Upload 8 files

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: deepseek-ai/deepseek-coder-1.3b-instruct
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.8.2

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/deepseek-coder-1.3b-instruct",
+  "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": 64,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "k_proj",
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85d76515933dc1c2cf8c456683fd689f123391051f239aa831d1f80056c06d17
+size 119975656

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d611c340e44ffb28d62426aa8860899647ba50ba0e4539c8c093901bf438cb01
+size 60477396

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443d056a0d0d4af964fa502e780199ba62f1a3c8f25e36674b083e90a89ba1ed
+size 14180

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed1d5b6062c3d2bcc942c3f308d7b1a16daae090511b1b21687f3981fca553e4
+size 1064

trainer_state.json

@@ -0,0 +1,1053 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.581755593803787,
+  "eval_steps": 500,
+  "global_step": 12000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.281562089920044,
+      "learning_rate": 4e-05,
+      "loss": 0.5044,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.3552560806274414,
+      "learning_rate": 8e-05,
+      "loss": 0.4867,
+      "step": 200
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.8318453431129456,
+      "learning_rate": 0.00012,
+      "loss": 0.4359,
+      "step": 300
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 1.3478361368179321,
+      "learning_rate": 0.00016,
+      "loss": 0.4475,
+      "step": 400
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.1437219381332397,
+      "learning_rate": 0.0002,
+      "loss": 0.4524,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 0.3725915253162384,
+      "eval_runtime": 90.4733,
+      "eval_samples_per_second": 11.053,
+      "eval_steps_per_second": 2.763,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.8374431133270264,
+      "learning_rate": 0.00019897435897435898,
+      "loss": 0.4569,
+      "step": 600
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.6386727094650269,
+      "learning_rate": 0.00019794871794871796,
+      "loss": 0.4584,
+      "step": 700
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.4089267253875732,
+      "learning_rate": 0.00019692307692307696,
+      "loss": 0.4625,
+      "step": 800
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.269509792327881,
+      "learning_rate": 0.0001958974358974359,
+      "loss": 0.464,
+      "step": 900
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.0896354913711548,
+      "learning_rate": 0.00019487179487179487,
+      "loss": 0.4807,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.3314511179924011,
+      "eval_runtime": 90.3867,
+      "eval_samples_per_second": 11.064,
+      "eval_steps_per_second": 2.766,
+      "step": 1000
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.0933148860931396,
+      "learning_rate": 0.00019384615384615385,
+      "loss": 0.4032,
+      "step": 1100
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.555145740509033,
+      "learning_rate": 0.00019282051282051282,
+      "loss": 0.4353,
+      "step": 1200
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.245523452758789,
+      "learning_rate": 0.00019179487179487182,
+      "loss": 0.409,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.084887981414795,
+      "learning_rate": 0.0001907692307692308,
+      "loss": 0.4214,
+      "step": 1400
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.2279912233352661,
+      "learning_rate": 0.00018974358974358974,
+      "loss": 0.4507,
+      "step": 1500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.312484472990036,
+      "eval_runtime": 90.4149,
+      "eval_samples_per_second": 11.06,
+      "eval_steps_per_second": 2.765,
+      "step": 1500
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.321805477142334,
+      "learning_rate": 0.0001887179487179487,
+      "loss": 0.4523,
+      "step": 1600
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.376891016960144,
+      "learning_rate": 0.0001876923076923077,
+      "loss": 0.441,
+      "step": 1700
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 2.077620267868042,
