Upload folder using huggingface_hub

README.md

@@ -9,55 +9,201 @@ tags:
 - transformers
 - trl
 ---
-### Framework versions
 
-- PEFT 0.17.0
+# 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:**
 
-# Model Card for foamqwen
+[More Information Needed]
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
-It has been trained using [TRL](https://github.com/huggingface/trl).
+## Glossary [optional]
 
-## Quick start
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
 
-```python
-from transformers import pipeline
+[More Information Needed]
 
-question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="None", device="cuda")
-output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
-print(output["generated_text"])
-```
+## More Information [optional]
 
-## Training procedure
+[More Information Needed]
 
- 
+## Model Card Authors [optional]
 
+[More Information Needed]
 
-This model was trained with SFT.
+## Model Card Contact
 
+[More Information Needed]
 ### Framework versions
 
-- PEFT 0.17.0
-- TRL: 0.19.0
-- Transformers: 4.52.3
-- Pytorch: 2.7.0
-- Datasets: 4.4.1
-- Tokenizers: 0.21.4
-
-## Citations
-
-
-
-Cite TRL as:
-    
-```bibtex
-@misc{vonwerra2022trl,
-	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
-	year         = 2020,
-	journal      = {GitHub repository},
-	publisher    = {GitHub},
-	howpublished = {\url{https://github.com/huggingface/trl}}
-}
-```
+- PEFT 0.17.0

adapter_config.json

@@ -25,13 +25,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
     "down_proj",
-    "up_proj",
-    "gate_proj",
+    "o_proj",
     "k_proj",
-    "o_proj"
+    "v_proj",
+    "gate_proj",
+    "up_proj",
+    "q_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c4b7c94260f78eb6b4165cbcfe2ddb885354992826a11e83ca4b9e7c8bd821
+oid sha256:e66061757a3f9c7e694bd0869920435ba5cd7a0117a26a35caaceea1882296a8
 size 645975704

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f46dc0b6cd60733e44769de8e8e0858d07c1b25a992eae50a74b529c3e4db236
+size 1292087499

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7192a40ca4014f502efc59dacc942dad83ac6b1e5dbffc44a7e2368a17abffd4
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22f988a134540f1261cc919cb029bec83fd4a129faeedd432eda41941d88caca
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a00527b6663b32e26bbe8bf4772fd7934576df924e6fc0a26b27e451253945f
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d158f929065935ff5e42e00f4c943d51cb4a72cc008d4cc7441b13796917f2b6
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452277350ad8f5efad158760275ed80bf2a10a74384da69a532b63915629f8f6
+size 1465

