Upload 8 files

checkpoint-1000/README.md

@@ -0,0 +1,204 @@
+---
+library_name: peft
+base_model: microsoft/phi-2
+---
+
+# 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 0.7.1

checkpoint-1000/adapter_config.json

@@ -0,0 +1,30 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-2",
+  "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": 32,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "fc1",
+    "fc2",
+    "q_proj",
+    "dense",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

checkpoint-1000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a36a3b73d5ff05abb5977d27e8f2b1b26f667a0ddfb2231f05c5a383d691576
+size 94422368

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07c93483b76b87ce2f267a5d71f9beaabe186cca5d1b9dccf119eae3f277307e
+size 47724385

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1698d89fdd66ec4ef945e947d531ef003b4626bc0ca789dcfe9ea5fc54b20faf
+size 14575

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae472c841adf3819dda221ed75de8337578682a35bb543a62b8daee29826e9bf
+size 627

checkpoint-1000/trainer_state.json

@@ -0,0 +1,721 @@
+{
+  "best_metric": 0.09502185136079788,
+  "best_model_checkpoint": "fine-tuning-Phi2-with-webglm-qa-with-lora_7/checkpoint-1000",
+  "epoch": 15.723270440251572,
+  "eval_steps": 20,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 7.3505,
+      "step": 20
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 6.286308765411377,
+      "eval_runtime": 25.4764,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 20
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 4.0914,
+      "step": 40
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 0.9255164861679077,
+      "eval_runtime": 25.461,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 40
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 5e-05,
+      "loss": 0.6517,
+      "step": 60
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.576193630695343,
+      "eval_runtime": 25.4995,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.431,
+      "step": 60
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 4.893617021276596e-05,
+      "loss": 0.4621,
+      "step": 80
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.40622055530548096,
+      "eval_runtime": 25.4724,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 80
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 4.787234042553192e-05,
+      "loss": 0.3128,
+      "step": 100
+    },
+    {
+      "epoch": 1.57,
+      "eval_loss": 0.30563685297966003,
+      "eval_runtime": 25.4374,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 100
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.680851063829788e-05,
+      "loss": 0.2536,
+      "step": 120
+    },
+    {
+      "epoch": 1.89,
+      "eval_loss": 0.2603812515735626,
+      "eval_runtime": 25.4763,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 120
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 4.574468085106383e-05,
+      "loss": 0.2227,
+      "step": 140
+    },
+    {
+      "epoch": 2.2,
+      "eval_loss": 0.22473430633544922,
+      "eval_runtime": 25.4963,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.431,
+      "step": 140
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.468085106382979e-05,
+      "loss": 0.1901,
+      "step": 160
+    },
+    {
+      "epoch": 2.52,
+      "eval_loss": 0.2041008621454239,
+      "eval_runtime": 25.459,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 160
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 4.3617021276595746e-05,
+      "loss": 0.176,
+      "step": 180
+    },
+    {
+      "epoch": 2.83,
+      "eval_loss": 0.1812312752008438,
+      "eval_runtime": 25.4868,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 180
+    },
+    {
+      "epoch": 3.14,
+      "learning_rate": 4.2553191489361704e-05,
+      "loss": 0.1453,
+      "step": 200
+    },
+    {
+      "epoch": 3.14,
+      "eval_loss": 0.16830970346927643,
+      "eval_runtime": 25.481,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 200
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 4.148936170212766e-05,
