Model save

README.md

@@ -0,0 +1,71 @@
+---
+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-case-6-ep5
+  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-case-6-ep5
+
+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: 0.3117
+
+## 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: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 5
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.0402        | 1.0   | 5    | 0.7510          |
+| 0.691         | 2.0   | 10   | 0.5701          |
+| 0.5239        | 3.0   | 15   | 0.4264          |
+| 0.3917        | 4.0   | 20   | 0.3359          |
+| 0.3221        | 5.0   | 25   | 0.3117          |
+
+
+### 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": 5.0,
+    "total_flos": 10468982784000.0,
+    "train_loss": 0.5895810270309448,
+    "train_runtime": 388.4587,
+    "train_samples": 4000,
+    "train_samples_per_second": 3.385,
+    "train_steps_per_second": 0.064
+}

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": 5.0,
+    "total_flos": 10468982784000.0,
+    "train_loss": 0.5895810270309448,
+    "train_runtime": 388.4587,
+    "train_samples": 4000,
+    "train_samples_per_second": 3.385,
+    "train_steps_per_second": 0.064
+}

trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 25,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 24.8895814604259,
+      "learning_rate": 1e-05,
+      "loss": 0.9347,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 10.507921581694449,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 1.0402,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.750956118106842,
+      "eval_runtime": 13.4777,
+      "eval_samples_per_second": 19.514,
+      "eval_steps_per_second": 0.371,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 3.2842066334321927,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 0.691,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.5700622200965881,
+      "eval_runtime": 13.3794,
+      "eval_samples_per_second": 19.657,
+      "eval_steps_per_second": 0.374,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.0707933492232007,
+      "learning_rate": 3.705904774487396e-06,
+      "loss": 0.5239,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.426382839679718,
+      "eval_runtime": 13.3851,
+      "eval_samples_per_second": 19.649,
+      "eval_steps_per_second": 0.374,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 3.1454642852295103,
+      "learning_rate": 1.0332332985438248e-06,
+      "loss": 0.3917,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.33590540289878845,
+      "eval_runtime": 13.3827,
+      "eval_samples_per_second": 19.652,
+      "eval_steps_per_second": 0.374,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.732790702100083,
+      "learning_rate": 0.0,
+      "loss": 0.3221,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.31167706847190857,
+      "eval_runtime": 13.3175,
+      "eval_samples_per_second": 19.749,
+      "eval_steps_per_second": 0.375,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "step": 25,
+      "total_flos": 10468982784000.0,
+      "train_loss": 0.5895810270309448,
+      "train_runtime": 388.4587,
+      "train_samples_per_second": 3.385,
+      "train_steps_per_second": 0.064
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 25,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}