Model save

README.md

@@ -0,0 +1,70 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: mistralai/Mistral-Nemo-Base-2407
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: Mistral-Nemo-Instruct-Baseline-SFT
+  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. -->
+
+# Mistral-Nemo-Instruct-Baseline-SFT
+
+This model is a fine-tuned version of [mistralai/Mistral-Nemo-Base-2407](https://huggingface.co/mistralai/Mistral-Nemo-Base-2407) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1750
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 256
+- 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: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.6158        | 0.9455 | 13   | 1.3800          |
+| 1.1061        | 1.9636 | 27   | 1.1854          |
+| 0.9071        | 2.8364 | 39   | 1.1750          |
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.1
+- Tokenizers 0.20.0

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.8363636363636364,
+    "total_flos": 50553107251200.0,
+    "train_loss": 1.237262059480716,
+    "train_runtime": 1937.0641,
+    "train_samples": 18999,
+    "train_samples_per_second": 5.391,
+    "train_steps_per_second": 0.02
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.1"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.8363636363636364,
+    "total_flos": 50553107251200.0,
+    "train_loss": 1.237262059480716,
+    "train_runtime": 1937.0641,
+    "train_samples": 18999,
+    "train_samples_per_second": 5.391,
+    "train_steps_per_second": 0.02
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8363636363636364,
+  "eval_steps": 500,
+  "global_step": 39,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07272727272727272,
+      "grad_norm": 40.167989617647805,
+      "learning_rate": 5e-06,
+      "loss": 1.8364,
+      "step": 1
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 24.721297347748504,
+      "learning_rate": 1.9959742939952393e-05,
+      "loss": 1.7021,
+      "step": 5
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 5.200831471943857,
+      "learning_rate": 1.8584487936018663e-05,
+      "loss": 1.6158,
+      "step": 10
+    },
+    {
+      "epoch": 0.9454545454545454,
+      "eval_loss": 1.380013108253479,
+      "eval_runtime": 17.9955,
+      "eval_samples_per_second": 19.838,
+      "eval_steps_per_second": 0.333,
+      "step": 13
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 8.417480656354106,
+      "learning_rate": 1.5508969814521026e-05,
+      "loss": 1.3717,
+      "step": 15
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 2.9015403857161433,
+      "learning_rate": 1.1342332658176556e-05,
+      "loss": 1.194,
+      "step": 20
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.4331768387247874,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 1.1061,
+      "step": 25
+    },
+    {
+      "epoch": 1.9636363636363636,
+      "eval_loss": 1.1853971481323242,
+      "eval_runtime": 17.707,
+      "eval_samples_per_second": 20.161,
+      "eval_steps_per_second": 0.339,
+      "step": 27
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.2443658592960614,
+      "learning_rate": 3.089373510131354e-06,
+      "loss": 1.0003,
+      "step": 30
+    },
+    {
+      "epoch": 2.5454545454545454,
+      "grad_norm": 0.8568687436721839,
+      "learning_rate": 6.37651293602628e-07,
+      "loss": 0.9071,
+      "step": 35
+    },
+    {
+      "epoch": 2.8363636363636364,
+      "eval_loss": 1.1750216484069824,
+      "eval_runtime": 17.732,
+      "eval_samples_per_second": 20.133,
+      "eval_steps_per_second": 0.338,
+      "step": 39
+    },
+    {
+      "epoch": 2.8363636363636364,
+      "step": 39,
+      "total_flos": 50553107251200.0,
+      "train_loss": 1.237262059480716,
+      "train_runtime": 1937.0641,
+      "train_samples_per_second": 5.391,
+      "train_steps_per_second": 0.02
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 39,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 50553107251200.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}