End of training

README.md

@@ -4,6 +4,7 @@ license: llama3.2
 base_model: meta-llama/Llama-3.2-3B
 tags:
 - llama-factory
+- full
 - generated_from_trainer
 model-index:
 - name: full_1-2_3B
@@ -15,7 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # full_1-2_3B
 
-This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the None dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) on the gulaschnascher4000/stream-dataset-0-2, the identity-chatgulaschpt, the dolly_15k_de and the alpaca-gpt4_de datasets.
+It achieves the following results on the evaluation set:
+- Loss: 1.2277
 
 ## Model description
 

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.4998118178396688,
+    "eval_loss": 1.2277323007583618,
+    "eval_runtime": 81.6182,
+    "eval_samples_per_second": 115.746,
+    "eval_steps_per_second": 3.627,
+    "total_flos": 2.9336259752728986e+17,
+    "train_loss": 1.3684147273201541,
+    "train_runtime": 1819.5691,
+    "train_samples_per_second": 23.361,
+    "train_steps_per_second": 0.182
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.4998118178396688,
+    "eval_loss": 1.2277323007583618,
+    "eval_runtime": 81.6182,
+    "eval_samples_per_second": 115.746,
+    "eval_steps_per_second": 3.627
+}

runs/Jan14_00-19-27_pss5xry2f0aq/events.out.tfevents.1736816122.pss5xry2f0aq.12973.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:89ea018229bcb4dff58de961eae72a84776bc2988040bd9d1a633673f1b090b0
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.4998118178396688,
+    "total_flos": 2.9336259752728986e+17,
+    "train_loss": 1.3684147273201541,
+    "train_runtime": 1819.5691,
+    "train_samples_per_second": 23.361,
+    "train_steps_per_second": 0.182
+}

