Model save

README.md

@@ -0,0 +1,62 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: tinyllama-1.1b-mt-sft-full_sardine_2gpus
+  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. -->
+
+# tinyllama-1.1b-mt-sft-full_sardine_2gpus
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9863013698630136,
+    "total_flos": 1954629550080.0,
+    "train_loss": 1.3019332091013591,
+    "train_runtime": 388.8606,
+    "train_samples": 15798,
+    "train_samples_per_second": 4.505,
+    "train_steps_per_second": 0.069
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.3"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9863013698630136,
+    "total_flos": 1954629550080.0,
+    "train_loss": 1.3019332091013591,
+    "train_runtime": 388.8606,
+    "train_samples": 15798,
+    "train_samples_per_second": 4.505,
+    "train_steps_per_second": 0.069
+}

trainer_state.json

@@ -0,0 +1,63 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9863013698630136,
+  "eval_steps": 500,
+  "global_step": 27,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0365296803652968,
+      "grad_norm": 21.481753895151215,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6412,
+      "step": 1
+    },
+    {
+      "epoch": 0.365296803652968,
+      "grad_norm": 2.2500616965036078,
+      "learning_rate": 8.043807145043604e-06,
+      "loss": 1.4447,
+      "step": 10
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 0.9544323271736276,
+      "learning_rate": 1.956192854956397e-06,
+      "loss": 1.2269,
+      "step": 20
+    },
+    {
+      "epoch": 0.9863013698630136,
+      "step": 27,
+      "total_flos": 1954629550080.0,
+      "train_loss": 1.3019332091013591,
+      "train_runtime": 388.8606,
+      "train_samples_per_second": 4.505,
+      "train_steps_per_second": 0.069
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 27,
+  "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": 1954629550080.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}