End of training

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -4,6 +4,8 @@ license: llama3.2
 base_model: meta-llama/Llama-3.2-1B
 tags:
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: squad_llama_finetuned
   results: []
@@ -14,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # squad_llama_finetuned
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on an unknown dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) on the squad dataset.
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 19.441816461684013,
+    "eval_f1": 29.861733635502148,
+    "eval_runtime": 244.9635,
+    "eval_samples": 10787,
+    "eval_samples_per_second": 44.035,
+    "eval_steps_per_second": 5.507,
+    "total_flos": 3.971230131335731e+17,
+    "train_loss": 3.130299679309049,
+    "train_runtime": 13722.7795,
+    "train_samples": 88559,
+    "train_samples_per_second": 12.907,
+    "train_steps_per_second": 1.076
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd692d745a647da9c31dabd52c9e1415964aa602b23d8fc69a917c672a674c0
+size 50840270

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 19.441816461684013,
+    "eval_f1": 29.861733635502148,
+    "eval_runtime": 244.9635,
+    "eval_samples": 10787,
+    "eval_samples_per_second": 44.035,
+    "eval_steps_per_second": 5.507
+}

runs/Nov15_23-17-58_xgpi8/events.out.tfevents.1731698261.xgpi8.290848.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:779905ce594ceed352860a2b5f51542d074def75adc9c5de577daf99e59e5cb8
+size 412

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 3.971230131335731e+17,
+    "train_loss": 3.130299679309049,
+    "train_runtime": 13722.7795,
+    "train_samples": 88559,
+    "train_samples_per_second": 12.907,
+    "train_steps_per_second": 1.076
+}

