Upload folder using huggingface_hub

README.md

@@ -3,7 +3,7 @@ base_model: deepseek-ai/deepseek-llm-7b-base
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:deepseek-ai/deepseek-llm-7b-base
+- "base_model:adapter:deepseek-ai/deepseek-llm-7b-base"
 - lora
 - transformers
 ---
@@ -22,7 +22,7 @@ tags:
 
 
 
-- **Developed by:** [More Information Needed]
+- **Developed by:** Yash Patel
 - **Funded by [optional]:** [More Information Needed]
 - **Shared by [optional]:** [More Information Needed]
 - **Model type:** [More Information Needed]
@@ -204,4 +204,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.17.0
+- PEFT 0.16.0

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "./local_deepseek",
+  "base_model_name_or_path": "deepseek-ai/deepseek-llm-7b-base",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -25,10 +25,9 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee2e75f6111b75502863e17f075419497350ef732733c7ccf240823cd1b2f01
+oid sha256:90afb5522f753a707d49aa165e0cec111ebf1fea7ef205d6353e91a9c4f3c7a0
 size 31473392

checkpoint-1500/README.md

@@ -0,0 +1,207 @@
+---
+base_model: ./local_deepseek
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./local_deepseek
+- lora
+- transformers
+---
+
+# 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 0.16.0

checkpoint-1500/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./local_deepseek",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de4507a6d4bbaab0f59a6bf44314afe0c34fcd44c7190a6ca2f219015b9b48b9
+size 31473392

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:852edeb9c5ce44862cbbec4e08f2ac2a19442d75532b8e0455ceea38369130ef
+size 63018123

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03d5be69efac24567c1fbaf3c4300f072cbb97fb82cfbcde6e7af7fdccac138
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcf829931b47e9815cf1b671ec171a9f49df4e5e418e94e0ffee769bb4b171a
+size 1465