trainer_state.json

@@ -0,0 +1,503 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1040,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.17040389776229858,
+      "learning_rate": 0.000511,
+      "loss": 0.4303,
+      "mean_token_accuracy": 0.8983636182546616,
+      "num_tokens": 569446.0,
+      "step": 25
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.19750550389289856,
+      "learning_rate": 0.000511,
+      "loss": 0.2953,
+      "mean_token_accuracy": 0.9258013522624969,
+      "num_tokens": 1138403.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.2441304326057434,
+      "learning_rate": 0.000511,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.9427212655544281,
+      "num_tokens": 1705606.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.19773538410663605,
+      "learning_rate": 0.000511,
+      "loss": 0.194,
+      "mean_token_accuracy": 0.9479873812198639,
+      "num_tokens": 2271060.0,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.1995953470468521,
+      "eval_mean_token_accuracy": 0.9460804703387808,
+      "eval_num_tokens": 2345411.0,
+      "eval_runtime": 4.3258,
+      "eval_samples_per_second": 85.303,
+      "eval_steps_per_second": 10.865,
+      "step": 104
+    },
+    {
+      "epoch": 1.202409638554217,
+      "grad_norm": 0.0789426863193512,
+      "learning_rate": 0.000511,
+      "loss": 0.16,
+      "mean_token_accuracy": 0.9584937607399141,
+      "num_tokens": 2836512.0,
+      "step": 125
+    },
+    {
+      "epoch": 1.4433734939759035,
+      "grad_norm": 0.10643763095140457,
+      "learning_rate": 0.000511,
+      "loss": 0.1408,
+      "mean_token_accuracy": 0.9620217531919479,
+      "num_tokens": 3403395.0,
+      "step": 150
+    },
+    {
+      "epoch": 1.6843373493975904,
+      "grad_norm": 0.08403506129980087,
+      "learning_rate": 0.000511,
+      "loss": 0.1314,
+      "mean_token_accuracy": 0.9630346685647965,
+      "num_tokens": 3970344.0,
+      "step": 175
+    },
+    {
+      "epoch": 1.9253012048192772,
+      "grad_norm": 0.10631190985441208,
+      "learning_rate": 0.000511,
+      "loss": 0.1272,
+      "mean_token_accuracy": 0.9646087974309921,
+      "num_tokens": 4538034.0,
+      "step": 200
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.14445580542087555,
+      "eval_mean_token_accuracy": 0.9612192435467497,
+      "eval_num_tokens": 4690349.0,
+      "eval_runtime": 4.2683,
+      "eval_samples_per_second": 86.451,
+      "eval_steps_per_second": 11.011,
+      "step": 208
+    },
+    {
+      "epoch": 2.163855421686747,
+      "grad_norm": 0.08164115995168686,
+      "learning_rate": 0.000511,
+      "loss": 0.1067,
+      "mean_token_accuracy": 0.9689010110768405,
+      "num_tokens": 5091219.0,
+      "step": 225
+    },
+    {
+      "epoch": 2.404819277108434,
+      "grad_norm": 0.08637778460979462,
+      "learning_rate": 0.000511,
+      "loss": 0.0968,
+      "mean_token_accuracy": 0.9721185141801834,
+      "num_tokens": 5658328.0,
+      "step": 250
+    },
+    {
+      "epoch": 2.6457831325301204,
+      "grad_norm": 0.0902683362364769,
+      "learning_rate": 0.000511,
+      "loss": 0.091,
+      "mean_token_accuracy": 0.9744718617200852,
+      "num_tokens": 6225744.0,
+      "step": 275
+    },
+    {
+      "epoch": 2.886746987951807,
+      "grad_norm": 0.09357521682977676,
+      "learning_rate": 0.000511,
+      "loss": 0.0929,
+      "mean_token_accuracy": 0.9727102434635162,
+      "num_tokens": 6794402.0,
+      "step": 300
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.14705069363117218,
+      "eval_mean_token_accuracy": 0.9624257531571896,
+      "eval_num_tokens": 7035273.0,
+      "eval_runtime": 4.2634,
+      "eval_samples_per_second": 86.55,
+      "eval_steps_per_second": 11.024,
+      "step": 312
+    },
+    {
+      "epoch": 3.125301204819277,
+      "grad_norm": 0.14760874211788177,
+      "learning_rate": 0.000511,
+      "loss": 0.0842,
+      "mean_token_accuracy": 0.9764150320881545,
+      "num_tokens": 7334495.0,
+      "step": 325
+    },
+    {
+      "epoch": 3.3662650602409636,
+      "grad_norm": 0.09895172715187073,
+      "learning_rate": 0.000511,
+      "loss": 0.0777,
+      "mean_token_accuracy": 0.9774631917476654,
+      "num_tokens": 7903478.0,
+      "step": 350
+    },
+    {
+      "epoch": 3.6072289156626507,
+      "grad_norm": 0.10538128763437271,
+      "learning_rate": 0.000511,
+      "loss": 0.0742,
