Training in progress, step 375, checkpoint

checkpoint-375/README.md

@@ -0,0 +1,202 @@
+---
+base_model: NESPED-GEN/StableCode-text2SQL-alias-indentacao
+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 0.13.2

checkpoint-375/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "StableLmForCausalLM",
+    "parent_library": "transformers.models.stablelm.modeling_stablelm"
+  },
+  "base_model_name_or_path": "NESPED-GEN/StableCode-text2SQL-alias-indentacao",
+  "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": 128,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-375/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eefc4c9c6b11a2569c35b4f2f06825826d03d25fe23cdec0d9bb4c5f9ee7a5be
+size 400616360

checkpoint-375/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c547c5d698cb5fa510ae8f8d9b677c23733df1bc038338fd01c1564288fe20c
+size 203945684

checkpoint-375/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd25ad948aee2cd37f8aaf1408d306a1578fcbcf46d53129be293b96438b55ef
+size 14308

checkpoint-375/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cf1731b6641be282bb186344db046c65d6f8e8730420f167b65308719422eef
+size 1064

checkpoint-375/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
+  }
+}

checkpoint-375/tokenizer_config.json

@@ -0,0 +1,392 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "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": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50278": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50279": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50280": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50281": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50282": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50283": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50284": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50285": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50286": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50287": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50288": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50289": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50290": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50291": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50292": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50293": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50294": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50295": {
+      "content": "<repo_continuation>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50296": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50297": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50298": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = 'You are a helpful assistant.' %}{% endif %}{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in loop_messages %}{% if loop.index0 == 0 %}{{'<|im_start|>system\n' + system_message + '<|im_end|>\n'}}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "map_device": "auto",
+  "model_max_length": 4096,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-375/trainer_state.json

