Model save

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: zephyr-7b-sft-full-sftwdpodata
+  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-sft-full-sftwdpodata
+
+This model was trained from scratch on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1374
+
+## 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: 5e-07
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- 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: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.1588        | 1.0   | 123  | 1.1374          |
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.1.0
+- Datasets 3.0.1
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 51507395297280.0,
+    "train_loss": 1.1927482141711847,
+    "train_runtime": 664.3286,
+    "train_samples": 61134,
+    "train_samples_per_second": 23.68,
+    "train_steps_per_second": 0.185
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e5ecf5db0001aae43d8f249f2ab57515fc696cdedab8ddacc70fddf7ce2d28
+oid sha256:58aa3ce910bf35d9d9b9a338a438c7050c6df0efce4da4e9652094ae11bd1a08
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d82fe2fa2c226d395074896ccf6701fa2c05c9734c700fc8cbe2ae7653e69bd7
+oid sha256:4bf12699df574992ffb1ced54af450aea6760dcb35661283f64e17994603e05c
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:265ef76f47fe8afba7d499bff28c1081f6b2dfb60500c8d31c86edacaece2236
+oid sha256:9269a74eced6f21d94d486d23cfdd420f3cc2e2bb29b8850059c832e699b224d
 size 4540516344

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 51507395297280.0,
+    "train_loss": 1.1927482141711847,
+    "train_runtime": 664.3286,
+    "train_samples": 61134,
+    "train_samples_per_second": 23.68,
+    "train_steps_per_second": 0.185
+}

trainer_state.json

@@ -0,0 +1,225 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 123,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008130081300813009,
+      "grad_norm": 5.968609245665954,
+      "learning_rate": 3.846153846153846e-08,
+      "loss": 1.3047,
+      "step": 1
+    },
+    {
+      "epoch": 0.04065040650406504,
+      "grad_norm": 6.622098028585483,
+      "learning_rate": 1.9230769230769231e-07,
+      "loss": 1.3293,
+      "step": 5
+    },
+    {
+      "epoch": 0.08130081300813008,
+      "grad_norm": 5.601752396412818,
+      "learning_rate": 3.8461538461538463e-07,
+      "loss": 1.3265,
+      "step": 10
+    },
+    {
+      "epoch": 0.12195121951219512,
+      "grad_norm": 3.3465461495166955,
+      "learning_rate": 4.995922759815338e-07,
+      "loss": 1.3014,
+      "step": 15
+    },
+    {
+      "epoch": 0.16260162601626016,
+      "grad_norm": 2.285061060375805,
+      "learning_rate": 4.950206402730983e-07,
+      "loss": 1.267,
+      "step": 20
+    },
+    {
+      "epoch": 0.2032520325203252,
+      "grad_norm": 2.906521061514324,
+      "learning_rate": 4.854610909098811e-07,
+      "loss": 1.2635,
+      "step": 25
+    },
+    {
+      "epoch": 0.24390243902439024,
+      "grad_norm": 2.2161224244788196,
+      "learning_rate": 4.7110823274945357e-07,
+      "loss": 1.2199,
+      "step": 30
+    },
+    {
+      "epoch": 0.2845528455284553,
+      "grad_norm": 1.9040029033032413,
+      "learning_rate": 4.5225424859373684e-07,
+      "loss": 1.2142,
+      "step": 35
+    },
+    {
+      "epoch": 0.3252032520325203,
+      "grad_norm": 1.8144925748816008,
+      "learning_rate": 4.292829511897409e-07,
+      "loss": 1.2051,
+      "step": 40
+    },
+    {
+      "epoch": 0.36585365853658536,
+      "grad_norm": 1.6349825973341405,
+      "learning_rate": 4.0266196990885955e-07,
+      "loss": 1.1723,
+      "step": 45
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 1.664912835299134,
+      "learning_rate": 3.72933231161401e-07,
+      "loss": 1.177,
+      "step": 50
+    },
+    {
+      "epoch": 0.44715447154471544,
+      "grad_norm": 1.6158486513675248,
+      "learning_rate": 3.407019263376602e-07,
+      "loss": 1.1748,
+      "step": 55
+    },
+    {
+      "epoch": 0.4878048780487805,
+      "grad_norm": 1.661677150645168,
+      "learning_rate": 3.0662419185644114e-07,
+      "loss": 1.1791,
+      "step": 60
+    },
+    {
+      "epoch": 0.5284552845528455,
+      "grad_norm": 1.5725357820334132,
+      "learning_rate": 2.7139375211970995e-07,
+      "loss": 1.1598,
+      "step": 65
+    },
+    {
+      "epoch": 0.5691056910569106,
+      "grad_norm": 1.621045635617722,
+      "learning_rate": 2.3572779728430797e-07,
+      "loss": 1.166,
+      "step": 70
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 1.6041377989080807,
+      "learning_rate": 2.0035238333856368e-07,
+      "loss": 1.1698,
+      "step": 75
+    },
+    {
+      "epoch": 0.6504065040650406,
+      "grad_norm": 1.6387599262025716,
+      "learning_rate": 1.6598765169614244e-07,
+      "loss": 1.1467,
+      "step": 80
+    },
+    {
+      "epoch": 0.6910569105691057,
+      "grad_norm": 1.5728900163922992,
+      "learning_rate": 1.3333316919358157e-07,
+      "loss": 1.1588,
+      "step": 85
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 1.630523905646432,
+      "learning_rate": 1.0305368692688174e-07,
+      "loss": 1.1511,
+      "step": 90
+    },
+    {
+      "epoch": 0.7723577235772358,
+      "grad_norm": 1.6142247634044153,
+      "learning_rate": 7.576560783617667e-08,
+      "loss": 1.1514,
+      "step": 95
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 1.6635344099346825,
+      "learning_rate": 5.202443851943125e-08,
+      "loss": 1.1339,
+      "step": 100
+    },
+    {
+      "epoch": 0.8536585365853658,
+      "grad_norm": 1.6142940019540397,
+      "learning_rate": 3.231348072005574e-08,
+      "loss": 1.1436,
+      "step": 105
+    },
+    {
+      "epoch": 0.8943089430894309,
+      "grad_norm": 1.7064997556493062,
+      "learning_rate": 1.7033992697136928e-08,
+      "loss": 1.1522,
+      "step": 110
+    },
+    {
+      "epoch": 0.9349593495934959,
+      "grad_norm": 1.5806639080165765,
+      "learning_rate": 6.497020764416633e-09,
+      "loss": 1.1297,
+      "step": 115
+    },
+    {
+      "epoch": 0.975609756097561,
+      "grad_norm": 1.649978945004722,
+      "learning_rate": 9.170672843271666e-10,
+      "loss": 1.1588,
+      "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.137434482574463,
+      "eval_runtime": 4.7008,
+      "eval_samples_per_second": 108.067,
+      "eval_steps_per_second": 1.702,
+      "step": 123
+    },
+    {
+      "epoch": 1.0,
+      "step": 123,
+      "total_flos": 51507395297280.0,
+      "train_loss": 1.1927482141711847,
+      "train_runtime": 664.3286,
+      "train_samples_per_second": 23.68,
+      "train_steps_per_second": 0.185
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 123,
+  "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": 51507395297280.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}