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,138 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.43920292801952,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016266775111834077,
+      "grad_norm": 0.15190425515174866,
+      "learning_rate": 1.9902439024390247e-05,
+      "loss": 2.4224,
+      "step": 10
+    },
+    {
+      "epoch": 0.032533550223668155,
+      "grad_norm": 0.13811910152435303,
+      "learning_rate": 1.9794037940379405e-05,
+      "loss": 2.4266,
+      "step": 20
+    },
+    {
+      "epoch": 0.048800325335502236,
+      "grad_norm": 0.14573918282985687,
+      "learning_rate": 1.9685636856368567e-05,
+      "loss": 2.4425,
+      "step": 30
+    },
+    {
+      "epoch": 0.06506710044733631,
+      "grad_norm": 0.16350996494293213,
+      "learning_rate": 1.9577235772357725e-05,
+      "loss": 2.397,
+      "step": 40
+    },
+    {
+      "epoch": 0.08133387555917039,
+      "grad_norm": 0.14666102826595306,
+      "learning_rate": 1.9468834688346883e-05,
+      "loss": 2.3677,
+      "step": 50
+    },
+    {
+      "epoch": 0.09760065067100447,
+      "grad_norm": 0.10224353522062302,
+      "learning_rate": 1.9360433604336045e-05,
+      "loss": 2.3969,
+      "step": 60
+    },
+    {
+      "epoch": 0.11386742578283855,
+      "grad_norm": 0.19328653812408447,
+      "learning_rate": 1.9252032520325206e-05,
+      "loss": 2.4367,
+      "step": 70
+    },
+    {
+      "epoch": 0.13013420089467262,
+      "grad_norm": 0.15589460730552673,
+      "learning_rate": 1.9143631436314365e-05,
+      "loss": 2.3979,
+      "step": 80
+    },
+    {
+      "epoch": 0.1464009760065067,
+      "grad_norm": 0.15351463854312897,
+      "learning_rate": 1.9035230352303523e-05,
+      "loss": 2.3628,
+      "step": 90
+    },
+    {
+      "epoch": 0.16266775111834078,
+      "grad_norm": 0.1756143420934677,
+      "learning_rate": 1.8926829268292684e-05,
+      "loss": 2.4175,
+      "step": 100
+    },
+    {
+      "epoch": 0.17893452623017486,
+      "grad_norm": 0.15267857909202576,
+      "learning_rate": 1.8818428184281846e-05,
+      "loss": 2.3335,
+      "step": 110
+    },
+    {
+      "epoch": 0.19520130134200894,
+      "grad_norm": 0.15103495121002197,
+      "learning_rate": 1.8710027100271004e-05,
+      "loss": 2.3256,
+      "step": 120
+    },
+    {
+      "epoch": 0.21146807645384302,
+      "grad_norm": 0.20331667363643646,
+      "learning_rate": 1.8601626016260162e-05,
+      "loss": 2.3173,
+      "step": 130
+    },
+    {
+      "epoch": 0.2277348515656771,
+      "grad_norm": 0.18745240569114685,
+      "learning_rate": 1.8493224932249324e-05,
+      "loss": 2.3128,
+      "step": 140
+    },
+    {
+      "epoch": 0.24400162667751119,
+      "grad_norm": 0.20769692957401276,
+      "learning_rate": 1.8384823848238485e-05,
+      "loss": 2.3524,
+      "step": 150
+    },
+    {
+      "epoch": 0.26026840178934524,
+      "grad_norm": 0.2246929258108139,
+      "learning_rate": 1.8276422764227644e-05,
+      "loss": 2.3513,
+      "step": 160
+    },
+    {
+      "epoch": 0.27653517690117935,
+      "grad_norm": 0.20076365768909454,
+      "learning_rate": 1.8168021680216802e-05,
+      "loss": 2.2622,
+      "step": 170
+    },
+    {
+      "epoch": 0.2928019520130134,
+      "grad_norm": 0.2003357708454132,
+      "learning_rate": 1.8059620596205963e-05,
+      "loss": 2.2533,
+      "step": 180
+    },
+    {
+      "epoch": 0.3090687271248475,
+      "grad_norm": 0.2662675082683563,
+      "learning_rate": 1.7951219512195125e-05,
+      "loss": 2.2756,
+      "step": 190
+    },
+    {
+      "epoch": 0.32533550223668156,
+      "grad_norm": 0.2601667046546936,
+      "learning_rate": 1.7842818428184283e-05,
+      "loss": 2.3471,
+      "step": 200
+    },
+    {
+      "epoch": 0.34160227734851567,
+      "grad_norm": 0.3059883117675781,
+      "learning_rate": 1.773441734417344e-05,
+      "loss": 2.3301,
+      "step": 210
+    },
+    {
+      "epoch": 0.3578690524603497,
+      "grad_norm": 0.20538951456546783,
+      "learning_rate": 1.7626016260162603e-05,
+      "loss": 2.2963,
+      "step": 220
+    },
+    {
+      "epoch": 0.37413582757218383,
+      "grad_norm": 0.3262976109981537,
+      "learning_rate": 1.7517615176151764e-05,
+      "loss": 2.2957,
+      "step": 230
+    },
+    {
+      "epoch": 0.3904026026840179,
+      "grad_norm": 0.22966964542865753,
+      "learning_rate": 1.7409214092140923e-05,
+      "loss": 2.2636,
+      "step": 240
+    },
+    {
+      "epoch": 0.406669377795852,
+      "grad_norm": 0.26744940876960754,
+      "learning_rate": 1.730081300813008e-05,
+      "loss": 2.288,
+      "step": 250
+    },
+    {
+      "epoch": 0.42293615290768605,
+      "grad_norm": 0.2023824006319046,
+      "learning_rate": 1.7192411924119242e-05,
+      "loss": 2.2703,
+      "step": 260
+    },
+    {
+      "epoch": 0.43920292801952016,
+      "grad_norm": 0.2542593479156494,
+      "learning_rate": 1.7084010840108404e-05,
+      "loss": 2.2129,
+      "step": 270
+    },
+    {
+      "epoch": 0.4554697031313542,
+      "grad_norm": 0.2524624466896057,
+      "learning_rate": 1.6975609756097562e-05,
+      "loss": 2.2678,
+      "step": 280
+    },
+    {
+      "epoch": 0.47173647824318826,
+      "grad_norm": 0.28020623326301575,
+      "learning_rate": 1.686720867208672e-05,
+      "loss": 2.3569,
+      "step": 290
+    },
+    {
+      "epoch": 0.48800325335502237,
+      "grad_norm": 0.2878577709197998,
+      "learning_rate": 1.6758807588075882e-05,
+      "loss": 2.2217,
+      "step": 300
+    },
+    {
+      "epoch": 0.5042700284668564,
+      "grad_norm": 0.20536544919013977,
+      "learning_rate": 1.6650406504065043e-05,
+      "loss": 2.3558,
+      "step": 310
+    },
+    {
+      "epoch": 0.5205368035786905,
+      "grad_norm": 0.20909422636032104,
+      "learning_rate": 1.65420054200542e-05,
+      "loss": 2.2742,
+      "step": 320
+    },
+    {
+      "epoch": 0.5368035786905246,
+      "grad_norm": 0.4000333249568939,
+      "learning_rate": 1.6433604336043363e-05,
+      "loss": 2.2846,
+      "step": 330
+    },
+    {
+      "epoch": 0.5530703538023587,
+      "grad_norm": 0.31831657886505127,
+      "learning_rate": 1.632520325203252e-05,
+      "loss": 2.2377,
+      "step": 340
+    },
+    {
+      "epoch": 0.5693371289141927,
+      "grad_norm": 0.28702083230018616,
+      "learning_rate": 1.6216802168021683e-05,
+      "loss": 2.3066,
+      "step": 350
+    },
+    {
+      "epoch": 0.5856039040260268,
+      "grad_norm": 0.34019768238067627,
+      "learning_rate": 1.610840108401084e-05,
+      "loss": 2.2489,
+      "step": 360
+    },
+    {
+      "epoch": 0.601870679137861,
+      "grad_norm": 0.3892984688282013,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3081,
+      "step": 370
+    },
+    {
+      "epoch": 0.618137454249695,
+      "grad_norm": 0.26910895109176636,
+      "learning_rate": 1.589159891598916e-05,
+      "loss": 2.1796,
+      "step": 380
+    },
+    {
+      "epoch": 0.6344042293615291,
+      "grad_norm": 0.25772690773010254,
+      "learning_rate": 1.5783197831978322e-05,
+      "loss": 2.2078,
+      "step": 390
+    },
+    {
+      "epoch": 0.6506710044733631,
+      "grad_norm": 0.553435206413269,
+      "learning_rate": 1.567479674796748e-05,
+      "loss": 2.2078,
+      "step": 400
+    },
+    {
+      "epoch": 0.6669377795851973,
+      "grad_norm": 0.22907570004463196,
+      "learning_rate": 1.5566395663956642e-05,
+      "loss": 2.2428,
+      "step": 410
+    },
+    {
+      "epoch": 0.6832045546970313,
+      "grad_norm": 0.3672320246696472,
+      "learning_rate": 1.54579945799458e-05,
+      "loss": 2.2479,
+      "step": 420
+    },
+    {
+      "epoch": 0.6994713298088654,
+      "grad_norm": 0.4416728615760803,
+      "learning_rate": 1.534959349593496e-05,
+      "loss": 2.2236,
+      "step": 430
+    },
+    {
+      "epoch": 0.7157381049206994,
+      "grad_norm": 0.37598440051078796,
+      "learning_rate": 1.524119241192412e-05,
+      "loss": 2.2146,
+      "step": 440
+    },
+    {
+      "epoch": 0.7320048800325335,
+      "grad_norm": 0.4336397647857666,
+      "learning_rate": 1.5132791327913282e-05,
+      "loss": 2.2324,
+      "step": 450
+    },
+    {
+      "epoch": 0.7482716551443677,
+      "grad_norm": 0.29831627011299133,
+      "learning_rate": 1.502439024390244e-05,
+      "loss": 2.2328,
+      "step": 460
+    },
+    {
+      "epoch": 0.7645384302562017,
+      "grad_norm": 0.5829563140869141,
+      "learning_rate": 1.49159891598916e-05,
+      "loss": 2.2147,
+      "step": 470
+    },
+    {
+      "epoch": 0.7808052053680358,
+      "grad_norm": 0.25096556544303894,
+      "learning_rate": 1.4807588075880761e-05,
+      "loss": 2.2572,
+      "step": 480
+    },
+    {
+      "epoch": 0.7970719804798698,
+      "grad_norm": 0.3719277083873749,
+      "learning_rate": 1.4699186991869921e-05,
+      "loss": 2.1964,
+      "step": 490
+    },
+    {
+      "epoch": 0.813338755591704,
+      "grad_norm": 0.3131086528301239,
+      "learning_rate": 1.459078590785908e-05,