+      "loss": 0.1557,
+      "step": 220
+    },
+    {
+      "epoch": 3.46,
+      "eval_loss": 0.15921901166439056,
+      "eval_runtime": 25.5028,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.431,
+      "step": 220
+    },
+    {
+      "epoch": 3.77,
+      "learning_rate": 4.0425531914893614e-05,
+      "loss": 0.1441,
+      "step": 240
+    },
+    {
+      "epoch": 3.77,
+      "eval_loss": 0.14882861077785492,
+      "eval_runtime": 25.4427,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 240
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 3.936170212765958e-05,
+      "loss": 0.1282,
+      "step": 260
+    },
+    {
+      "epoch": 4.09,
+      "eval_loss": 0.1429978758096695,
+      "eval_runtime": 25.4905,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 260
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 3.829787234042553e-05,
+      "loss": 0.1215,
+      "step": 280
+    },
+    {
+      "epoch": 4.4,
+      "eval_loss": 0.13476386666297913,
+      "eval_runtime": 25.4804,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 280
+    },
+    {
+      "epoch": 4.72,
+      "learning_rate": 3.723404255319149e-05,
+      "loss": 0.1217,
+      "step": 300
+    },
+    {
+      "epoch": 4.72,
+      "eval_loss": 0.13230670988559723,
+      "eval_runtime": 25.4706,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 300
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 3.617021276595745e-05,
+      "loss": 0.117,
+      "step": 320
+    },
+    {
+      "epoch": 5.03,
+      "eval_loss": 0.12707628309726715,
+      "eval_runtime": 25.4283,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.433,
+      "step": 320
+    },
+    {
+      "epoch": 5.35,
+      "learning_rate": 3.5106382978723407e-05,
+      "loss": 0.109,
+      "step": 340
+    },
+    {
+      "epoch": 5.35,
+      "eval_loss": 0.12554581463336945,
+      "eval_runtime": 25.4583,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 340
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 3.4042553191489365e-05,
+      "loss": 0.1094,
+      "step": 360
+    },
+    {
+      "epoch": 5.66,
+      "eval_loss": 0.12099047005176544,
+      "eval_runtime": 25.4606,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 360
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 3.2978723404255317e-05,
+      "loss": 0.1057,
+      "step": 380
+    },
+    {
+      "epoch": 5.97,
+      "eval_loss": 0.11747618019580841,
+      "eval_runtime": 25.4382,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 380
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 3.191489361702128e-05,
+      "loss": 0.0937,
+      "step": 400
+    },
+    {
+      "epoch": 6.29,
+      "eval_loss": 0.11580007523298264,
+      "eval_runtime": 25.4149,
+      "eval_samples_per_second": 0.866,
+      "eval_steps_per_second": 0.433,
+      "step": 400
+    },
+    {
+      "epoch": 6.6,
+      "learning_rate": 3.085106382978723e-05,
+      "loss": 0.0942,
+      "step": 420
+    },
+    {
+      "epoch": 6.6,
+      "eval_loss": 0.11587951332330704,
+      "eval_runtime": 25.4544,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 420
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 2.9787234042553192e-05,
+      "loss": 0.1007,
+      "step": 440
+    },
+    {
+      "epoch": 6.92,
+      "eval_loss": 0.11250220984220505,
+      "eval_runtime": 25.4316,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.433,
+      "step": 440
+    },
+    {
+      "epoch": 7.23,
+      "learning_rate": 2.8723404255319154e-05,
+      "loss": 0.0876,
+      "step": 460
+    },
+    {
+      "epoch": 7.23,
+      "eval_loss": 0.11185076832771301,
+      "eval_runtime": 25.4765,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 460
+    },
+    {
+      "epoch": 7.55,
+      "learning_rate": 2.765957446808511e-05,
+      "loss": 0.0894,
+      "step": 480
+    },
+    {
+      "epoch": 7.55,
+      "eval_loss": 0.1098945215344429,
+      "eval_runtime": 25.4185,
+      "eval_samples_per_second": 0.866,
