End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- wikitext
+metrics:
+- accuracy
 model-index:
 - name: test_pretrain
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: wikitext wikitext-2-v1
+      type: wikitext
+      args: wikitext-2-v1
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.28011557471332055
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # test_pretrain
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the wikitext wikitext-2-v1 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.0612
+- Accuracy: 0.2801
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.28011557471332055,
+    "eval_loss": 5.061196804046631,
+    "eval_runtime": 16.9445,
+    "eval_samples": 249,
+    "eval_samples_per_second": 14.695,
+    "eval_steps_per_second": 1.889,
+    "perplexity": 157.77923419764554,
+    "train_loss": 5.833661626916525,
+    "train_runtime": 1259.5482,
+    "train_samples": 2346,
+    "train_samples_per_second": 5.588,
+    "train_steps_per_second": 1.398
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.28011557471332055,
+    "eval_loss": 5.061196804046631,
+    "eval_runtime": 16.9445,
+    "eval_samples": 249,
+    "eval_samples_per_second": 14.695,
+    "eval_steps_per_second": 1.889,
+    "perplexity": 157.77923419764554
+}

runs/Jan16_12-19-24_0048b83c9bcc/events.out.tfevents.1705408904.0048b83c9bcc.8085.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdccfc534e36e0ef05618e84cfb2030fcda248989d02f6fb1ae9ed49b5dc571d
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 5.833661626916525,
+    "train_runtime": 1259.5482,
+    "train_samples": 2346,
+    "train_samples_per_second": 5.588,
+    "train_steps_per_second": 1.398
+}

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1761,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.580352072685974e-05,
+      "loss": 6.4049,
+      "step": 500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.160704145371948e-05,
+      "loss": 5.7387,
+      "step": 1000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.410562180579217e-06,
+      "loss": 5.5475,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "step": 1761,
+      "total_flos": 3677946642432000.0,
+      "train_loss": 5.833661626916525,
+      "train_runtime": 1259.5482,
+      "train_samples_per_second": 5.588,
+      "train_steps_per_second": 1.398
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1761,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 3677946642432000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}