Model save

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: nvidia/Minitron-4B-Base
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: minitron-4b-tulu-v2-mix
+  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. -->
+
+# minitron-4b-tulu-v2-mix
+
+This model is a fine-tuned version of [nvidia/Minitron-4B-Base](https://huggingface.co/nvidia/Minitron-4B-Base) on the generator dataset.
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 5
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| No log        | 0.0088 | 5    | 1.1978          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.2
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.008827099194527198,
+    "total_flos": 6242130984960.0,
+    "train_loss": 1.322617530822754,
+    "train_runtime": 636.4506,
+    "train_samples": 326149,
+    "train_samples_per_second": 1.006,
+    "train_steps_per_second": 0.008
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 3,
+  "transformers_version": "4.44.2",
+  "use_cache": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.008827099194527198,
+    "total_flos": 6242130984960.0,
+    "train_loss": 1.322617530822754,
+    "train_runtime": 636.4506,
+    "train_samples": 326149,
+    "train_samples_per_second": 1.006,
+    "train_steps_per_second": 0.008
+}

trainer_state.json

@@ -0,0 +1,50 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.008827099194527198,
+  "eval_steps": 500,
+  "global_step": 5,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008827099194527198,
+      "eval_loss": 1.1978037357330322,
+      "eval_runtime": 377.4812,
+      "eval_samples_per_second": 14.74,
+      "eval_steps_per_second": 3.685,
+      "step": 5
+    },
+    {
+      "epoch": 0.008827099194527198,
+      "step": 5,
+      "total_flos": 6242130984960.0,
+      "train_loss": 1.322617530822754,
+      "train_runtime": 636.4506,
+      "train_samples_per_second": 1.006,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5,
+  "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": 6242130984960.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}