+      "eval_steps_per_second": 0.433,
+      "step": 480
+    },
+    {
+      "epoch": 7.86,
+      "learning_rate": 2.6595744680851064e-05,
+      "loss": 0.0827,
+      "step": 500
+    },
+    {
+      "epoch": 7.86,
+      "eval_loss": 0.10724210739135742,
+      "eval_runtime": 25.4969,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.431,
+      "step": 500
+    },
+    {
+      "epoch": 8.18,
+      "learning_rate": 2.5531914893617022e-05,
+      "loss": 0.0894,
+      "step": 520
+    },
+    {
+      "epoch": 8.18,
+      "eval_loss": 0.10687847435474396,
+      "eval_runtime": 25.4493,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 520
+    },
+    {
+      "epoch": 8.49,
+      "learning_rate": 2.446808510638298e-05,
+      "loss": 0.0805,
+      "step": 540
+    },
+    {
+      "epoch": 8.49,
+      "eval_loss": 0.10752053558826447,
+      "eval_runtime": 25.4419,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 540
+    },
+    {
+      "epoch": 8.81,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 0.0782,
+      "step": 560
+    },
+    {
+      "epoch": 8.81,
+      "eval_loss": 0.10425343364477158,
+      "eval_runtime": 25.4865,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 560
+    },
+    {
+      "epoch": 9.12,
+      "learning_rate": 2.2340425531914894e-05,
+      "loss": 0.0881,
+      "step": 580
+    },
+    {
+      "epoch": 9.12,
+      "eval_loss": 0.1033911183476448,
+      "eval_runtime": 25.4549,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 580
+    },
+    {
+      "epoch": 9.43,
+      "learning_rate": 2.1276595744680852e-05,
+      "loss": 0.0839,
+      "step": 600
+    },
+    {
+      "epoch": 9.43,
+      "eval_loss": 0.10145573318004608,
+      "eval_runtime": 25.4481,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 600
+    },
+    {
+      "epoch": 9.75,
+      "learning_rate": 2.0212765957446807e-05,
+      "loss": 0.0694,
+      "step": 620
+    },
+    {
+      "epoch": 9.75,
+      "eval_loss": 0.10002648830413818,
+      "eval_runtime": 25.4089,
+      "eval_samples_per_second": 0.866,
+      "eval_steps_per_second": 0.433,
+      "step": 620
+    },
+    {
+      "epoch": 10.06,
+      "learning_rate": 1.9148936170212766e-05,
+      "loss": 0.068,
+      "step": 640
+    },
+    {
+      "epoch": 10.06,
+      "eval_loss": 0.10073428601026535,
+      "eval_runtime": 25.4963,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.431,
+      "step": 640
+    },
+    {
+      "epoch": 10.38,
+      "learning_rate": 1.8085106382978724e-05,
+      "loss": 0.072,
+      "step": 660
+    },
+    {
+      "epoch": 10.38,
+      "eval_loss": 0.09940142929553986,
+      "eval_runtime": 25.4629,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 660
+    },
+    {
+      "epoch": 10.69,
+      "learning_rate": 1.7021276595744682e-05,
+      "loss": 0.0709,
+      "step": 680
+    },
+    {
+      "epoch": 10.69,
+      "eval_loss": 0.09847569465637207,
+      "eval_runtime": 25.5056,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.431,
+      "step": 680
+    },
+    {
+      "epoch": 11.01,
+      "learning_rate": 1.595744680851064e-05,
+      "loss": 0.0712,
+      "step": 700
+    },
+    {
+      "epoch": 11.01,
+      "eval_loss": 0.09858354926109314,
+      "eval_runtime": 25.4627,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 700
+    },
+    {
+      "epoch": 11.32,
+      "learning_rate": 1.4893617021276596e-05,
+      "loss": 0.0673,
+      "step": 720
+    },
+    {
+      "epoch": 11.32,
+      "eval_loss": 0.09991483390331268,
+      "eval_runtime": 25.4891,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 720
+    },
+    {
+      "epoch": 11.64,
+      "learning_rate": 1.3829787234042554e-05,
+      "loss": 0.0669,
+      "step": 740
+    },
+    {
+      "epoch": 11.64,
+      "eval_loss": 0.09741941094398499,
+      "eval_runtime": 25.4606,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 740
+    },
+    {
+      "epoch": 11.95,
+      "learning_rate": 1.2765957446808511e-05,
+      "loss": 0.0706,
+      "step": 760
+    },
+    {
