Uploaded checkpoint-10000

README.md

@@ -0,0 +1,202 @@
+---
+library_name: peft
+base_model: meta-llama/Meta-Llama-3-8B-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": "meta-llama/Meta-Llama-3-8B-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": 256,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "up_proj",
+    "v_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:c1a3fb834b1e7403413ce8a6e90846b03fd9892e7deddf7d1f661c376c664a63
+size 671149168

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6e6b6ee186c78f463b236ee03905bb837e56fa0da75cf624eafe6793a05c2d8
+size 1342555602

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:784e48ec96b46ab6412cf243f9ea7749aae76d4f44b7d1ce8926f67a33f43c64
+size 14308

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de08dfe2b75b71f2154800fdb9d53cf07b2f8dd634749a8467d8ff5c91e63d47
+size 1064

trainer_state.json

@@ -0,0 +1,761 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 2000,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 39.588829040527344,
+      "learning_rate": 9.499999999999999e-07,
+      "loss": 1.2125,
+      "step": 100
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 24.040372848510742,
+      "learning_rate": 9.904040404040403e-07,
+      "loss": 1.0367,
+      "step": 200
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 23.623809814453125,
+      "learning_rate": 9.803030303030302e-07,
+      "loss": 0.9513,
+      "step": 300
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.24086859822273254,
+      "learning_rate": 9.7020202020202e-07,
+      "loss": 0.8004,
+      "step": 400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 22.336132049560547,
+      "learning_rate": 9.601010101010101e-07,
+      "loss": 0.8263,
+      "step": 500
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 42.77682876586914,
+      "learning_rate": 9.499999999999999e-07,
+      "loss": 0.769,
+      "step": 600
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 16.354448318481445,
+      "learning_rate": 9.398989898989899e-07,
+      "loss": 0.7974,
+      "step": 700
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 40.2994270324707,
+      "learning_rate": 9.297979797979798e-07,
+      "loss": 0.8112,
+      "step": 800
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 15.487586975097656,
+      "learning_rate": 9.196969696969696e-07,
+      "loss": 0.7657,
+      "step": 900
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 20.020811080932617,
+      "learning_rate": 9.095959595959596e-07,
+      "loss": 0.7554,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.6317849159240723,
+      "learning_rate": 8.995959595959596e-07,
+      "loss": 0.7687,
+      "step": 1100
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 8.649179458618164,
+      "learning_rate": 8.894949494949494e-07,
+      "loss": 0.7567,
+      "step": 1200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 27.93072509765625,
+      "learning_rate": 8.793939393939394e-07,
+      "loss": 0.7014,
+      "step": 1300
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 34.16617202758789,
+      "learning_rate": 8.692929292929293e-07,
+      "loss": 0.6642,
+      "step": 1400
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 61.1443977355957,
+      "learning_rate": 8.591919191919191e-07,
+      "loss": 0.7243,
+      "step": 1500
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 69.2451400756836,
+      "learning_rate": 8.490909090909091e-07,
+      "loss": 0.7365,
+      "step": 1600
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 30.576330184936523,
+      "learning_rate": 8.38989898989899e-07,
+      "loss": 0.657,
+      "step": 1700
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 15.208847045898438,
+      "learning_rate": 8.288888888888888e-07,
+      "loss": 0.7884,
+      "step": 1800
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 39.78324508666992,
+      "learning_rate": 8.187878787878788e-07,
+      "loss": 0.7657,
+      "step": 1900
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 43.55222702026367,
+      "learning_rate": 8.086868686868686e-07,
+      "loss": 0.6678,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.751860499382019,
+      "eval_runtime": 241.5179,
+      "eval_samples_per_second": 4.14,
+      "eval_steps_per_second": 1.035,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 26.86771011352539,
+      "learning_rate": 7.985858585858586e-07,
+      "loss": 0.6361,
+      "step": 2100
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 25.721782684326172,
+      "learning_rate": 7.884848484848484e-07,