+      "loss": 2.2893,
+      "step": 500
+    },
+    {
+      "epoch": 0.829605530703538,
+      "grad_norm": 0.31521037220954895,
+      "learning_rate": 1.448238482384824e-05,
+      "loss": 2.2498,
+      "step": 510
+    },
+    {
+      "epoch": 0.8458723058153721,
+      "grad_norm": 0.3911826014518738,
+      "learning_rate": 1.43739837398374e-05,
+      "loss": 2.2444,
+      "step": 520
+    },
+    {
+      "epoch": 0.8621390809272061,
+      "grad_norm": 0.27660906314849854,
+      "learning_rate": 1.4265582655826559e-05,
+      "loss": 2.2571,
+      "step": 530
+    },
+    {
+      "epoch": 0.8784058560390403,
+      "grad_norm": 0.5232799053192139,
+      "learning_rate": 1.4157181571815719e-05,
+      "loss": 2.2419,
+      "step": 540
+    },
+    {
+      "epoch": 0.8946726311508744,
+      "grad_norm": 0.3597722053527832,
+      "learning_rate": 1.4048780487804879e-05,
+      "loss": 2.2426,
+      "step": 550
+    },
+    {
+      "epoch": 0.9109394062627084,
+      "grad_norm": 0.3321545422077179,
+      "learning_rate": 1.394037940379404e-05,
+      "loss": 2.2136,
+      "step": 560
+    },
+    {
+      "epoch": 0.9272061813745425,
+      "grad_norm": 0.4088381826877594,
+      "learning_rate": 1.3831978319783199e-05,
+      "loss": 2.1917,
+      "step": 570
+    },
+    {
+      "epoch": 0.9434729564863765,
+      "grad_norm": 0.4453414976596832,
+      "learning_rate": 1.3723577235772358e-05,
+      "loss": 2.2404,
+      "step": 580
+    },
+    {
+      "epoch": 0.9597397315982107,
+      "grad_norm": 0.33261504769325256,
+      "learning_rate": 1.3615176151761518e-05,
+      "loss": 2.2778,
+      "step": 590
+    },
+    {
+      "epoch": 0.9760065067100447,
+      "grad_norm": 0.3876469135284424,
+      "learning_rate": 1.350677506775068e-05,
+      "loss": 2.1898,
+      "step": 600
+    },
+    {
+      "epoch": 0.9922732818218788,
+      "grad_norm": 0.33917632699012756,
+      "learning_rate": 1.3398373983739838e-05,
+      "loss": 2.2822,
+      "step": 610
+    },
+    {
+      "epoch": 1.008133387555917,
+      "grad_norm": 0.33381298184394836,
+      "learning_rate": 1.3289972899728998e-05,
+      "loss": 2.2269,
+      "step": 620
+    },
+    {
+      "epoch": 1.024400162667751,
+      "grad_norm": 0.284834623336792,
+      "learning_rate": 1.318157181571816e-05,
+      "loss": 2.2241,
+      "step": 630
+    },
+    {
+      "epoch": 1.0406669377795852,
+      "grad_norm": 0.4045396149158478,
+      "learning_rate": 1.307317073170732e-05,
+      "loss": 2.2347,
+      "step": 640
+    },
+    {
+      "epoch": 1.0569337128914194,
+      "grad_norm": 0.543749213218689,
+      "learning_rate": 1.2964769647696478e-05,
+      "loss": 2.1799,
+      "step": 650
+    },
+    {
+      "epoch": 1.0732004880032533,
+      "grad_norm": 0.34489476680755615,
+      "learning_rate": 1.2856368563685637e-05,
+      "loss": 2.24,
+      "step": 660
+    },
+    {
+      "epoch": 1.0894672631150875,
+      "grad_norm": 0.4727187752723694,
+      "learning_rate": 1.2747967479674799e-05,
+      "loss": 2.2818,
+      "step": 670
+    },
+    {
+      "epoch": 1.1057340382269216,
+      "grad_norm": 0.41018274426460266,
+      "learning_rate": 1.2639566395663959e-05,
+      "loss": 2.1991,
+      "step": 680
+    },
+    {
+      "epoch": 1.1220008133387556,
+      "grad_norm": 0.3846307098865509,
+      "learning_rate": 1.2531165311653117e-05,
+      "loss": 2.1835,
+      "step": 690
+    },
+    {
+      "epoch": 1.1382675884505897,
+      "grad_norm": 0.45072686672210693,
+      "learning_rate": 1.2422764227642277e-05,
+      "loss": 2.2661,
+      "step": 700
+    },
+    {
+      "epoch": 1.1545343635624237,
+      "grad_norm": 0.4832310676574707,
+      "learning_rate": 1.2314363143631439e-05,
+      "loss": 2.216,
+      "step": 710
+    },
+    {
+      "epoch": 1.1708011386742578,
+      "grad_norm": 0.5275405049324036,
+      "learning_rate": 1.2205962059620597e-05,
+      "loss": 2.208,
+      "step": 720
+    },
+    {
+      "epoch": 1.187067913786092,
+      "grad_norm": 0.3692767322063446,
+      "learning_rate": 1.2097560975609757e-05,
+      "loss": 2.289,
+      "step": 730
+    },
+    {
+      "epoch": 1.203334688897926,
+      "grad_norm": 0.29335182905197144,
+      "learning_rate": 1.1989159891598916e-05,
+      "loss": 2.1959,
+      "step": 740
+    },
+    {
+      "epoch": 1.21960146400976,
+      "grad_norm": 0.49091747403144836,
+      "learning_rate": 1.1880758807588078e-05,
+      "loss": 2.1451,
+      "step": 750
+    },
+    {
+      "epoch": 1.235868239121594,
+      "grad_norm": 0.3522561490535736,
+      "learning_rate": 1.1772357723577236e-05,
+      "loss": 2.248,
+      "step": 760
+    },
+    {
+      "epoch": 1.2521350142334282,
+      "grad_norm": 0.41444632411003113,
+      "learning_rate": 1.1663956639566396e-05,
+      "loss": 2.1832,
+      "step": 770
+    },
+    {
+      "epoch": 1.2684017893452624,
+      "grad_norm": 0.4403276741504669,
+      "learning_rate": 1.1555555555555556e-05,
+      "loss": 2.1923,
+      "step": 780
+    },
+    {
+      "epoch": 1.2846685644570963,
+      "grad_norm": 0.4993409514427185,
+      "learning_rate": 1.1447154471544718e-05,
+      "loss": 2.1518,
+      "step": 790
+    },
+    {
+      "epoch": 1.3009353395689305,
+      "grad_norm": 0.3903736174106598,
+      "learning_rate": 1.1338753387533876e-05,
+      "loss": 2.19,
+      "step": 800
+    },
+    {
+      "epoch": 1.3172021146807644,
+      "grad_norm": 0.31108370423316956,
+      "learning_rate": 1.1230352303523036e-05,
+      "loss": 2.1852,
+      "step": 810
+    },
+    {
+      "epoch": 1.3334688897925986,
+      "grad_norm": 0.3845357894897461,
+      "learning_rate": 1.1121951219512197e-05,
+      "loss": 2.1589,
+      "step": 820
+    },
+    {
+      "epoch": 1.3497356649044328,
+      "grad_norm": 0.4706804156303406,
+      "learning_rate": 1.1013550135501357e-05,
+      "loss": 2.1925,
+      "step": 830
+    },
+    {
+      "epoch": 1.3660024400162667,
+      "grad_norm": 0.33979251980781555,
+      "learning_rate": 1.0905149051490515e-05,
+      "loss": 2.2165,
+      "step": 840
+    },
+    {
+      "epoch": 1.3822692151281009,
+      "grad_norm": 0.6070290803909302,
+      "learning_rate": 1.0796747967479675e-05,
+      "loss": 2.2304,
+      "step": 850
+    },
+    {
+      "epoch": 1.3985359902399348,
+      "grad_norm": 0.3914659321308136,
+      "learning_rate": 1.0688346883468837e-05,
+      "loss": 2.1945,
+      "step": 860
+    },
+    {
+      "epoch": 1.414802765351769,
+      "grad_norm": 0.38425302505493164,
+      "learning_rate": 1.0579945799457995e-05,
+      "loss": 2.1799,
+      "step": 870
+    },
+    {
+      "epoch": 1.4310695404636031,
+      "grad_norm": 0.3691774904727936,
+      "learning_rate": 1.0471544715447155e-05,
+      "loss": 2.1812,
+      "step": 880
+    },
+    {
+      "epoch": 1.4473363155754373,
+      "grad_norm": 0.4350150525569916,
+      "learning_rate": 1.0363143631436315e-05,
+      "loss": 2.2151,
+      "step": 890
+    },
+    {
+      "epoch": 1.4636030906872712,
+      "grad_norm": 0.37822458148002625,
+      "learning_rate": 1.0254742547425476e-05,
+      "loss": 2.2839,
+      "step": 900
+    },
+    {
+      "epoch": 1.4798698657991054,
+      "grad_norm": 0.4036807715892792,
+      "learning_rate": 1.0146341463414634e-05,
+      "loss": 2.2456,
+      "step": 910
+    },
+    {
+      "epoch": 1.4961366409109393,
+      "grad_norm": 0.3395715653896332,
+      "learning_rate": 1.0037940379403794e-05,
+      "loss": 2.2455,
+      "step": 920
+    },
+    {
+      "epoch": 1.5124034160227735,
+      "grad_norm": 0.8333190679550171,
+      "learning_rate": 9.929539295392954e-06,
+      "loss": 2.215,
+      "step": 930
+    },
+    {
+      "epoch": 1.5286701911346077,
+      "grad_norm": 0.47911304235458374,
+      "learning_rate": 9.821138211382114e-06,
+      "loss": 2.2095,
+      "step": 940
+    },
+    {
+      "epoch": 1.5449369662464416,
+      "grad_norm": 0.421014666557312,
+      "learning_rate": 9.712737127371274e-06,
+      "loss": 2.2236,
+      "step": 950
+    },
+    {
+      "epoch": 1.5612037413582758,
+      "grad_norm": 0.48267999291419983,
+      "learning_rate": 9.604336043360435e-06,
+      "loss": 2.2163,
+      "step": 960
+    },
+    {
+      "epoch": 1.5774705164701097,
+      "grad_norm": 0.39987218379974365,
+      "learning_rate": 9.495934959349594e-06,
+      "loss": 2.1863,
+      "step": 970
+    },
+    {
+      "epoch": 1.5937372915819439,
+      "grad_norm": 0.6446450352668762,
+      "learning_rate": 9.387533875338755e-06,
+      "loss": 2.1801,
+      "step": 980
+    },
+    {
+      "epoch": 1.610004066693778,
+      "grad_norm": 0.4291459321975708,
+      "learning_rate": 9.279132791327913e-06,
+      "loss": 2.2346,
+      "step": 990
+    },
+    {
+      "epoch": 1.626270841805612,
+      "grad_norm": 0.5329392552375793,
+      "learning_rate": 9.170731707317075e-06,
+      "loss": 2.1606,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6425376169174462,
