Upload 14 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen2-0.5B-Instruct-bnb-4bit
+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 0.12.0

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen2-0.5B-Instruct-bnb-4bit",
+  "bias": "none",
+  "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": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_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:e13e7c01bbb0065436fab16a930fab30f5b0200d39df14e03366299c333328c6
+size 35237104

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:116cbf1e05b3f8acc09fa764d666b8f42ee8dabe723f60077f05b09ee7637f64
+size 18570356

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a9337380b1c8b42f061128687c6d9fabd8433ca045abf799c6e561b561e4621
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c72869181363c7c0dcffb7a71857fd6a7c81a93e70aff2985fc26363295969
+size 1064

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,893 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.254170497832654,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.052541704978326546,
+      "grad_norm": 0.9754809141159058,
+      "learning_rate": 5e-06,
+      "loss": 1.2583,
+      "step": 100
+    },
+    {
+      "epoch": 0.10508340995665309,
+      "grad_norm": 0.6179457902908325,
+      "learning_rate": 1e-05,
+      "loss": 1.0217,
+      "step": 200
+    },
+    {
+      "epoch": 0.15762511493497963,
+      "grad_norm": 0.6895671486854553,
+      "learning_rate": 1.5e-05,
+      "loss": 0.8382,
+      "step": 300
+    },
+    {
+      "epoch": 0.21016681991330619,
+      "grad_norm": 1.0476884841918945,
+      "learning_rate": 2e-05,
+      "loss": 0.7851,
+      "step": 400
+    },
+    {
+      "epoch": 0.2627085248916327,
+      "grad_norm": 0.8948929905891418,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7133,
+      "step": 500
+    },
+    {
+      "epoch": 0.2627085248916327,
+      "eval_loss": 0.6265314221382141,
+      "eval_runtime": 1.2508,
+      "eval_samples_per_second": 7.995,
+      "eval_steps_per_second": 3.997,
+      "step": 500
+    },
+    {
+      "epoch": 0.31525022986995926,
+      "grad_norm": 1.1585056781768799,
+      "learning_rate": 3e-05,
+      "loss": 0.6821,
+      "step": 600
+    },
+    {
+      "epoch": 0.3677919348482858,
+      "grad_norm": 0.838334321975708,
+      "learning_rate": 3.5e-05,
+      "loss": 0.6574,
+      "step": 700
+    },
+    {
+      "epoch": 0.42033363982661237,
+      "grad_norm": 1.056951642036438,
+      "learning_rate": 4e-05,
+      "loss": 0.6456,
+      "step": 800
+    },
+    {
+      "epoch": 0.4728753448049389,
+      "grad_norm": 1.043925404548645,
+      "learning_rate": 4.5e-05,
+      "loss": 0.6396,
+      "step": 900
+    },
+    {
+      "epoch": 0.5254170497832654,
+      "grad_norm": 1.2812925577163696,
+      "learning_rate": 5e-05,
+      "loss": 0.6351,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5254170497832654,
+      "eval_loss": 0.5569401979446411,
+      "eval_runtime": 1.2148,
+      "eval_samples_per_second": 8.232,
+      "eval_steps_per_second": 4.116,
+      "step": 1000
+    },
+    {
+      "epoch": 0.577958754761592,
+      "grad_norm": 1.3376405239105225,
+      "learning_rate": 4.9444444444444446e-05,
+      "loss": 0.6051,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6305004597399185,
+      "grad_norm": 1.3639925718307495,
+      "learning_rate": 4.888888888888889e-05,
+      "loss": 0.6182,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6830421647182451,
+      "grad_norm": 1.4436575174331665,
+      "learning_rate": 4.8333333333333334e-05,
+      "loss": 0.6145,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7355838696965716,
+      "grad_norm": 2.0778963565826416,
+      "learning_rate": 4.7777777777777784e-05,
+      "loss": 0.5879,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7881255746748982,
