Uploaded checkpoint-1000

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": [
+    "down_proj",
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_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:e4dc39c1c81e244cafbc9fe4cd5fdfef7e857d99f56ebf43a6e7383f8e062eff
+size 119975656

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65225e6f5c8910e487c555e211950aec486a73e1ba543852565f824e5ac76f7a
+size 240145026

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6757b3664e681248dd0b7f0adf41683e511d900c1d79f0636a9ea13d529e49b
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c69e416a1c1c7cfbd03505995e73f15a3c32b1cc0b0dc09a821d33b4e92286e
+size 1064

trainer_state.json

@@ -0,0 +1,737 @@
+{
+  "best_metric": 0.03033074364066124,
+  "best_model_checkpoint": "runs/deepseek_lora_20240423-133229/checkpoint-1000",
+  "epoch": 0.31330774653403304,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 1.5461480617523193,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.5239,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 2.797250747680664,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.4966,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.274460315704346,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.4788,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.9981650114059448,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.4001,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2322547435760498,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4683,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.250878930091858,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.1961,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.917982578277588,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.4261,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 3.885340929031372,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.2742,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.170296311378479,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.253,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 6.992724895477295,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2521,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9540568590164185,
+      "learning_rate": 4.4e-06,
+      "loss": 1.0828,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9779148697853088,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.1255,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2271130084991455,
+      "learning_rate": 5.2e-06,
+      "loss": 0.9496,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 2.1939122676849365,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.953,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.5918376445770264,
+      "learning_rate": 6e-06,
+      "loss": 0.9348,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.772602379322052,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.7762,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8226258158683777,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.6798,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0945135354995728,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.5936,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.6972842812538147,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.4161,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.9560859203338623,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.3959,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.4297197759151459,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.3166,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.4494841992855072,
+      "learning_rate": 8.8e-06,
+      "loss": 0.2056,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.6981032490730286,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.3024,
+      "step": 230
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.5783653259277344,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.4392,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.33407163619995117,
+      "learning_rate": 1e-05,
+      "loss": 0.3708,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3096323311328888,
+      "learning_rate": 1.04e-05,
+      "loss": 0.1637,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.6187375783920288,
+      "learning_rate": 1.0800000000000002e-05,
+      "loss": 0.1078,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.27954748272895813,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.2668,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.4082590937614441,
+      "learning_rate": 1.16e-05,
+      "loss": 0.1843,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2993428707122803,
+      "learning_rate": 1.2e-05,
+      "loss": 0.1969,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 3.0335004329681396,
+      "learning_rate": 1.2400000000000002e-05,
+      "loss": 0.122,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.0972365066409111,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.1354,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.26203760504722595,
+      "learning_rate": 1.3200000000000002e-05,
+      "loss": 0.17,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 5.179258346557617,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.1409,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.032190825790166855,
+      "learning_rate": 1.4e-05,
+      "loss": 0.076,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.02556140348315239,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.0468,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.667189121246338,
+      "learning_rate": 1.48e-05,
+      "loss": 0.1345,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.07244217395782471,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.0411,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.11255475878715515,
+      "learning_rate": 1.5600000000000003e-05,
+      "loss": 0.1907,
+      "step": 390
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 1.9602845907211304,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0717,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.013551376760005951,
+      "learning_rate": 1.64e-05,
+      "loss": 0.0808,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.14421305060386658,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.0604,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.01705547235906124,
+      "learning_rate": 1.72e-05,
+      "loss": 0.1742,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.021360402926802635,
+      "learning_rate": 1.76e-05,
+      "loss": 0.0886,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.04369840770959854,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1063,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.2816083431243896,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.1061,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.00989863183349371,
+      "learning_rate": 1.88e-05,
+      "loss": 0.2317,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.014644264243543148,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.1054,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.13385985791683197,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.1196,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 2.099637985229492,
+      "learning_rate": 2e-05,
+      "loss": 0.1584,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.05546905845403671,
+      "eval_runtime": 62.1757,
