Upload 14 files

README.md

@@ -0,0 +1,202 @@
+---
+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 0.10.0

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,
+  "layer_replication": null,
+  "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": [
+    "Wqkv",
+    "fc2",
+    "fc1"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1350ab271c68977f15494c37ab5a6863fe7e7cd1a495f02f3c81132eea0cd6
+size 104873776

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdeffab6e4359da77fd5b4860c6c365c6752656b065a2df56b0a8f9896d160ef
+size 209793210

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a902e380560ad6047237cf9cb9aa3d14c42c278517d6349f5f65bc2a1d15a331
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d85fd0dcc980904bdfd3763281a80094639a2b2b63af9676380dd57c838a883
+size 1064

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,325 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "return_token_type_ids": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,441 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.18562874251497,
+  "eval_steps": 500,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11976047904191617,
+      "grad_norm": 2.8749659061431885,
+      "learning_rate": 0.0002,
+      "loss": 1.4673,
+      "step": 10
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 3.4398715496063232,
+      "learning_rate": 0.0002,
+      "loss": 1.0019,
+      "step": 20
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 1.9059951305389404,
+      "learning_rate": 0.0002,
+      "loss": 1.0575,
+      "step": 30
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 4.149394989013672,
+      "learning_rate": 0.0002,
+      "loss": 0.8164,
+      "step": 40
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 1.4866076707839966,
+      "learning_rate": 0.0002,
+      "loss": 0.8684,
+      "step": 50
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 3.1927452087402344,
+      "learning_rate": 0.0002,
+      "loss": 0.8016,
+      "step": 60
+    },
+    {
+      "epoch": 0.8383233532934131,
+      "grad_norm": 1.1162314414978027,
+      "learning_rate": 0.0002,
+      "loss": 0.6809,
+      "step": 70
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 2.829102039337158,
+      "learning_rate": 0.0002,
+      "loss": 0.6962,
+      "step": 80
+    },
+    {
+      "epoch": 1.0778443113772456,
+      "grad_norm": 1.2642532587051392,
+      "learning_rate": 0.0002,
+      "loss": 0.5769,
+      "step": 90
+    },
+    {
+      "epoch": 1.1976047904191618,
+      "grad_norm": 1.3799452781677246,
+      "learning_rate": 0.0002,
+      "loss": 0.4128,
+      "step": 100
+    },
+    {
+      "epoch": 1.3173652694610778,
+      "grad_norm": 2.3143367767333984,
+      "learning_rate": 0.0002,
+      "loss": 0.6441,
+      "step": 110
+    },
+    {
+      "epoch": 1.437125748502994,
+      "grad_norm": 1.085919976234436,
+      "learning_rate": 0.0002,
+      "loss": 0.393,
+      "step": 120
+    },
+    {
+      "epoch": 1.55688622754491,
+      "grad_norm": 1.2423957586288452,
+      "learning_rate": 0.0002,
+      "loss": 0.5582,
+      "step": 130
+    },
+    {
+      "epoch": 1.6766467065868262,
+      "grad_norm": 1.2964059114456177,
+      "learning_rate": 0.0002,
+      "loss": 0.4276,
+      "step": 140
+    },
+    {
+      "epoch": 1.7964071856287425,
+      "grad_norm": 1.8397400379180908,
+      "learning_rate": 0.0002,
+      "loss": 0.6162,
+      "step": 150
+    },
+    {
+      "epoch": 1.9161676646706587,
+      "grad_norm": 1.0209627151489258,
+      "learning_rate": 0.0002,
+      "loss": 0.4565,
+      "step": 160
+    },
+    {
+      "epoch": 2.035928143712575,