+      "grad_norm": 1.6049619913101196,
+      "learning_rate": 4.722222222222222e-05,
+      "loss": 0.5851,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7881255746748982,
+      "eval_loss": 0.5357321500778198,
+      "eval_runtime": 1.2208,
+      "eval_samples_per_second": 8.192,
+      "eval_steps_per_second": 4.096,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8406672796532247,
+      "grad_norm": 1.5120118856430054,
+      "learning_rate": 4.666666666666667e-05,
+      "loss": 0.5693,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8932089846315513,
+      "grad_norm": 3.5921452045440674,
+      "learning_rate": 4.6111111111111115e-05,
+      "loss": 0.579,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9457506896098778,
+      "grad_norm": 0.9748013615608215,
+      "learning_rate": 4.555555555555556e-05,
+      "loss": 0.5686,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9982923945882044,
+      "grad_norm": 0.8585628271102905,
+      "learning_rate": 4.5e-05,
+      "loss": 0.5688,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0508340995665308,
+      "grad_norm": 3.2674453258514404,
+      "learning_rate": 4.4444444444444447e-05,
+      "loss": 0.5521,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0508340995665308,
+      "eval_loss": 0.5279057621955872,
+      "eval_runtime": 1.2064,
+      "eval_samples_per_second": 8.289,
+      "eval_steps_per_second": 4.145,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1033758045448574,
+      "grad_norm": 1.5048810243606567,
+      "learning_rate": 4.388888888888889e-05,
+      "loss": 0.5315,
+      "step": 2100
+    },
+    {
+      "epoch": 1.155917509523184,
+      "grad_norm": 1.1342097520828247,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.53,
+      "step": 2200
+    },
+    {
+      "epoch": 1.2084592145015105,
+      "grad_norm": 1.418641448020935,
+      "learning_rate": 4.277777777777778e-05,
+      "loss": 0.5345,
+      "step": 2300
+    },
+    {
+      "epoch": 1.261000919479837,
+      "grad_norm": 1.1525490283966064,
+      "learning_rate": 4.222222222222222e-05,
+      "loss": 0.5364,
+      "step": 2400
+    },
+    {
+      "epoch": 1.3135426244581636,
+      "grad_norm": 1.1001209020614624,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 0.5365,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3135426244581636,
+      "eval_loss": 0.5235944986343384,
+      "eval_runtime": 1.2217,
+      "eval_samples_per_second": 8.186,
+      "eval_steps_per_second": 4.093,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3660843294364902,
+      "grad_norm": 1.8745806217193604,
+      "learning_rate": 4.111111111111111e-05,
+      "loss": 0.5228,
+      "step": 2600
+    },
+    {
+      "epoch": 1.4186260344148167,
+      "grad_norm": 1.1493146419525146,
+      "learning_rate": 4.055555555555556e-05,
+      "loss": 0.5244,
+      "step": 2700
+    },
+    {
+      "epoch": 1.4711677393931433,
+      "grad_norm": 2.0443015098571777,
+      "learning_rate": 4e-05,
+      "loss": 0.5321,
+      "step": 2800
+    },
+    {
+      "epoch": 1.5237094443714698,
+      "grad_norm": 2.053090810775757,
+      "learning_rate": 3.944444444444445e-05,
+      "loss": 0.5221,
+      "step": 2900
+    },
+    {
+      "epoch": 1.5762511493497964,
+      "grad_norm": 2.0530471801757812,
+      "learning_rate": 3.888888888888889e-05,
+      "loss": 0.5192,
+      "step": 3000
+    },
+    {
+      "epoch": 1.5762511493497964,
+      "eval_loss": 0.5113556981086731,
+      "eval_runtime": 1.221,
+      "eval_samples_per_second": 8.19,
+      "eval_steps_per_second": 4.095,
+      "step": 3000
+    },
+    {
+      "epoch": 1.628792854328123,
+      "grad_norm": 1.469416856765747,
+      "learning_rate": 3.8333333333333334e-05,
+      "loss": 0.5312,