@@ -0,0 +1,498 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9467878001297858,
+  "eval_steps": 25,
+  "global_step": 375,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12978585334198572,
+      "grad_norm": 64.38245391845703,
+      "learning_rate": 5e-07,
+      "logits/chosen": -1.9029332399368286,
+      "logits/rejected": -2.053706407546997,
+      "logps/chosen": -40.4902458190918,
+      "logps/rejected": -25.3558406829834,
+      "loss": 0.5968,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": 0.17978771030902863,
+      "rewards/margins": 0.2116149365901947,
+      "rewards/rejected": -0.031827230006456375,
+      "step": 25
+    },
+    {
+      "epoch": 0.12978585334198572,
+      "eval_logits/chosen": -1.9241564273834229,
+      "eval_logits/rejected": -2.0354554653167725,
+      "eval_logps/chosen": -38.01565933227539,
+      "eval_logps/rejected": -26.247798919677734,
+      "eval_loss": 0.454921156167984,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 0.4693543612957001,
+      "eval_rewards/margins": 0.5530296564102173,
+      "eval_rewards/rejected": -0.083675317466259,
+      "eval_runtime": 140.2735,
+      "eval_samples_per_second": 0.585,
+      "eval_steps_per_second": 0.585,
+      "step": 25
+    },
+    {
+      "epoch": 0.25957170668397145,
+      "grad_norm": 40.388370513916016,
+      "learning_rate": 5e-07,
+      "logits/chosen": -1.9818081855773926,
+      "logits/rejected": -2.0913336277008057,
+      "logps/chosen": -34.876155853271484,
+      "logps/rejected": -27.348379135131836,
+      "loss": 0.3498,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.7389992475509644,
+      "rewards/margins": 0.8872407674789429,
+      "rewards/rejected": -0.14824140071868896,
+      "step": 50
+    },
+    {
+      "epoch": 0.25957170668397145,
+      "eval_logits/chosen": -2.0032734870910645,
+      "eval_logits/rejected": -2.0942301750183105,
+      "eval_logps/chosen": -32.67618942260742,
+      "eval_logps/rejected": -27.68032455444336,
+      "eval_loss": 0.2584493160247803,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.003301739692688,
+      "eval_rewards/margins": 1.2302298545837402,
+      "eval_rewards/rejected": -0.22692809998989105,
+      "eval_runtime": 140.4996,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 50
+    },
+    {
+      "epoch": 0.3893575600259572,
+      "grad_norm": 29.64296531677246,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.0457983016967773,
+      "logits/rejected": -2.112644910812378,
+      "logps/chosen": -29.919565200805664,
+      "logps/rejected": -29.504945755004883,
+      "loss": 0.1989,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.2103655338287354,
+      "rewards/margins": 1.545750379562378,
+      "rewards/rejected": -0.33538496494293213,
+      "step": 75
+    },
+    {
+      "epoch": 0.3893575600259572,
+      "eval_logits/chosen": -2.056947946548462,
+      "eval_logits/rejected": -2.1299691200256348,
+      "eval_logps/chosen": -28.753862380981445,
+      "eval_logps/rejected": -30.1635684967041,
+      "eval_loss": 0.14609307050704956,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.3955342769622803,
+      "eval_rewards/margins": 1.8707866668701172,
+      "eval_rewards/rejected": -0.4752523899078369,
+      "eval_runtime": 140.5032,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 75
+    },
+    {
+      "epoch": 0.5191434133679429,
+      "grad_norm": 15.144841194152832,
+      "learning_rate": 5e-07,
+      "logits/chosen": -1.9773192405700684,
+      "logits/rejected": -2.081099271774292,
+      "logps/chosen": -27.414873123168945,
+      "logps/rejected": -32.0408935546875,
+      "loss": 0.1067,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.5709582567214966,
+      "rewards/margins": 2.2332875728607178,
+      "rewards/rejected": -0.6623291969299316,
+      "step": 100
+    },
+    {
+      "epoch": 0.5191434133679429,
+      "eval_logits/chosen": -2.0898687839508057,
+      "eval_logits/rejected": -2.1492760181427,
+      "eval_logps/chosen": -25.59548568725586,
+      "eval_logps/rejected": -34.3668098449707,
+      "eval_loss": 0.07369648665189743,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.7113721370697021,
+      "eval_rewards/margins": 2.6069483757019043,
+      "eval_rewards/rejected": -0.8955763578414917,
+      "eval_runtime": 140.7464,
+      "eval_samples_per_second": 0.583,
+      "eval_steps_per_second": 0.583,
+      "step": 100
+    },
+    {
+      "epoch": 0.6489292667099286,
+      "grad_norm": 6.891702175140381,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.0497264862060547,
+      "logits/rejected": -2.113835334777832,
+      "logps/chosen": -25.3034725189209,
+      "logps/rejected": -37.589698791503906,
+      "loss": 0.0501,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.810562014579773,
+      "rewards/margins": 3.047495126724243,
+      "rewards/rejected": -1.2369328737258911,
+      "step": 125
+    },
+    {
+      "epoch": 0.6489292667099286,
+      "eval_logits/chosen": -2.117217540740967,
+      "eval_logits/rejected": -2.166142463684082,
+      "eval_logps/chosen": -24.0587100982666,
+      "eval_logps/rejected": -42.671173095703125,
+      "eval_loss": 0.02941078133881092,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.8650493621826172,
+      "eval_rewards/margins": 3.59106183052063,
+      "eval_rewards/rejected": -1.7260124683380127,
+      "eval_runtime": 140.3665,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 125
+    },