+      "learning_rate": 0.0001866666666666667,
+      "loss": 0.4392,
+      "step": 1800
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.546964168548584,
+      "learning_rate": 0.00018564102564102566,
+      "loss": 0.4749,
+      "step": 1900
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 2.035524845123291,
+      "learning_rate": 0.00018461538461538463,
+      "loss": 0.4116,
+      "step": 2000
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 0.2960582375526428,
+      "eval_runtime": 90.8091,
+      "eval_samples_per_second": 11.012,
+      "eval_steps_per_second": 2.753,
+      "step": 2000
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 1.3167320489883423,
+      "learning_rate": 0.00018358974358974358,
+      "loss": 0.4135,
+      "step": 2100
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 2.908482074737549,
+      "learning_rate": 0.00018256410256410258,
+      "loss": 0.4092,
+      "step": 2200
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 2.8161234855651855,
+      "learning_rate": 0.00018153846153846155,
+      "loss": 0.4364,
+      "step": 2300
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 1.0435675382614136,
+      "learning_rate": 0.00018051282051282052,
+      "loss": 0.4258,
+      "step": 2400
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 0.7152374982833862,
+      "learning_rate": 0.0001794871794871795,
+      "loss": 0.4208,
+      "step": 2500
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.3006269633769989,
+      "eval_runtime": 90.5246,
+      "eval_samples_per_second": 11.047,
+      "eval_steps_per_second": 2.762,
+      "step": 2500
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.79283607006073,
+      "learning_rate": 0.00017846153846153847,
+      "loss": 0.4209,
+      "step": 2600
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 1.5817480087280273,
+      "learning_rate": 0.00017743589743589744,
+      "loss": 0.415,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.306807279586792,
+      "learning_rate": 0.00017641025641025642,
+      "loss": 0.4231,
+      "step": 2800
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 1.0432254076004028,
+      "learning_rate": 0.0001753846153846154,
+      "loss": 0.38,
+      "step": 2900
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 1.0641353130340576,
+      "learning_rate": 0.00017435897435897436,
+      "loss": 0.4671,
+      "step": 3000
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 0.3091895282268524,
+      "eval_runtime": 90.8377,
+      "eval_samples_per_second": 11.009,
+      "eval_steps_per_second": 2.752,
+      "step": 3000
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 2.6519484519958496,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 0.4148,
+      "step": 3100
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.851606547832489,
+      "learning_rate": 0.00017230769230769234,
+      "loss": 0.37,
+      "step": 3200
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 1.1799293756484985,
+      "learning_rate": 0.0001712923076923077,
+      "loss": 0.3687,
+      "step": 3300
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 1.2787513732910156,
+      "learning_rate": 0.0001702666666666667,
+      "loss": 0.3997,
+      "step": 3400
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.2793489694595337,
+      "learning_rate": 0.00016924102564102564,
+      "loss": 0.3936,
+      "step": 3500
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.2866547703742981,
+      "eval_runtime": 90.8477,
+      "eval_samples_per_second": 11.007,
+      "eval_steps_per_second": 2.752,
+      "step": 3500
+    },
+    {
+      "epoch": 0.77,
+      "grad_norm": 0.7189435362815857,
+      "learning_rate": 0.0001682153846153846,
+      "loss": 0.4191,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.9801158308982849,
+      "learning_rate": 0.0001671897435897436,
+      "loss": 0.3978,
+      "step": 3700
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 1.41176438331604,
+      "learning_rate": 0.0001661641025641026,
+      "loss": 0.3762,
+      "step": 3800
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.9064908027648926,
+      "learning_rate": 0.00016513846153846156,
+      "loss": 0.3746,
