Model save

README.md

@@ -0,0 +1,69 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: mistral7b-kasa-coding-11-v1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# mistral7b-kasa-coding-11-v1
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5500
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 12
+- eval_batch_size: 12
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 192
+- total_eval_batch_size: 96
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.5519        | 0.9951 | 102  | 1.5500          |
+
+
+### Framework versions
+
+- PEFT 0.13.1.dev0
+- Transformers 4.46.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dae2b689159078c1aa56f5ef39d807fa905276ddaa8d87c3fcce4d1bc27e5e2
+oid sha256:069540c7ce3c9f87b9235774a6ede1c35690b7806e8a2ba1f5df0587143d8eaf
 size 1087481480

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9951219512195122,
+    "total_flos": 4.281868708751606e+17,
+    "train_loss": 1.6186961426454431,
+    "train_runtime": 363.7432,
+    "train_samples": 51241,
+    "train_samples_per_second": 53.848,
+    "train_steps_per_second": 0.28
+}

runs/Nov18_17-51-21_bold-food-flourishes-fin-02/events.out.tfevents.1731953307.bold-food-flourishes-fin-02.106436.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74ba5aa3ea01a498e073f58f213ad51bde8406b18b32c6b76d36a81ea3aad4d
-size 9862
+oid sha256:75e08e02e31f381d45e0d2220ce4ef2ddafd1781325dcb3ab251f55f29dbd036
+size 10476

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9951219512195122,
+    "total_flos": 4.281868708751606e+17,
+    "train_loss": 1.6186961426454431,
+    "train_runtime": 363.7432,
+    "train_samples": 51241,
+    "train_samples_per_second": 53.848,
+    "train_steps_per_second": 0.28
+}

trainer_state.json

@@ -0,0 +1,197 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9951219512195122,
+  "eval_steps": 500,
+  "global_step": 102,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00975609756097561,
+      "grad_norm": 2.371129274368286,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 2.0473,
+      "step": 1
+    },
+    {
+      "epoch": 0.04878048780487805,
+      "grad_norm": 2.3514864444732666,
+      "learning_rate": 9.090909090909092e-05,
+      "loss": 2.0124,
+      "step": 5
+    },
+    {
+      "epoch": 0.0975609756097561,
+      "grad_norm": 1.9732930660247803,
+      "learning_rate": 0.00018181818181818183,
+      "loss": 1.9222,
+      "step": 10
+    },
+    {
+      "epoch": 0.14634146341463414,
+      "grad_norm": 2.1772541999816895,
+      "learning_rate": 0.00019904804439875633,
+      "loss": 1.7928,
+      "step": 15
+    },
+    {
+      "epoch": 0.1951219512195122,
+      "grad_norm": 1.5341215133666992,
+      "learning_rate": 0.00019521176659107142,
+      "loss": 1.7354,
+      "step": 20
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 1.4509671926498413,
+      "learning_rate": 0.000188545602565321,
+      "loss": 1.6622,
+      "step": 25
+    },
+    {
+      "epoch": 0.2926829268292683,
+      "grad_norm": 0.9245131015777588,
+      "learning_rate": 0.00017924768419510904,
+      "loss": 1.5826,
+      "step": 30
+    },
+    {
+      "epoch": 0.34146341463414637,
+      "grad_norm": 0.8397857546806335,
+      "learning_rate": 0.00016759436441447545,
+      "loss": 1.5755,
+      "step": 35
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 0.7870491743087769,
+      "learning_rate": 0.00015393200344991995,
+      "loss": 1.5685,
+      "step": 40
+    },
+    {
+      "epoch": 0.43902439024390244,
+      "grad_norm": 0.7064230442047119,
+      "learning_rate": 0.0001386666742941419,
+      "loss": 1.5434,
+      "step": 45
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 0.8221641182899475,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 1.5552,
+      "step": 50
+    },
+    {
+      "epoch": 0.5365853658536586,
+      "grad_norm": 0.7419559359550476,
+      "learning_rate": 0.00010517613528842097,
+      "loss": 1.5569,
+      "step": 55
+    },
+    {
+      "epoch": 0.5853658536585366,
+      "grad_norm": 0.7535139322280884,
+      "learning_rate": 8.79463319744677e-05,
+      "loss": 1.5627,
+      "step": 60
+    },
+    {
+      "epoch": 0.6341463414634146,
+      "grad_norm": 0.709441065788269,
+      "learning_rate": 7.107478804634325e-05,
+      "loss": 1.5634,
+      "step": 65
+    },
+    {
+      "epoch": 0.6829268292682927,
+      "grad_norm": 0.6745243668556213,
+      "learning_rate": 5.506295990328385e-05,
+      "loss": 1.5537,
+      "step": 70
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.6785560250282288,
+      "learning_rate": 4.038675145307747e-05,
+      "loss": 1.5373,
+      "step": 75
+    },
+    {
+      "epoch": 0.7804878048780488,
+      "grad_norm": 0.7758954167366028,
+      "learning_rate": 2.7482369285662378e-05,
+      "loss": 1.5341,
+      "step": 80
+    },
+    {
+      "epoch": 0.8292682926829268,
+      "grad_norm": 0.6606050729751587,
+      "learning_rate": 1.6733357731279377e-05,
+      "loss": 1.5326,
+      "step": 85
+    },
+    {
+      "epoch": 0.8780487804878049,
+      "grad_norm": 0.8155940771102905,
+      "learning_rate": 8.45919914746337e-06,
+      "loss": 1.5411,
+      "step": 90
+    },
+    {
+      "epoch": 0.926829268292683,
+      "grad_norm": 0.7202953100204468,
+      "learning_rate": 2.905818257394799e-06,
+      "loss": 1.5414,
+      "step": 95
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 0.670049786567688,
+      "learning_rate": 2.382727698752474e-07,
+      "loss": 1.5519,
+      "step": 100
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "eval_loss": 1.5499577522277832,
+      "eval_runtime": 1.7555,
+      "eval_samples_per_second": 111.078,
+      "eval_steps_per_second": 1.709,
+      "step": 102
+    },
+    {
+      "epoch": 0.9951219512195122,
+      "step": 102,
+      "total_flos": 4.281868708751606e+17,
+      "train_loss": 1.6186961426454431,
+      "train_runtime": 363.7432,
+      "train_samples_per_second": 53.848,
+      "train_steps_per_second": 0.28
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 102,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.281868708751606e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}