End of training

README.md

@@ -3,11 +3,24 @@ license: apache-2.0
 base_model: Qwen/Qwen2.5-0.5B-Instruct
 tags:
 - generated_from_trainer
+datasets:
+- wikitext
 metrics:
 - accuracy
 model-index:
 - name: llm2vec-qwen2.5-0.5-instruct
-  results: []
+  results:
+  - task:
+      name: Masked Language Modeling
+      type: fill-mask
+    dataset:
+      name: wikitext wikitext-103-raw-v1
+      type: wikitext
+      args: wikitext-103-raw-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.629556877924779
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,10 +28,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llm2vec-qwen2.5-0.5-instruct
 
-This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on an unknown dataset.
+This model is a fine-tuned version of [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct) on the wikitext wikitext-103-raw-v1 dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.7920
-- Accuracy: 0.6351
+- Loss: 1.8264
+- Accuracy: 0.6296
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 0.08279516476237787,
+    "eval_accuracy": 0.629556877924779,
+    "eval_loss": 1.8264291286468506,
+    "eval_runtime": 6.3204,
+    "eval_samples": 408,
+    "eval_samples_per_second": 64.553,
+    "eval_steps_per_second": 2.057,
+    "perplexity": 6.211665948497031,
+    "total_flos": 2.198926000128e+16,
+    "train_loss": 2.0824306030273436,
+    "train_runtime": 944.4845,
+    "train_samples": 193233,
+    "train_samples_per_second": 613.773,
+    "train_steps_per_second": 38.364
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 0.08279516476237787,
+    "eval_accuracy": 0.629556877924779,
+    "eval_loss": 1.8264291286468506,
+    "eval_runtime": 6.3204,
+    "eval_samples": 408,
+    "eval_samples_per_second": 64.553,
+    "eval_steps_per_second": 2.057,
+    "perplexity": 6.211665948497031
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.08279516476237787,
+    "total_flos": 2.198926000128e+16,
+    "train_loss": 2.0824306030273436,
+    "train_runtime": 944.4845,
+    "train_samples": 193233,
+    "train_samples_per_second": 613.773,
+    "train_steps_per_second": 38.364
+}

trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.08279516476237787,
+  "eval_steps": 100,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008279516476237788,
+      "eval_accuracy": 0.5510729122994245,
+      "eval_loss": 2.3376457691192627,
+      "eval_runtime": 6.8445,
+      "eval_samples_per_second": 59.61,
+      "eval_steps_per_second": 1.899,
+      "step": 100
+    },
+    {
+      "epoch": 0.016559032952475575,
+      "eval_accuracy": 0.5764662925666846,
+      "eval_loss": 2.173574447631836,
+      "eval_runtime": 6.6808,
+      "eval_samples_per_second": 61.071,
+      "eval_steps_per_second": 1.946,
+      "step": 200
+    },
+    {
+      "epoch": 0.024838549428713365,
+      "eval_accuracy": 0.5929699147520929,
+      "eval_loss": 2.0678670406341553,
+      "eval_runtime": 6.4137,
+      "eval_samples_per_second": 63.614,
+      "eval_steps_per_second": 2.027,
+      "step": 300
+    },
+    {
+      "epoch": 0.03311806590495115,
+      "eval_accuracy": 0.6055573666749765,
+      "eval_loss": 1.9839483499526978,
+      "eval_runtime": 6.4017,
+      "eval_samples_per_second": 63.734,
+      "eval_steps_per_second": 2.031,
+      "step": 400
+    },
+    {
+      "epoch": 0.04139758238118894,
+      "grad_norm": 8.5625,
+      "learning_rate": 4.931004029364685e-05,
+      "loss": 2.2761,
+      "step": 500
+    },
+    {
+      "epoch": 0.04139758238118894,
+      "eval_accuracy": 0.6084943562272814,
+      "eval_loss": 1.9611371755599976,
+      "eval_runtime": 6.4249,
+      "eval_samples_per_second": 63.503,
+      "eval_steps_per_second": 2.023,
+      "step": 500
+    },
+    {
+      "epoch": 0.04967709885742673,
+      "eval_accuracy": 0.6203082851637765,
+      "eval_loss": 1.905377984046936,
+      "eval_runtime": 6.4365,
+      "eval_samples_per_second": 63.388,
+      "eval_steps_per_second": 2.02,
+      "step": 600
+    },
+    {
+      "epoch": 0.057956615333664516,
+      "eval_accuracy": 0.6241699612328715,
+      "eval_loss": 1.8838109970092773,
+      "eval_runtime": 6.4118,
+      "eval_samples_per_second": 63.632,
+      "eval_steps_per_second": 2.028,
+      "step": 700
+    },
+    {
+      "epoch": 0.0662361318099023,
+      "eval_accuracy": 0.6295839990759813,
+      "eval_loss": 1.8403326272964478,
+      "eval_runtime": 6.397,
+      "eval_samples_per_second": 63.78,
+      "eval_steps_per_second": 2.032,
+      "step": 800
+    },
+    {
+      "epoch": 0.07451564828614009,
+      "eval_accuracy": 0.6300428691724719,
+      "eval_loss": 1.8234734535217285,
+      "eval_runtime": 6.4304,
+      "eval_samples_per_second": 63.449,
+      "eval_steps_per_second": 2.022,
+      "step": 900
+    },
+    {
+      "epoch": 0.08279516476237787,
+      "grad_norm": 7.65625,
+      "learning_rate": 4.862008058729371e-05,
+      "loss": 1.8887,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08279516476237787,
+      "eval_accuracy": 0.6351211866350639,
+      "eval_loss": 1.7919981479644775,
+      "eval_runtime": 6.4,
+      "eval_samples_per_second": 63.75,
+      "eval_steps_per_second": 2.031,
+      "step": 1000
+    },
+    {
+      "epoch": 0.08279516476237787,
+      "step": 1000,
+      "total_flos": 2.198926000128e+16,
+      "train_loss": 2.0824306030273436,
+      "train_runtime": 944.4845,
+      "train_samples_per_second": 613.773,
+      "train_steps_per_second": 38.364
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 36234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "total_flos": 2.198926000128e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}