+      "step": 3100
+    },
+    {
+      "epoch": 1.6813345593064495,
+      "grad_norm": 2.854994535446167,
+      "learning_rate": 3.777777777777778e-05,
+      "loss": 0.5223,
+      "step": 3200
+    },
+    {
+      "epoch": 1.733876264284776,
+      "grad_norm": 1.2286680936813354,
+      "learning_rate": 3.722222222222222e-05,
+      "loss": 0.5235,
+      "step": 3300
+    },
+    {
+      "epoch": 1.7864179692631026,
+      "grad_norm": 1.3007181882858276,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.5086,
+      "step": 3400
+    },
+    {
+      "epoch": 1.8389596742414291,
+      "grad_norm": 2.007951498031616,
+      "learning_rate": 3.611111111111111e-05,
+      "loss": 0.5241,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8389596742414291,
+      "eval_loss": 0.5189292430877686,
+      "eval_runtime": 1.2074,
+      "eval_samples_per_second": 8.282,
+      "eval_steps_per_second": 4.141,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8915013792197557,
+      "grad_norm": 1.0643136501312256,
+      "learning_rate": 3.555555555555556e-05,
+      "loss": 0.504,
+      "step": 3600
+    },
+    {
+      "epoch": 1.9440430841980822,
+      "grad_norm": 1.4835437536239624,
+      "learning_rate": 3.5e-05,
+      "loss": 0.5161,
+      "step": 3700
+    },
+    {
+      "epoch": 1.9965847891764088,
+      "grad_norm": 1.4298534393310547,
+      "learning_rate": 3.444444444444445e-05,
+      "loss": 0.5095,
+      "step": 3800
+    },
+    {
+      "epoch": 2.049126494154735,
+      "grad_norm": 1.0783276557922363,
+      "learning_rate": 3.388888888888889e-05,
+      "loss": 0.4978,
+      "step": 3900
+    },
+    {
+      "epoch": 2.1016681991330617,
+      "grad_norm": 2.3203086853027344,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 0.4854,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1016681991330617,
+      "eval_loss": 0.5047374963760376,
+      "eval_runtime": 1.2234,
+      "eval_samples_per_second": 8.174,
+      "eval_steps_per_second": 4.087,
+      "step": 4000
+    },
+    {
+      "epoch": 2.1542099041113882,
+      "grad_norm": 1.2583634853363037,
+      "learning_rate": 3.277777777777778e-05,
+      "loss": 0.4934,
+      "step": 4100
+    },
+    {
+      "epoch": 2.206751609089715,
+      "grad_norm": 2.2736079692840576,
+      "learning_rate": 3.222222222222223e-05,
+      "loss": 0.4895,
+      "step": 4200
+    },
+    {
+      "epoch": 2.2592933140680413,
+      "grad_norm": 2.931607484817505,
+      "learning_rate": 3.1666666666666666e-05,
+      "loss": 0.489,
+      "step": 4300
+    },
+    {
+      "epoch": 2.311835019046368,
+      "grad_norm": 1.2253628969192505,
+      "learning_rate": 3.111111111111111e-05,
+      "loss": 0.4868,
+      "step": 4400
+    },
+    {
+      "epoch": 2.3643767240246945,
+      "grad_norm": 1.2433133125305176,
+      "learning_rate": 3.055555555555556e-05,
+      "loss": 0.4926,
+      "step": 4500
+    },
+    {
+      "epoch": 2.3643767240246945,
+      "eval_loss": 0.5110575556755066,
+      "eval_runtime": 1.2952,
+      "eval_samples_per_second": 7.721,
+      "eval_steps_per_second": 3.86,
+      "step": 4500
+    },
+    {
+      "epoch": 2.416918429003021,
+      "grad_norm": 1.1074525117874146,
+      "learning_rate": 3e-05,
+      "loss": 0.4918,
+      "step": 4600
+    },
+    {
+      "epoch": 2.4694601339813476,
+      "grad_norm": 1.3761866092681885,
+      "learning_rate": 2.9444444444444448e-05,
+      "loss": 0.4915,
+      "step": 4700
+    },
+    {
+      "epoch": 2.522001838959674,
+      "grad_norm": 2.135338068008423,
+      "learning_rate": 2.8888888888888888e-05,
+      "loss": 0.483,
+      "step": 4800
+    },
+    {
+      "epoch": 2.5745435439380007,
+      "grad_norm": 1.0095371007919312,
+      "learning_rate": 2.8333333333333335e-05,
+      "loss": 0.4918,
+      "step": 4900