+      "step": 3900
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 1.3439726829528809,
+      "learning_rate": 0.00016411282051282053,
+      "loss": 0.3823,
+      "step": 4000
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 0.2893534004688263,
+      "eval_runtime": 90.8714,
+      "eval_samples_per_second": 11.005,
+      "eval_steps_per_second": 2.751,
+      "step": 4000
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 1.6646331548690796,
+      "learning_rate": 0.00016308717948717948,
+      "loss": 0.4029,
+      "step": 4100
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.9874048829078674,
+      "learning_rate": 0.00016206153846153845,
+      "loss": 0.3933,
+      "step": 4200
+    },
+    {
+      "epoch": 0.93,
+      "grad_norm": 1.0010713338851929,
+      "learning_rate": 0.00016103589743589745,
+      "loss": 0.41,
+      "step": 4300
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.9607357978820801,
+      "learning_rate": 0.00016001025641025642,
+      "loss": 0.3659,
+      "step": 4400
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 1.3652217388153076,
+      "learning_rate": 0.0001589846153846154,
+      "loss": 0.3794,
+      "step": 4500
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 0.2667659819126129,
+      "eval_runtime": 90.9201,
+      "eval_samples_per_second": 10.999,
+      "eval_steps_per_second": 2.75,
+      "step": 4500
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 1.056810736656189,
+      "learning_rate": 0.00015795897435897437,
+      "loss": 0.3878,
+      "step": 4600
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 0.7765600085258484,
+      "learning_rate": 0.00015693333333333334,
+      "loss": 0.3396,
+      "step": 4700
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 1.0664465427398682,
+      "learning_rate": 0.00015590769230769232,
+      "loss": 0.2813,
+      "step": 4800
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.6342141628265381,
+      "learning_rate": 0.0001548820512820513,
+      "loss": 0.309,
+      "step": 4900
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 1.1380507946014404,
+      "learning_rate": 0.00015385641025641026,
+      "loss": 0.2888,
+      "step": 5000
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.27630186080932617,
+      "eval_runtime": 90.9762,
+      "eval_samples_per_second": 10.992,
+      "eval_steps_per_second": 2.748,
+      "step": 5000
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 1.6043438911437988,
+      "learning_rate": 0.00015283076923076924,
+      "loss": 0.3836,
+      "step": 5100
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.2961331307888031,
+      "learning_rate": 0.0001518051282051282,
+      "loss": 0.2964,
+      "step": 5200
+    },
+    {
+      "epoch": 1.14,
+      "grad_norm": 1.0106085538864136,
+      "learning_rate": 0.00015077948717948718,
+      "loss": 0.2837,
+      "step": 5300
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 1.2187350988388062,
+      "learning_rate": 0.00014975384615384616,
+      "loss": 0.3093,
+      "step": 5400
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 1.4018324613571167,
+      "learning_rate": 0.00014872820512820513,
+      "loss": 0.3029,
+      "step": 5500
+    },
+    {
+      "epoch": 1.18,
+      "eval_loss": 0.2620677351951599,
+      "eval_runtime": 90.8592,
+      "eval_samples_per_second": 11.006,
+      "eval_steps_per_second": 2.752,
+      "step": 5500
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.8634820580482483,
+      "learning_rate": 0.00014771282051282051,
+      "loss": 0.3046,
+      "step": 5600
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.6309552788734436,
+      "learning_rate": 0.0001466871794871795,
+      "loss": 0.3041,
+      "step": 5700
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2985124588012695,
+      "learning_rate": 0.00014566153846153846,
+      "loss": 0.312,
+      "step": 5800
+    },
+    {
+      "epoch": 1.27,
+      "grad_norm": 0.9580160975456238,
+      "learning_rate": 0.00014463589743589746,
+      "loss": 0.3306,
+      "step": 5900
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 1.0316152572631836,
+      "learning_rate": 0.00014361025641025643,
+      "loss": 0.2979,
+      "step": 6000
