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": [
+    "v_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9506707d190c9846d953b1721120642c7060403907ba3bee15a8c1cc0a3efe94
+size 119975656

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2047b6c642969d6c06ec76f0d26f23bdfac7da425311985adcbcbf11c97a994
+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": 0.02997952327132225,
+  "best_model_checkpoint": "runs/deepseek_lora_20240424-122712/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": 2.6060585975646973,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.6667,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 5.726912021636963,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.6606,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 6.3224616050720215,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.6875,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 4.4585185050964355,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.5512,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 2.849210023880005,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.598,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.7917169332504272,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.3203,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 10.056238174438477,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.4914,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 5.542996406555176,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.3369,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.5463522672653198,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.3185,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 9.401649475097656,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2827,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.238974928855896,
+      "learning_rate": 4.4e-06,
+      "loss": 1.0366,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2282520532608032,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.0715,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.4583073854446411,
+      "learning_rate": 5.2e-06,
+      "loss": 0.868,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.3194146156311035,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.8281,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 4.280028820037842,
+      "learning_rate": 6e-06,
+      "loss": 0.8666,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9424476027488708,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.6691,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9174453616142273,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.5405,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.0179359912872314,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.5103,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4516351521015167,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.2679,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 6.054721355438232,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.2634,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.40070173144340515,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.2254,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.6031996011734009,
+      "learning_rate": 8.8e-06,
+      "loss": 0.1281,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 3.0129740238189697,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.2365,
+      "step": 230
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.6611989140510559,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.3255,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.3195549547672272,
+      "learning_rate": 1e-05,
+      "loss": 0.3287,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.27022993564605713,
+      "learning_rate": 1.04e-05,
+      "loss": 0.1439,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 4.671290874481201,
+      "learning_rate": 1.0800000000000002e-05,
+      "loss": 0.0676,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2435157746076584,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.2338,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.40632137656211853,
+      "learning_rate": 1.16e-05,
+      "loss": 0.1661,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.2910804748535156,
+      "learning_rate": 1.2e-05,
+      "loss": 0.1781,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 7.506131649017334,
+      "learning_rate": 1.2400000000000002e-05,
+      "loss": 0.1283,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.04508267343044281,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.1022,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.23127306997776031,
+      "learning_rate": 1.3200000000000002e-05,
+      "loss": 0.1243,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 6.1613383293151855,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.1485,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.023777758702635765,
+      "learning_rate": 1.4e-05,
+      "loss": 0.0538,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.014769719913601875,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.0285,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 5.690178871154785,
+      "learning_rate": 1.48e-05,
+      "loss": 0.1325,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.02117346040904522,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.0507,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.06630611419677734,
+      "learning_rate": 1.5600000000000003e-05,
+      "loss": 0.199,
+      "step": 390
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.16532257199287415,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0652,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.009799620136618614,
+      "learning_rate": 1.64e-05,
+      "loss": 0.1011,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.12324853241443634,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.0364,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.010026533156633377,
+      "learning_rate": 1.72e-05,
+      "loss": 0.1973,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.0071570691652596,
+      "learning_rate": 1.76e-05,
+      "loss": 0.0819,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.04149964451789856,
+      "learning_rate": 1.8e-05,
+      "loss": 0.1046,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 3.45990252494812,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.1011,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.00734300771728158,
+      "learning_rate": 1.88e-05,
+      "loss": 0.223,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.01419814396649599,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.1178,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.10111651569604874,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.1416,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 3.1214537620544434,
+      "learning_rate": 2e-05,
+      "loss": 0.1258,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.05367860943078995,
+      "eval_runtime": 62.0108,
+      "eval_samples_per_second": 16.126,
+      "eval_steps_per_second": 16.126,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.013164438307285309,
