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-math-train
+  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-math-train
+
+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: 0.0188
+
+## 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: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 64
+- 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: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8757        | 1.0   | 5    | 0.7950          |
+| 0.6949        | 2.0   | 10   | 0.5316          |
+| 0.48          | 3.0   | 15   | 0.3425          |
+| 0.2951        | 4.0   | 20   | 0.1809          |
+| 0.1534        | 5.0   | 25   | 0.0872          |
+| 0.0746        | 6.0   | 30   | 0.0426          |
+| 0.0409        | 7.0   | 35   | 0.0291          |
+| 0.0287        | 8.0   | 40   | 0.0229          |
+| 0.022         | 9.0   | 45   | 0.0196          |
+| 0.019         | 10.0  | 50   | 0.0188          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu124
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 10468982784000.0,
+    "train_loss": 0.2698070502281189,
+    "train_runtime": 354.7739,
+    "train_samples": 2000,
+    "train_samples_per_second": 8.569,
+    "train_steps_per_second": 0.141
+}

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": 10468982784000.0,
+    "train_loss": 0.2698070502281189,
+    "train_runtime": 354.7739,
+    "train_samples": 2000,
+    "train_samples_per_second": 8.569,
+    "train_steps_per_second": 0.141
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 17.521699083442236,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.9449,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 16.40180953776377,
+      "learning_rate": 1e-05,
+      "loss": 0.8757,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.7949993014335632,
+      "eval_runtime": 5.7244,
+      "eval_samples_per_second": 53.106,
+      "eval_steps_per_second": 1.747,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 5.483468983754786,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.6949,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5316293835639954,
+      "eval_runtime": 5.7356,
+      "eval_samples_per_second": 53.002,
+      "eval_steps_per_second": 1.743,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.5800992892125247,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.48,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.3424782156944275,
+      "eval_runtime": 5.7308,
+      "eval_samples_per_second": 53.047,
+      "eval_steps_per_second": 1.745,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.0290800502634267,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.2951,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.18087059259414673,
+      "eval_runtime": 5.7338,
+      "eval_samples_per_second": 53.019,
+      "eval_steps_per_second": 1.744,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 3.0982583119481917,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.1534,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.08724663406610489,
+      "eval_runtime": 5.7282,
+      "eval_samples_per_second": 53.07,
+      "eval_steps_per_second": 1.746,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 2.9484898560874275,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.0746,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.04263892024755478,
+      "eval_runtime": 5.7324,
+      "eval_samples_per_second": 53.032,
+      "eval_steps_per_second": 1.744,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.7269539147644108,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.0409,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 0.029139719903469086,
+      "eval_runtime": 5.7305,
+      "eval_samples_per_second": 53.05,
+      "eval_steps_per_second": 1.745,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.272582408957205,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.0287,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.022901222109794617,
+      "eval_runtime": 5.729,
+      "eval_samples_per_second": 53.064,
+      "eval_steps_per_second": 1.746,
+      "step": 40
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.7341515458123513,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.022,
+      "step": 45
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.019588297232985497,
+      "eval_runtime": 5.7356,
+      "eval_samples_per_second": 53.003,
+      "eval_steps_per_second": 1.744,
+      "step": 45
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.516988345404078,
+      "learning_rate": 0.0,
+      "loss": 0.019,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.018791092559695244,
+      "eval_runtime": 5.7051,
+      "eval_samples_per_second": 53.286,
+      "eval_steps_per_second": 1.753,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "step": 50,
+      "total_flos": 10468982784000.0,
+      "train_loss": 0.2698070502281189,
+      "train_runtime": 354.7739,
+      "train_samples_per_second": 8.569,
+      "train_steps_per_second": 0.141
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "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": 10468982784000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}