+      "loss": 0.8334,
+      "step": 2200
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 10.995915412902832,
+      "learning_rate": 7.783838383838383e-07,
+      "loss": 0.7052,
+      "step": 2300
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 33.5030403137207,
+      "learning_rate": 7.682828282828282e-07,
+      "loss": 0.6972,
+      "step": 2400
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 3.3341565132141113,
+      "learning_rate": 7.581818181818182e-07,
+      "loss": 0.7283,
+      "step": 2500
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 10.039573669433594,
+      "learning_rate": 7.480808080808081e-07,
+      "loss": 0.725,
+      "step": 2600
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 41.933143615722656,
+      "learning_rate": 7.379797979797979e-07,
+      "loss": 0.6081,
+      "step": 2700
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 32.512107849121094,
+      "learning_rate": 7.278787878787879e-07,
+      "loss": 0.7128,
+      "step": 2800
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 28.775693893432617,
+      "learning_rate": 7.177777777777777e-07,
+      "loss": 0.6757,
+      "step": 2900
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 47.666160583496094,
+      "learning_rate": 7.076767676767677e-07,
+      "loss": 0.587,
+      "step": 3000
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 23.707677841186523,
+      "learning_rate": 6.975757575757576e-07,
+      "loss": 0.7217,
+      "step": 3100
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 38.1664924621582,
+      "learning_rate": 6.874747474747474e-07,
+      "loss": 0.7153,
+      "step": 3200
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 43.21916198730469,
+      "learning_rate": 6.773737373737374e-07,
+      "loss": 0.7504,
+      "step": 3300
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 28.080886840820312,
+      "learning_rate": 6.674747474747474e-07,
+      "loss": 0.6828,
+      "step": 3400
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 24.497976303100586,
+      "learning_rate": 6.573737373737374e-07,
+      "loss": 0.6419,
+      "step": 3500
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 71.72598266601562,
+      "learning_rate": 6.472727272727272e-07,
+      "loss": 0.6036,
+      "step": 3600
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 30.938745498657227,
+      "learning_rate": 6.371717171717171e-07,
+      "loss": 0.705,
+      "step": 3700
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 27.01025390625,
+      "learning_rate": 6.270707070707071e-07,
+      "loss": 0.5679,
+      "step": 3800
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 24.72421646118164,
+      "learning_rate": 6.169696969696969e-07,
+      "loss": 0.6707,
+      "step": 3900
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 17.81386375427246,
+      "learning_rate": 6.068686868686869e-07,
+      "loss": 0.653,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "eval_loss": 0.6371002197265625,
+      "eval_runtime": 241.2671,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 1.036,
+      "step": 4000
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 22.987863540649414,
+      "learning_rate": 5.967676767676767e-07,
+      "loss": 0.6111,
+      "step": 4100
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 28.384014129638672,
+      "learning_rate": 5.866666666666666e-07,
+      "loss": 0.7237,
+      "step": 4200
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 9.547513961791992,
+      "learning_rate": 5.765656565656566e-07,
+      "loss": 0.6313,
+      "step": 4300
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 35.17210388183594,
+      "learning_rate": 5.664646464646465e-07,
+      "loss": 0.6212,
+      "step": 4400
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 27.639326095581055,
+      "learning_rate": 5.563636363636363e-07,
+      "loss": 0.6434,
+      "step": 4500
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 47.38414764404297,
+      "learning_rate": 5.462626262626262e-07,
+      "loss": 0.6834,
+      "step": 4600
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 24.167831420898438,
+      "learning_rate": 5.361616161616162e-07,
+      "loss": 0.6669,
+      "step": 4700
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 32.78892517089844,
+      "learning_rate": 5.26060606060606e-07,
+      "loss": 0.6857,
+      "step": 4800
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 14.563433647155762,
+      "learning_rate": 5.159595959595959e-07,