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.26443469524383545,
+      "eval_runtime": 90.9026,
+      "eval_samples_per_second": 11.001,
+      "eval_steps_per_second": 2.75,
+      "step": 6000
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 1.9922102689743042,
+      "learning_rate": 0.00014258461538461538,
+      "loss": 0.3105,
+      "step": 6100
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 1.274574875831604,
+      "learning_rate": 0.00014155897435897435,
+      "loss": 0.3174,
+      "step": 6200
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 1.1152174472808838,
+      "learning_rate": 0.00014053333333333335,
+      "loss": 0.3094,
+      "step": 6300
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 1.4428844451904297,
+      "learning_rate": 0.00013950769230769233,
+      "loss": 0.3136,
+      "step": 6400
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 1.418609380722046,
+      "learning_rate": 0.0001384820512820513,
+      "loss": 0.3425,
+      "step": 6500
+    },
+    {
+      "epoch": 1.4,
+      "eval_loss": 0.299164742231369,
+      "eval_runtime": 90.9837,
+      "eval_samples_per_second": 10.991,
+      "eval_steps_per_second": 2.748,
+      "step": 6500
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 1.309278130531311,
+      "learning_rate": 0.00013745641025641027,
+      "loss": 0.3318,
+      "step": 6600
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.0984652042388916,
+      "learning_rate": 0.00013643076923076922,
+      "loss": 0.3221,
+      "step": 6700
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 1.1776598691940308,
+      "learning_rate": 0.00013540512820512822,
+      "loss": 0.3151,
+      "step": 6800
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 1.1536751985549927,
+      "learning_rate": 0.0001343794871794872,
+      "loss": 0.3471,
+      "step": 6900
+    },
+    {
+      "epoch": 1.51,
+      "grad_norm": 1.5731265544891357,
+      "learning_rate": 0.00013335384615384616,
+      "loss": 0.3342,
+      "step": 7000
+    },
+    {
+      "epoch": 1.51,
+      "eval_loss": 0.25467580556869507,
+      "eval_runtime": 90.9083,
+      "eval_samples_per_second": 11.0,
+      "eval_steps_per_second": 2.75,
+      "step": 7000
+    },
+    {
+      "epoch": 1.53,
+      "grad_norm": 1.5424981117248535,
+      "learning_rate": 0.00013233846153846155,
+      "loss": 0.3337,
+      "step": 7100
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 1.2443273067474365,
+      "learning_rate": 0.00013131282051282052,
+      "loss": 0.2955,
+      "step": 7200
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.7886701822280884,
+      "learning_rate": 0.0001302871794871795,
+      "loss": 0.3017,
+      "step": 7300
+    },
+    {
+      "epoch": 1.59,
+      "grad_norm": 1.6013621091842651,
+      "learning_rate": 0.00012926153846153847,
+      "loss": 0.2976,
+      "step": 7400
+    },
+    {
+      "epoch": 1.61,
+      "grad_norm": 1.495753288269043,
+      "learning_rate": 0.00012823589743589744,
+      "loss": 0.3086,
+      "step": 7500
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.25845155119895935,
+      "eval_runtime": 90.8943,
+      "eval_samples_per_second": 11.002,
+      "eval_steps_per_second": 2.75,
+      "step": 7500
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 1.181015968322754,
+      "learning_rate": 0.00012721025641025641,
+      "loss": 0.2657,
+      "step": 7600
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 1.2074403762817383,
+      "learning_rate": 0.0001261846153846154,
+      "loss": 0.3149,
+      "step": 7700
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 1.216676950454712,
+      "learning_rate": 0.00012515897435897436,
+      "loss": 0.2999,
+      "step": 7800
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 1.8093730211257935,
+      "learning_rate": 0.00012413333333333333,
+      "loss": 0.3144,
+      "step": 7900
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 3.7325637340545654,
+      "learning_rate": 0.00012310769230769233,
+      "loss": 0.3326,
+      "step": 8000
+    },
+    {
+      "epoch": 1.72,
+      "eval_loss": 0.23783066868782043,
+      "eval_runtime": 90.8877,
+      "eval_samples_per_second": 11.003,