+      "grad_norm": 0.8725757598876953,
+      "learning_rate": 0.0002,
+      "loss": 0.4807,
+      "step": 170
+    },
+    {
+      "epoch": 2.155688622754491,
+      "grad_norm": 1.1269447803497314,
+      "learning_rate": 0.0002,
+      "loss": 0.3895,
+      "step": 180
+    },
+    {
+      "epoch": 2.2754491017964074,
+      "grad_norm": 1.528011679649353,
+      "learning_rate": 0.0002,
+      "loss": 0.3553,
+      "step": 190
+    },
+    {
+      "epoch": 2.3952095808383236,
+      "grad_norm": 0.8296527862548828,
+      "learning_rate": 0.0002,
+      "loss": 0.3516,
+      "step": 200
+    },
+    {
+      "epoch": 2.5149700598802394,
+      "grad_norm": 1.301917552947998,
+      "learning_rate": 0.0002,
+      "loss": 0.3918,
+      "step": 210
+    },
+    {
+      "epoch": 2.6347305389221556,
+      "grad_norm": 0.8420801758766174,
+      "learning_rate": 0.0002,
+      "loss": 0.3497,
+      "step": 220
+    },
+    {
+      "epoch": 2.754491017964072,
+      "grad_norm": 1.1430580615997314,
+      "learning_rate": 0.0002,
+      "loss": 0.4311,
+      "step": 230
+    },
+    {
+      "epoch": 2.874251497005988,
+      "grad_norm": 0.9065356850624084,
+      "learning_rate": 0.0002,
+      "loss": 0.3551,
+      "step": 240
+    },
+    {
+      "epoch": 2.9940119760479043,
+      "grad_norm": 1.1302285194396973,
+      "learning_rate": 0.0002,
+      "loss": 0.3513,
+      "step": 250
+    },
+    {
+      "epoch": 3.1137724550898205,
+      "grad_norm": 0.9960314631462097,
+      "learning_rate": 0.0002,
+      "loss": 0.3124,
+      "step": 260
+    },
+    {
+      "epoch": 3.2335329341317367,
+      "grad_norm": 1.680296778678894,
+      "learning_rate": 0.0002,
+      "loss": 0.3065,
+      "step": 270
+    },
+    {
+      "epoch": 3.3532934131736525,
+      "grad_norm": 1.1697853803634644,
+      "learning_rate": 0.0002,
+      "loss": 0.3009,
+      "step": 280
+    },
+    {
+      "epoch": 3.4730538922155687,
+      "grad_norm": 1.9219907522201538,
+      "learning_rate": 0.0002,
+      "loss": 0.2802,
+      "step": 290
+    },
+    {
+      "epoch": 3.592814371257485,
+      "grad_norm": 1.384773850440979,
+      "learning_rate": 0.0002,
+      "loss": 0.3419,
+      "step": 300
+    },
+    {
+      "epoch": 3.712574850299401,
+      "grad_norm": 1.3956997394561768,
+      "learning_rate": 0.0002,
+      "loss": 0.3172,
+      "step": 310
+    },
+    {
+      "epoch": 3.8323353293413174,
+      "grad_norm": 1.058669924736023,
+      "learning_rate": 0.0002,
+      "loss": 0.3723,
+      "step": 320
+    },
+    {
+      "epoch": 3.9520958083832336,
+      "grad_norm": 1.5626955032348633,
+      "learning_rate": 0.0002,
+      "loss": 0.325,
+      "step": 330
+    },
+    {
+      "epoch": 4.07185628742515,
+      "grad_norm": 1.2782564163208008,
+      "learning_rate": 0.0002,
+      "loss": 0.2912,
+      "step": 340
+    },
+    {
+      "epoch": 4.191616766467066,
+      "grad_norm": 1.0916423797607422,
+      "learning_rate": 0.0002,
+      "loss": 0.233,
+      "step": 350
+    },
+    {
+      "epoch": 4.311377245508982,
+      "grad_norm": 0.8613762855529785,
+      "learning_rate": 0.0002,
+      "loss": 0.3058,
+      "step": 360
+    },
+    {
+      "epoch": 4.431137724550898,
+      "grad_norm": 0.6293674111366272,
+      "learning_rate": 0.0002,
+      "loss": 0.2334,
+      "step": 370
+    },
+    {
+      "epoch": 4.550898203592815,
+      "grad_norm": 1.6042566299438477,
+      "learning_rate": 0.0002,
+      "loss": 0.3287,
+      "step": 380
+    },
+    {
+      "epoch": 4.6706586826347305,
+      "grad_norm": 0.8140411376953125,
+      "learning_rate": 0.0002,
+      "loss": 0.2372,
