End of training

README.md

@@ -0,0 +1,56 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: HuggingFaceTB/SmolLM-135M
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: nature-buddy
+  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. -->
+
+# nature-buddy
+
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on the None 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: 0.0005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2990143010382336.0,
+    "train_loss": 0.5055735324683629,
+    "train_runtime": 417.7958,
+    "train_samples_per_second": 38.344,
+    "train_steps_per_second": 4.799
+}

generation_config.json

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

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f71ef1bb24455ebff53ee3f79cd2c073bb252c14c213d9d27c5c637230eed102
+oid sha256:55e4e607657b976b9630015a8876895943023749d0c8fa953ad86f9a1cbed34c
 size 269060552

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 2990143010382336.0,
+    "train_loss": 0.5055735324683629,
+    "train_runtime": 417.7958,
+    "train_samples_per_second": 38.344,
+    "train_steps_per_second": 4.799
+}

trainer_state.json

@@ -0,0 +1,182 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2005,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24937655860349128,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.0004950495049504951,
+      "loss": 1.4705,
+      "step": 100
+    },
+    {
+      "epoch": 0.49875311720698257,
+      "grad_norm": 1.265625,
+      "learning_rate": 0.0004966720227318671,
+      "loss": 0.9437,
+      "step": 200
+    },
+    {
+      "epoch": 0.7481296758104738,
+      "grad_norm": 1.078125,
+      "learning_rate": 0.0004866439935228541,
+      "loss": 0.8591,
+      "step": 300
+    },
+    {
+      "epoch": 0.9975062344139651,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.00047018796504965955,
+      "loss": 0.8111,
+      "step": 400
+    },
+    {
+      "epoch": 1.2468827930174564,
+      "grad_norm": 0.8359375,
+      "learning_rate": 0.0004477509350887423,
+      "loss": 0.574,
+      "step": 500
+    },
+    {
+      "epoch": 1.4962593516209477,
+      "grad_norm": 1.0234375,
+      "learning_rate": 0.0004199423643322254,
+      "loss": 0.5806,
+      "step": 600
+    },
+    {
+      "epoch": 1.745635910224439,
+      "grad_norm": 1.0078125,
+      "learning_rate": 0.00038751762150804385,
+      "loss": 0.5699,
+      "step": 700
+    },
+    {
+      "epoch": 1.9950124688279303,
+      "grad_norm": 0.8046875,
+      "learning_rate": 0.00035135746517639757,
+      "loss": 0.5553,
+      "step": 800
+    },
+    {
+      "epoch": 2.2443890274314215,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00031244411954180673,
+      "loss": 0.3753,
+      "step": 900
+    },
+    {
+      "epoch": 2.493765586034913,
+      "grad_norm": 0.91796875,
+      "learning_rate": 0.00027183459413737774,
+      "loss": 0.374,
+      "step": 1000
+    },
+    {
+      "epoch": 2.743142144638404,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.00023063197210303058,
+      "loss": 0.3746,
+      "step": 1100
+    },
+    {
+      "epoch": 2.9925187032418954,
+      "grad_norm": 1.0625,
+      "learning_rate": 0.00018995544695885592,
+      "loss": 0.3789,
+      "step": 1200
+    },
+    {
+      "epoch": 3.2418952618453867,
+      "grad_norm": 0.94140625,
+      "learning_rate": 0.0001509099217695958,
+      "loss": 0.2943,
+      "step": 1300
+    },
+    {
+      "epoch": 3.491271820448878,
+      "grad_norm": 0.81640625,
+      "learning_rate": 0.00011455599648308674,
+      "loss": 0.288,
+      "step": 1400
+    },
+    {
+      "epoch": 3.7406483790523692,
+      "grad_norm": 0.78515625,
+      "learning_rate": 8.18811586814684e-05,
+      "loss": 0.2878,
+      "step": 1500
+    },
+    {
+      "epoch": 3.9900249376558605,
+      "grad_norm": 0.82421875,
+      "learning_rate": 5.377296029546741e-05,
+      "loss": 0.2929,
+      "step": 1600
+    },
+    {
+      "epoch": 4.239401496259352,
+      "grad_norm": 0.8203125,
+      "learning_rate": 3.099490888702508e-05,
+      "loss": 0.2837,
+      "step": 1700
+    },
+    {
+      "epoch": 4.488778054862843,
+      "grad_norm": 0.8125,
+      "learning_rate": 1.4165728369278874e-05,
+      "loss": 0.2715,
+      "step": 1800
+    },
+    {
+      "epoch": 4.738154613466334,
+      "grad_norm": 0.85546875,
+      "learning_rate": 3.7425525083322754e-06,
+      "loss": 0.268,
+      "step": 1900
+    },
+    {
+      "epoch": 4.987531172069826,
+      "grad_norm": 0.88671875,
+      "learning_rate": 8.507724455514287e-09,
+      "loss": 0.2712,
+      "step": 2000
+    },
+    {
+      "epoch": 5.0,
+      "step": 2005,
+      "total_flos": 2990143010382336.0,
+      "train_loss": 0.5055735324683629,
+      "train_runtime": 417.7958,
+      "train_samples_per_second": 38.344,
+      "train_steps_per_second": 4.799
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2005,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2990143010382336.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}