+      "grad_norm": 0.6420161128044128,
+      "learning_rate": 9.062330623306233e-06,
+      "loss": 2.1936,
+      "step": 1010
+    },
+    {
+      "epoch": 1.65880439202928,
+      "grad_norm": 0.5436628460884094,
+      "learning_rate": 8.953929539295395e-06,
+      "loss": 2.182,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6750711671411143,
+      "grad_norm": 0.3877139985561371,
+      "learning_rate": 8.845528455284553e-06,
+      "loss": 2.2317,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6913379422529484,
+      "grad_norm": 0.5903089046478271,
+      "learning_rate": 8.737127371273714e-06,
+      "loss": 2.2121,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7076047173647826,
+      "grad_norm": 0.4182610511779785,
+      "learning_rate": 8.628726287262873e-06,
+      "loss": 2.1664,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7238714924766165,
+      "grad_norm": 0.701687216758728,
+      "learning_rate": 8.520325203252033e-06,
+      "loss": 2.1705,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7401382675884505,
+      "grad_norm": 0.6748879551887512,
+      "learning_rate": 8.411924119241192e-06,
+      "loss": 2.209,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7564050427002846,
+      "grad_norm": 0.49491748213768005,
+      "learning_rate": 8.303523035230352e-06,
+      "loss": 2.1947,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7726718178121188,
+      "grad_norm": 0.4370752274990082,
+      "learning_rate": 8.195121951219512e-06,
+      "loss": 2.1833,
+      "step": 1090
+    },
+    {
+      "epoch": 1.788938592923953,
+      "grad_norm": 0.3895672559738159,
+      "learning_rate": 8.086720867208672e-06,
+      "loss": 2.2577,
+      "step": 1100
+    },
+    {
+      "epoch": 1.805205368035787,
+      "grad_norm": 0.3882943093776703,
+      "learning_rate": 7.978319783197834e-06,
+      "loss": 2.1802,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8214721431476208,
+      "grad_norm": 0.4686112403869629,
+      "learning_rate": 7.869918699186992e-06,
+      "loss": 2.1258,
+      "step": 1120
+    },
+    {
+      "epoch": 1.837738918259455,
+      "grad_norm": 0.5097848773002625,
+      "learning_rate": 7.761517615176153e-06,
+      "loss": 2.212,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8540056933712892,
+      "grad_norm": 0.49870142340660095,
+      "learning_rate": 7.653116531165312e-06,
+      "loss": 2.2587,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8702724684831233,
+      "grad_norm": 0.612582266330719,
+      "learning_rate": 7.544715447154472e-06,
+      "loss": 2.1571,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8865392435949573,
+      "grad_norm": 0.5550523400306702,
+      "learning_rate": 7.436314363143632e-06,
+      "loss": 2.1993,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9028060187067912,
+      "grad_norm": 0.921201229095459,
+      "learning_rate": 7.327913279132792e-06,
+      "loss": 2.1619,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9190727938186254,
+      "grad_norm": 0.5052744746208191,
+      "learning_rate": 7.219512195121952e-06,
+      "loss": 2.1743,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9353395689304596,
+      "grad_norm": 0.6115371584892273,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 2.1839,
+      "step": 1190
+    },
+    {
+      "epoch": 1.9516063440422937,
+      "grad_norm": 0.5317726731300354,
+      "learning_rate": 7.002710027100271e-06,
+      "loss": 2.1704,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9678731191541277,
+      "grad_norm": 0.4624195694923401,
+      "learning_rate": 6.894308943089432e-06,
+      "loss": 2.2127,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9841398942659618,
+      "grad_norm": 0.50515216588974,
+      "learning_rate": 6.785907859078591e-06,
+      "loss": 2.1522,
+      "step": 1220
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6244822144508362,
+      "learning_rate": 6.677506775067751e-06,
+      "loss": 2.1697,
+      "step": 1230
+    },
+    {
+      "epoch": 2.016266775111834,
+      "grad_norm": 0.5226220488548279,
+      "learning_rate": 6.56910569105691e-06,
+      "loss": 2.2529,
+      "step": 1240
+    },
+    {
+      "epoch": 2.0325335502236683,
+      "grad_norm": 0.4408818483352661,
+      "learning_rate": 6.460704607046071e-06,
+      "loss": 2.1999,
+      "step": 1250
+    },
+    {
+      "epoch": 2.048800325335502,
+      "grad_norm": 0.7718443870544434,
+      "learning_rate": 6.35230352303523e-06,
+      "loss": 2.2005,
+      "step": 1260
+    },
+    {
+      "epoch": 2.065067100447336,
+      "grad_norm": 0.6275615692138672,
+      "learning_rate": 6.243902439024391e-06,
+      "loss": 2.2281,
+      "step": 1270
+    },
+    {
+      "epoch": 2.0813338755591704,
+      "grad_norm": 0.6543229222297668,
+      "learning_rate": 6.1355013550135516e-06,
+      "loss": 2.1983,
+      "step": 1280
+    },
+    {
+      "epoch": 2.0976006506710045,
+      "grad_norm": 0.7339210510253906,
+      "learning_rate": 6.027100271002711e-06,
+      "loss": 2.1846,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1138674257828387,
+      "grad_norm": 0.5071961879730225,
+      "learning_rate": 5.9186991869918705e-06,
+      "loss": 2.2138,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1301342008946724,
+      "grad_norm": 0.45426690578460693,
+      "learning_rate": 5.81029810298103e-06,
+      "loss": 2.1002,
+      "step": 1310
+    },
+    {
+      "epoch": 2.1464009760065066,
+      "grad_norm": 0.47942936420440674,
+      "learning_rate": 5.70189701897019e-06,
+      "loss": 2.1142,
+      "step": 1320
+    },
+    {
+      "epoch": 2.1626677511183408,
+      "grad_norm": 0.44700875878334045,
+      "learning_rate": 5.59349593495935e-06,
+      "loss": 2.1702,
+      "step": 1330
+    },
+    {
+      "epoch": 2.178934526230175,
+      "grad_norm": 0.7139628529548645,
+      "learning_rate": 5.48509485094851e-06,
+      "loss": 2.1564,
+      "step": 1340
+    },
+    {
+      "epoch": 2.195201301342009,
+      "grad_norm": 0.657394289970398,
+      "learning_rate": 5.37669376693767e-06,
+      "loss": 2.1804,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2114680764538432,
+      "grad_norm": 0.4319300651550293,
+      "learning_rate": 5.26829268292683e-06,
+      "loss": 2.195,
+      "step": 1360
+    },
+    {
+      "epoch": 2.227734851565677,
+      "grad_norm": 0.71416175365448,
+      "learning_rate": 5.15989159891599e-06,
+      "loss": 2.1752,
+      "step": 1370
+    },
+    {
+      "epoch": 2.244001626677511,
+      "grad_norm": 0.5899174213409424,
+      "learning_rate": 5.0514905149051495e-06,
+      "loss": 2.1484,
+      "step": 1380
+    },
+    {
+      "epoch": 2.2602684017893453,
+      "grad_norm": 0.5278040766716003,
+      "learning_rate": 4.943089430894309e-06,
+      "loss": 2.1897,
+      "step": 1390
+    },
+    {
+      "epoch": 2.2765351769011795,
+      "grad_norm": 0.7354372143745422,
+      "learning_rate": 4.834688346883469e-06,
+      "loss": 2.1969,
+      "step": 1400
+    },
+    {
+      "epoch": 2.292801952013013,
+      "grad_norm": 0.5477260947227478,
+      "learning_rate": 4.726287262872629e-06,
+      "loss": 2.2058,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3090687271248473,
+      "grad_norm": 0.5498638153076172,
+      "learning_rate": 4.617886178861789e-06,
+      "loss": 2.1328,
+      "step": 1420
+    },
+    {
+      "epoch": 2.3253355022366815,
+      "grad_norm": 0.6466209292411804,
+      "learning_rate": 4.509485094850949e-06,
+      "loss": 2.1908,
+      "step": 1430
+    },
+    {
+      "epoch": 2.3416022773485157,
+      "grad_norm": 0.6899780631065369,
+      "learning_rate": 4.401084010840109e-06,
+      "loss": 2.1283,
+      "step": 1440
+    },
+    {
+      "epoch": 2.35786905246035,
+      "grad_norm": 0.6455110907554626,
+      "learning_rate": 4.292682926829269e-06,
+      "loss": 2.2166,
+      "step": 1450
+    },
+    {
+      "epoch": 2.374135827572184,
+      "grad_norm": 0.4662465751171112,
+      "learning_rate": 4.1842818428184285e-06,
+      "loss": 2.0987,
+      "step": 1460
+    },
+    {
+      "epoch": 2.3904026026840177,
+      "grad_norm": 0.5388475656509399,
+      "learning_rate": 4.075880758807588e-06,
+      "loss": 2.1783,
+      "step": 1470
+    },
+    {
+      "epoch": 2.406669377795852,
+      "grad_norm": 0.5845710039138794,
+      "learning_rate": 3.967479674796748e-06,
+      "loss": 2.1145,
+      "step": 1480
+    },
+    {
+      "epoch": 2.422936152907686,
+      "grad_norm": 0.4962908923625946,
+      "learning_rate": 3.859078590785908e-06,
+      "loss": 2.1879,
+      "step": 1490
+    },
+    {
+      "epoch": 2.43920292801952,
+      "grad_norm": 0.7771344780921936,
+      "learning_rate": 3.7506775067750676e-06,
+      "loss": 2.1892,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1845,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.8085481399373005e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018cc1d55d2ff18e3ef653458af0905c473e4c15684121019fe78e8b522e3247
+size 5713

