.00017975730097346312,
+      "loss": 0.5993,
+      "step": 3800
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 1.5155959129333496,
+      "learning_rate": 0.00017869049206560876,
+      "loss": 0.6139,
+      "step": 4000
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.1921544075012207,
+      "learning_rate": 0.00017762368315775437,
+      "loss": 0.6352,
+      "step": 4200
+    },
+    {
+      "epoch": 0.5866666666666667,
+      "grad_norm": 1.1144263744354248,
+      "learning_rate": 0.0001765568742499,
+      "loss": 0.6004,
+      "step": 4400
+    },
+    {
+      "epoch": 0.6133333333333333,
+      "grad_norm": 1.6893116235733032,
+      "learning_rate": 0.00017549006534204562,
+      "loss": 0.6312,
+      "step": 4600
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.4080637693405151,
+      "learning_rate": 0.00017442325643419123,
+      "loss": 0.6002,
+      "step": 4800
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.4908393621444702,
+      "learning_rate": 0.00017335644752633687,
+      "loss": 0.603,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.5237169861793518,
+      "learning_rate": 0.00017228963861848245,
+      "loss": 0.6179,
+      "step": 5200
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 0.4859675168991089,
+      "learning_rate": 0.0001712228297106281,
+      "loss": 0.6421,
+      "step": 5400
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 1.4541916847229004,
+      "learning_rate": 0.0001701560208027737,
+      "loss": 0.615,
+      "step": 5600
+    },
+    {
+      "epoch": 0.7733333333333333,
+      "grad_norm": 2.2076306343078613,
+      "learning_rate": 0.00016908921189491934,
+      "loss": 0.6419,
+      "step": 5800
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.6922993659973145,
+      "learning_rate": 0.00016802240298706495,
+      "loss": 0.6234,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8266666666666667,
+      "grad_norm": 0.6677654385566711,
+      "learning_rate": 0.00016695559407921057,
+      "loss": 0.5954,
+      "step": 6200
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.704343855381012,
+      "learning_rate": 0.0001658887851713562,
+      "loss": 0.6175,
+      "step": 6400
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.9924121499061584,
+      "learning_rate": 0.0001648219762635018,
+      "loss": 0.6172,
+      "step": 6600
+    },
+    {
+      "epoch": 0.9066666666666666,
+      "grad_norm": 1.5889892578125,
+      "learning_rate": 0.00016375516735564743,
+      "loss": 0.6131,
+      "step": 6800
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 1.3223360776901245,
+      "learning_rate": 0.00016268835844779304,
+      "loss": 0.632,
+      "step": 7000
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.9497195482254028,
+      "learning_rate": 0.00016162154953993868,
+      "loss": 0.6314,
+      "step": 7200
+    },
+    {
+      "epoch": 0.9866666666666667,
+      "grad_norm": 1.2201488018035889,
+      "learning_rate": 0.0001605547406320843,
+      "loss": 0.6003,
+      "step": 7400
+    },
+    {
+      "epoch": 1.0133333333333334,
+      "grad_norm": 0.9246127605438232,
+      "learning_rate": 0.0001594879317242299,
+      "loss": 0.5296,
+      "step": 7600
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 0.8949518203735352,
+      "learning_rate": 0.00015842112281637554,
+      "loss": 0.4514,
+      "step": 7800
+    },
+    {
+      "epoch": 1.0666666666666667,
+      "grad_norm": 0.639042317867279,
+      "learning_rate": 0.00015735431390852112,
+      "loss": 0.4582,
+      "step": 8000
+    },
+    {
+      "epoch": 1.0933333333333333,
+      "grad_norm": 0.9326872229576111,
+      "learning_rate": 0.00015628750500066676,
+      "loss": 0.4339,
+      "step": 8200
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.5695537328720093,
+      "learning_rate": 0.00015522069609281237,
+      "loss": 0.4511,
+      "step": 8400
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 0.8884285092353821,
+      "learning_rate": 0.000154153887184958,
+      "loss": 0.4151,
+      "step": 8600
+    },
+    {
+      "epoch": 1.1733333333333333,
+      "grad_norm": 0.9930616617202759,
+      "learning_rate": 0.00015308707827710362,
+      "loss": 0.4551,
+      "step": 8800
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 1.1548641920089722,
+      "learning_rate": 0.00015202026936924923,
+      "loss": 0.4594,
+      "step": 9000
+    },
+    {
+      "epoch": 1.2266666666666666,
+      "grad_norm": 0.7928484082221985,
+      "learning_rate": 0.00015095346046139487,
+      "loss": 0.4704,
+      "step": 9200
+    },
+    {
+      "epoch": 1.2533333333333334,
+      "grad_norm": 2.5043861865997314,
+      "learning_rate": 0.00014988665155354046,
+      "loss": 0.5059,
+      "step": 9400
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.363883376121521,
+      "learning_rate": 0.0001488198426456861,
+      "loss": 0.4488,
+      "step": 9600
