End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pred_LAMA_TREx_test.jsonl filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "perplexity": 3.185801175999141,
+    "test_loss": 1.1587038040161133,
+    "test_runtime": 67.0223,
+    "test_samples": 8824,
+    "test_samples_per_second": 131.658,
+    "test_steps_per_second": 1.03,
+    "train_loss": 1.5075447494919236,
+    "train_runtime": 2186.2674,
+    "train_samples": 37860,
+    "train_samples_per_second": 51.952,
+    "train_steps_per_second": 0.406
+}

pred_LAMA_TREx_test.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0f47d4ac8b49e298a59dcaffa4cdbcf9953fcbf1f30042fc30b068ec853f7fc
+size 171855862

test_results.json

@@ -0,0 +1,8 @@
+{
+    "perplexity": 3.185801175999141,
+    "test_loss": 1.1587038040161133,
+    "test_runtime": 67.0223,
+    "test_samples": 8824,
+    "test_samples_per_second": 131.658,
+    "test_steps_per_second": 1.03
+}

tokenizer.json

@@ -1,21 +1,7 @@
 {
   "version": "1.0",
-  "truncation": {
-    "direction": "Right",
-    "max_length": 128,
-    "strategy": "LongestFirst",
-    "stride": 0
-  },
-  "padding": {
-    "strategy": {
-      "Fixed": 128
-    },
-    "direction": "Right",
-    "pad_to_multiple_of": null,
-    "pad_id": 50257,
-    "pad_type_id": 0,
-    "pad_token": "[PAD]"
-  },
+  "truncation": null,
+  "padding": null,
   "added_tokens": [
     {
       "id": 50256,

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.5075447494919236,
+    "train_runtime": 2186.2674,
+    "train_samples": 37860,
+    "train_samples_per_second": 51.952,
+    "train_steps_per_second": 0.406
+}

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 888,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.69,
+      "learning_rate": 8.806306306306306e-06,
+      "loss": 1.7195,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 888,
+      "total_flos": 7416975529082880.0,
+      "train_loss": 1.5075447494919236,
+      "train_runtime": 2186.2674,
+      "train_samples_per_second": 51.952,
+      "train_steps_per_second": 0.406
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 888,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 7416975529082880.0,
+  "trial_name": null,
+  "trial_params": null
+}