Model save

README.md

@@ -0,0 +1,76 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-stem-case-2
+  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. -->
+
+# zephyr-7b-stem-case-2
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2113
+
+## 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: 1e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0974        | 1.0   | 1    | 1.1027          |
+| 1.0974        | 2.0   | 2    | 1.2132          |
+| 1.0974        | 3.0   | 3    | 0.9654          |
+| 1.0974        | 4.0   | 4    | 0.6956          |
+| 0.9948        | 5.0   | 5    | 0.5648          |
+| 0.9948        | 6.0   | 6    | 0.3997          |
+| 0.9948        | 7.0   | 7    | 0.3115          |
+| 0.9948        | 8.0   | 8    | 0.2529          |
+| 0.9948        | 9.0   | 9    | 0.2212          |
+| 0.3483        | 10.0  | 10   | 0.2113          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5.592050747991654e+16,
+    "train_loss": 0.6817932724952698,
+    "train_runtime": 211.7828,
+    "train_samples": 424,
+    "train_samples_per_second": 1.133,
+    "train_steps_per_second": 0.047
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.2"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 5.592050747991654e+16,
+    "train_loss": 0.6817932724952698,
+    "train_runtime": 211.7828,
+    "train_samples": 424,
+    "train_samples_per_second": 1.133,
+    "train_steps_per_second": 0.047
+}

trainer_state.json

@@ -0,0 +1,143 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 20.091201782226562,
+      "learning_rate": 1e-05,
+      "loss": 1.0974,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.1026824712753296,
+      "eval_runtime": 2.5398,
+      "eval_samples_per_second": 9.45,
+      "eval_steps_per_second": 0.394,
+      "step": 1
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.2132011651992798,
+      "eval_runtime": 2.5504,
+      "eval_samples_per_second": 9.41,
+      "eval_steps_per_second": 0.392,
+      "step": 2
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9654137492179871,
+      "eval_runtime": 2.5582,
+      "eval_samples_per_second": 9.382,
+      "eval_steps_per_second": 0.391,
+      "step": 3
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.6955726742744446,
+      "eval_runtime": 2.5684,
+      "eval_samples_per_second": 9.344,
+      "eval_steps_per_second": 0.389,
+      "step": 4
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 17.220090866088867,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.9948,
+      "step": 5
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.5648126602172852,
+      "eval_runtime": 2.5655,
+      "eval_samples_per_second": 9.355,
+      "eval_steps_per_second": 0.39,
+      "step": 5
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.39974427223205566,
+      "eval_runtime": 2.5699,
+      "eval_samples_per_second": 9.339,
+      "eval_steps_per_second": 0.389,
+      "step": 6
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.3115054666996002,
+      "eval_runtime": 2.5785,
+      "eval_samples_per_second": 9.308,
+      "eval_steps_per_second": 0.388,
+      "step": 7
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.2529359757900238,
+      "eval_runtime": 2.5839,
+      "eval_samples_per_second": 9.288,
+      "eval_steps_per_second": 0.387,
+      "step": 8
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.22118614614009857,
+      "eval_runtime": 2.5806,
+      "eval_samples_per_second": 9.3,
+      "eval_steps_per_second": 0.388,
+      "step": 9
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 3.2548158168792725,
+      "learning_rate": 0.0,
+      "loss": 0.3483,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.2112644463777542,
+      "eval_runtime": 2.5219,
+      "eval_samples_per_second": 9.517,
+      "eval_steps_per_second": 0.397,
+      "step": 10
+    },
+    {
+      "epoch": 10.0,
+      "step": 10,
+      "total_flos": 5.592050747991654e+16,
+      "train_loss": 0.6817932724952698,
+      "train_runtime": 211.7828,
+      "train_samples_per_second": 1.133,
+      "train_steps_per_second": 0.047
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 10,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 5.592050747991654e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}