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",
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_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 sha256:5fa5d9a487128e218925f812672dda35c0dfee52ffd1a663bf73911fabf90156
+size 119975656

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be3e0407c75417fb6b6e255987cda42e5ad91e0e9407d7c71b4ec57c667c06e7
+size 240145026

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cbedf2f679f473ea49fc2279d7455bcf73a898ecce097b09cd6c432385067e3
+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": 0.02973618172109127,
+  "best_model_checkpoint": "runs/deepseek_lora_/home/mac/air2/runs/deepseek_lora_20240422-141601/checkpoint-30000_20240423-210253/checkpoint-1000",
+  "epoch": 0.3132832080200501,
+  "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": 1.4201024770736694,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.4508,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.6313552856445312,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.4463,
+      "step": 20
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.2772644758224487,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 1.4462,
+      "step": 30
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.3495179414749146,
+      "learning_rate": 1.6000000000000001e-06,
+      "loss": 1.463,
+      "step": 40
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.3023079633712769,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.4931,
+      "step": 50
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.2231166362762451,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 1.4886,
+      "step": 60
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.5659693479537964,
+      "learning_rate": 2.8000000000000003e-06,
+      "loss": 1.4963,
+      "step": 70
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.8523041009902954,
+      "learning_rate": 3.2000000000000003e-06,
+      "loss": 1.3668,
+      "step": 80
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.399263620376587,
+      "learning_rate": 3.6000000000000003e-06,
+      "loss": 1.296,
+      "step": 90
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.6715140342712402,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.2411,
+      "step": 100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.1111788749694824,
+      "learning_rate": 4.4e-06,
+      "loss": 1.0886,
+      "step": 110
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9370793104171753,
+      "learning_rate": 4.800000000000001e-06,
+      "loss": 1.0653,
+      "step": 120
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.3835300207138062,
+      "learning_rate": 5.2e-06,
+      "loss": 0.8878,
+      "step": 130
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.646286129951477,
+      "learning_rate": 5.600000000000001e-06,
+      "loss": 0.7921,
+      "step": 140
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.2522785663604736,
+      "learning_rate": 6e-06,
+      "loss": 0.7373,
+      "step": 150
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9030014872550964,
+      "learning_rate": 6.4000000000000006e-06,
+      "loss": 0.5454,
+      "step": 160
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.8196408152580261,
+      "learning_rate": 6.800000000000001e-06,
+      "loss": 0.4356,
+      "step": 170
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.4333338141441345,
+      "learning_rate": 7.2000000000000005e-06,
+      "loss": 0.3329,
+      "step": 180
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.37946629524230957,
+      "learning_rate": 7.600000000000001e-06,
+      "loss": 0.2524,
+      "step": 190
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.2624123096466064,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.1601,
+      "step": 200
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.7884108424186707,
+      "learning_rate": 8.400000000000001e-06,
+      "loss": 0.1937,
+      "step": 210
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.46105730533599854,
+      "learning_rate": 8.8e-06,
+      "loss": 0.0807,
+      "step": 220
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 0.6495872735977173,
+      "learning_rate": 9.200000000000002e-06,
+      "loss": 0.1566,
+      "step": 230
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.9866824150085449,
+      "learning_rate": 9.600000000000001e-06,
+      "loss": 0.2515,
+      "step": 240
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.31797927618026733,
+      "learning_rate": 1e-05,
+      "loss": 0.0861,
+      "step": 250
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.07518763095140457,
+      "learning_rate": 1.04e-05,
+      "loss": 0.0498,
+      "step": 260
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.23027415573596954,
+      "learning_rate": 1.0800000000000002e-05,
+      "loss": 0.0473,
+      "step": 270
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.22770297527313232,
+      "learning_rate": 1.1200000000000001e-05,
+      "loss": 0.0469,
+      "step": 280
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.22862806916236877,
+      "learning_rate": 1.16e-05,
+      "loss": 0.0974,
+      "step": 290
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 0.3330214023590088,
+      "learning_rate": 1.2e-05,
+      "loss": 0.0597,
+      "step": 300
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.966628909111023,
+      "learning_rate": 1.2400000000000002e-05,
+      "loss": 0.0315,
+      "step": 310
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.022704431787133217,
+      "learning_rate": 1.2800000000000001e-05,