+      "loss": 0.6279,
+      "step": 4900
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 24.523794174194336,
+      "learning_rate": 5.058585858585858e-07,
+      "loss": 0.5623,
+      "step": 5000
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 54.16361618041992,
+      "learning_rate": 4.957575757575757e-07,
+      "loss": 0.6236,
+      "step": 5100
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 39.292449951171875,
+      "learning_rate": 4.856565656565657e-07,
+      "loss": 0.695,
+      "step": 5200
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 27.683238983154297,
+      "learning_rate": 4.7555555555555554e-07,
+      "loss": 0.6286,
+      "step": 5300
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 42.612430572509766,
+      "learning_rate": 4.6545454545454546e-07,
+      "loss": 0.5533,
+      "step": 5400
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 12.680336952209473,
+      "learning_rate": 4.553535353535353e-07,
+      "loss": 0.6878,
+      "step": 5500
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 29.51133918762207,
+      "learning_rate": 4.4525252525252524e-07,
+      "loss": 0.6772,
+      "step": 5600
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 60.08015823364258,
+      "learning_rate": 4.3515151515151515e-07,
+      "loss": 0.5839,
+      "step": 5700
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 32.535728454589844,
+      "learning_rate": 4.2505050505050507e-07,
+      "loss": 0.7245,
+      "step": 5800
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 27.34471893310547,
+      "learning_rate": 4.1494949494949493e-07,
+      "loss": 0.6402,
+      "step": 5900
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 5.2399139404296875,
+      "learning_rate": 4.0484848484848485e-07,
+      "loss": 0.5824,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3,
+      "eval_loss": 0.6514798402786255,
+      "eval_runtime": 241.275,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 1.036,
+      "step": 6000
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 54.833457946777344,
+      "learning_rate": 3.947474747474747e-07,
+      "loss": 0.6579,
+      "step": 6100
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 29.26833152770996,
+      "learning_rate": 3.8464646464646463e-07,
+      "loss": 0.5482,
+      "step": 6200
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 20.299970626831055,
+      "learning_rate": 3.7454545454545454e-07,
+      "loss": 0.5854,
+      "step": 6300
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.119832515716553,
+      "learning_rate": 3.6444444444444446e-07,
+      "loss": 0.613,
+      "step": 6400
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 14.71923828125,
+      "learning_rate": 3.543434343434343e-07,
+      "loss": 0.7214,
+      "step": 6500
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 3.2650656700134277,
+      "learning_rate": 3.4424242424242424e-07,
+      "loss": 0.5775,
+      "step": 6600
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 16.577056884765625,
+      "learning_rate": 3.341414141414141e-07,
+      "loss": 0.5611,
+      "step": 6700
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 28.803749084472656,
+      "learning_rate": 3.24040404040404e-07,
+      "loss": 0.6372,
+      "step": 6800
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 16.91265869140625,
+      "learning_rate": 3.1393939393939394e-07,
+      "loss": 0.6302,
+      "step": 6900
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 21.173931121826172,
+      "learning_rate": 3.0383838383838385e-07,
+      "loss": 0.6071,
+      "step": 7000
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 44.6800537109375,
+      "learning_rate": 2.937373737373737e-07,
+      "loss": 0.588,
+      "step": 7100
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 25.73281478881836,
+      "learning_rate": 2.8363636363636363e-07,
+      "loss": 0.6173,
+      "step": 7200
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 92.61457061767578,
+      "learning_rate": 2.735353535353535e-07,
+      "loss": 0.6438,
+      "step": 7300
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 47.508995056152344,
+      "learning_rate": 2.634343434343434e-07,
+      "loss": 0.5693,
+      "step": 7400
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 49.36333084106445,
+      "learning_rate": 2.533333333333333e-07,
+      "loss": 0.6199,
+      "step": 7500
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.993002891540527,
+      "learning_rate": 2.4323232323232324e-07,
+      "loss": 0.4921,