+      "mean_token_accuracy": 0.9783486902713776,
+      "num_tokens": 8469479.0,
+      "step": 375
+    },
+    {
+      "epoch": 3.8481927710843373,
+      "grad_norm": 0.09741026163101196,
+      "learning_rate": 0.000511,
+      "loss": 0.0679,
+      "mean_token_accuracy": 0.9803410685062408,
+      "num_tokens": 9036138.0,
+      "step": 400
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.14550796151161194,
+      "eval_mean_token_accuracy": 0.9638357936067784,
+      "eval_num_tokens": 9380804.0,
+      "eval_runtime": 4.2387,
+      "eval_samples_per_second": 87.055,
+      "eval_steps_per_second": 11.088,
+      "step": 416
+    },
+    {
+      "epoch": 4.086746987951807,
+      "grad_norm": 0.10616449266672134,
+      "learning_rate": 0.000511,
+      "loss": 0.0625,
+      "mean_token_accuracy": 0.9811063475079007,
+      "num_tokens": 9598059.0,
+      "step": 425
+    },
+    {
+      "epoch": 4.327710843373494,
+      "grad_norm": 0.09445353597402573,
+      "learning_rate": 0.000511,
+      "loss": 0.0545,
+      "mean_token_accuracy": 0.9833864039182663,
+      "num_tokens": 10165089.0,
+      "step": 450
+    },
+    {
+      "epoch": 4.5686746987951805,
+      "grad_norm": 0.07407805323600769,
+      "learning_rate": 0.000511,
+      "loss": 0.0545,
+      "mean_token_accuracy": 0.984256454706192,
+      "num_tokens": 10732931.0,
+      "step": 475
+    },
+    {
+      "epoch": 4.809638554216868,
+      "grad_norm": 0.07322381436824799,
+      "learning_rate": 0.000511,
+      "loss": 0.0462,
+      "mean_token_accuracy": 0.9861221539974213,
+      "num_tokens": 11301466.0,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.14242176711559296,
+      "eval_mean_token_accuracy": 0.9691625554510888,
+      "eval_num_tokens": 11726407.0,
+      "eval_runtime": 4.2397,
+      "eval_samples_per_second": 87.035,
+      "eval_steps_per_second": 11.086,
+      "step": 520
+    },
+    {
+      "epoch": 5.048192771084337,
+      "grad_norm": 0.06890378147363663,
+      "learning_rate": 0.000511,
+      "loss": 0.0538,
+      "mean_token_accuracy": 0.9846178467827614,
+      "num_tokens": 11856936.0,
+      "step": 525
+    },
+    {
+      "epoch": 5.289156626506024,
+      "grad_norm": 0.05453705042600632,
+      "learning_rate": 0.000511,
+      "loss": 0.0485,
+      "mean_token_accuracy": 0.9858993107080459,
+      "num_tokens": 12423275.0,
+      "step": 550
+    },
+    {
+      "epoch": 5.530120481927711,
+      "grad_norm": 0.0743594691157341,
+      "learning_rate": 0.000511,
+      "loss": 0.0455,
+      "mean_token_accuracy": 0.9857969325780869,
+      "num_tokens": 12992045.0,
+      "step": 575
+    },
+    {
+      "epoch": 5.771084337349397,
+      "grad_norm": 0.06587184965610504,
+      "learning_rate": 0.000511,
+      "loss": 0.0446,
+      "mean_token_accuracy": 0.9862634456157684,
+      "num_tokens": 13560037.0,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.1241711750626564,
+      "eval_mean_token_accuracy": 0.9710005204728309,
+      "eval_num_tokens": 14071932.0,
+      "eval_runtime": 4.2228,
+      "eval_samples_per_second": 87.383,
+      "eval_steps_per_second": 11.13,
+      "step": 624
+    },
+    {
+      "epoch": 6.009638554216868,
+      "grad_norm": 0.06124307960271835,
+      "learning_rate": 0.000511,
+      "loss": 0.0368,
+      "mean_token_accuracy": 0.9886124525407348,
+      "num_tokens": 14102915.0,
+      "step": 625
+    },
+    {
+      "epoch": 6.250602409638554,
+      "grad_norm": 0.10462699830532074,
+      "learning_rate": 0.000511,
+      "loss": 0.0378,
+      "mean_token_accuracy": 0.9887062352895737,
+      "num_tokens": 14669309.0,
+      "step": 650
+    },
+    {
+      "epoch": 6.491566265060241,
+      "grad_norm": 0.09343062341213226,
+      "learning_rate": 0.000511,
+      "loss": 0.0353,
+      "mean_token_accuracy": 0.9892213380336762,
+      "num_tokens": 15237353.0,
+      "step": 675
+    },
+    {
+      "epoch": 6.732530120481927,
+      "grad_norm": 0.08443740010261536,
+      "learning_rate": 0.000511,
+      "loss": 0.0364,
+      "mean_token_accuracy": 0.9892494148015976,
+      "num_tokens": 15804441.0,
+      "step": 700
+    },
+    {
+      "epoch": 6.973493975903614,
+      "grad_norm": 0.07635796070098877,
+      "learning_rate": 0.000511,
+      "loss": 0.0397,
+      "mean_token_accuracy": 0.9886371964216232,
+      "num_tokens": 16368577.0,
+      "step": 725
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.17054519057273865,