+      "epoch": 11.95,
+      "eval_loss": 0.0980500727891922,
+      "eval_runtime": 25.4509,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 760
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 1.170212765957447e-05,
+      "loss": 0.0641,
+      "step": 780
+    },
+    {
+      "epoch": 12.26,
+      "eval_loss": 0.09693228453397751,
+      "eval_runtime": 25.436,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 780
+    },
+    {
+      "epoch": 12.58,
+      "learning_rate": 1.0638297872340426e-05,
+      "loss": 0.0652,
+      "step": 800
+    },
+    {
+      "epoch": 12.58,
+      "eval_loss": 0.0963829830288887,
+      "eval_runtime": 25.4744,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 800
+    },
+    {
+      "epoch": 12.89,
+      "learning_rate": 9.574468085106383e-06,
+      "loss": 0.0668,
+      "step": 820
+    },
+    {
+      "epoch": 12.89,
+      "eval_loss": 0.09619712829589844,
+      "eval_runtime": 25.446,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 820
+    },
+    {
+      "epoch": 13.21,
+      "learning_rate": 8.510638297872341e-06,
+      "loss": 0.0617,
+      "step": 840
+    },
+    {
+      "epoch": 13.21,
+      "eval_loss": 0.09718295931816101,
+      "eval_runtime": 25.4457,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 840
+    },
+    {
+      "epoch": 13.52,
+      "learning_rate": 7.446808510638298e-06,
+      "loss": 0.0628,
+      "step": 860
+    },
+    {
+      "epoch": 13.52,
+      "eval_loss": 0.09600641578435898,
+      "eval_runtime": 25.4516,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 860
+    },
+    {
+      "epoch": 13.84,
+      "learning_rate": 6.3829787234042555e-06,
+      "loss": 0.0637,
+      "step": 880
+    },
+    {
+      "epoch": 13.84,
+      "eval_loss": 0.09490146487951279,
+      "eval_runtime": 25.4889,
+      "eval_samples_per_second": 0.863,
+      "eval_steps_per_second": 0.432,
+      "step": 880
+    },
+    {
+      "epoch": 14.15,
+      "learning_rate": 5.319148936170213e-06,
+      "loss": 0.0633,
+      "step": 900
+    },
+    {
+      "epoch": 14.15,
+      "eval_loss": 0.0950675681233406,
+      "eval_runtime": 25.4561,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 900
+    },
+    {
+      "epoch": 14.47,
+      "learning_rate": 4.255319148936171e-06,
+      "loss": 0.0577,
+      "step": 920
+    },
+    {
+      "epoch": 14.47,
+      "eval_loss": 0.09526454657316208,
+      "eval_runtime": 25.5288,
+      "eval_samples_per_second": 0.862,
+      "eval_steps_per_second": 0.431,
+      "step": 920
+    },
+    {
+      "epoch": 14.78,
+      "learning_rate": 3.1914893617021277e-06,
+      "loss": 0.0646,
+      "step": 940
+    },
+    {
+      "epoch": 14.78,
+      "eval_loss": 0.09467268735170364,
+      "eval_runtime": 25.4341,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 940
+    },
+    {
+      "epoch": 15.09,
+      "learning_rate": 2.1276595744680853e-06,
+      "loss": 0.06,
+      "step": 960
+    },
+    {
+      "epoch": 15.09,
+      "eval_loss": 0.09462392330169678,
+      "eval_runtime": 25.446,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 960
+    },
+    {
+      "epoch": 15.41,
+      "learning_rate": 1.0638297872340427e-06,
+      "loss": 0.0584,
+      "step": 980
+    },
+    {
+      "epoch": 15.41,
+      "eval_loss": 0.09491446614265442,
+      "eval_runtime": 25.4603,
+      "eval_samples_per_second": 0.864,
+      "eval_steps_per_second": 0.432,
+      "step": 980
+    },
+    {
+      "epoch": 15.72,
+      "learning_rate": 0.0,
+      "loss": 0.0638,
+      "step": 1000
+    },
+    {
+      "epoch": 15.72,
+      "eval_loss": 0.09502185136079788,
+      "eval_runtime": 25.4343,
+      "eval_samples_per_second": 0.865,
+      "eval_steps_per_second": 0.432,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 1000,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 16,
+  "save_steps": 200,
+  "total_flos": 1.63933992517632e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0625f5be598e6f058625d3231cef9487de3096ee8bbf8a08d82ab48f97747322
+size 4283