trainer_state.json

@@ -0,0 +1,245 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 14760,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06775067750677506,
+      "grad_norm": 13.977642059326172,
+      "learning_rate": 2.8983739837398373e-05,
+      "loss": 4.614,
+      "step": 500
+    },
+    {
+      "epoch": 0.13550135501355012,
+      "grad_norm": 8.07140064239502,
+      "learning_rate": 2.7967479674796748e-05,
+      "loss": 4.1059,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2032520325203252,
+      "grad_norm": 13.195443153381348,
+      "learning_rate": 2.695121951219512e-05,
+      "loss": 3.9346,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27100271002710025,
+      "grad_norm": 7.072673797607422,
+      "learning_rate": 2.59349593495935e-05,
+      "loss": 3.8225,
+      "step": 2000
+    },
+    {
+      "epoch": 0.33875338753387535,
+      "grad_norm": 8.832470893859863,
+      "learning_rate": 2.491869918699187e-05,
+      "loss": 3.7412,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 6.735231876373291,
+      "learning_rate": 2.3902439024390246e-05,
+      "loss": 3.6643,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4742547425474255,
+      "grad_norm": 7.775442123413086,
+      "learning_rate": 2.2886178861788618e-05,
+      "loss": 3.6398,
+      "step": 3500
+    },
+    {
+      "epoch": 0.5420054200542005,
+      "grad_norm": 10.120951652526855,
+      "learning_rate": 2.186991869918699e-05,
+      "loss": 3.5632,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6097560975609756,
+      "grad_norm": 6.712512493133545,
+      "learning_rate": 2.0853658536585365e-05,
+      "loss": 3.5075,
+      "step": 4500
+    },
+    {
+      "epoch": 0.6775067750677507,
+      "grad_norm": 9.954794883728027,
+      "learning_rate": 1.983739837398374e-05,
+      "loss": 3.4741,
+      "step": 5000
+    },
+    {
+      "epoch": 0.7452574525745257,
+      "grad_norm": 8.68674087524414,
+      "learning_rate": 1.8821138211382116e-05,
+      "loss": 3.4156,
+      "step": 5500
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 10.184517860412598,
+      "learning_rate": 1.7804878048780488e-05,
+      "loss": 3.4252,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8807588075880759,
+      "grad_norm": 10.719181060791016,
+      "learning_rate": 1.6788617886178863e-05,
+      "loss": 3.3686,
+      "step": 6500
+    },
+    {
+      "epoch": 0.948509485094851,
+      "grad_norm": 7.8517560958862305,
+      "learning_rate": 1.5772357723577235e-05,
+      "loss": 3.3269,
+      "step": 7000
+    },
+    {
+      "epoch": 1.016260162601626,
+      "grad_norm": 11.628539085388184,
+      "learning_rate": 1.475609756097561e-05,
+      "loss": 3.208,
+      "step": 7500
+    },
+    {
+      "epoch": 1.084010840108401,
+      "grad_norm": 20.40143585205078,
+      "learning_rate": 1.3739837398373984e-05,
+      "loss": 2.7868,
+      "step": 8000
+    },
+    {
+      "epoch": 1.151761517615176,
+      "grad_norm": 18.49318504333496,
+      "learning_rate": 1.2723577235772358e-05,
+      "loss": 2.7465,
+      "step": 8500
+    },
+    {
+      "epoch": 1.2195121951219512,
+      "grad_norm": 18.326629638671875,
+      "learning_rate": 1.1707317073170733e-05,
+      "loss": 2.6684,
+      "step": 9000
+    },
+    {
+      "epoch": 1.2872628726287263,
+      "grad_norm": 23.60063362121582,
+      "learning_rate": 1.0691056910569105e-05,
+      "loss": 2.6501,
+      "step": 9500
+    },
+    {
+      "epoch": 1.3550135501355014,
+      "grad_norm": 27.22466278076172,
+      "learning_rate": 9.674796747967479e-06,
+      "loss": 2.656,
+      "step": 10000
+    },
+    {
+      "epoch": 1.4227642276422765,
+      "grad_norm": 24.0554141998291,
+      "learning_rate": 8.658536585365854e-06,
+      "loss": 2.5892,
+      "step": 10500
+    },
+    {
+      "epoch": 1.4905149051490514,
+      "grad_norm": 22.511192321777344,
+      "learning_rate": 7.642276422764228e-06,
+      "loss": 2.5712,
+      "step": 11000
+    },
+    {
+      "epoch": 1.5582655826558267,
+      "grad_norm": 25.18529510498047,
+      "learning_rate": 6.626016260162602e-06,
+      "loss": 2.5993,
+      "step": 11500
+    },
+    {
+      "epoch": 1.6260162601626016,
+      "grad_norm": 33.19571304321289,
+      "learning_rate": 5.609756097560976e-06,
+      "loss": 2.5777,
+      "step": 12000
+    },
+    {
+      "epoch": 1.6937669376693767,
+      "grad_norm": 22.047767639160156,
+      "learning_rate": 4.5934959349593495e-06,
+      "loss": 2.5205,
+      "step": 12500
+    },
+    {
+      "epoch": 1.7615176151761518,
+      "grad_norm": 25.974809646606445,
+      "learning_rate": 3.5772357723577236e-06,
+      "loss": 2.5055,
+      "step": 13000
+    },
+    {
+      "epoch": 1.8292682926829267,
+      "grad_norm": 27.9240779876709,
+      "learning_rate": 2.5609756097560977e-06,
+      "loss": 2.4599,
+      "step": 13500
+    },
+    {
+      "epoch": 1.897018970189702,
+      "grad_norm": 28.034526824951172,
+      "learning_rate": 1.5447154471544717e-06,
+      "loss": 2.4843,
+      "step": 14000
+    },
+    {
+      "epoch": 1.9647696476964769,
+      "grad_norm": 28.660612106323242,
+      "learning_rate": 5.284552845528455e-07,
+      "loss": 2.4865,
+      "step": 14500
+    },
+    {
+      "epoch": 2.0,
+      "step": 14760,
+      "total_flos": 3.971230131335731e+17,
+      "train_loss": 3.130299679309049,
+      "train_runtime": 13722.7795,
+      "train_samples_per_second": 12.907,
+      "train_steps_per_second": 1.076
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14760,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.971230131335731e+17,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}