Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/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 0.15.2

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8967d9b6102a7a4400c0e7b219a968388a7574bebef2c55c5db5099fd2a0e2
+size 12591456

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 sha256:314b918b5fc9f4ba7dcdbbe25e04368783d7af877291c99c37db179ed65a9fcb
+size 25219898

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e25d28facc6f7857d8dd8e8da61f6d7c55da4e9ebc535b4cbab0324f65393b62
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157488aabe3e3a3d69331e12ad906e4041818e78393c1fdcb2cb7857a7689d9e
+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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "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": "<|endoftext|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,379 @@
+{
+  "best_global_step": 55,
+  "best_metric": 0.020872214809060097,
+  "best_model_checkpoint": "outputs/microsoft/Phi-3.5-mini-instruct/countdown_mcl_1024/checkpoint-15",
+  "epoch": 3.0,
+  "eval_steps": 5,
+  "global_step": 75,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.019189711660146713,
+      "learning_rate": 9.466666666666666e-07,
+      "loss": 0.0336,
+      "step": 5
+    },
+    {
+      "epoch": 0.2,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 802.8125,
+      "eval_kl": 3.0040740966796875e-05,
+      "eval_loss": 0.07697294652462006,
+      "eval_num_tokens": 76355.0,
+      "eval_reward": 0.0875,
+      "eval_reward_std": 0.13273502588272096,
+      "eval_rewards/equation_reward_func": 0.075,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1338.4011,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 5
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.01623854786157608,
+      "learning_rate": 8.799999999999999e-07,
+      "loss": 0.0454,
+      "step": 10
+    },
+    {
+      "epoch": 0.4,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 855.5625,
+      "eval_kl": 3.3321976661682126e-05,
+      "eval_loss": 0.04702009633183479,
+      "eval_num_tokens": 152886.0,
+      "eval_reward": 0.0625,
+      "eval_reward_std": 0.125,
+      "eval_rewards/equation_reward_func": 0.0375,
+      "eval_rewards/format_reward_func": 0.025,
+      "eval_runtime": 1294.6762,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 10
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.0,
+      "learning_rate": 8.133333333333333e-07,
+      "loss": 0.0494,
+      "step": 15
+    },
+    {
+      "epoch": 0.6,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 796.0875,
+      "eval_kl": 3.191232681274414e-05,
+      "eval_loss": 0.03644490987062454,
+      "eval_num_tokens": 230732.0,
+      "eval_reward": 0.1125,
+      "eval_reward_std": 0.18273502588272095,
+      "eval_rewards/equation_reward_func": 0.0875,
+      "eval_rewards/format_reward_func": 0.025,
+      "eval_runtime": 1335.5012,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 15
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.009749338962137699,
+      "learning_rate": 7.466666666666667e-07,
+      "loss": 0.0723,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 810.8,
+      "eval_kl": 2.9605627059936523e-05,
+      "eval_loss": 0.04239075630903244,
+      "eval_num_tokens": 308908.0,
+      "eval_reward": 0.0875,
+      "eval_reward_std": 0.15386751294136047,
+      "eval_rewards/equation_reward_func": 0.05,
+      "eval_rewards/format_reward_func": 0.0375,
+      "eval_runtime": 1337.0845,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.0265500470995903,
+      "learning_rate": 6.800000000000001e-07,
+      "loss": 0.0296,
+      "step": 25
+    },
+    {
+      "epoch": 1.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 769.025,
+      "eval_kl": 2.89231538772583e-05,
+      "eval_loss": 0.07508356869220734,
+      "eval_num_tokens": 385628.0,
+      "eval_reward": 0.1125,
+      "eval_reward_std": 0.18273502588272095,
+      "eval_rewards/equation_reward_func": 0.1,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1334.3196,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 25
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.0,
+      "learning_rate": 6.133333333333332e-07,
+      "loss": 0.0476,
+      "step": 30
+    },
+    {
+      "epoch": 1.2,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 743.5375,
+      "eval_kl": 3.173947334289551e-05,
+      "eval_loss": 0.09708776324987411,
+      "eval_num_tokens": 463386.0,
+      "eval_reward": 0.15,
+      "eval_reward_std": 0.25773502588272096,
+      "eval_rewards/equation_reward_func": 0.1375,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1333.5969,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 30
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 0.0,
+      "learning_rate": 5.466666666666666e-07,
+      "loss": 0.0398,
+      "step": 35
+    },
+    {
+      "epoch": 1.4,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 791.5125,
+      "eval_kl": 3.103315830230713e-05,
+      "eval_loss": 0.04481809586286545,
+      "eval_num_tokens": 536555.0,
+      "eval_reward": 0.1125,
+      "eval_reward_std": 0.20386751294136046,
+      "eval_rewards/equation_reward_func": 0.0875,
+      "eval_rewards/format_reward_func": 0.025,