+      "learning_rate": 1.9955555555555557e-05,
+      "loss": 0.0268,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.15392057597637177,
+      "learning_rate": 1.9911111111111112e-05,
+      "loss": 0.0843,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.006180985830724239,
+      "learning_rate": 1.9866666666666667e-05,
+      "loss": 0.1384,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.2702454924583435,
+      "learning_rate": 1.9822222222222226e-05,
+      "loss": 0.0956,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.5135071277618408,
+      "learning_rate": 1.977777777777778e-05,
+      "loss": 0.1615,
+      "step": 550
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.005121675785630941,
+      "learning_rate": 1.9733333333333336e-05,
+      "loss": 0.1201,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.09728775173425674,
+      "learning_rate": 1.968888888888889e-05,
+      "loss": 0.1112,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 4.736963748931885,
+      "learning_rate": 1.9644444444444447e-05,
+      "loss": 0.1546,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.006898015271872282,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.1116,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.005388608202338219,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.1597,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.0133949751034379,
+      "learning_rate": 1.9511111111111113e-05,
+      "loss": 0.0799,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.11226101964712143,
+      "learning_rate": 1.9466666666666668e-05,
+      "loss": 0.0448,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.011205198243260384,
+      "learning_rate": 1.9422222222222223e-05,
+      "loss": 0.0739,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.007312687113881111,
+      "learning_rate": 1.9377777777777778e-05,
+      "loss": 0.0779,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.006550287362188101,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.2039,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.961844563484192,
+      "learning_rate": 1.928888888888889e-05,
+      "loss": 0.0618,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.012318034656345844,
+      "learning_rate": 1.9244444444444444e-05,
+      "loss": 0.1166,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.08778905868530273,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.0822,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.010623461566865444,
+      "learning_rate": 1.9155555555555558e-05,
+      "loss": 0.095,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.0858495905995369,
+      "learning_rate": 1.9111111111111113e-05,
+      "loss": 0.0468,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.7685880661010742,
+      "learning_rate": 1.9066666666666668e-05,
+      "loss": 0.0288,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.032682083547115326,
+      "learning_rate": 1.9022222222222223e-05,
+      "loss": 0.1024,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.010010900907218456,
+      "learning_rate": 1.897777777777778e-05,
+      "loss": 0.0129,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.037693481892347336,
+      "learning_rate": 1.8933333333333334e-05,
+      "loss": 0.1217,
+      "step": 740
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 2.2111008167266846,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.1206,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.4000599384307861,
+      "learning_rate": 1.8844444444444444e-05,
+      "loss": 0.1214,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.3877034187316895,
+      "learning_rate": 1.88e-05,
+      "loss": 0.0408,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 4.164296627044678,
+      "learning_rate": 1.8755555555555558e-05,
+      "loss": 0.1315,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.07969211786985397,
+      "learning_rate": 1.8711111111111113e-05,
+      "loss": 0.0149,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.9340951442718506,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.1169,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.006517359986901283,
+      "learning_rate": 1.8622222222222224e-05,
+      "loss": 0.0517,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.008951540105044842,
+      "learning_rate": 1.857777777777778e-05,
+      "loss": 0.0935,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.03655437007546425,
+      "learning_rate": 1.8533333333333334e-05,
+      "loss": 0.0883,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.0346522182226181,
+      "learning_rate": 1.848888888888889e-05,
+      "loss": 0.0479,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.006223162170499563,
+      "learning_rate": 1.8444444444444448e-05,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.004037676844745874,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.0333,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.004569903016090393,
+      "learning_rate": 1.835555555555556e-05,
+      "loss": 0.0536,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.005509174894541502,
+      "learning_rate": 1.8311111111111114e-05,
+      "loss": 0.1528,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.007597978692501783,
+      "learning_rate": 1.826666666666667e-05,
+      "loss": 0.0052,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 4.2217936515808105,
+      "learning_rate": 1.8222222222222224e-05,
+      "loss": 0.0776,
+      "step": 900
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.004342419560998678,
+      "learning_rate": 1.817777777777778e-05,
+      "loss": 0.0552,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.0696156695485115,
+      "learning_rate": 1.8133333333333335e-05,
+      "loss": 0.0412,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.022448547184467316,
+      "learning_rate": 1.808888888888889e-05,
+      "loss": 0.0109,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 4.305741310119629,
+      "learning_rate": 1.8044444444444445e-05,
+      "loss": 0.0428,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.344078779220581,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0651,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.585327386856079,
+      "learning_rate": 1.7955555555555556e-05,
+      "loss": 0.1474,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 2.2476861476898193,
+      "learning_rate": 1.791111111111111e-05,
+      "loss": 0.0892,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.06212488189339638,
+      "learning_rate": 1.7866666666666666e-05,
+      "loss": 0.0659,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.012895594350993633,
+      "learning_rate": 1.782222222222222e-05,
+      "loss": 0.0915,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.1314150094985962,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.0456,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.02997952327132225,
+      "eval_runtime": 62.0027,
+      "eval_samples_per_second": 16.128,
+      "eval_steps_per_second": 16.128,
+      "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:ff69c33f3d304761f55064bdbe6147ea87f0629f77c48e86c119c142add47706
+size 4920