+    },
+    {
+      "epoch": 2.627085248916327,
+      "grad_norm": 0.9606950879096985,
+      "learning_rate": 2.777777777777778e-05,
+      "loss": 0.486,
+      "step": 5000
+    },
+    {
+      "epoch": 2.627085248916327,
+      "eval_loss": 0.5079401731491089,
+      "eval_runtime": 1.2665,
+      "eval_samples_per_second": 7.896,
+      "eval_steps_per_second": 3.948,
+      "step": 5000
+    },
+    {
+      "epoch": 2.6796269538946538,
+      "grad_norm": 1.0660576820373535,
+      "learning_rate": 2.7222222222222223e-05,
+      "loss": 0.4922,
+      "step": 5100
+    },
+    {
+      "epoch": 2.7321686588729803,
+      "grad_norm": 2.1245779991149902,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 0.4933,
+      "step": 5200
+    },
+    {
+      "epoch": 2.784710363851307,
+      "grad_norm": 1.7832878828048706,
+      "learning_rate": 2.6111111111111114e-05,
+      "loss": 0.4794,
+      "step": 5300
+    },
+    {
+      "epoch": 2.8372520688296334,
+      "grad_norm": 2.381094455718994,
+      "learning_rate": 2.5555555555555554e-05,
+      "loss": 0.4852,
+      "step": 5400
+    },
+    {
+      "epoch": 2.88979377380796,
+      "grad_norm": 1.01780104637146,
+      "learning_rate": 2.5e-05,
+      "loss": 0.4775,
+      "step": 5500
+    },
+    {
+      "epoch": 2.88979377380796,
+      "eval_loss": 0.49784645438194275,
+      "eval_runtime": 1.2033,
+      "eval_samples_per_second": 8.31,
+      "eval_steps_per_second": 4.155,
+      "step": 5500
+    },
+    {
+      "epoch": 2.9423354787862865,
+      "grad_norm": 2.5046234130859375,
+      "learning_rate": 2.4444444444444445e-05,
+      "loss": 0.4786,
+      "step": 5600
+    },
+    {
+      "epoch": 2.994877183764613,
+      "grad_norm": 2.6457679271698,
+      "learning_rate": 2.3888888888888892e-05,
+      "loss": 0.479,
+      "step": 5700
+    },
+    {
+      "epoch": 3.0474188887429396,
+      "grad_norm": 1.8499191999435425,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.4741,
+      "step": 5800
+    },
+    {
+      "epoch": 3.099960593721266,
+      "grad_norm": 1.0821927785873413,
+      "learning_rate": 2.277777777777778e-05,
+      "loss": 0.4647,
+      "step": 5900
+    },
+    {
+      "epoch": 3.1525022986995928,
+      "grad_norm": 1.5793670415878296,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 0.483,
+      "step": 6000
+    },
+    {
+      "epoch": 3.1525022986995928,
+      "eval_loss": 0.49618691205978394,
+      "eval_runtime": 1.2172,
+      "eval_samples_per_second": 8.216,
+      "eval_steps_per_second": 4.108,
+      "step": 6000
+    },
+    {
+      "epoch": 3.2050440036779193,
+      "grad_norm": 1.7674349546432495,
+      "learning_rate": 2.1666666666666667e-05,
+      "loss": 0.4682,
+      "step": 6100
+    },
+    {
+      "epoch": 3.257585708656246,
+      "grad_norm": 1.8406447172164917,
+      "learning_rate": 2.111111111111111e-05,
+      "loss": 0.4658,
+      "step": 6200
+    },
+    {
+      "epoch": 3.3101274136345724,
+      "grad_norm": 1.0926892757415771,
+      "learning_rate": 2.0555555555555555e-05,
+      "loss": 0.4676,
+      "step": 6300
+    },
+    {
+      "epoch": 3.362669118612899,
+      "grad_norm": 2.300992488861084,
+      "learning_rate": 2e-05,
+      "loss": 0.4595,
+      "step": 6400
+    },
+    {
+      "epoch": 3.4152108235912255,
+      "grad_norm": 1.148647665977478,
+      "learning_rate": 1.9444444444444445e-05,
+      "loss": 0.4674,
+      "step": 6500
+    },
+    {
+      "epoch": 3.4152108235912255,
+      "eval_loss": 0.4925019145011902,
+      "eval_runtime": 1.2002,
+      "eval_samples_per_second": 8.332,
+      "eval_steps_per_second": 4.166,
+      "step": 6500
+    },
+    {
+      "epoch": 3.467752528569552,
+      "grad_norm": 1.1826932430267334,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.4563,