+      "eval_runtime": 1304.5413,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 35
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.01814551278948784,
+      "learning_rate": 4.8e-07,
+      "loss": 0.0884,
+      "step": 40
+    },
+    {
+      "epoch": 1.6,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 798.8,
+      "eval_kl": 3.2714009284973146e-05,
+      "eval_loss": 0.06108971685171127,
+      "eval_num_tokens": 615157.0,
+      "eval_reward": 0.125,
+      "eval_reward_std": 0.17886751294136047,
+      "eval_rewards/equation_reward_func": 0.1125,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1301.9697,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 40
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 0.0,
+      "learning_rate": 4.1333333333333333e-07,
+      "loss": 0.1015,
+      "step": 45
+    },
+    {
+      "epoch": 1.8,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 792.85,
+      "eval_kl": 2.993345260620117e-05,
+      "eval_loss": 0.06866836547851562,
+      "eval_num_tokens": 687524.0,
+      "eval_reward": 0.1375,
+      "eval_reward_std": 0.22673887014389038,
+      "eval_rewards/equation_reward_func": 0.075,
+      "eval_rewards/format_reward_func": 0.0625,
+      "eval_runtime": 1314.7184,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 45
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.01888681948184967,
+      "learning_rate": 3.4666666666666665e-07,
+      "loss": 0.0441,
+      "step": 50
+    },
+    {
+      "epoch": 2.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 828.3625,
+      "eval_kl": 3.242790699005127e-05,
+      "eval_loss": 0.03552088886499405,
+      "eval_num_tokens": 764139.0,
+      "eval_reward": 0.0375,
+      "eval_reward_std": 0.075,
+      "eval_rewards/equation_reward_func": 0.0125,
+      "eval_rewards/format_reward_func": 0.025,
+      "eval_runtime": 1335.2965,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 50
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.012753931805491447,
+      "learning_rate": 2.8e-07,
+      "loss": 0.0577,
+      "step": 55
+    },
+    {
+      "epoch": 2.2,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 838.8,
+      "eval_kl": 3.0362606048583983e-05,
+      "eval_loss": 0.020872214809060097,
+      "eval_num_tokens": 845274.0,
+      "eval_reward": 0.05,
+      "eval_reward_std": 0.1,
+      "eval_rewards/equation_reward_func": 0.0375,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1294.8372,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 55
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.0,
+      "learning_rate": 2.1333333333333334e-07,
+      "loss": 0.1044,
+      "step": 60
+    },
+    {
+      "epoch": 2.4,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 786.7,
+      "eval_kl": 3.013014793395996e-05,
+      "eval_loss": 0.07739870995283127,
+      "eval_num_tokens": 919161.0,
+      "eval_reward": 0.1,
+      "eval_reward_std": 0.17886751294136047,
+      "eval_rewards/equation_reward_func": 0.0875,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1281.0863,
+      "eval_samples_per_second": 0.016,
+      "eval_steps_per_second": 0.004,
+      "step": 60
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.0,
+      "learning_rate": 1.4666666666666666e-07,
+      "loss": 0.0556,
+      "step": 65
+    },
+    {
+      "epoch": 2.6,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 787.15,
+      "eval_kl": 3.191828727722168e-05,
+      "eval_loss": 0.12674936652183533,
+      "eval_num_tokens": 991008.0,
+      "eval_reward": 0.125,
+      "eval_reward_std": 0.22886751294136048,
+      "eval_rewards/equation_reward_func": 0.1,
+      "eval_rewards/format_reward_func": 0.025,
+      "eval_runtime": 1337.2162,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 65
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.011743688955903053,
+      "learning_rate": 8e-08,
+      "loss": 0.0575,
+      "step": 70
+    },
+    {
+      "epoch": 2.8,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 865.05,
+      "eval_kl": 3.235936164855957e-05,
+      "eval_loss": 0.022181231528520584,
+      "eval_num_tokens": 1072417.0,
+      "eval_reward": 0.0375,
+      "eval_reward_std": 0.075,
+      "eval_rewards/equation_reward_func": 0.025,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1336.7662,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 70
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.012797041796147823,
+      "learning_rate": 1.3333333333333334e-08,
+      "loss": 0.0873,
+      "step": 75
+    },
+    {
+      "epoch": 3.0,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 838.275,
+      "eval_kl": 3.303289413452149e-05,
+      "eval_loss": 0.026845881715416908,
+      "eval_num_tokens": 1151449.0,
+      "eval_reward": 0.1125,
+      "eval_reward_std": 0.15560638308525085,
+      "eval_rewards/equation_reward_func": 0.1,
+      "eval_rewards/format_reward_func": 0.0125,
+      "eval_runtime": 1328.2121,
+      "eval_samples_per_second": 0.015,
+      "eval_steps_per_second": 0.004,
+      "step": 75
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 75,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 15,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8f917de4232cf792f6c0454b1cb6a902bdd376d99901cde7826f8c84dab22e6
+size 6200