checkpoint-1845/README.md

@@ -0,0 +1,207 @@
+---
+base_model: ./local_deepseek
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:./local_deepseek
+- lora
+- transformers
+---
+
+# 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 0.16.0

checkpoint-1845/adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "./local_deepseek",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1845/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90afb5522f753a707d49aa165e0cec111ebf1fea7ef205d6353e91a9c4f3c7a0
+size 31473392

checkpoint-1845/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8637067a20de144575c3d316b5e4bd6742a961c10694a10282636bd51ebca6a
+size 63018123

checkpoint-1845/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf1116cc1aeff093c47ddee96d1879863e5bc603b48e39a215db03c20e8e7cea
+size 14645

checkpoint-1845/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39e7840d44b82d33101594ea51e52772977204dd84b908360b3d0952d5ef06af
+size 1465

checkpoint-1845/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<｜end▁of▁sentence｜>"
+}

checkpoint-1845/tokenizer_config.json

@@ -0,0 +1,138 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizerFast",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}

checkpoint-1845/trainer_state.json

@@ -0,0 +1,1322 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1845,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.016266775111834077,
+      "grad_norm": 0.15190425515174866,
+      "learning_rate": 1.9902439024390247e-05,
+      "loss": 2.4224,
+      "step": 10
+    },
+    {
+      "epoch": 0.032533550223668155,
+      "grad_norm": 0.13811910152435303,
+      "learning_rate": 1.9794037940379405e-05,
+      "loss": 2.4266,
+      "step": 20
+    },
+    {
+      "epoch": 0.048800325335502236,
+      "grad_norm": 0.14573918282985687,
+      "learning_rate": 1.9685636856368567e-05,
+      "loss": 2.4425,
+      "step": 30
+    },
+    {
+      "epoch": 0.06506710044733631,
+      "grad_norm": 0.16350996494293213,
+      "learning_rate": 1.9577235772357725e-05,
+      "loss": 2.397,
+      "step": 40
+    },
+    {
+      "epoch": 0.08133387555917039,
+      "grad_norm": 0.14666102826595306,
+      "learning_rate": 1.9468834688346883e-05,
+      "loss": 2.3677,
+      "step": 50
+    },
+    {
+      "epoch": 0.09760065067100447,
+      "grad_norm": 0.10224353522062302,
+      "learning_rate": 1.9360433604336045e-05,
+      "loss": 2.3969,
+      "step": 60
+    },
+    {
+      "epoch": 0.11386742578283855,
+      "grad_norm": 0.19328653812408447,
+      "learning_rate": 1.9252032520325206e-05,
+      "loss": 2.4367,
+      "step": 70
+    },
+    {
+      "epoch": 0.13013420089467262,
+      "grad_norm": 0.15589460730552673,
+      "learning_rate": 1.9143631436314365e-05,
+      "loss": 2.3979,
+      "step": 80
+    },
+    {
+      "epoch": 0.1464009760065067,
+      "grad_norm": 0.15351463854312897,
+      "learning_rate": 1.9035230352303523e-05,
+      "loss": 2.3628,
+      "step": 90
+    },
+    {
+      "epoch": 0.16266775111834078,
+      "grad_norm": 0.1756143420934677,
+      "learning_rate": 1.8926829268292684e-05,
+      "loss": 2.4175,
+      "step": 100
+    },
+    {
+      "epoch": 0.17893452623017486,
+      "grad_norm": 0.15267857909202576,
+      "learning_rate": 1.8818428184281846e-05,
+      "loss": 2.3335,
+      "step": 110
+    },
+    {
+      "epoch": 0.19520130134200894,
+      "grad_norm": 0.15103495121002197,
+      "learning_rate": 1.8710027100271004e-05,
+      "loss": 2.3256,
+      "step": 120
+    },
+    {
+      "epoch": 0.21146807645384302,
+      "grad_norm": 0.20331667363643646,
+      "learning_rate": 1.8601626016260162e-05,
+      "loss": 2.3173,
+      "step": 130
+    },
+    {
+      "epoch": 0.2277348515656771,
+      "grad_norm": 0.18745240569114685,
+      "learning_rate": 1.8493224932249324e-05,
+      "loss": 2.3128,
+      "step": 140
+    },
+    {
+      "epoch": 0.24400162667751119,
+      "grad_norm": 0.20769692957401276,
+      "learning_rate": 1.8384823848238485e-05,
+      "loss": 2.3524,
+      "step": 150
+    },
+    {
+      "epoch": 0.26026840178934524,
+      "grad_norm": 0.2246929258108139,
+      "learning_rate": 1.8276422764227644e-05,
+      "loss": 2.3513,
+      "step": 160
+    },
+    {
+      "epoch": 0.27653517690117935,
+      "grad_norm": 0.20076365768909454,
+      "learning_rate": 1.8168021680216802e-05,
+      "loss": 2.2622,
+      "step": 170
+    },
+    {
+      "epoch": 0.2928019520130134,
+      "grad_norm": 0.2003357708454132,
+      "learning_rate": 1.8059620596205963e-05,
+      "loss": 2.2533,
+      "step": 180
+    },
+    {
+      "epoch": 0.3090687271248475,
+      "grad_norm": 0.2662675082683563,
+      "learning_rate": 1.7951219512195125e-05,
+      "loss": 2.2756,
+      "step": 190
+    },
+    {
+      "epoch": 0.32533550223668156,
+      "grad_norm": 0.2601667046546936,
+      "learning_rate": 1.7842818428184283e-05,
+      "loss": 2.3471,
+      "step": 200
+    },
+    {
+      "epoch": 0.34160227734851567,
+      "grad_norm": 0.3059883117675781,
+      "learning_rate": 1.773441734417344e-05,
+      "loss": 2.3301,
+      "step": 210
+    },
+    {
+      "epoch": 0.3578690524603497,
+      "grad_norm": 0.20538951456546783,
+      "learning_rate": 1.7626016260162603e-05,
+      "loss": 2.2963,
+      "step": 220
+    },
+    {
+      "epoch": 0.37413582757218383,
+      "grad_norm": 0.3262976109981537,
+      "learning_rate": 1.7517615176151764e-05,
+      "loss": 2.2957,
+      "step": 230
+    },
+    {
+      "epoch": 0.3904026026840179,
+      "grad_norm": 0.22966964542865753,
+      "learning_rate": 1.7409214092140923e-05,
+      "loss": 2.2636,
+      "step": 240
+    },
+    {
+      "epoch": 0.406669377795852,
+      "grad_norm": 0.26744940876960754,
+      "learning_rate": 1.730081300813008e-05,
+      "loss": 2.288,
+      "step": 250
+    },
+    {
+      "epoch": 0.42293615290768605,
+      "grad_norm": 0.2023824006319046,
+      "learning_rate": 1.7192411924119242e-05,
+      "loss": 2.2703,
+      "step": 260
+    },
+    {
+      "epoch": 0.43920292801952016,
+      "grad_norm": 0.2542593479156494,
+      "learning_rate": 1.7084010840108404e-05,
+      "loss": 2.2129,
+      "step": 270
+    },
+    {
+      "epoch": 0.4554697031313542,
+      "grad_norm": 0.2524624466896057,
+      "learning_rate": 1.6975609756097562e-05,
+      "loss": 2.2678,
+      "step": 280
+    },
+    {
+      "epoch": 0.47173647824318826,
+      "grad_norm": 0.28020623326301575,
+      "learning_rate": 1.686720867208672e-05,
+      "loss": 2.3569,
+      "step": 290
+    },
+    {
+      "epoch": 0.48800325335502237,
+      "grad_norm": 0.2878577709197998,
+      "learning_rate": 1.6758807588075882e-05,
+      "loss": 2.2217,
+      "step": 300
+    },
+    {
+      "epoch": 0.5042700284668564,
+      "grad_norm": 0.20536544919013977,
+      "learning_rate": 1.6650406504065043e-05,
+      "loss": 2.3558,
+      "step": 310
+    },
+    {
+      "epoch": 0.5205368035786905,
+      "grad_norm": 0.20909422636032104,
+      "learning_rate": 1.65420054200542e-05,
+      "loss": 2.2742,
+      "step": 320
+    },
+    {
+      "epoch": 0.5368035786905246,
+      "grad_norm": 0.4000333249568939,
+      "learning_rate": 1.6433604336043363e-05,
+      "loss": 2.2846,
+      "step": 330
+    },
+    {
+      "epoch": 0.5530703538023587,
+      "grad_norm": 0.31831657886505127,
+      "learning_rate": 1.632520325203252e-05,
+      "loss": 2.2377,
+      "step": 340
+    },
+    {
+      "epoch": 0.5693371289141927,
+      "grad_norm": 0.28702083230018616,
+      "learning_rate": 1.6216802168021683e-05,
+      "loss": 2.3066,
+      "step": 350
+    },
+    {
+      "epoch": 0.5856039040260268,
+      "grad_norm": 0.34019768238067627,
+      "learning_rate": 1.610840108401084e-05,
+      "loss": 2.2489,
+      "step": 360
+    },
+    {
+      "epoch": 0.601870679137861,
+      "grad_norm": 0.3892984688282013,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3081,
+      "step": 370
+    },
+    {
+      "epoch": 0.618137454249695,
+      "grad_norm": 0.26910895109176636,
+      "learning_rate": 1.589159891598916e-05,
+      "loss": 2.1796,
+      "step": 380
+    },
+    {
+      "epoch": 0.6344042293615291,
+      "grad_norm": 0.25772690773010254,
+      "learning_rate": 1.5783197831978322e-05,
+      "loss": 2.2078,
+      "step": 390
+    },
+    {
+      "epoch": 0.6506710044733631,
+      "grad_norm": 0.553435206413269,
+      "learning_rate": 1.567479674796748e-05,
+      "loss": 2.2078,
+      "step": 400
+    },
+    {
+      "epoch": 0.6669377795851973,
+      "grad_norm": 0.22907570004463196,
+      "learning_rate": 1.5566395663956642e-05,
+      "loss": 2.2428,
+      "step": 410
+    },
+    {
+      "epoch": 0.6832045546970313,
+      "grad_norm": 0.3672320246696472,