trainer_state.json

@@ -0,0 +1,273 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4998118178396688,
+  "eval_steps": 1000,
+  "global_step": 332,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.015054572826496047,
+      "grad_norm": 3.01820707321167,
+      "learning_rate": 1.4705882352941177e-05,
+      "loss": 1.4874,
+      "step": 10
+    },
+    {
+      "epoch": 0.030109145652992095,
+      "grad_norm": 5.344997882843018,
+      "learning_rate": 2.9411764705882354e-05,
+      "loss": 1.4372,
+      "step": 20
+    },
+    {
+      "epoch": 0.04516371847948814,
+      "grad_norm": 4.847251892089844,
+      "learning_rate": 4.411764705882353e-05,
+      "loss": 1.5973,
+      "step": 30
+    },
+    {
+      "epoch": 0.06021829130598419,
+      "grad_norm": 31.4217586517334,
+      "learning_rate": 4.995000403852057e-05,
+      "loss": 1.8488,
+      "step": 40
+    },
+    {
+      "epoch": 0.07527286413248024,
+      "grad_norm": 4.010560035705566,
+      "learning_rate": 4.9645197025242506e-05,
+      "loss": 1.6171,
+      "step": 50
+    },
+    {
+      "epoch": 0.09032743695897628,
+      "grad_norm": 3.573289394378662,
+      "learning_rate": 4.9066738880408945e-05,
+      "loss": 1.5635,
+      "step": 60
+    },
+    {
+      "epoch": 0.10538200978547234,
+      "grad_norm": 3.300258159637451,
+      "learning_rate": 4.822105258882007e-05,
+      "loss": 1.5138,
+      "step": 70
+    },
+    {
+      "epoch": 0.12043658261196838,
+      "grad_norm": 2.9470131397247314,
+      "learning_rate": 4.711752833755362e-05,
+      "loss": 1.5063,
+      "step": 80
+    },
+    {
+      "epoch": 0.13549115543846443,
+      "grad_norm": 3.3921890258789062,
+      "learning_rate": 4.576841925080853e-05,
+      "loss": 1.4952,
+      "step": 90
+    },
+    {
+      "epoch": 0.1505457282649605,
+      "grad_norm": 2.8532607555389404,
+      "learning_rate": 4.418870533575625e-05,
+      "loss": 1.4475,
+      "step": 100
+    },
+    {
+      "epoch": 0.16560030109145654,
+      "grad_norm": 2.333944082260132,
+      "learning_rate": 4.239592715009429e-05,
+      "loss": 1.4654,
+      "step": 110
+    },
+    {
+      "epoch": 0.18065487391795257,
+      "grad_norm": 2.1384618282318115,
+      "learning_rate": 4.040999103819606e-05,
+      "loss": 1.4262,
+      "step": 120
+    },
+    {
+      "epoch": 0.19570944674444862,
+      "grad_norm": 2.218015193939209,
+      "learning_rate": 3.8252948098442344e-05,
+      "loss": 1.4034,
+      "step": 130
+    },
+    {
+      "epoch": 0.21076401957094468,
+      "grad_norm": 2.2272789478302,
+      "learning_rate": 3.5948749335999496e-05,
+      "loss": 1.3977,
+      "step": 140
+    },
+    {
+      "epoch": 0.22581859239744073,
+      "grad_norm": 2.2398104667663574,
+      "learning_rate": 3.3522979719736926e-05,
+      "loss": 1.3365,
+      "step": 150
+    },
+    {
+      "epoch": 0.24087316522393676,
+      "grad_norm": 1.9465758800506592,
+      "learning_rate": 3.100257409621738e-05,
+      "loss": 1.3573,
+      "step": 160
+    },
+    {
+      "epoch": 0.25592773805043284,
+      "grad_norm": 1.9894447326660156,
+      "learning_rate": 2.8415518115145674e-05,
+      "loss": 1.3378,
+      "step": 170
+    },
+    {
+      "epoch": 0.27098231087692887,
+      "grad_norm": 2.052354335784912,
+      "learning_rate": 2.5790537487088974e-05,
+      "loss": 1.3316,
+      "step": 180
+    },
+    {
+      "epoch": 0.2860368837034249,
+      "grad_norm": 2.086660861968994,
+      "learning_rate": 2.3156779023835525e-05,
+      "loss": 1.3145,
+      "step": 190
+    },
+    {
+      "epoch": 0.301091456529921,
+      "grad_norm": 1.757770299911499,
+      "learning_rate": 2.054348700300158e-05,
+      "loss": 1.3088,
+      "step": 200
+    },
+    {
+      "epoch": 0.316146029356417,
+      "grad_norm": 1.7598217725753784,
+      "learning_rate": 1.7979678450413845e-05,
+      "loss": 1.2496,
+      "step": 210
+    },
+    {
+      "epoch": 0.3312006021829131,
+      "grad_norm": 1.96985924243927,
+      "learning_rate": 1.549382094581166e-05,
+      "loss": 1.2671,
+      "step": 220
+    },
+    {
+      "epoch": 0.3462551750094091,
+      "grad_norm": 2.18863582611084,
+      "learning_rate": 1.3113516529394704e-05,
+      "loss": 1.2616,
+      "step": 230
+    },
+    {
+      "epoch": 0.36130974783590514,
+      "grad_norm": 1.9665237665176392,
+      "learning_rate": 1.086519521900103e-05,
+      "loss": 1.2281,
+      "step": 240
+    },
+    {
+      "epoch": 0.3763643206624012,
+      "grad_norm": 1.5388092994689941,
+      "learning_rate": 8.77382154098679e-06,
+      "loss": 1.2435,
+      "step": 250
+    },
+    {
+      "epoch": 0.39141889348889725,
+      "grad_norm": 2.0164120197296143,
+      "learning_rate": 6.862617333380214e-06,
+      "loss": 1.2359,
+      "step": 260
+    },
+    {
+      "epoch": 0.40647346631539333,
+      "grad_norm": 1.8150506019592285,
+      "learning_rate": 5.1528038992007e-06,
+      "loss": 1.2225,
+      "step": 270
+    },
+    {
+      "epoch": 0.42152803914188935,
+      "grad_norm": 1.8402557373046875,
+      "learning_rate": 3.6633663729770008e-06,
+      "loss": 1.2176,
+      "step": 280
+    },
+    {
+      "epoch": 0.4365826119683854,
+      "grad_norm": 1.8227931261062622,
+      "learning_rate": 2.4108429168514245e-06,
+      "loss": 1.2321,
+      "step": 290
+    },
+    {
+      "epoch": 0.45163718479488146,
+      "grad_norm": 1.6499103307724,
+      "learning_rate": 1.4091410869582267e-06,
+      "loss": 1.2331,
+      "step": 300
+    },
+    {
+      "epoch": 0.4666917576213775,
+      "grad_norm": 1.8676466941833496,
+      "learning_rate": 6.69383409075991e-07,
+      "loss": 1.2173,
+      "step": 310
+    },
+    {
+      "epoch": 0.4817463304478735,
+      "grad_norm": 1.8943265676498413,
+      "learning_rate": 1.9978387822460197e-07,
+      "loss": 1.2157,
+      "step": 320
+    },
+    {
+      "epoch": 0.4968009032743696,
+      "grad_norm": 1.675297737121582,
+      "learning_rate": 5.55675350954743e-09,
+      "loss": 1.1926,
+      "step": 330
+    },
+    {
+      "epoch": 0.4998118178396688,
+      "step": 332,
+      "total_flos": 2.9336259752728986e+17,
+      "train_loss": 1.3684147273201541,
+      "train_runtime": 1819.5691,
+      "train_samples_per_second": 23.361,
+      "train_steps_per_second": 0.182
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 332,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.9336259752728986e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}