Upload 14 files

README.md

@@ -0,0 +1,202 @@
+---
+base_model: microsoft/phi-2
+library_name: peft
+---
+
+# 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 0.11.2.dev0

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": null,
+  "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": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "fc2",
+    "q_proj",
+    "v_proj",
+    "fc1",
+    "dense",
+    "k_proj"
+  ],
+  "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 sha256:836db6ba5213b86be4a4571578452aa8aabd50de0b46aa1e943c279b7580966b
+size 47242496

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 sha256:2b61d54be3776786d2fc187f44064a5de265c205b5e5f917670f2e537a593f69
+size 94599226

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00acd1320f57f6400e21aa660c55aad0f2afef58070d4657e32f4f7c9dfb7892
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20374b9ce355f11e9edb49681e41eebe542315634b5fda6eec73f8247a8005f1
+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 +1,483 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.056603773584905,
+  "eval_steps": 10,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3018867924528302,
+      "grad_norm": 0.12168226391077042,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.5839,
+      "step": 10
+    },
+    {
+      "epoch": 0.3018867924528302,
+      "eval_loss": 2.4508910179138184,
+      "eval_runtime": 356.5361,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 10
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "grad_norm": 0.13410530984401703,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.5791,
+      "step": 20
+    },
+    {
+      "epoch": 0.6037735849056604,
+      "eval_loss": 2.438781261444092,
+      "eval_runtime": 355.7723,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 20
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "grad_norm": 0.16412803530693054,
+      "learning_rate": 2e-05,
+      "loss": 2.561,
+      "step": 30
+    },
+    {
+      "epoch": 0.9056603773584906,
+      "eval_loss": 2.409200429916382,
+      "eval_runtime": 356.6858,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 30
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "grad_norm": 0.1962829828262329,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 2.515,
+      "step": 40
+    },
+    {
+      "epoch": 1.2075471698113207,
+      "eval_loss": 2.369290828704834,
+      "eval_runtime": 356.4653,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 40
+    },
+    {
+      "epoch": 1.509433962264151,
+      "grad_norm": 0.2138909250497818,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 2.4646,
+      "step": 50
+    },
+    {
+      "epoch": 1.509433962264151,
+      "eval_loss": 2.330085039138794,
+      "eval_runtime": 355.0797,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 50
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "grad_norm": 0.24827434122562408,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 2.4343,
+      "step": 60
+    },
+    {
+      "epoch": 1.8113207547169812,
+      "eval_loss": 2.2919955253601074,
+      "eval_runtime": 355.0754,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 60
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "grad_norm": 0.27827900648117065,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 2.4112,
+      "step": 70
+    },
+    {
+      "epoch": 2.1132075471698113,
+      "eval_loss": 2.257754325866699,
+      "eval_runtime": 355.8986,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 70
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "grad_norm": 0.26660796999931335,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 2.3651,
+      "step": 80
+    },
+    {
+      "epoch": 2.4150943396226414,
+      "eval_loss": 2.2276153564453125,
+      "eval_runtime": 355.81,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 80
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "grad_norm": 0.2869923412799835,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 2.3413,
+      "step": 90
+    },
+    {
+      "epoch": 2.7169811320754715,
+      "eval_loss": 2.1996243000030518,
+      "eval_runtime": 356.1237,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 90
+    },
+    {
+      "epoch": 3.018867924528302,
+      "grad_norm": 0.29539480805397034,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 2.309,
+      "step": 100
+    },
+    {
+      "epoch": 3.018867924528302,
+      "eval_loss": 2.175126552581787,
+      "eval_runtime": 355.2283,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 100
+    },
+    {
+      "epoch": 3.3207547169811322,
+      "grad_norm": 0.2869047224521637,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 2.2908,
+      "step": 110
+    },
+    {
+      "epoch": 3.3207547169811322,
+      "eval_loss": 2.1576268672943115,
+      "eval_runtime": 354.9528,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 110
+    },
+    {
+      "epoch": 3.6226415094339623,
+      "grad_norm": 0.29853248596191406,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 2.2538,
+      "step": 120
+    },
+    {
+      "epoch": 3.6226415094339623,
+      "eval_loss": 2.1427152156829834,
+      "eval_runtime": 355.8889,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 120
+    },
+    {
+      "epoch": 3.9245283018867925,
+      "grad_norm": 0.3196108043193817,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 2.262,
+      "step": 130
+    },
+    {
+      "epoch": 3.9245283018867925,
+      "eval_loss": 2.1301257610321045,
+      "eval_runtime": 356.3065,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 130
+    },
+    {
+      "epoch": 4.226415094339623,
+      "grad_norm": 0.32266777753829956,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 2.2209,
+      "step": 140
+    },
+    {
+      "epoch": 4.226415094339623,
+      "eval_loss": 2.119654893875122,
+      "eval_runtime": 354.8329,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 140
+    },
+    {
