Model save

README.md

@@ -0,0 +1,60 @@
+---
+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
+  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
+
+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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 8
+- 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 4.41.2
+- Pytorch 2.1.2
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.2271578481885184e+16,
+    "train_loss": 1.2611416202701935,
+    "train_runtime": 537.6163,
+    "train_samples": 15798,
+    "train_samples_per_second": 3.259,
+    "train_steps_per_second": 0.407
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2d986cbefe075f048290507c5d0be01aa25a5cec9c61c61465f2aff61d68f3
+oid sha256:1714328733e822b7d5924b4a8909cabefac4ba22a38c0c86a41949dfa8bb87f2
 size 2200119864

runs/Jul20_12-51-42_poseidon/events.out.tfevents.1721479919.poseidon.1507708.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dfc915524c2ca452e0cfcde8ef95cad9711d71a1e698fe96af0f5ff3eceae0c
-size 9434
+oid sha256:25efb6748dd2d7a9c922303247336908b688504d4d84fb83ae367272d6765d31
+size 9999

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.2271578481885184e+16,
+    "train_loss": 1.2611416202701935,
+    "train_runtime": 537.6163,
+    "train_samples": 15798,
+    "train_samples_per_second": 3.259,
+    "train_steps_per_second": 0.407
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 219,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0045662100456621,
+      "grad_norm": 23.25,
+      "learning_rate": 4.5454545454545457e-07,
+      "loss": 1.6483,
+      "step": 1
+    },
+    {
+      "epoch": 0.045662100456621,
+      "grad_norm": 11.5,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.6309,
+      "step": 10
+    },
+    {
+      "epoch": 0.091324200913242,
+      "grad_norm": 3.015625,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.4979,
+      "step": 20
+    },
+    {
+      "epoch": 0.136986301369863,
+      "grad_norm": 2.96875,
+      "learning_rate": 9.959365197965824e-06,
+      "loss": 1.3794,
+      "step": 30
+    },
+    {
+      "epoch": 0.182648401826484,
+      "grad_norm": 2.78125,
+      "learning_rate": 9.795417628509857e-06,
+      "loss": 1.316,
+      "step": 40
+    },
+    {
+      "epoch": 0.228310502283105,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.50977494371594e-06,
+      "loss": 1.2561,
+      "step": 50
+    },
+    {
+      "epoch": 0.273972602739726,
+      "grad_norm": 2.421875,
+      "learning_rate": 9.109686005344258e-06,
+      "loss": 1.2691,
+      "step": 60
+    },
+    {
+      "epoch": 0.319634703196347,
+      "grad_norm": 2.328125,
+      "learning_rate": 8.60530402074241e-06,
+      "loss": 1.2524,
+      "step": 70
+    },
+    {
+      "epoch": 0.365296803652968,
+      "grad_norm": 2.296875,
+      "learning_rate": 8.009428881086836e-06,
+      "loss": 1.2188,
+      "step": 80
+    },
+    {
+      "epoch": 0.410958904109589,
+      "grad_norm": 2.25,
+      "learning_rate": 7.33718233373407e-06,
+      "loss": 1.2069,
+      "step": 90
+    },
+    {
+      "epoch": 0.45662100456621,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.6056242319551315e-06,
+      "loss": 1.2022,
+      "step": 100
+    },
+    {
+      "epoch": 0.502283105022831,
+      "grad_norm": 2.3125,
+      "learning_rate": 5.8333196006277536e-06,
+      "loss": 1.2224,
+      "step": 110
+    },
+    {
+      "epoch": 0.547945205479452,
+      "grad_norm": 2.265625,
+      "learning_rate": 5.039867504623084e-06,
+      "loss": 1.2076,
+      "step": 120
+    },
+    {
+      "epoch": 0.593607305936073,
+      "grad_norm": 2.265625,
+      "learning_rate": 4.245403675970877e-06,
+      "loss": 1.2082,
+      "step": 130
+    },
+    {
+      "epoch": 0.639269406392694,
+      "grad_norm": 2.234375,
+      "learning_rate": 3.4700895218205026e-06,
+      "loss": 1.1879,
+      "step": 140
+    },
+    {
+      "epoch": 0.684931506849315,
+      "grad_norm": 2.359375,
+      "learning_rate": 2.7336004808348094e-06,
+      "loss": 1.2127,
+      "step": 150
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 2.21875,
+      "learning_rate": 2.0546267121888863e-06,
+      "loss": 1.2206,
+      "step": 160
+    },
+    {
+      "epoch": 0.776255707762557,
+      "grad_norm": 2.34375,
+      "learning_rate": 1.4503987883766857e-06,
+      "loss": 1.2045,
+      "step": 170
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 2.453125,
+      "learning_rate": 9.362504284973683e-07,
+      "loss": 1.2108,
+      "step": 180
+    },
+    {
+      "epoch": 0.867579908675799,
+      "grad_norm": 2.25,
+      "learning_rate": 5.252293687031196e-07,
+      "loss": 1.1964,
+      "step": 190
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 2.390625,
+      "learning_rate": 2.2776624489530664e-07,
+      "loss": 1.209,
+      "step": 200
+    },
+    {
+      "epoch": 0.958904109589041,
+      "grad_norm": 2.390625,
+      "learning_rate": 5.1409890557246876e-08,
+      "loss": 1.2177,
+      "step": 210
+    },
+    {
+      "epoch": 1.0,
+      "step": 219,
+      "total_flos": 2.2271578481885184e+16,
+      "train_loss": 1.2611416202701935,
+      "train_runtime": 537.6163,
+      "train_samples_per_second": 3.259,
+      "train_steps_per_second": 0.407
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 219,
+  "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": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.2271578481885184e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}