+      "eval_mean_token_accuracy": 0.9649876089806252,
+      "eval_num_tokens": 16416958.0,
+      "eval_runtime": 4.2384,
+      "eval_samples_per_second": 87.061,
+      "eval_steps_per_second": 11.089,
+      "step": 728
+    },
+    {
+      "epoch": 7.212048192771085,
+      "grad_norm": 0.0668734461069107,
+      "learning_rate": 0.000511,
+      "loss": 0.0333,
+      "mean_token_accuracy": 0.9895464802029157,
+      "num_tokens": 16927490.0,
+      "step": 750
+    },
+    {
+      "epoch": 7.453012048192771,
+      "grad_norm": 0.06639474630355835,
+      "learning_rate": 0.000511,
+      "loss": 0.0325,
+      "mean_token_accuracy": 0.9908391135931015,
+      "num_tokens": 17494143.0,
+      "step": 775
+    },
+    {
+      "epoch": 7.693975903614458,
+      "grad_norm": 0.10801058262586594,
+      "learning_rate": 0.000511,
+      "loss": 0.029,
+      "mean_token_accuracy": 0.9909009468555451,
+      "num_tokens": 18063423.0,
+      "step": 800
+    },
+    {
+      "epoch": 7.934939759036144,
+      "grad_norm": 0.048982683569192886,
+      "learning_rate": 0.000511,
+      "loss": 0.0313,
+      "mean_token_accuracy": 0.9908118671178818,
+      "num_tokens": 18630905.0,
+      "step": 825
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.1113305315375328,
+      "eval_mean_token_accuracy": 0.9737493814306056,
+      "eval_num_tokens": 18762023.0,
+      "eval_runtime": 4.2275,
+      "eval_samples_per_second": 87.285,
+      "eval_steps_per_second": 11.118,
+      "step": 832
+    },
+    {
+      "epoch": 8.173493975903614,
+      "grad_norm": 0.05220003426074982,
+      "learning_rate": 0.000511,
+      "loss": 0.0277,
+      "mean_token_accuracy": 0.9916808304160533,
+      "num_tokens": 19184427.0,
+      "step": 850
+    },
+    {
+      "epoch": 8.4144578313253,
+      "grad_norm": 0.08605129271745682,
+      "learning_rate": 0.000511,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9915985196828843,
+      "num_tokens": 19754417.0,
+      "step": 875
+    },
+    {
+      "epoch": 8.655421686746989,
+      "grad_norm": 0.0517394132912159,
+      "learning_rate": 0.000511,
+      "loss": 0.0258,
+      "mean_token_accuracy": 0.9922689855098724,
+      "num_tokens": 20322925.0,
+      "step": 900
+    },
+    {
+      "epoch": 8.896385542168675,
+      "grad_norm": 0.059128183871507645,
+      "learning_rate": 0.000511,
+      "loss": 0.0256,
+      "mean_token_accuracy": 0.9923817366361618,
+      "num_tokens": 20889889.0,
+      "step": 925
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.1412837952375412,
+      "eval_mean_token_accuracy": 0.97177672893443,
+      "eval_num_tokens": 21107006.0,
+      "eval_runtime": 4.2426,
+      "eval_samples_per_second": 86.974,
+      "eval_steps_per_second": 11.078,
+      "step": 936
+    },
+    {
+      "epoch": 9.134939759036145,
+      "grad_norm": 0.08735097944736481,
+      "learning_rate": 0.000511,
+      "loss": 0.0214,
+      "mean_token_accuracy": 0.9934688914905895,
+      "num_tokens": 21433768.0,
+      "step": 950
+    },
+    {
+      "epoch": 9.375903614457831,
+      "grad_norm": 0.07706229388713837,
+      "learning_rate": 0.000511,
+      "loss": 0.0219,
+      "mean_token_accuracy": 0.9933523815870285,
+      "num_tokens": 22001855.0,
+      "step": 975
+    },
+    {
+      "epoch": 9.616867469879518,
+      "grad_norm": 0.0835743248462677,
+      "learning_rate": 0.000511,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9938382267951965,
+      "num_tokens": 22568226.0,
+      "step": 1000
+    },
+    {
+      "epoch": 9.857831325301206,
+      "grad_norm": 0.10814040899276733,
+      "learning_rate": 0.000511,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.99358702480793,
+      "num_tokens": 23136558.0,
+      "step": 1025
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.1364360749721527,
+      "eval_mean_token_accuracy": 0.9739730041077796,
+      "eval_num_tokens": 23451914.0,
+      "eval_runtime": 4.2514,
+      "eval_samples_per_second": 86.796,
+      "eval_steps_per_second": 11.055,
+      "step": 1040
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 1248,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "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": 1.0255354758734807e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb24a2e21c60358ea1e7c21423d18ace82a12d90960084fd56c8a7388a71c974
+oid sha256:9abd2e560826c250d1fd3df1ec10e14fef0b5ef3b175f43df982f2fc9f2f11d9
 size 6097