+      "epoch": 4.528301886792453,
+      "grad_norm": 0.32279086112976074,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 2.2248,
+      "step": 150
+    },
+    {
+      "epoch": 4.528301886792453,
+      "eval_loss": 2.11035418510437,
+      "eval_runtime": 355.4708,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 150
+    },
+    {
+      "epoch": 4.830188679245283,
+      "grad_norm": 0.3195267617702484,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 2.2249,
+      "step": 160
+    },
+    {
+      "epoch": 4.830188679245283,
+      "eval_loss": 2.102231025695801,
+      "eval_runtime": 355.8543,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 160
+    },
+    {
+      "epoch": 5.132075471698113,
+      "grad_norm": 0.3310501277446747,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 2.2063,
+      "step": 170
+    },
+    {
+      "epoch": 5.132075471698113,
+      "eval_loss": 2.094794750213623,
+      "eval_runtime": 357.0843,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 170
+    },
+    {
+      "epoch": 5.433962264150943,
+      "grad_norm": 0.33955734968185425,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 2.1997,
+      "step": 180
+    },
+    {
+      "epoch": 5.433962264150943,
+      "eval_loss": 2.0882046222686768,
+      "eval_runtime": 356.6814,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 180
+    },
+    {
+      "epoch": 5.735849056603773,
+      "grad_norm": 0.3333246111869812,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 2.1985,
+      "step": 190
+    },
+    {
+      "epoch": 5.735849056603773,
+      "eval_loss": 2.0826594829559326,
+      "eval_runtime": 355.813,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 190
+    },
+    {
+      "epoch": 6.037735849056604,
+      "grad_norm": 0.34075412154197693,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 2.1992,
+      "step": 200
+    },
+    {
+      "epoch": 6.037735849056604,
+      "eval_loss": 2.078132390975952,
+      "eval_runtime": 357.7349,
+      "eval_samples_per_second": 0.366,
+      "eval_steps_per_second": 0.366,
+      "step": 200
+    },
+    {
+      "epoch": 6.339622641509434,
+      "grad_norm": 0.3513352870941162,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 2.1851,
+      "step": 210
+    },
+    {
+      "epoch": 6.339622641509434,
+      "eval_loss": 2.0746688842773438,
+      "eval_runtime": 355.6074,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 210
+    },
+    {
+      "epoch": 6.6415094339622645,
+      "grad_norm": 0.359353631734848,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 2.178,
+      "step": 220
+    },
+    {
+      "epoch": 6.6415094339622645,
+      "eval_loss": 2.0718541145324707,
+      "eval_runtime": 354.8685,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 220
+    },
+    {
+      "epoch": 6.943396226415095,
+      "grad_norm": 0.3545942008495331,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 2.1698,
+      "step": 230
+    },
+    {
+      "epoch": 6.943396226415095,
+      "eval_loss": 2.069652557373047,
+      "eval_runtime": 356.0491,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 230
+    },
+    {
+      "epoch": 7.245283018867925,
+      "grad_norm": 0.35219329595565796,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 2.1768,
+      "step": 240
+    },
+    {
+      "epoch": 7.245283018867925,
+      "eval_loss": 2.068044424057007,
+      "eval_runtime": 355.5515,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 240
+    },
+    {
+      "epoch": 7.547169811320755,
+      "grad_norm": 0.3606317341327667,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 2.17,
+      "step": 250
+    },
+    {
+      "epoch": 7.547169811320755,
+      "eval_loss": 2.0668373107910156,
+      "eval_runtime": 355.9606,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 250
+    },
+    {
+      "epoch": 7.849056603773585,
+      "grad_norm": 0.345058798789978,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 2.1755,
+      "step": 260
+    },
+    {
+      "epoch": 7.849056603773585,
+      "eval_loss": 2.066086769104004,
+      "eval_runtime": 354.824,
+      "eval_samples_per_second": 0.369,
+      "eval_steps_per_second": 0.369,
+      "step": 260
+    },
+    {
+      "epoch": 8.150943396226415,
+      "grad_norm": 0.3428496718406677,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 2.1665,
+      "step": 270
+    },
+    {
+      "epoch": 8.150943396226415,
+      "eval_loss": 2.065619707107544,
+      "eval_runtime": 355.814,
+      "eval_samples_per_second": 0.368,
+      "eval_steps_per_second": 0.368,
+      "step": 270
+    },
+    {
+      "epoch": 8.452830188679245,
+      "grad_norm": 0.34520721435546875,
+      "learning_rate": 2.6955129420176193e-07,
+      "loss": 2.1752,
+      "step": 280
+    },
+    {
+      "epoch": 8.452830188679245,
+      "eval_loss": 2.0653860569000244,
+      "eval_runtime": 357.4979,
+      "eval_samples_per_second": 0.366,
+      "eval_steps_per_second": 0.366,
+      "step": 280
+    },
+    {
+      "epoch": 8.754716981132075,
+      "grad_norm": 0.3415066599845886,
+      "learning_rate": 6.761642258056977e-08,
+      "loss": 2.1724,
+      "step": 290
+    },
+    {
+      "epoch": 8.754716981132075,
+      "eval_loss": 2.065295934677124,
+      "eval_runtime": 357.1321,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 290
+    },
+    {
+      "epoch": 9.056603773584905,
+      "grad_norm": 0.35265278816223145,
+      "learning_rate": 0.0,
+      "loss": 2.168,
+      "step": 300
+    },
+    {
+      "epoch": 9.056603773584905,
+      "eval_loss": 2.0652811527252197,
+      "eval_runtime": 357.0379,
+      "eval_samples_per_second": 0.367,
+      "eval_steps_per_second": 0.367,
+      "step": 300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.97219261251584e+17,
+  "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 sha256:0f65acf41c3dffa61f91d36447a291291d816db100a90d20dbb375584643e8b7
+size 5048