+    {
+      "epoch": 0.7787151200519143,
+      "grad_norm": 2.0042898654937744,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.1526224613189697,
+      "logits/rejected": -2.214064598083496,
+      "logps/chosen": -24.000539779663086,
+      "logps/rejected": -47.32194900512695,
+      "loss": 0.0177,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.8812981843948364,
+      "rewards/margins": 4.163049697875977,
+      "rewards/rejected": -2.2817516326904297,
+      "step": 150
+    },
+    {
+      "epoch": 0.7787151200519143,
+      "eval_logits/chosen": -2.1497561931610107,
+      "eval_logits/rejected": -2.1853065490722656,
+      "eval_logps/chosen": -23.404022216796875,
+      "eval_logps/rejected": -53.90214538574219,
+      "eval_loss": 0.009417637251317501,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.930518388748169,
+      "eval_rewards/margins": 4.779628276824951,
+      "eval_rewards/rejected": -2.849109649658203,
+      "eval_runtime": 140.3986,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 150
+    },
+    {
+      "epoch": 0.9085009733939,
+      "grad_norm": 0.955883264541626,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.123363971710205,
+      "logits/rejected": -2.164508581161499,
+      "logps/chosen": -23.00540542602539,
+      "logps/rejected": -57.601531982421875,
+      "loss": 0.0062,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.9459924697875977,
+      "rewards/margins": 5.212995529174805,
+      "rewards/rejected": -3.2670037746429443,
+      "step": 175
+    },
+    {
+      "epoch": 0.9085009733939,
+      "eval_logits/chosen": -2.178921937942505,
+      "eval_logits/rejected": -2.198212146759033,
+      "eval_logps/chosen": -22.801753997802734,
+      "eval_logps/rejected": -63.14146423339844,
+      "eval_loss": 0.0035098514053970575,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 1.990744948387146,
+      "eval_rewards/margins": 5.763787269592285,
+      "eval_rewards/rejected": -3.7730419635772705,
+      "eval_runtime": 140.3451,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 175
+    },
+    {
+      "epoch": 1.0382868267358858,
+      "grad_norm": 0.22394584119319916,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.161266803741455,
+      "logits/rejected": -2.1958141326904297,
+      "logps/chosen": -22.247957229614258,
+      "logps/rejected": -67.36149597167969,
+      "loss": 0.0024,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 1.9859832525253296,
+      "rewards/margins": 6.165727615356445,
+      "rewards/rejected": -4.179744720458984,
+      "step": 200
+    },
+    {
+      "epoch": 1.0382868267358858,
+      "eval_logits/chosen": -2.2002382278442383,
+      "eval_logits/rejected": -2.2000482082366943,
+      "eval_logps/chosen": -22.139089584350586,
+      "eval_logps/rejected": -72.42859649658203,
+      "eval_loss": 0.001294078305363655,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.057011604309082,
+      "eval_rewards/margins": 6.7587666511535645,
+      "eval_rewards/rejected": -4.701755523681641,
+      "eval_runtime": 140.2609,
+      "eval_samples_per_second": 0.585,
+      "eval_steps_per_second": 0.585,
+      "step": 200
+    },
+    {
+      "epoch": 1.1680726800778716,
+      "grad_norm": 0.10501434653997421,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.195300340652466,
+      "logits/rejected": -2.1965079307556152,
+      "logps/chosen": -22.331872940063477,
+      "logps/rejected": -75.86756896972656,
+      "loss": 0.0009,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.0966131687164307,
+      "rewards/margins": 7.172005653381348,
+      "rewards/rejected": -5.075392723083496,
+      "step": 225
+    },
+    {
+      "epoch": 1.1680726800778716,
+      "eval_logits/chosen": -2.2084293365478516,
+      "eval_logits/rejected": -2.1937882900238037,
+      "eval_logps/chosen": -21.62232208251953,
+      "eval_logps/rejected": -80.40409088134766,
+      "eval_loss": 0.0005517782410606742,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.1086885929107666,
+      "eval_rewards/margins": 7.607994079589844,
+      "eval_rewards/rejected": -5.499305725097656,
+      "eval_runtime": 140.4282,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 225
+    },
+    {
+      "epoch": 1.2978585334198574,
+      "grad_norm": 0.12079267203807831,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.2555391788482666,
+      "logits/rejected": -2.2508366107940674,
+      "logps/chosen": -21.726062774658203,
+      "logps/rejected": -83.389892578125,
+      "loss": 0.0005,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.083451271057129,
+      "rewards/margins": 7.826067924499512,
+      "rewards/rejected": -5.742616653442383,
+      "step": 250
+    },
+    {
+      "epoch": 1.2978585334198574,
+      "eval_logits/chosen": -2.2094874382019043,
+      "eval_logits/rejected": -2.183870553970337,
+      "eval_logps/chosen": -21.337453842163086,
+      "eval_logps/rejected": -85.59798431396484,
+      "eval_loss": 0.00031946305534802377,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.1371753215789795,
+      "eval_rewards/margins": 8.155868530273438,
+      "eval_rewards/rejected": -6.018693923950195,
+      "eval_runtime": 140.1924,
+      "eval_samples_per_second": 0.585,
+      "eval_steps_per_second": 0.585,
+      "step": 250
+    },
+    {
+      "epoch": 1.427644386761843,
+      "grad_norm": 0.03313301131129265,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.1494364738464355,