+      "step": 390
+    },
+    {
+      "epoch": 4.790419161676647,
+      "grad_norm": 1.5365833044052124,
+      "learning_rate": 0.0002,
+      "loss": 0.3266,
+      "step": 400
+    },
+    {
+      "epoch": 4.910179640718563,
+      "grad_norm": 0.9418448805809021,
+      "learning_rate": 0.0002,
+      "loss": 0.2513,
+      "step": 410
+    },
+    {
+      "epoch": 5.029940119760479,
+      "grad_norm": 0.6695829033851624,
+      "learning_rate": 0.0002,
+      "loss": 0.2688,
+      "step": 420
+    },
+    {
+      "epoch": 5.149700598802395,
+      "grad_norm": 0.628887414932251,
+      "learning_rate": 0.0002,
+      "loss": 0.2149,
+      "step": 430
+    },
+    {
+      "epoch": 5.269461077844311,
+      "grad_norm": 0.964766263961792,
+      "learning_rate": 0.0002,
+      "loss": 0.2606,
+      "step": 440
+    },
+    {
+      "epoch": 5.389221556886228,
+      "grad_norm": 0.5990360975265503,
+      "learning_rate": 0.0002,
+      "loss": 0.2364,
+      "step": 450
+    },
+    {
+      "epoch": 5.508982035928144,
+      "grad_norm": 0.8189520835876465,
+      "learning_rate": 0.0002,
+      "loss": 0.2857,
+      "step": 460
+    },
+    {
+      "epoch": 5.62874251497006,
+      "grad_norm": 0.5583224296569824,
+      "learning_rate": 0.0002,
+      "loss": 0.2414,
+      "step": 470
+    },
+    {
+      "epoch": 5.748502994011976,
+      "grad_norm": 0.7695009708404541,
+      "learning_rate": 0.0002,
+      "loss": 0.2434,
+      "step": 480
+    },
+    {
+      "epoch": 5.868263473053892,
+      "grad_norm": 0.3456665575504303,
+      "learning_rate": 0.0002,
+      "loss": 0.2597,
+      "step": 490
+    },
+    {
+      "epoch": 5.9880239520958085,
+      "grad_norm": 0.7596808671951294,
+      "learning_rate": 0.0002,
+      "loss": 0.2983,
+      "step": 500
+    },
+    {
+      "epoch": 6.107784431137724,
+      "grad_norm": 0.9513673782348633,
+      "learning_rate": 0.0002,
+      "loss": 0.2139,
+      "step": 510
+    },
+    {
+      "epoch": 6.227544910179641,
+      "grad_norm": 1.0958881378173828,
+      "learning_rate": 0.0002,
+      "loss": 0.2211,
+      "step": 520
+    },
+    {
+      "epoch": 6.347305389221557,
+      "grad_norm": 0.6882690787315369,
+      "learning_rate": 0.0002,
+      "loss": 0.2347,
+      "step": 530
+    },
+    {
+      "epoch": 6.467065868263473,
+      "grad_norm": 1.0562934875488281,
+      "learning_rate": 0.0002,
+      "loss": 0.2276,
+      "step": 540
+    },
+    {
+      "epoch": 6.586826347305389,
+      "grad_norm": 1.1535356044769287,
+      "learning_rate": 0.0002,
+      "loss": 0.2469,
+      "step": 550
+    },
+    {
+      "epoch": 6.706586826347305,
+      "grad_norm": 0.9436424970626831,
+      "learning_rate": 0.0002,
+      "loss": 0.2713,
+      "step": 560
+    },
+    {
+      "epoch": 6.826347305389222,
+      "grad_norm": 1.0283164978027344,
+      "learning_rate": 0.0002,
+      "loss": 0.2449,
+      "step": 570
+    },
+    {
+      "epoch": 6.946107784431137,
+      "grad_norm": 1.3945902585983276,
+      "learning_rate": 0.0002,
+      "loss": 0.2193,
+      "step": 580
+    },
+    {
+      "epoch": 7.065868263473054,
+      "grad_norm": 0.5662649869918823,
+      "learning_rate": 0.0002,
+      "loss": 0.2415,
+      "step": 590
+    },
+    {
+      "epoch": 7.18562874251497,
+      "grad_norm": 0.4687662720680237,
+      "learning_rate": 0.0002,
+      "loss": 0.1792,
+      "step": 600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 100,
+  "total_flos": 1753733775298560.0,
+  "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 sha256:61628cace3d23a0b192a9deedee77f44155861bd679d5aea8149c0bf78beb87c
+size 5048