+      "eval_steps_per_second": 2.751,
+      "step": 8000
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 0.6969020366668701,
+      "learning_rate": 0.00012208205128205128,
+      "loss": 0.2935,
+      "step": 8100
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 2.1927125453948975,
+      "learning_rate": 0.00012105641025641025,
+      "loss": 0.3091,
+      "step": 8200
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 1.8521186113357544,
+      "learning_rate": 0.00012003076923076924,
+      "loss": 0.2517,
+      "step": 8300
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 1.5349504947662354,
+      "learning_rate": 0.00011900512820512821,
+      "loss": 0.2794,
+      "step": 8400
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.6325456500053406,
+      "learning_rate": 0.00011797948717948718,
+      "loss": 0.2912,
+      "step": 8500
+    },
+    {
+      "epoch": 1.83,
+      "eval_loss": 0.23375801742076874,
+      "eval_runtime": 90.8478,
+      "eval_samples_per_second": 11.007,
+      "eval_steps_per_second": 2.752,
+      "step": 8500
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 1.615515112876892,
+      "learning_rate": 0.00011695384615384617,
+      "loss": 0.2953,
+      "step": 8600
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 1.2424674034118652,
+      "learning_rate": 0.00011592820512820513,
+      "loss": 0.3047,
+      "step": 8700
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 1.2125675678253174,
+      "learning_rate": 0.0001149025641025641,
+      "loss": 0.3209,
+      "step": 8800
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 1.6464908123016357,
+      "learning_rate": 0.00011387692307692308,
+      "loss": 0.3214,
+      "step": 8900
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 1.300310730934143,
+      "learning_rate": 0.00011285128205128206,
+      "loss": 0.2965,
+      "step": 9000
+    },
+    {
+      "epoch": 1.94,
+      "eval_loss": 0.2334287166595459,
+      "eval_runtime": 90.9451,
+      "eval_samples_per_second": 10.996,
+      "eval_steps_per_second": 2.749,
+      "step": 9000
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 1.7211843729019165,
+      "learning_rate": 0.00011182564102564104,
+      "loss": 0.2813,
+      "step": 9100
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.5777404308319092,
+      "learning_rate": 0.00011080000000000001,
+      "loss": 0.2951,
+      "step": 9200
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.3048077821731567,
+      "learning_rate": 0.00010977435897435897,
+      "loss": 0.301,
+      "step": 9300
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 1.1753878593444824,
+      "learning_rate": 0.00010874871794871794,
+      "loss": 0.1944,
+      "step": 9400
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.8378590941429138,
+      "learning_rate": 0.00010772307692307693,
+      "loss": 0.2041,
+      "step": 9500
+    },
+    {
+      "epoch": 2.04,
+      "eval_loss": 0.2733120024204254,
+      "eval_runtime": 90.9249,
+      "eval_samples_per_second": 10.998,
+      "eval_steps_per_second": 2.75,
+      "step": 9500
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 1.4123268127441406,
+      "learning_rate": 0.0001066974358974359,
+      "loss": 0.2206,
+      "step": 9600
+    },
+    {
+      "epoch": 2.09,
+      "grad_norm": 1.5923714637756348,
+      "learning_rate": 0.00010567179487179489,
+      "loss": 0.2331,
+      "step": 9700
+    },
+    {
+      "epoch": 2.11,
+      "grad_norm": 2.31000018119812,
+      "learning_rate": 0.00010465641025641026,
+      "loss": 0.2564,
+      "step": 9800
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 1.4770272970199585,
+      "learning_rate": 0.00010363076923076925,
+      "loss": 0.2009,
+      "step": 9900
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 1.5393586158752441,
+      "learning_rate": 0.00010260512820512822,
+      "loss": 0.2168,
+      "step": 10000
+    },
+    {
+      "epoch": 2.15,
+      "eval_loss": 0.24773281812667847,
+      "eval_runtime": 90.901,
+      "eval_samples_per_second": 11.001,
+      "eval_steps_per_second": 2.75,
+      "step": 10000
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 2.3399605751037598,
+      "learning_rate": 0.00010157948717948718,
