End of training

README.md

@@ -1,8 +1,13 @@
 ---
 base_model: barc0/cot-transduction-arc-heavy
+datasets:
+- barc0/cot_train_dataset_960_ms10_v2
+- barc0/cot_rearc_dataset_100_ms10
+- barc0/seeds_cot
 library_name: peft
 license: llama3.1
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -16,9 +21,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # cot-trainset-ft-transduction-v3-lora-train
 
-This model is a fine-tuned version of [barc0/cot-transduction-arc-heavy](https://huggingface.co/barc0/cot-transduction-arc-heavy) on the None dataset.
+This model is a fine-tuned version of [barc0/cot-transduction-arc-heavy](https://huggingface.co/barc0/cot-transduction-arc-heavy) on the barc0/cot_train_dataset_960_ms10_v2, the barc0/cot_rearc_dataset_100_ms10 and the barc0/seeds_cot datasets.
 It achieves the following results on the evaluation set:
-- Loss: 0.1333
+- Loss: 0.1921
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.9982608695652173,
+    "eval_loss": 0.1921355128288269,
+    "eval_runtime": 54.3907,
+    "eval_samples": 239,
+    "eval_samples_per_second": 4.394,
+    "eval_steps_per_second": 0.552,
     "total_flos": 466200922914816.0,
     "train_loss": 0.0,
     "train_runtime": 1.1199,

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "barc0/cot-transduction-arc-heavy",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.9982608695652173,
+    "eval_loss": 0.1921355128288269,
+    "eval_runtime": 54.3907,
+    "eval_samples": 239,
+    "eval_samples_per_second": 4.394,
+    "eval_steps_per_second": 0.552
+}

runs/Dec17_23-46-54_ellis-compute-02.cs.cornell.edu/events.out.tfevents.1734497324.ellis-compute-02.cs.cornell.edu.267747.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b037ef8e4dd21a2d1ce19626e976c827cd9670b7ca5a6227fec3c60512920c40
+size 359