+      "eval_samples_per_second": 16.083,
+      "eval_steps_per_second": 16.083,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.013259253464639187,
+      "learning_rate": 1.9955555555555557e-05,
+      "loss": 0.0373,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.1753215193748474,
+      "learning_rate": 1.9911111111111112e-05,
+      "loss": 0.0986,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.006998735014349222,
+      "learning_rate": 1.9866666666666667e-05,
+      "loss": 0.1372,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.3990759253501892,
+      "learning_rate": 1.9822222222222226e-05,
+      "loss": 0.127,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.8248735666275024,
+      "learning_rate": 1.977777777777778e-05,
+      "loss": 0.1239,
+      "step": 550
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.005832708440721035,
+      "learning_rate": 1.9733333333333336e-05,
+      "loss": 0.1181,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.10705375671386719,
+      "learning_rate": 1.968888888888889e-05,
+      "loss": 0.0972,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 3.7429046630859375,
+      "learning_rate": 1.9644444444444447e-05,
+      "loss": 0.1543,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.010058793239295483,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.1146,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.012124909088015556,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.1582,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.012700803577899933,
+      "learning_rate": 1.9511111111111113e-05,
+      "loss": 0.0711,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.2153177261352539,
+      "learning_rate": 1.9466666666666668e-05,
+      "loss": 0.0452,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.01289213914424181,
+      "learning_rate": 1.9422222222222223e-05,
+      "loss": 0.067,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.007021366152912378,
+      "learning_rate": 1.9377777777777778e-05,
+      "loss": 0.0776,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.005274974275380373,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.2159,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.6235843896865845,
+      "learning_rate": 1.928888888888889e-05,
+      "loss": 0.0664,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.009710369631648064,
+      "learning_rate": 1.9244444444444444e-05,
+      "loss": 0.1125,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.0918051227927208,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.0755,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.012988925911486149,
+      "learning_rate": 1.9155555555555558e-05,
+      "loss": 0.095,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.09063850343227386,
+      "learning_rate": 1.9111111111111113e-05,
+      "loss": 0.0419,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.1540229320526123,
+      "learning_rate": 1.9066666666666668e-05,
+      "loss": 0.0338,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.009780442342162132,
+      "learning_rate": 1.9022222222222223e-05,
+      "loss": 0.0935,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.011248274706304073,
+      "learning_rate": 1.897777777777778e-05,
+      "loss": 0.017,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.03275947645306587,
+      "learning_rate": 1.8933333333333334e-05,
+      "loss": 0.1128,
+      "step": 740
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.224815607070923,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.1213,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.9777376651763916,
+      "learning_rate": 1.8844444444444444e-05,
+      "loss": 0.1128,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.6119561195373535,
+      "learning_rate": 1.88e-05,
+      "loss": 0.0557,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.7092978954315186,
+      "learning_rate": 1.8755555555555558e-05,
+      "loss": 0.1196,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.08959495276212692,
+      "learning_rate": 1.8711111111111113e-05,
+      "loss": 0.0231,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 2.716322183609009,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.1253,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.006216592621058226,
+      "learning_rate": 1.8622222222222224e-05,
+      "loss": 0.0377,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.005503402091562748,
+      "learning_rate": 1.857777777777778e-05,
+      "loss": 0.1072,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.4769572913646698,
+      "learning_rate": 1.8533333333333334e-05,
+      "loss": 0.0888,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.034854818135499954,
+      "learning_rate": 1.848888888888889e-05,
+      "loss": 0.0424,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.00536635797470808,
+      "learning_rate": 1.8444444444444448e-05,
+      "loss": 0.0161,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.002790963975712657,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.025,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.003568426240235567,
+      "learning_rate": 1.835555555555556e-05,
+      "loss": 0.0597,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.005008562933653593,
+      "learning_rate": 1.8311111111111114e-05,
+      "loss": 0.1817,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.006756258197128773,
+      "learning_rate": 1.826666666666667e-05,
+      "loss": 0.0084,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 2.3732385635375977,
+      "learning_rate": 1.8222222222222224e-05,
+      "loss": 0.072,
+      "step": 900
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.003554440103471279,
+      "learning_rate": 1.817777777777778e-05,
+      "loss": 0.0507,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.06785377860069275,
+      "learning_rate": 1.8133333333333335e-05,
+      "loss": 0.0428,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.009546133689582348,
+      "learning_rate": 1.808888888888889e-05,
+      "loss": 0.0179,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.595461368560791,
+      "learning_rate": 1.8044444444444445e-05,
+      "loss": 0.0506,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.310696601867676,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0719,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.8953649997711182,
+      "learning_rate": 1.7955555555555556e-05,
+      "loss": 0.1718,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.706213116645813,
+      "learning_rate": 1.791111111111111e-05,
+      "loss": 0.0807,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.06022366136312485,
+      "learning_rate": 1.7866666666666666e-05,
+      "loss": 0.0792,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.033781811594963074,
+      "learning_rate": 1.782222222222222e-05,
+      "loss": 0.0864,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.014879009686410427,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.0527,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.03033074364066124,
+      "eval_runtime": 62.1716,
+      "eval_samples_per_second": 16.085,
+      "eval_steps_per_second": 16.085,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 1.6102125993984e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2d1561fbb0fa7f65b0db5d86f23ee1739bb6795482559825c8e8b613d481005
+size 4920