+      "logits/rejected": -2.1585676670074463,
+      "logps/chosen": -21.17609405517578,
+      "logps/rejected": -86.35639953613281,
+      "loss": 0.0003,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.207101821899414,
+      "rewards/margins": 8.373501777648926,
+      "rewards/rejected": -6.166399955749512,
+      "step": 275
+    },
+    {
+      "epoch": 1.427644386761843,
+      "eval_logits/chosen": -2.2073066234588623,
+      "eval_logits/rejected": -2.174794912338257,
+      "eval_logps/chosen": -21.185022354125977,
+      "eval_logps/rejected": -89.19384765625,
+      "eval_loss": 0.00021948952053207904,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.1524181365966797,
+      "eval_rewards/margins": 8.530698776245117,
+      "eval_rewards/rejected": -6.378280162811279,
+      "eval_runtime": 140.1155,
+      "eval_samples_per_second": 0.585,
+      "eval_steps_per_second": 0.585,
+      "step": 275
+    },
+    {
+      "epoch": 1.5574302401038287,
+      "grad_norm": 0.03680599108338356,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.191593647003174,
+      "logits/rejected": -2.178603410720825,
+      "logps/chosen": -20.61453628540039,
+      "logps/rejected": -89.9397201538086,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.125040292739868,
+      "rewards/margins": 8.604403495788574,
+      "rewards/rejected": -6.479363918304443,
+      "step": 300
+    },
+    {
+      "epoch": 1.5574302401038287,
+      "eval_logits/chosen": -2.2045023441314697,
+      "eval_logits/rejected": -2.1671271324157715,
+      "eval_logps/chosen": -21.077783584594727,
+      "eval_logps/rejected": -91.99667358398438,
+      "eval_loss": 0.0001641342241782695,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.163142204284668,
+      "eval_rewards/margins": 8.821704864501953,
+      "eval_rewards/rejected": -6.658563613891602,
+      "eval_runtime": 140.5186,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 300
+    },
+    {
+      "epoch": 1.6872160934458145,
+      "grad_norm": 0.028771178796887398,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.203645706176758,
+      "logits/rejected": -2.166923761367798,
+      "logps/chosen": -20.792112350463867,
+      "logps/rejected": -93.08446502685547,
+      "loss": 0.0002,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.144740104675293,
+      "rewards/margins": 8.90222454071045,
+      "rewards/rejected": -6.7574849128723145,
+      "step": 325
+    },
+    {
+      "epoch": 1.6872160934458145,
+      "eval_logits/chosen": -2.2036421298980713,
+      "eval_logits/rejected": -2.1623051166534424,
+      "eval_logps/chosen": -20.99409294128418,
+      "eval_logps/rejected": -94.2848892211914,
+      "eval_loss": 0.000129787833429873,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.171510934829712,
+      "eval_rewards/margins": 9.0588960647583,
+      "eval_rewards/rejected": -6.887384414672852,
+      "eval_runtime": 140.302,
+      "eval_samples_per_second": 0.584,
+      "eval_steps_per_second": 0.584,
+      "step": 325
+    },
+    {
+      "epoch": 1.8170019467878,
+      "grad_norm": 0.022831246256828308,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.078533411026001,
+      "logits/rejected": -2.01901912689209,
+      "logps/chosen": -21.031679153442383,
+      "logps/rejected": -93.99193572998047,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.2570154666900635,
+      "rewards/margins": 9.124194145202637,
+      "rewards/rejected": -6.867178440093994,
+      "step": 350
+    },
+    {
+      "epoch": 1.8170019467878,
+      "eval_logits/chosen": -2.2034356594085693,
+      "eval_logits/rejected": -2.159289836883545,
+      "eval_logps/chosen": -20.922840118408203,
+      "eval_logps/rejected": -96.17369842529297,
+      "eval_loss": 0.00010680888954084367,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.178636312484741,
+      "eval_rewards/margins": 9.254901885986328,
+      "eval_rewards/rejected": -7.076265811920166,
+      "eval_runtime": 140.2323,
+      "eval_samples_per_second": 0.585,
+      "eval_steps_per_second": 0.585,
+      "step": 350
+    },
+    {
+      "epoch": 1.9467878001297858,
+      "grad_norm": 0.02170448750257492,
+      "learning_rate": 5e-07,
+      "logits/chosen": -2.220951795578003,
+      "logits/rejected": -2.174309015274048,
+      "logps/chosen": -20.899547576904297,
+      "logps/rejected": -96.2768325805664,
+      "loss": 0.0001,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 2.155444383621216,
+      "rewards/margins": 9.21989631652832,
+      "rewards/rejected": -7.064451217651367,
+      "step": 375
+    },
+    {
+      "epoch": 1.9467878001297858,
+      "eval_logits/chosen": -2.203279972076416,
+      "eval_logits/rejected": -2.1563150882720947,
+      "eval_logps/chosen": -20.860851287841797,
+      "eval_logps/rejected": -97.92994689941406,
+      "eval_loss": 8.922202687244862e-05,
+      "eval_rewards/accuracies": 1.0,
+      "eval_rewards/chosen": 2.184835195541382,
+      "eval_rewards/margins": 9.436725616455078,
+      "eval_rewards/rejected": -7.251890659332275,
+      "eval_runtime": 140.2052,
+      "eval_samples_per_second": 0.585,
+      "eval_steps_per_second": 0.585,
+      "step": 375
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 384,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 25,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-375/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0875d54ad5a021ce9621b2e913b94e8ad5ccf9d0e31a41995f438014f4e991db
+size 6072