+      "learning_rate": 1.54579945799458e-05,
+      "loss": 2.2479,
+      "step": 420
+    },
+    {
+      "epoch": 0.6994713298088654,
+      "grad_norm": 0.4416728615760803,
+      "learning_rate": 1.534959349593496e-05,
+      "loss": 2.2236,
+      "step": 430
+    },
+    {
+      "epoch": 0.7157381049206994,
+      "grad_norm": 0.37598440051078796,
+      "learning_rate": 1.524119241192412e-05,
+      "loss": 2.2146,
+      "step": 440
+    },
+    {
+      "epoch": 0.7320048800325335,
+      "grad_norm": 0.4336397647857666,
+      "learning_rate": 1.5132791327913282e-05,
+      "loss": 2.2324,
+      "step": 450
+    },
+    {
+      "epoch": 0.7482716551443677,
+      "grad_norm": 0.29831627011299133,
+      "learning_rate": 1.502439024390244e-05,
+      "loss": 2.2328,
+      "step": 460
+    },
+    {
+      "epoch": 0.7645384302562017,
+      "grad_norm": 0.5829563140869141,
+      "learning_rate": 1.49159891598916e-05,
+      "loss": 2.2147,
+      "step": 470
+    },
+    {
+      "epoch": 0.7808052053680358,
+      "grad_norm": 0.25096556544303894,
+      "learning_rate": 1.4807588075880761e-05,
+      "loss": 2.2572,
+      "step": 480
+    },
+    {
+      "epoch": 0.7970719804798698,
+      "grad_norm": 0.3719277083873749,
+      "learning_rate": 1.4699186991869921e-05,
+      "loss": 2.1964,
+      "step": 490
+    },
+    {
+      "epoch": 0.813338755591704,
+      "grad_norm": 0.3131086528301239,
+      "learning_rate": 1.459078590785908e-05,
+      "loss": 2.2893,
+      "step": 500
+    },
+    {
+      "epoch": 0.829605530703538,
+      "grad_norm": 0.31521037220954895,
+      "learning_rate": 1.448238482384824e-05,
+      "loss": 2.2498,
+      "step": 510
+    },
+    {
+      "epoch": 0.8458723058153721,
+      "grad_norm": 0.3911826014518738,
+      "learning_rate": 1.43739837398374e-05,
+      "loss": 2.2444,
+      "step": 520
+    },
+    {
+      "epoch": 0.8621390809272061,
+      "grad_norm": 0.27660906314849854,
+      "learning_rate": 1.4265582655826559e-05,
+      "loss": 2.2571,
+      "step": 530
+    },
+    {
+      "epoch": 0.8784058560390403,
+      "grad_norm": 0.5232799053192139,
+      "learning_rate": 1.4157181571815719e-05,
+      "loss": 2.2419,
+      "step": 540
+    },
+    {
+      "epoch": 0.8946726311508744,
+      "grad_norm": 0.3597722053527832,
+      "learning_rate": 1.4048780487804879e-05,
+      "loss": 2.2426,
+      "step": 550
+    },
+    {
+      "epoch": 0.9109394062627084,
+      "grad_norm": 0.3321545422077179,
+      "learning_rate": 1.394037940379404e-05,
+      "loss": 2.2136,
+      "step": 560
+    },
+    {
+      "epoch": 0.9272061813745425,
+      "grad_norm": 0.4088381826877594,
+      "learning_rate": 1.3831978319783199e-05,
+      "loss": 2.1917,
+      "step": 570
+    },
+    {
+      "epoch": 0.9434729564863765,
+      "grad_norm": 0.4453414976596832,
+      "learning_rate": 1.3723577235772358e-05,
+      "loss": 2.2404,
+      "step": 580
+    },
+    {
+      "epoch": 0.9597397315982107,
+      "grad_norm": 0.33261504769325256,
+      "learning_rate": 1.3615176151761518e-05,
+      "loss": 2.2778,
+      "step": 590
+    },
+    {
+      "epoch": 0.9760065067100447,
+      "grad_norm": 0.3876469135284424,
+      "learning_rate": 1.350677506775068e-05,
+      "loss": 2.1898,
+      "step": 600
+    },
+    {
+      "epoch": 0.9922732818218788,
+      "grad_norm": 0.33917632699012756,
+      "learning_rate": 1.3398373983739838e-05,
+      "loss": 2.2822,
+      "step": 610
+    },
+    {
+      "epoch": 1.008133387555917,
+      "grad_norm": 0.33381298184394836,
+      "learning_rate": 1.3289972899728998e-05,
+      "loss": 2.2269,
+      "step": 620
+    },
+    {
+      "epoch": 1.024400162667751,
+      "grad_norm": 0.284834623336792,
+      "learning_rate": 1.318157181571816e-05,
+      "loss": 2.2241,
+      "step": 630
+    },
+    {
+      "epoch": 1.0406669377795852,
+      "grad_norm": 0.4045396149158478,
+      "learning_rate": 1.307317073170732e-05,
+      "loss": 2.2347,
+      "step": 640
+    },
+    {
+      "epoch": 1.0569337128914194,
+      "grad_norm": 0.543749213218689,
+      "learning_rate": 1.2964769647696478e-05,
+      "loss": 2.1799,
+      "step": 650
+    },
+    {
+      "epoch": 1.0732004880032533,
+      "grad_norm": 0.34489476680755615,
+      "learning_rate": 1.2856368563685637e-05,
+      "loss": 2.24,
+      "step": 660
+    },
+    {
+      "epoch": 1.0894672631150875,
+      "grad_norm": 0.4727187752723694,
+      "learning_rate": 1.2747967479674799e-05,
+      "loss": 2.2818,
+      "step": 670
+    },
+    {
+      "epoch": 1.1057340382269216,
+      "grad_norm": 0.41018274426460266,
+      "learning_rate": 1.2639566395663959e-05,
+      "loss": 2.1991,
+      "step": 680
+    },
+    {
+      "epoch": 1.1220008133387556,
+      "grad_norm": 0.3846307098865509,
+      "learning_rate": 1.2531165311653117e-05,
+      "loss": 2.1835,
+      "step": 690
+    },
+    {
+      "epoch": 1.1382675884505897,
+      "grad_norm": 0.45072686672210693,
+      "learning_rate": 1.2422764227642277e-05,
+      "loss": 2.2661,
+      "step": 700
+    },
+    {
+      "epoch": 1.1545343635624237,
+      "grad_norm": 0.4832310676574707,
+      "learning_rate": 1.2314363143631439e-05,
+      "loss": 2.216,
+      "step": 710
+    },
+    {
+      "epoch": 1.1708011386742578,
+      "grad_norm": 0.5275405049324036,
+      "learning_rate": 1.2205962059620597e-05,
+      "loss": 2.208,
+      "step": 720
+    },
+    {
+      "epoch": 1.187067913786092,
+      "grad_norm": 0.3692767322063446,
+      "learning_rate": 1.2097560975609757e-05,
+      "loss": 2.289,
+      "step": 730
+    },
+    {
+      "epoch": 1.203334688897926,
+      "grad_norm": 0.29335182905197144,
+      "learning_rate": 1.1989159891598916e-05,
+      "loss": 2.1959,
+      "step": 740
+    },
+    {
+      "epoch": 1.21960146400976,
+      "grad_norm": 0.49091747403144836,
+      "learning_rate": 1.1880758807588078e-05,
+      "loss": 2.1451,
+      "step": 750
+    },
+    {
+      "epoch": 1.235868239121594,
+      "grad_norm": 0.3522561490535736,
+      "learning_rate": 1.1772357723577236e-05,
+      "loss": 2.248,
+      "step": 760
+    },
+    {
+      "epoch": 1.2521350142334282,
+      "grad_norm": 0.41444632411003113,
+      "learning_rate": 1.1663956639566396e-05,
+      "loss": 2.1832,
+      "step": 770
+    },
+    {
+      "epoch": 1.2684017893452624,
+      "grad_norm": 0.4403276741504669,
+      "learning_rate": 1.1555555555555556e-05,
+      "loss": 2.1923,
+      "step": 780
+    },
+    {
+      "epoch": 1.2846685644570963,
+      "grad_norm": 0.4993409514427185,
+      "learning_rate": 1.1447154471544718e-05,
+      "loss": 2.1518,
+      "step": 790
+    },
+    {
+      "epoch": 1.3009353395689305,
+      "grad_norm": 0.3903736174106598,
+      "learning_rate": 1.1338753387533876e-05,
+      "loss": 2.19,
+      "step": 800
+    },
+    {
+      "epoch": 1.3172021146807644,
+      "grad_norm": 0.31108370423316956,
+      "learning_rate": 1.1230352303523036e-05,
+      "loss": 2.1852,
+      "step": 810
+    },
+    {
+      "epoch": 1.3334688897925986,
+      "grad_norm": 0.3845357894897461,
+      "learning_rate": 1.1121951219512197e-05,
+      "loss": 2.1589,
+      "step": 820
+    },
+    {
+      "epoch": 1.3497356649044328,
+      "grad_norm": 0.4706804156303406,
+      "learning_rate": 1.1013550135501357e-05,
+      "loss": 2.1925,
+      "step": 830
+    },
+    {
+      "epoch": 1.3660024400162667,
+      "grad_norm": 0.33979251980781555,
+      "learning_rate": 1.0905149051490515e-05,
+      "loss": 2.2165,
+      "step": 840
+    },
+    {
+      "epoch": 1.3822692151281009,
+      "grad_norm": 0.6070290803909302,
+      "learning_rate": 1.0796747967479675e-05,
+      "loss": 2.2304,
+      "step": 850
+    },
+    {
+      "epoch": 1.3985359902399348,
+      "grad_norm": 0.3914659321308136,
+      "learning_rate": 1.0688346883468837e-05,
+      "loss": 2.1945,
+      "step": 860
+    },
+    {
+      "epoch": 1.414802765351769,
+      "grad_norm": 0.38425302505493164,
+      "learning_rate": 1.0579945799457995e-05,
+      "loss": 2.1799,
+      "step": 870
+    },
+    {
+      "epoch": 1.4310695404636031,
+      "grad_norm": 0.3691774904727936,
+      "learning_rate": 1.0471544715447155e-05,
+      "loss": 2.1812,
+      "step": 880
+    },
+    {
+      "epoch": 1.4473363155754373,
+      "grad_norm": 0.4350150525569916,
+      "learning_rate": 1.0363143631436315e-05,
+      "loss": 2.2151,
+      "step": 890
+    },
+    {
+      "epoch": 1.4636030906872712,
+      "grad_norm": 0.37822458148002625,
+      "learning_rate": 1.0254742547425476e-05,
+      "loss": 2.2839,
+      "step": 900
+    },
+    {
+      "epoch": 1.4798698657991054,
+      "grad_norm": 0.4036807715892792,
+      "learning_rate": 1.0146341463414634e-05,
+      "loss": 2.2456,