+      "loss": 0.042,
+      "step": 320
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.216924786567688,
+      "learning_rate": 1.3200000000000002e-05,
+      "loss": 0.0353,
+      "step": 330
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.6081690192222595,
+      "learning_rate": 1.3600000000000002e-05,
+      "loss": 0.0247,
+      "step": 340
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.012569287791848183,
+      "learning_rate": 1.4e-05,
+      "loss": 0.0251,
+      "step": 350
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.010333358310163021,
+      "learning_rate": 1.4400000000000001e-05,
+      "loss": 0.0236,
+      "step": 360
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.37758347392082214,
+      "learning_rate": 1.48e-05,
+      "loss": 0.0268,
+      "step": 370
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.015816116705536842,
+      "learning_rate": 1.5200000000000002e-05,
+      "loss": 0.0107,
+      "step": 380
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.025576846674084663,
+      "learning_rate": 1.5600000000000003e-05,
+      "loss": 0.0213,
+      "step": 390
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.31375065445899963,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0177,
+      "step": 400
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.008338396437466145,
+      "learning_rate": 1.64e-05,
+      "loss": 0.023,
+      "step": 410
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.24885450303554535,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.013,
+      "step": 420
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.0110774552449584,
+      "learning_rate": 1.72e-05,
+      "loss": 0.0397,
+      "step": 430
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.006729575805366039,
+      "learning_rate": 1.76e-05,
+      "loss": 0.0155,
+      "step": 440
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.01409532967954874,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0198,
+      "step": 450
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.3871189057826996,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.0212,
+      "step": 460
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.006107095163315535,
+      "learning_rate": 1.88e-05,
+      "loss": 0.07,
+      "step": 470
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.010062485933303833,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.0157,
+      "step": 480
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.1705617755651474,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.0241,
+      "step": 490
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.5236091613769531,
+      "learning_rate": 2e-05,
+      "loss": 0.0208,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.04813479632139206,
+      "eval_runtime": 105.8284,
+      "eval_samples_per_second": 9.449,
+      "eval_steps_per_second": 9.449,
+      "step": 500
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.007713190745562315,
+      "learning_rate": 1.9955555555555557e-05,
+      "loss": 0.007,
+      "step": 510
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.028844956308603287,
+      "learning_rate": 1.9911111111111112e-05,
+      "loss": 0.018,
+      "step": 520
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.004528562072664499,
+      "learning_rate": 1.9866666666666667e-05,
+      "loss": 0.0519,
+      "step": 530
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.5867981910705566,
+      "learning_rate": 1.9822222222222226e-05,
+      "loss": 0.0193,
+      "step": 540
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.08260989189147949,
+      "learning_rate": 1.977777777777778e-05,
+      "loss": 0.0359,
+      "step": 550
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.005006667226552963,
+      "learning_rate": 1.9733333333333336e-05,
+      "loss": 0.0187,
+      "step": 560
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.017591852694749832,
+      "learning_rate": 1.968888888888889e-05,
+      "loss": 0.0143,
+      "step": 570
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8018626570701599,
+      "learning_rate": 1.9644444444444447e-05,
+      "loss": 0.0161,
+      "step": 580
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.005714430473744869,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.0159,
+      "step": 590
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.006446035113185644,
+      "learning_rate": 1.9555555555555557e-05,
+      "loss": 0.0249,
+      "step": 600
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.00910472497344017,
+      "learning_rate": 1.9511111111111113e-05,
+      "loss": 0.009,
+      "step": 610
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.0680340826511383,
+      "learning_rate": 1.9466666666666668e-05,
+      "loss": 0.01,
+      "step": 620
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.009966106154024601,
+      "learning_rate": 1.9422222222222223e-05,
+      "loss": 0.0189,
+      "step": 630
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.004922552965581417,
+      "learning_rate": 1.9377777777777778e-05,
+      "loss": 0.0189,
+      "step": 640
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.0045297518372535706,
+      "learning_rate": 1.9333333333333333e-05,
+      "loss": 0.0636,
+      "step": 650
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.17961235344409943,
+      "learning_rate": 1.928888888888889e-05,
+      "loss": 0.0077,
+      "step": 660
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.010727491229772568,
+      "learning_rate": 1.9244444444444444e-05,