+    },
+    {
+      "epoch": 1.3066666666666666,
+      "grad_norm": 1.1422014236450195,
+      "learning_rate": 0.0001477530337378317,
+      "loss": 0.4636,
+      "step": 9800
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.7344350218772888,
+      "learning_rate": 0.00014668622482997735,
+      "loss": 0.4694,
+      "step": 10000
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 2.64691162109375,
+      "learning_rate": 0.00014561941592212296,
+      "loss": 0.4494,
+      "step": 10200
+    },
+    {
+      "epoch": 1.3866666666666667,
+      "grad_norm": 0.8812822103500366,
+      "learning_rate": 0.00014455260701426857,
+      "loss": 0.4881,
+      "step": 10400
+    },
+    {
+      "epoch": 1.4133333333333333,
+      "grad_norm": 2.2142817974090576,
+      "learning_rate": 0.0001434857981064142,
+      "loss": 0.4651,
+      "step": 10600
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.6976217031478882,
+      "learning_rate": 0.0001424189891985598,
+      "loss": 0.4591,
+      "step": 10800
+    },
+    {
+      "epoch": 1.4666666666666668,
+      "grad_norm": 1.3944759368896484,
+      "learning_rate": 0.00014135218029070543,
+      "loss": 0.475,
+      "step": 11000
+    },
+    {
+      "epoch": 1.4933333333333334,
+      "grad_norm": 1.502564787864685,
+      "learning_rate": 0.00014028537138285104,
+      "loss": 0.4752,
+      "step": 11200
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.7984268069267273,
+      "learning_rate": 0.00013921856247499668,
+      "loss": 0.4641,
+      "step": 11400
+    },
+    {
+      "epoch": 1.5466666666666666,
+      "grad_norm": 1.7251499891281128,
+      "learning_rate": 0.0001381517535671423,
+      "loss": 0.4791,
+      "step": 11600
+    },
+    {
+      "epoch": 1.5733333333333333,
+      "grad_norm": 1.0267277956008911,
+      "learning_rate": 0.0001370849446592879,
+      "loss": 0.4511,
+      "step": 11800
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 2.1689605712890625,
+      "learning_rate": 0.00013601813575143354,
+      "loss": 0.4613,
+      "step": 12000
+    },
+    {
+      "epoch": 1.6266666666666667,
+      "grad_norm": 1.6752183437347412,
+      "learning_rate": 0.00013495132684357913,
+      "loss": 0.4765,
+      "step": 12200
+    },
+    {
+      "epoch": 1.6533333333333333,
+      "grad_norm": 0.49789512157440186,
+      "learning_rate": 0.00013388451793572477,
+      "loss": 0.4735,
+      "step": 12400
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.8861690759658813,
+      "learning_rate": 0.00013281770902787038,
+      "loss": 0.4647,
+      "step": 12600
+    },
+    {
+      "epoch": 1.7066666666666666,
+      "grad_norm": 1.4024194478988647,
+      "learning_rate": 0.00013175090012001602,
+      "loss": 0.4566,
+      "step": 12800
+    },
+    {
+      "epoch": 1.7333333333333334,
+      "grad_norm": 1.691872239112854,
+      "learning_rate": 0.00013068409121216163,
+      "loss": 0.4646,
+      "step": 13000
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.8841276168823242,
+      "learning_rate": 0.00012961728230430724,
+      "loss": 0.47,
+      "step": 13200
+    },
+    {
+      "epoch": 1.7866666666666666,
+      "grad_norm": 2.0173470973968506,
+      "learning_rate": 0.00012855047339645288,
+      "loss": 0.5013,
+      "step": 13400
+    },
+    {
+      "epoch": 1.8133333333333335,
+      "grad_norm": 0.7734861373901367,
+      "learning_rate": 0.00012748366448859846,
+      "loss": 0.474,
+      "step": 13600
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.8500189781188965,
+      "learning_rate": 0.0001264168555807441,
+      "loss": 0.4881,
+      "step": 13800
+    },
+    {
+      "epoch": 1.8666666666666667,
+      "grad_norm": 1.2855855226516724,
+      "learning_rate": 0.0001253500466728897,
+      "loss": 0.4784,
+      "step": 14000
+    },
+    {
+      "epoch": 1.8933333333333333,
+      "grad_norm": 2.410865306854248,
+      "learning_rate": 0.00012428323776503535,
+      "loss": 0.4673,
+      "step": 14200
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.5624301433563232,
+      "learning_rate": 0.00012321642885718096,
+      "loss": 0.4781,
+      "step": 14400
+    },
+    {
+      "epoch": 1.9466666666666668,
+      "grad_norm": 2.08925461769104,
+      "learning_rate": 0.0001221496199493266,
+      "loss": 0.4613,
+      "step": 14600
+    },
+    {
+      "epoch": 1.9733333333333334,
+      "grad_norm": 2.586411476135254,
+      "learning_rate": 0.00012108281104147221,
+      "loss": 0.5001,
+      "step": 14800
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7612062692642212,
+      "learning_rate": 0.00012001600213361781,
+      "loss": 0.4566,
+      "step": 15000
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 37500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1669474815034573e+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:b335bc31e6b5f349b01320f2d92515fc463c038267bca90c958a33e87860f8ad
+size 5560