+      "step": 910
+    },
+    {
+      "epoch": 1.4961366409109393,
+      "grad_norm": 0.3395715653896332,
+      "learning_rate": 1.0037940379403794e-05,
+      "loss": 2.2455,
+      "step": 920
+    },
+    {
+      "epoch": 1.5124034160227735,
+      "grad_norm": 0.8333190679550171,
+      "learning_rate": 9.929539295392954e-06,
+      "loss": 2.215,
+      "step": 930
+    },
+    {
+      "epoch": 1.5286701911346077,
+      "grad_norm": 0.47911304235458374,
+      "learning_rate": 9.821138211382114e-06,
+      "loss": 2.2095,
+      "step": 940
+    },
+    {
+      "epoch": 1.5449369662464416,
+      "grad_norm": 0.421014666557312,
+      "learning_rate": 9.712737127371274e-06,
+      "loss": 2.2236,
+      "step": 950
+    },
+    {
+      "epoch": 1.5612037413582758,
+      "grad_norm": 0.48267999291419983,
+      "learning_rate": 9.604336043360435e-06,
+      "loss": 2.2163,
+      "step": 960
+    },
+    {
+      "epoch": 1.5774705164701097,
+      "grad_norm": 0.39987218379974365,
+      "learning_rate": 9.495934959349594e-06,
+      "loss": 2.1863,
+      "step": 970
+    },
+    {
+      "epoch": 1.5937372915819439,
+      "grad_norm": 0.6446450352668762,
+      "learning_rate": 9.387533875338755e-06,
+      "loss": 2.1801,
+      "step": 980
+    },
+    {
+      "epoch": 1.610004066693778,
+      "grad_norm": 0.4291459321975708,
+      "learning_rate": 9.279132791327913e-06,
+      "loss": 2.2346,
+      "step": 990
+    },
+    {
+      "epoch": 1.626270841805612,
+      "grad_norm": 0.5329392552375793,
+      "learning_rate": 9.170731707317075e-06,
+      "loss": 2.1606,
+      "step": 1000
+    },
+    {
+      "epoch": 1.6425376169174462,
+      "grad_norm": 0.6420161128044128,
+      "learning_rate": 9.062330623306233e-06,
+      "loss": 2.1936,
+      "step": 1010
+    },
+    {
+      "epoch": 1.65880439202928,
+      "grad_norm": 0.5436628460884094,
+      "learning_rate": 8.953929539295395e-06,
+      "loss": 2.182,
+      "step": 1020
+    },
+    {
+      "epoch": 1.6750711671411143,
+      "grad_norm": 0.3877139985561371,
+      "learning_rate": 8.845528455284553e-06,
+      "loss": 2.2317,
+      "step": 1030
+    },
+    {
+      "epoch": 1.6913379422529484,
+      "grad_norm": 0.5903089046478271,
+      "learning_rate": 8.737127371273714e-06,
+      "loss": 2.2121,
+      "step": 1040
+    },
+    {
+      "epoch": 1.7076047173647826,
+      "grad_norm": 0.4182610511779785,
+      "learning_rate": 8.628726287262873e-06,
+      "loss": 2.1664,
+      "step": 1050
+    },
+    {
+      "epoch": 1.7238714924766165,
+      "grad_norm": 0.701687216758728,
+      "learning_rate": 8.520325203252033e-06,
+      "loss": 2.1705,
+      "step": 1060
+    },
+    {
+      "epoch": 1.7401382675884505,
+      "grad_norm": 0.6748879551887512,
+      "learning_rate": 8.411924119241192e-06,
+      "loss": 2.209,
+      "step": 1070
+    },
+    {
+      "epoch": 1.7564050427002846,
+      "grad_norm": 0.49491748213768005,
+      "learning_rate": 8.303523035230352e-06,
+      "loss": 2.1947,
+      "step": 1080
+    },
+    {
+      "epoch": 1.7726718178121188,
+      "grad_norm": 0.4370752274990082,
+      "learning_rate": 8.195121951219512e-06,
+      "loss": 2.1833,
+      "step": 1090
+    },
+    {
+      "epoch": 1.788938592923953,
+      "grad_norm": 0.3895672559738159,
+      "learning_rate": 8.086720867208672e-06,
+      "loss": 2.2577,
+      "step": 1100
+    },
+    {
+      "epoch": 1.805205368035787,
+      "grad_norm": 0.3882943093776703,
+      "learning_rate": 7.978319783197834e-06,
+      "loss": 2.1802,
+      "step": 1110
+    },
+    {
+      "epoch": 1.8214721431476208,
+      "grad_norm": 0.4686112403869629,
+      "learning_rate": 7.869918699186992e-06,
+      "loss": 2.1258,
+      "step": 1120
+    },
+    {
+      "epoch": 1.837738918259455,
+      "grad_norm": 0.5097848773002625,
+      "learning_rate": 7.761517615176153e-06,
+      "loss": 2.212,
+      "step": 1130
+    },
+    {
+      "epoch": 1.8540056933712892,
+      "grad_norm": 0.49870142340660095,
+      "learning_rate": 7.653116531165312e-06,
+      "loss": 2.2587,
+      "step": 1140
+    },
+    {
+      "epoch": 1.8702724684831233,
+      "grad_norm": 0.612582266330719,
+      "learning_rate": 7.544715447154472e-06,
+      "loss": 2.1571,
+      "step": 1150
+    },
+    {
+      "epoch": 1.8865392435949573,
+      "grad_norm": 0.5550523400306702,
+      "learning_rate": 7.436314363143632e-06,
+      "loss": 2.1993,
+      "step": 1160
+    },
+    {
+      "epoch": 1.9028060187067912,
+      "grad_norm": 0.921201229095459,
+      "learning_rate": 7.327913279132792e-06,
+      "loss": 2.1619,
+      "step": 1170
+    },
+    {
+      "epoch": 1.9190727938186254,
+      "grad_norm": 0.5052744746208191,
+      "learning_rate": 7.219512195121952e-06,
+      "loss": 2.1743,
+      "step": 1180
+    },
+    {
+      "epoch": 1.9353395689304596,
+      "grad_norm": 0.6115371584892273,
+      "learning_rate": 7.111111111111112e-06,
+      "loss": 2.1839,
+      "step": 1190
+    },
+    {
+      "epoch": 1.9516063440422937,
+      "grad_norm": 0.5317726731300354,
+      "learning_rate": 7.002710027100271e-06,
+      "loss": 2.1704,
+      "step": 1200
+    },
+    {
+      "epoch": 1.9678731191541277,
+      "grad_norm": 0.4624195694923401,
+      "learning_rate": 6.894308943089432e-06,
+      "loss": 2.2127,
+      "step": 1210
+    },
+    {
+      "epoch": 1.9841398942659618,
+      "grad_norm": 0.50515216588974,
+      "learning_rate": 6.785907859078591e-06,
+      "loss": 2.1522,
+      "step": 1220
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6244822144508362,
+      "learning_rate": 6.677506775067751e-06,
+      "loss": 2.1697,
+      "step": 1230
+    },
+    {
+      "epoch": 2.016266775111834,
+      "grad_norm": 0.5226220488548279,
+      "learning_rate": 6.56910569105691e-06,
+      "loss": 2.2529,
+      "step": 1240
+    },
+    {
+      "epoch": 2.0325335502236683,
+      "grad_norm": 0.4408818483352661,
+      "learning_rate": 6.460704607046071e-06,
+      "loss": 2.1999,
+      "step": 1250
+    },
+    {
+      "epoch": 2.048800325335502,
+      "grad_norm": 0.7718443870544434,
+      "learning_rate": 6.35230352303523e-06,
+      "loss": 2.2005,
+      "step": 1260
+    },
+    {
+      "epoch": 2.065067100447336,
+      "grad_norm": 0.6275615692138672,
+      "learning_rate": 6.243902439024391e-06,
+      "loss": 2.2281,
+      "step": 1270
+    },
+    {
+      "epoch": 2.0813338755591704,
+      "grad_norm": 0.6543229222297668,
+      "learning_rate": 6.1355013550135516e-06,
+      "loss": 2.1983,
+      "step": 1280
+    },
+    {
+      "epoch": 2.0976006506710045,
+      "grad_norm": 0.7339210510253906,
+      "learning_rate": 6.027100271002711e-06,
+      "loss": 2.1846,
+      "step": 1290
+    },
+    {
+      "epoch": 2.1138674257828387,
+      "grad_norm": 0.5071961879730225,
+      "learning_rate": 5.9186991869918705e-06,
+      "loss": 2.2138,
+      "step": 1300
+    },
+    {
+      "epoch": 2.1301342008946724,
+      "grad_norm": 0.45426690578460693,
+      "learning_rate": 5.81029810298103e-06,
+      "loss": 2.1002,
+      "step": 1310
+    },
+    {
+      "epoch": 2.1464009760065066,
+      "grad_norm": 0.47942936420440674,
+      "learning_rate": 5.70189701897019e-06,
+      "loss": 2.1142,
+      "step": 1320
+    },
+    {
+      "epoch": 2.1626677511183408,
+      "grad_norm": 0.44700875878334045,
+      "learning_rate": 5.59349593495935e-06,
+      "loss": 2.1702,
+      "step": 1330
+    },
+    {
+      "epoch": 2.178934526230175,
+      "grad_norm": 0.7139628529548645,
+      "learning_rate": 5.48509485094851e-06,
+      "loss": 2.1564,
+      "step": 1340
+    },
+    {
+      "epoch": 2.195201301342009,
+      "grad_norm": 0.657394289970398,
+      "learning_rate": 5.37669376693767e-06,
+      "loss": 2.1804,
+      "step": 1350
+    },
+    {
+      "epoch": 2.2114680764538432,
+      "grad_norm": 0.4319300651550293,
+      "learning_rate": 5.26829268292683e-06,
+      "loss": 2.195,
+      "step": 1360
+    },
+    {
+      "epoch": 2.227734851565677,
+      "grad_norm": 0.71416175365448,
+      "learning_rate": 5.15989159891599e-06,
+      "loss": 2.1752,
+      "step": 1370
+    },
+    {
+      "epoch": 2.244001626677511,
+      "grad_norm": 0.5899174213409424,
+      "learning_rate": 5.0514905149051495e-06,
+      "loss": 2.1484,
+      "step": 1380
+    },
+    {
+      "epoch": 2.2602684017893453,
+      "grad_norm": 0.5278040766716003,
+      "learning_rate": 4.943089430894309e-06,
+      "loss": 2.1897,
+      "step": 1390
+    },
+    {
+      "epoch": 2.2765351769011795,
+      "grad_norm": 0.7354372143745422,
+      "learning_rate": 4.834688346883469e-06,
+      "loss": 2.1969,
+      "step": 1400
+    },
+    {
+      "epoch": 2.292801952013013,
+      "grad_norm": 0.5477260947227478,