+      "step": 7600
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 49.10454177856445,
+      "learning_rate": 2.3313131313131313e-07,
+      "loss": 0.6299,
+      "step": 7700
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 23.325441360473633,
+      "learning_rate": 2.2303030303030302e-07,
+      "loss": 0.6931,
+      "step": 7800
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.007521418854594231,
+      "learning_rate": 2.1303030303030304e-07,
+      "loss": 0.5363,
+      "step": 7900
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 27.83951187133789,
+      "learning_rate": 2.0292929292929293e-07,
+      "loss": 0.5613,
+      "step": 8000
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.600296139717102,
+      "eval_runtime": 241.351,
+      "eval_samples_per_second": 4.143,
+      "eval_steps_per_second": 1.036,
+      "step": 8000
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 30.96291160583496,
+      "learning_rate": 1.9282828282828282e-07,
+      "loss": 0.6247,
+      "step": 8100
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 44.98584747314453,
+      "learning_rate": 1.8272727272727273e-07,
+      "loss": 0.5562,
+      "step": 8200
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 25.331201553344727,
+      "learning_rate": 1.7262626262626262e-07,
+      "loss": 0.5618,
+      "step": 8300
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 9.330756187438965,
+      "learning_rate": 1.625252525252525e-07,
+      "loss": 0.6281,
+      "step": 8400
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 26.370899200439453,
+      "learning_rate": 1.5242424242424243e-07,
+      "loss": 0.5367,
+      "step": 8500
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 44.39433288574219,
+      "learning_rate": 1.4232323232323232e-07,
+      "loss": 0.5459,
+      "step": 8600
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 13.395641326904297,
+      "learning_rate": 1.322222222222222e-07,
+      "loss": 0.5933,
+      "step": 8700
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 35.475257873535156,
+      "learning_rate": 1.2212121212121212e-07,
+      "loss": 0.563,
+      "step": 8800
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 17.025686264038086,
+      "learning_rate": 1.1202020202020201e-07,
+      "loss": 0.6993,
+      "step": 8900
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 47.12898254394531,
+      "learning_rate": 1.0191919191919191e-07,
+      "loss": 0.5684,
+      "step": 9000
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 18.88089942932129,
+      "learning_rate": 9.18181818181818e-08,
+      "loss": 0.5771,
+      "step": 9100
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 23.8131160736084,
+      "learning_rate": 8.171717171717171e-08,
+      "loss": 0.5883,
+      "step": 9200
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 51.621604919433594,
+      "learning_rate": 7.161616161616161e-08,
+      "loss": 0.7248,
+      "step": 9300
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 4.187072277069092,
+      "learning_rate": 6.151515151515151e-08,
+      "loss": 0.5615,
+      "step": 9400
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 20.36664390563965,
+      "learning_rate": 5.141414141414141e-08,
+      "loss": 0.57,
+      "step": 9500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 20.075712203979492,
+      "learning_rate": 4.131313131313131e-08,
+      "loss": 0.5463,
+      "step": 9600
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 20.317596435546875,
+      "learning_rate": 3.121212121212121e-08,
+      "loss": 0.6842,
+      "step": 9700
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 20.718721389770508,
+      "learning_rate": 2.111111111111111e-08,
+      "loss": 0.6139,
+      "step": 9800
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 6.301636219024658,
+      "learning_rate": 1.101010101010101e-08,
+      "loss": 0.5611,
+      "step": 9900
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 9.210123062133789,
+      "learning_rate": 9.090909090909091e-10,
+      "loss": 0.5539,
+      "step": 10000
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.6385700106620789,
+      "eval_runtime": 241.419,
+      "eval_samples_per_second": 4.142,
+      "eval_steps_per_second": 1.036,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 10000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000,
+  "total_flos": 9.4282098671616e+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:af80731cb62a49344deff0dd24fdefc42b5cd6017a74f9f408125790bde0a870
+size 4920