+      "step": 6600
+    },
+    {
+      "epoch": 3.5202942335478786,
+      "grad_norm": 1.0678240060806274,
+      "learning_rate": 1.8333333333333333e-05,
+      "loss": 0.47,
+      "step": 6700
+    },
+    {
+      "epoch": 3.572835938526205,
+      "grad_norm": 2.3626327514648438,
+      "learning_rate": 1.777777777777778e-05,
+      "loss": 0.4563,
+      "step": 6800
+    },
+    {
+      "epoch": 3.6253776435045317,
+      "grad_norm": 1.1958198547363281,
+      "learning_rate": 1.7222222222222224e-05,
+      "loss": 0.4621,
+      "step": 6900
+    },
+    {
+      "epoch": 3.6779193484828583,
+      "grad_norm": 1.61029052734375,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.4629,
+      "step": 7000
+    },
+    {
+      "epoch": 3.6779193484828583,
+      "eval_loss": 0.4930470585823059,
+      "eval_runtime": 1.2074,
+      "eval_samples_per_second": 8.282,
+      "eval_steps_per_second": 4.141,
+      "step": 7000
+    },
+    {
+      "epoch": 3.730461053461185,
+      "grad_norm": 1.0514099597930908,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 0.467,
+      "step": 7100
+    },
+    {
+      "epoch": 3.7830027584395114,
+      "grad_norm": 1.5292298793792725,
+      "learning_rate": 1.5555555555555555e-05,
+      "loss": 0.4657,
+      "step": 7200
+    },
+    {
+      "epoch": 3.835544463417838,
+      "grad_norm": 1.8738545179367065,
+      "learning_rate": 1.5e-05,
+      "loss": 0.4741,
+      "step": 7300
+    },
+    {
+      "epoch": 3.8880861683961645,
+      "grad_norm": 1.5150409936904907,
+      "learning_rate": 1.4444444444444444e-05,
+      "loss": 0.4598,
+      "step": 7400
+    },
+    {
+      "epoch": 3.940627873374491,
+      "grad_norm": 1.3109909296035767,
+      "learning_rate": 1.388888888888889e-05,
+      "loss": 0.4682,
+      "step": 7500
+    },
+    {
+      "epoch": 3.940627873374491,
+      "eval_loss": 0.49467793107032776,
+      "eval_runtime": 1.241,
+      "eval_samples_per_second": 8.058,
+      "eval_steps_per_second": 4.029,
+      "step": 7500
+    },
+    {
+      "epoch": 3.9931695783528176,
+      "grad_norm": 1.4036318063735962,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.4652,
+      "step": 7600
+    },
+    {
+      "epoch": 4.045711283331144,
+      "grad_norm": 1.308784008026123,
+      "learning_rate": 1.2777777777777777e-05,
+      "loss": 0.4535,
+      "step": 7700
+    },
+    {
+      "epoch": 4.09825298830947,
+      "grad_norm": 1.1499841213226318,
+      "learning_rate": 1.2222222222222222e-05,
+      "loss": 0.4554,
+      "step": 7800
+    },
+    {
+      "epoch": 4.150794693287797,
+      "grad_norm": 1.1128175258636475,
+      "learning_rate": 1.1666666666666668e-05,
+      "loss": 0.4574,
+      "step": 7900
+    },
+    {
+      "epoch": 4.203336398266123,
+      "grad_norm": 1.2397664785385132,
+      "learning_rate": 1.1111111111111112e-05,
+      "loss": 0.4456,
+      "step": 8000
+    },
+    {
+      "epoch": 4.203336398266123,
+      "eval_loss": 0.49332427978515625,
+      "eval_runtime": 1.2363,
+      "eval_samples_per_second": 8.089,
+      "eval_steps_per_second": 4.044,
+      "step": 8000
+    },
+    {
+      "epoch": 4.25587810324445,
+      "grad_norm": 1.3388928174972534,
+      "learning_rate": 1.0555555555555555e-05,
+      "loss": 0.4619,
+      "step": 8100
+    },
+    {
+      "epoch": 4.3084198082227765,
+      "grad_norm": 0.97515869140625,
+      "learning_rate": 1e-05,
+      "loss": 0.4623,
+      "step": 8200
+    },
+    {
+      "epoch": 4.3609615132011035,
+      "grad_norm": 1.0904083251953125,
+      "learning_rate": 9.444444444444445e-06,
+      "loss": 0.4456,
+      "step": 8300
+    },
+    {
+      "epoch": 4.41350321817943,
+      "grad_norm": 1.3429654836654663,
+      "learning_rate": 8.88888888888889e-06,
+      "loss": 0.4501,
+      "step": 8400