+      "learning_rate": 4.726287262872629e-06,
+      "loss": 2.2058,
+      "step": 1410
+    },
+    {
+      "epoch": 2.3090687271248473,
+      "grad_norm": 0.5498638153076172,
+      "learning_rate": 4.617886178861789e-06,
+      "loss": 2.1328,
+      "step": 1420
+    },
+    {
+      "epoch": 2.3253355022366815,
+      "grad_norm": 0.6466209292411804,
+      "learning_rate": 4.509485094850949e-06,
+      "loss": 2.1908,
+      "step": 1430
+    },
+    {
+      "epoch": 2.3416022773485157,
+      "grad_norm": 0.6899780631065369,
+      "learning_rate": 4.401084010840109e-06,
+      "loss": 2.1283,
+      "step": 1440
+    },
+    {
+      "epoch": 2.35786905246035,
+      "grad_norm": 0.6455110907554626,
+      "learning_rate": 4.292682926829269e-06,
+      "loss": 2.2166,
+      "step": 1450
+    },
+    {
+      "epoch": 2.374135827572184,
+      "grad_norm": 0.4662465751171112,
+      "learning_rate": 4.1842818428184285e-06,
+      "loss": 2.0987,
+      "step": 1460
+    },
+    {
+      "epoch": 2.3904026026840177,
+      "grad_norm": 0.5388475656509399,
+      "learning_rate": 4.075880758807588e-06,
+      "loss": 2.1783,
+      "step": 1470
+    },
+    {
+      "epoch": 2.406669377795852,
+      "grad_norm": 0.5845710039138794,
+      "learning_rate": 3.967479674796748e-06,
+      "loss": 2.1145,
+      "step": 1480
+    },
+    {
+      "epoch": 2.422936152907686,
+      "grad_norm": 0.4962908923625946,
+      "learning_rate": 3.859078590785908e-06,
+      "loss": 2.1879,
+      "step": 1490
+    },
+    {
+      "epoch": 2.43920292801952,
+      "grad_norm": 0.7771344780921936,
+      "learning_rate": 3.7506775067750676e-06,
+      "loss": 2.1892,
+      "step": 1500
+    },
+    {
+      "epoch": 2.4554697031313544,
+      "grad_norm": 0.6176280975341797,
+      "learning_rate": 3.6422764227642283e-06,
+      "loss": 2.2419,
+      "step": 1510
+    },
+    {
+      "epoch": 2.471736478243188,
+      "grad_norm": 0.4214126467704773,
+      "learning_rate": 3.5338753387533882e-06,
+      "loss": 2.1975,
+      "step": 1520
+    },
+    {
+      "epoch": 2.4880032533550223,
+      "grad_norm": 0.57136470079422,
+      "learning_rate": 3.425474254742548e-06,
+      "loss": 2.2209,
+      "step": 1530
+    },
+    {
+      "epoch": 2.5042700284668564,
+      "grad_norm": 0.5058287978172302,
+      "learning_rate": 3.3170731707317076e-06,
+      "loss": 2.126,
+      "step": 1540
+    },
+    {
+      "epoch": 2.5205368035786906,
+      "grad_norm": 0.5051369667053223,
+      "learning_rate": 3.2086720867208674e-06,
+      "loss": 2.138,
+      "step": 1550
+    },
+    {
+      "epoch": 2.5368035786905248,
+      "grad_norm": 0.5508773922920227,
+      "learning_rate": 3.1002710027100273e-06,
+      "loss": 2.2178,
+      "step": 1560
+    },
+    {
+      "epoch": 2.553070353802359,
+      "grad_norm": 0.402597039937973,
+      "learning_rate": 2.991869918699187e-06,
+      "loss": 2.1865,
+      "step": 1570
+    },
+    {
+      "epoch": 2.5693371289141926,
+      "grad_norm": 0.48877769708633423,
+      "learning_rate": 2.883468834688347e-06,
+      "loss": 2.1334,
+      "step": 1580
+    },
+    {
+      "epoch": 2.585603904026027,
+      "grad_norm": 0.5393285751342773,
+      "learning_rate": 2.775067750677507e-06,
+      "loss": 2.1944,
+      "step": 1590
+    },
+    {
+      "epoch": 2.601870679137861,
+      "grad_norm": 0.5359148979187012,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.1265,
+      "step": 1600
+    },
+    {
+      "epoch": 2.618137454249695,
+      "grad_norm": 0.44901204109191895,
+      "learning_rate": 2.5582655826558267e-06,
+      "loss": 2.1863,
+      "step": 1610
+    },
+    {
+      "epoch": 2.634404229361529,
+      "grad_norm": 0.621069610118866,
+      "learning_rate": 2.4498644986449866e-06,
+      "loss": 2.1268,
+      "step": 1620
+    },
+    {
+      "epoch": 2.650671004473363,
+      "grad_norm": 0.7652748823165894,
+      "learning_rate": 2.3414634146341465e-06,
+      "loss": 2.1838,
+      "step": 1630
+    },
+    {
+      "epoch": 2.666937779585197,
+      "grad_norm": 0.49381202459335327,
+      "learning_rate": 2.2330623306233063e-06,
+      "loss": 2.1923,
+      "step": 1640
+    },
+    {
+      "epoch": 2.6832045546970313,
+      "grad_norm": 0.47194594144821167,
+      "learning_rate": 2.1246612466124662e-06,
+      "loss": 2.2004,
+      "step": 1650
+    },
+    {
+      "epoch": 2.6994713298088655,
+      "grad_norm": 0.5487152934074402,
+      "learning_rate": 2.016260162601626e-06,
+      "loss": 2.2393,
+      "step": 1660
+    },
+    {
+      "epoch": 2.7157381049206997,
+      "grad_norm": 0.6591639518737793,
+      "learning_rate": 1.907859078590786e-06,
+      "loss": 2.1216,
+      "step": 1670
+    },
+    {
+      "epoch": 2.7320048800325334,
+      "grad_norm": 0.4983465075492859,
+      "learning_rate": 1.7994579945799459e-06,
+      "loss": 2.1119,
+      "step": 1680
+    },
+    {
+      "epoch": 2.7482716551443676,
+      "grad_norm": 0.7329484820365906,
+      "learning_rate": 1.6910569105691057e-06,
+      "loss": 2.1102,
+      "step": 1690
+    },
+    {
+      "epoch": 2.7645384302562017,
+      "grad_norm": 0.93742436170578,
+      "learning_rate": 1.5826558265582656e-06,
+      "loss": 2.2423,
+      "step": 1700
+    },
+    {
+      "epoch": 2.780805205368036,
+      "grad_norm": 0.6207740306854248,
+      "learning_rate": 1.4742547425474257e-06,
+      "loss": 2.1586,
+      "step": 1710
+    },
+    {
+      "epoch": 2.7970719804798696,
+      "grad_norm": 0.41883742809295654,
+      "learning_rate": 1.3658536585365856e-06,
+      "loss": 2.189,
+      "step": 1720
+    },
+    {
+      "epoch": 2.8133387555917038,
+      "grad_norm": 0.7352700233459473,
+      "learning_rate": 1.2574525745257455e-06,
+      "loss": 2.1331,
+      "step": 1730
+    },
+    {
+      "epoch": 2.829605530703538,
+      "grad_norm": 0.6216088533401489,
+      "learning_rate": 1.1490514905149053e-06,
+      "loss": 2.1928,
+      "step": 1740
+    },
+    {
+      "epoch": 2.845872305815372,
+      "grad_norm": 0.694766104221344,
+      "learning_rate": 1.0406504065040652e-06,
+      "loss": 2.1648,
+      "step": 1750
+    },
+    {
+      "epoch": 2.8621390809272063,
+      "grad_norm": 0.8991151452064514,
+      "learning_rate": 9.32249322493225e-07,
+      "loss": 2.1362,
+      "step": 1760
+    },
+    {
+      "epoch": 2.8784058560390404,
+      "grad_norm": 1.1037092208862305,
+      "learning_rate": 8.23848238482385e-07,
+      "loss": 2.1617,
+      "step": 1770
+    },
+    {
+      "epoch": 2.8946726311508746,
+      "grad_norm": 0.5003814697265625,
+      "learning_rate": 7.154471544715448e-07,
+      "loss": 2.2079,
+      "step": 1780
+    },
+    {
+      "epoch": 2.9109394062627083,
+      "grad_norm": 0.5789722204208374,
+      "learning_rate": 6.070460704607046e-07,
+      "loss": 2.1699,
+      "step": 1790
+    },
+    {
+      "epoch": 2.9272061813745425,
+      "grad_norm": 0.7220056653022766,
+      "learning_rate": 4.986449864498646e-07,
+      "loss": 2.1337,
+      "step": 1800
+    },
+    {
+      "epoch": 2.9434729564863766,
+      "grad_norm": 0.6918893456459045,
+      "learning_rate": 3.9024390243902443e-07,
+      "loss": 2.1949,
+      "step": 1810
+    },
+    {
+      "epoch": 2.959739731598211,
+      "grad_norm": 0.7044161558151245,
+      "learning_rate": 2.818428184281843e-07,
+      "loss": 2.1213,
+      "step": 1820
+    },
+    {
+      "epoch": 2.9760065067100445,
+      "grad_norm": 0.7030537128448486,
+      "learning_rate": 1.7344173441734418e-07,
+      "loss": 2.178,
+      "step": 1830
+    },
+    {
+      "epoch": 2.9922732818218787,
+      "grad_norm": 0.5555047392845154,
+      "learning_rate": 6.504065040650408e-08,
+      "loss": 2.198,
+      "step": 1840
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1845,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.91408129848574e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1845/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018cc1d55d2ff18e3ef653458af0905c473e4c15684121019fe78e8b522e3247
+size 5713

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 512,
+    "max_length": 1028,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 512
+      "Fixed": 1028
     },
     "direction": "Left",
     "pad_to_multiple_of": null,

tokenizer_config.json

@@ -129,17 +129,10 @@
   "eos_token": "<｜end▁of▁sentence｜>",
   "extra_special_tokens": {},
   "legacy": true,
-  "max_length": 1028,
   "model_max_length": 4096,
-  "pad_to_multiple_of": null,
   "pad_token": "<｜end▁of▁sentence｜>",
-  "pad_token_type_id": 0,
-  "padding_side": "left",
   "sp_model_kwargs": {},
-  "stride": 0,
   "tokenizer_class": "LlamaTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "unk_token": null,
   "use_default_system_prompt": false
 }