Model save

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: orca-gpt4-wik-revise
+  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. -->
+
+# orca-gpt4-wik-revise
+
+This model was trained from scratch on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0593
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 1024
+- total_eval_batch_size: 32
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.3697        | 0.9389 | 12   | 1.2250          |
+| 1.0231        | 1.9560 | 25   | 1.0662          |
+| 0.901         | 2.8166 | 36   | 1.0593          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.8166259168704157,
+    "total_flos": 120497991843840.0,
+    "train_loss": 1.135702931218677,
+    "train_runtime": 11898.7844,
+    "train_samples": 49800,
+    "train_samples_per_second": 3.299,
+    "train_steps_per_second": 0.003
+}

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": 2.8166259168704157,
+    "total_flos": 120497991843840.0,
+    "train_loss": 1.135702931218677,
+    "train_runtime": 11898.7844,
+    "train_samples": 49800,
+    "train_samples_per_second": 3.299,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,122 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.8166259168704157,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07823960880195599,
+      "grad_norm": 24.32354215756571,
+      "learning_rate": 5e-06,
+      "loss": 1.579,
+      "step": 1
+    },
+    {
+      "epoch": 0.39119804400978,
+      "grad_norm": 49.96314997488065,
+      "learning_rate": 1.995184726672197e-05,
+      "loss": 1.4677,
+      "step": 5
+    },
+    {
+      "epoch": 0.78239608801956,
+      "grad_norm": 4.9439904702205855,
+      "learning_rate": 1.8314696123025456e-05,
+      "loss": 1.3697,
+      "step": 10
+    },
+    {
+      "epoch": 0.9388753056234719,
+      "eval_loss": 1.2249956130981445,
+      "eval_runtime": 6.2806,
+      "eval_samples_per_second": 8.439,
+      "eval_steps_per_second": 0.318,
+      "step": 12
+    },
+    {
+      "epoch": 1.17359413202934,
+      "grad_norm": 5.393870573942289,
+      "learning_rate": 1.4713967368259981e-05,
+      "loss": 1.2118,
+      "step": 15
+    },
+    {
+      "epoch": 1.56479217603912,
+      "grad_norm": 1.7797044387765701,
+      "learning_rate": 1e-05,
+      "loss": 1.0764,
+      "step": 20
+    },
+    {
+      "epoch": 1.9559902200488999,
+      "grad_norm": 1.307540863093363,
+      "learning_rate": 5.286032631740023e-06,
+      "loss": 1.0231,
+      "step": 25
+    },
+    {
+      "epoch": 1.9559902200488999,
+      "eval_loss": 1.066247820854187,
+      "eval_runtime": 8.3677,
+      "eval_samples_per_second": 6.334,
+      "eval_steps_per_second": 0.239,
+      "step": 25
+    },
+    {
+      "epoch": 2.34718826405868,
+      "grad_norm": 1.1252690680547968,
+      "learning_rate": 1.6853038769745466e-06,
+      "loss": 0.93,
+      "step": 30
+    },
+    {
+      "epoch": 2.73838630806846,
+      "grad_norm": 0.7799666146844121,
+      "learning_rate": 4.815273327803183e-08,
+      "loss": 0.901,
+      "step": 35
+    },
+    {
+      "epoch": 2.8166259168704157,
+      "eval_loss": 1.0592604875564575,
+      "eval_runtime": 8.1855,
+      "eval_samples_per_second": 6.475,
+      "eval_steps_per_second": 0.244,
+      "step": 36
+    },
+    {
+      "epoch": 2.8166259168704157,
+      "step": 36,
+      "total_flos": 120497991843840.0,
+      "train_loss": 1.135702931218677,
+      "train_runtime": 11898.7844,
+      "train_samples_per_second": 3.299,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 36,
+  "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": 120497991843840.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}