+    },
+    {
+      "epoch": 4.466044923157757,
+      "grad_norm": 1.919039249420166,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.4486,
+      "step": 8500
+    },
+    {
+      "epoch": 4.466044923157757,
+      "eval_loss": 0.4914402365684509,
+      "eval_runtime": 1.2335,
+      "eval_samples_per_second": 8.107,
+      "eval_steps_per_second": 4.053,
+      "step": 8500
+    },
+    {
+      "epoch": 4.518586628136083,
+      "grad_norm": 2.0423989295959473,
+      "learning_rate": 7.777777777777777e-06,
+      "loss": 0.4571,
+      "step": 8600
+    },
+    {
+      "epoch": 4.57112833311441,
+      "grad_norm": 1.3525835275650024,
+      "learning_rate": 7.222222222222222e-06,
+      "loss": 0.46,
+      "step": 8700
+    },
+    {
+      "epoch": 4.623670038092736,
+      "grad_norm": 1.1251217126846313,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.4522,
+      "step": 8800
+    },
+    {
+      "epoch": 4.676211743071063,
+      "grad_norm": 1.8645511865615845,
+      "learning_rate": 6.111111111111111e-06,
+      "loss": 0.4605,
+      "step": 8900
+    },
+    {
+      "epoch": 4.728753448049389,
+      "grad_norm": 1.1539450883865356,
+      "learning_rate": 5.555555555555556e-06,
+      "loss": 0.4544,
+      "step": 9000
+    },
+    {
+      "epoch": 4.728753448049389,
+      "eval_loss": 0.490975946187973,
+      "eval_runtime": 1.2066,
+      "eval_samples_per_second": 8.288,
+      "eval_steps_per_second": 4.144,
+      "step": 9000
+    },
+    {
+      "epoch": 4.781295153027716,
+      "grad_norm": 1.1662914752960205,
+      "learning_rate": 5e-06,
+      "loss": 0.4521,
+      "step": 9100
+    },
+    {
+      "epoch": 4.833836858006042,
+      "grad_norm": 0.9396342635154724,
+      "learning_rate": 4.444444444444445e-06,
+      "loss": 0.4643,
+      "step": 9200
+    },
+    {
+      "epoch": 4.886378562984369,
+      "grad_norm": 2.0316038131713867,
+      "learning_rate": 3.888888888888889e-06,
+      "loss": 0.4632,
+      "step": 9300
+    },
+    {
+      "epoch": 4.938920267962695,
+      "grad_norm": 1.1537178754806519,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.442,
+      "step": 9400
+    },
+    {
+      "epoch": 4.991461972941022,
+      "grad_norm": 1.3441674709320068,
+      "learning_rate": 2.777777777777778e-06,
+      "loss": 0.4531,
+      "step": 9500
+    },
+    {
+      "epoch": 4.991461972941022,
+      "eval_loss": 0.4903333783149719,
+      "eval_runtime": 1.2203,
+      "eval_samples_per_second": 8.194,
+      "eval_steps_per_second": 4.097,
+      "step": 9500
+    },
+    {
+      "epoch": 5.044003677919348,
+      "grad_norm": 1.1727863550186157,
+      "learning_rate": 2.2222222222222225e-06,
+      "loss": 0.4564,
+      "step": 9600
+    },
+    {
+      "epoch": 5.096545382897675,
+      "grad_norm": 1.2154302597045898,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 0.4369,
+      "step": 9700
+    },
+    {
+      "epoch": 5.149087087876001,
+      "grad_norm": 0.9445755481719971,
+      "learning_rate": 1.1111111111111112e-06,
+      "loss": 0.4377,
+      "step": 9800
+    },
+    {
+      "epoch": 5.201628792854328,
+      "grad_norm": 1.6093214750289917,
+      "learning_rate": 5.555555555555556e-07,
+      "loss": 0.4503,
+      "step": 9900
+    },
+    {
+      "epoch": 5.254170497832654,
+      "grad_norm": 1.092114806175232,
+      "learning_rate": 0.0,
+      "loss": 0.4549,
+      "step": 10000
+    },
+    {
+      "epoch": 5.254170497832654,
+      "eval_loss": 0.4912105202674866,
+      "eval_runtime": 1.2188,
+      "eval_samples_per_second": 8.205,
+      "eval_steps_per_second": 4.102,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7932422620461716e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3670591dadcbf08a87189430baf1a9dac306ea8c533347bfe97613950a48a389
+size 5304