End of training

README.md

@@ -1,11 +1,23 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- kanishka/counterfactual-babylm-pipps-random_removal
 metrics:
 - accuracy
 model-index:
 - name: smolm-autoreg-bpe-counterfactual-babylm-pipps-random_removal-seed_211-1e-3
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: kanishka/counterfactual-babylm-pipps-random_removal
+      type: kanishka/counterfactual-babylm-pipps-random_removal
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.40988659662430754
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +25,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # smolm-autoreg-bpe-counterfactual-babylm-pipps-random_removal-seed_211-1e-3
 
-This model was trained from scratch on an unknown dataset.
+This model was trained from scratch on the kanishka/counterfactual-babylm-pipps-random_removal dataset.
 It achieves the following results on the evaluation set:
 - Loss: 3.4120
 - Accuracy: 0.4099

all_results.json

@@ -1,5 +1,12 @@
 {
     "epoch": 20.0,
+    "eval_accuracy": 0.40988659662430754,
+    "eval_loss": 3.4119651317596436,
+    "eval_runtime": 155.2726,
+    "eval_samples": 57919,
+    "eval_samples_per_second": 373.015,
+    "eval_steps_per_second": 5.828,
+    "perplexity": 30.324777928701113,
     "train_loss": 3.030422134530729,
     "train_runtime": 80926.4318,
     "train_samples": 594939,

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.40988659662430754,
+    "eval_loss": 3.4119651317596436,
+    "eval_runtime": 155.2726,
+    "eval_samples": 57919,
+    "eval_samples_per_second": 373.015,
+    "eval_steps_per_second": 5.828,
+    "perplexity": 30.324777928701113
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:866ae496a28f15b35dfb30fa2f043c02fb6c175430b187d91d02380bf2402232
+oid sha256:1058b70cf082e7f824f2d844164b70b137bd58d41d330f2d17357c9901276236
 size 391376736

runs/Feb18_17-40-04_phyl-ling-p01.la.utexas.edu/events.out.tfevents.1708380750.phyl-ling-p01.la.utexas.edu.4114048.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c87054010ca6ee0b58970cd1c47b37f9ddd12d2b2fa08db528047175dd33d06
+size 417

special_tokens_map.json

@@ -1,30 +1,6 @@
 {
-  "bos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "eos_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "pad_token": {
-    "content": "<pad>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "unk_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<pad>",
+  "unk_token": "<|endoftext|>"
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de628e904610dcfc03c8f4606b469daa89ac1840808e7a168bc0db43dab9131
+oid sha256:784c6b58a52872de687c89103584b1d7734dd70dbbac0b46d0dff013ee7d2a3f
 size 4984