+      "loss": 0.0338,
+      "step": 670
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.14529484510421753,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.0162,
+      "step": 680
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.011789410375058651,
+      "learning_rate": 1.9155555555555558e-05,
+      "loss": 0.0371,
+      "step": 690
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.03757067024707794,
+      "learning_rate": 1.9111111111111113e-05,
+      "loss": 0.0082,
+      "step": 700
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 0.11487198621034622,
+      "learning_rate": 1.9066666666666668e-05,
+      "loss": 0.0039,
+      "step": 710
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.005442380905151367,
+      "learning_rate": 1.9022222222222223e-05,
+      "loss": 0.0108,
+      "step": 720
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.005606868304312229,
+      "learning_rate": 1.897777777777778e-05,
+      "loss": 0.0016,
+      "step": 730
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.00637522479519248,
+      "learning_rate": 1.8933333333333334e-05,
+      "loss": 0.0268,
+      "step": 740
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.1989319920539856,
+      "learning_rate": 1.888888888888889e-05,
+      "loss": 0.0227,
+      "step": 750
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.13159094750881195,
+      "learning_rate": 1.8844444444444444e-05,
+      "loss": 0.0313,
+      "step": 760
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 3.0459349155426025,
+      "learning_rate": 1.88e-05,
+      "loss": 0.0201,
+      "step": 770
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 1.1915451288223267,
+      "learning_rate": 1.8755555555555558e-05,
+      "loss": 0.0245,
+      "step": 780
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.013696914538741112,
+      "learning_rate": 1.8711111111111113e-05,
+      "loss": 0.0018,
+      "step": 790
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 1.1634104251861572,
+      "learning_rate": 1.866666666666667e-05,
+      "loss": 0.026,
+      "step": 800
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.007169550750404596,
+      "learning_rate": 1.8622222222222224e-05,
+      "loss": 0.0071,
+      "step": 810
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.004371534567326307,
+      "learning_rate": 1.857777777777778e-05,
+      "loss": 0.0153,
+      "step": 820
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.020073844119906425,
+      "learning_rate": 1.8533333333333334e-05,
+      "loss": 0.0096,
+      "step": 830
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.008414236828684807,
+      "learning_rate": 1.848888888888889e-05,
+      "loss": 0.007,
+      "step": 840
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.003889534855261445,
+      "learning_rate": 1.8444444444444448e-05,
+      "loss": 0.002,
+      "step": 850
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.002301928121596575,
+      "learning_rate": 1.8400000000000003e-05,
+      "loss": 0.0025,
+      "step": 860
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.002069896785542369,
+      "learning_rate": 1.835555555555556e-05,
+      "loss": 0.0147,
+      "step": 870
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.0038117747753858566,
+      "learning_rate": 1.8311111111111114e-05,
+      "loss": 0.0414,
+      "step": 880
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.007180278189480305,
+      "learning_rate": 1.826666666666667e-05,
+      "loss": 0.0007,
+      "step": 890
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.722541332244873,
+      "learning_rate": 1.8222222222222224e-05,
+      "loss": 0.0173,
+      "step": 900
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.021056558936834335,
+      "learning_rate": 1.817777777777778e-05,
+      "loss": 0.0111,
+      "step": 910
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.009726395830512047,
+      "learning_rate": 1.8133333333333335e-05,
+      "loss": 0.0045,
+      "step": 920
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.00808757171034813,
+      "learning_rate": 1.808888888888889e-05,
+      "loss": 0.0021,
+      "step": 930
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.3323584794998169,
+      "learning_rate": 1.8044444444444445e-05,
+      "loss": 0.0052,
+      "step": 940
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.45399293303489685,
+      "learning_rate": 1.8e-05,
+      "loss": 0.0095,
+      "step": 950
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.43379417061805725,
+      "learning_rate": 1.7955555555555556e-05,
+      "loss": 0.0401,
+      "step": 960
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.7372444868087769,
+      "learning_rate": 1.791111111111111e-05,
+      "loss": 0.0184,
+      "step": 970
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.013180572539567947,
+      "learning_rate": 1.7866666666666666e-05,
+      "loss": 0.0116,
+      "step": 980
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.008782428689301014,
+      "learning_rate": 1.782222222222222e-05,
+      "loss": 0.0223,
+      "step": 990
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.011336304247379303,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.0026,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 0.02973618172109127,
+      "eval_runtime": 105.7708,
+      "eval_samples_per_second": 9.454,
+      "eval_steps_per_second": 9.454,
+      "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:443fe9a39f0d2e1fe0f04266f9101e8b7afd492e2740cd8e09ab25fd40711010
+size 5048