+      "loss": 0.2275,
+      "step": 10100
+    },
+    {
+      "epoch": 2.19,
+      "grad_norm": 1.417143702507019,
+      "learning_rate": 0.00010055384615384615,
+      "loss": 0.2093,
+      "step": 10200
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 1.7041810750961304,
+      "learning_rate": 9.952820512820513e-05,
+      "loss": 0.2105,
+      "step": 10300
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 3.7192060947418213,
+      "learning_rate": 9.850256410256411e-05,
+      "loss": 0.2078,
+      "step": 10400
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.7868184447288513,
+      "learning_rate": 9.747692307692307e-05,
+      "loss": 0.2058,
+      "step": 10500
+    },
+    {
+      "epoch": 2.26,
+      "eval_loss": 0.22978341579437256,
+      "eval_runtime": 90.9187,
+      "eval_samples_per_second": 10.999,
+      "eval_steps_per_second": 2.75,
+      "step": 10500
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 2.572187662124634,
+      "learning_rate": 9.645128205128206e-05,
+      "loss": 0.2304,
+      "step": 10600
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 1.3671247959136963,
+      "learning_rate": 9.542564102564103e-05,
+      "loss": 0.1962,
+      "step": 10700
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 2.6237735748291016,
+      "learning_rate": 9.44e-05,
+      "loss": 0.2201,
+      "step": 10800
+    },
+    {
+      "epoch": 2.35,
+      "grad_norm": 1.1776219606399536,
+      "learning_rate": 9.337435897435898e-05,
+      "loss": 0.1972,
+      "step": 10900
+    },
+    {
+      "epoch": 2.37,
+      "grad_norm": 1.236425757408142,
+      "learning_rate": 9.234871794871795e-05,
+      "loss": 0.2126,
+      "step": 11000
+    },
+    {
+      "epoch": 2.37,
+      "eval_loss": 0.24023191630840302,
+      "eval_runtime": 90.9406,
+      "eval_samples_per_second": 10.996,
+      "eval_steps_per_second": 2.749,
+      "step": 11000
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 1.0826618671417236,
+      "learning_rate": 9.132307692307692e-05,
+      "loss": 0.2168,
+      "step": 11100
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.8385189771652222,
+      "learning_rate": 9.02974358974359e-05,
+      "loss": 0.2029,
+      "step": 11200
+    },
+    {
+      "epoch": 2.43,
+      "grad_norm": 0.7595863342285156,
+      "learning_rate": 8.927179487179488e-05,
+      "loss": 0.1902,
+      "step": 11300
+    },
+    {
+      "epoch": 2.45,
+      "grad_norm": 2.0246148109436035,
+      "learning_rate": 8.824615384615384e-05,
+      "loss": 0.2276,
+      "step": 11400
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 1.2247196435928345,
+      "learning_rate": 8.722051282051283e-05,
+      "loss": 0.2,
+      "step": 11500
+    },
+    {
+      "epoch": 2.47,
+      "eval_loss": 0.25648975372314453,
+      "eval_runtime": 90.8579,
+      "eval_samples_per_second": 11.006,
+      "eval_steps_per_second": 2.752,
+      "step": 11500
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.0143483877182007,
+      "learning_rate": 8.61948717948718e-05,
+      "loss": 0.2179,
+      "step": 11600
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 2.7020885944366455,
+      "learning_rate": 8.516923076923076e-05,
+      "loss": 0.2214,
+      "step": 11700
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 1.8533117771148682,
+      "learning_rate": 8.414358974358975e-05,
+      "loss": 0.2074,
+      "step": 11800
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 1.7365753650665283,
+      "learning_rate": 8.311794871794872e-05,
+      "loss": 0.2396,
+      "step": 11900
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.8160982131958008,
+      "learning_rate": 8.209230769230771e-05,
+      "loss": 0.1786,
+      "step": 12000
+    },
+    {
+      "epoch": 2.58,
+      "eval_loss": 0.2251870185136795,
+      "eval_runtime": 90.8167,
+      "eval_samples_per_second": 11.011,
+      "eval_steps_per_second": 2.753,
+      "step": 12000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 20000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3.86418819603628e+17,
+  "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 sha256:1318554bac5c9740d383c017d6e24e057c161337444188e13c83dba33fc00e24
+size 4920