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_old
+  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_old
+
+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: 16
+- total_train_batch_size: 32
+- 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: 2
+
+### 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": 1.9726027397260273,
+    "total_flos": 3911524024320.0,
+    "train_loss": 1.0647009246879153,
+    "train_runtime": 784.6331,
+    "train_samples": 15798,
+    "train_samples_per_second": 4.466,
+    "train_steps_per_second": 0.138
+}

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"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aba8507b6166ac50e982d1107d2d0129231b5ff780e5f543f5d4c211a88d4716
+oid sha256:6d585a465b9c2ba5a2f48b37a3e72f751d98c4b9603052d99f648b176303be07
 size 2200119864

runs/Aug06_22-29-25_poseidon/events.out.tfevents.1722983380.poseidon.1773058.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:515702cfe52cdae98cc572f222a361328b8783c5ade56dcf1b805e64cbfdcad6
-size 7469
+oid sha256:5595097f02e3b122cf2be2c5632a21b41e4386faed0267eaa802407b64f3d93f
+size 7817

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9726027397260273,
+    "total_flos": 3911524024320.0,
+    "train_loss": 1.0647009246879153,
+    "train_runtime": 784.6331,
+    "train_samples": 15798,
+    "train_samples_per_second": 4.466,
+    "train_steps_per_second": 0.138
+}

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9726027397260273,
+  "eval_steps": 500,
+  "global_step": 108,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0182648401826484,
+      "grad_norm": 21.109767473838268,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 1.6365,
+      "step": 1
+    },
+    {
+      "epoch": 0.182648401826484,
+      "grad_norm": 1.9665126756085918,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.5289,
+      "step": 10
+    },
+    {
+      "epoch": 0.365296803652968,
+      "grad_norm": 1.3148117828569053,
+      "learning_rate": 9.789086620939936e-06,
+      "loss": 1.2835,
+      "step": 20
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 1.1804824330362151,
+      "learning_rate": 9.082818315286054e-06,
+      "loss": 1.1618,
+      "step": 30
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 1.116060986988856,
+      "learning_rate": 7.952011865029614e-06,
+      "loss": 1.1206,
+      "step": 40
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 1.1216076426923212,
+      "learning_rate": 6.514250379489754e-06,
+      "loss": 1.0685,
+      "step": 50
+    },
+    {
+      "epoch": 1.095890410958904,
+      "grad_norm": 1.1626749139232289,
+      "learning_rate": 4.919034655987493e-06,
+      "loss": 0.9895,
+      "step": 60
+    },
+    {
+      "epoch": 1.278538812785388,
+      "grad_norm": 1.0776560696316984,
+      "learning_rate": 3.3322378417458985e-06,
+      "loss": 0.9347,
+      "step": 70
+    },
+    {
+      "epoch": 1.461187214611872,
+      "grad_norm": 1.0533230608492796,
+      "learning_rate": 1.9188576719953635e-06,
+      "loss": 0.9082,
+      "step": 80
+    },
+    {
+      "epoch": 1.643835616438356,
+      "grad_norm": 1.0469386406850305,
+      "learning_rate": 8.258597348536452e-07,
+      "loss": 0.89,
+      "step": 90
+    },
+    {
+      "epoch": 1.82648401826484,
+      "grad_norm": 1.0954009517444092,
+      "learning_rate": 1.6689574843694433e-07,
+      "loss": 0.8899,
+      "step": 100
+    },
+    {
+      "epoch": 1.9726027397260273,
+      "step": 108,
+      "total_flos": 3911524024320.0,
+      "train_loss": 1.0647009246879153,
+      "train_runtime": 784.6331,
+      "train_samples_per_second": 4.466,
+      "train_steps_per_second": 0.138
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 108,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 3911524024320.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}