Save benchmark: stable-run-sft-step-480

checkpoints/stable-run-sft-step-480/config.json

@@ -0,0 +1,45 @@
+{
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoints/stable-run-sft-step-480/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.56.1"
+}

checkpoints/stable-run-sft-step-480/hyperparameters.json

@@ -0,0 +1,17 @@
+{
+    "repo_id": "broadfield-dev/savant_2_gsm8k_final",
+    "resume_from_benchmark": "",
+    "benchmark_name_prefix": "stable-run",
+    "benchmark_interval": 20,
+    "sft_epochs": 4,
+    "sft_lr": 2e-05,
+    "sft_warmup_proportion": 0.1,
+    "rl_lr": 1.5e-06,
+    "sft_slice": "0:2000",
+    "rl_slice": "4000:7473",
+    "context_length": 1024,
+    "base_model_name": "distilgpt2",
+    "use_scheduler": true,
+    "sft_batch_size": 1,
+    "grad_accum_steps": 16
+}

checkpoints/stable-run-sft-step-480/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12044ad2f1c0c22cfadd27d74c4eaab007eef07e80ecb0905ab68722f3876516
+size 327657928

checkpoints/stable-run-sft-step-480/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af39c6c6a4c91f1b06cef2c0445b04f299edc724ea6c2a5e2ec3e7e1fec20756
+size 655362635

checkpoints/stable-run-sft-step-480/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c18b438109f254b43b89c96b7f4ba29b060d8d41ddc26fd705396a3d10ca32b
+size 1465

checkpoints/stable-run-sft-step-480/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoints/stable-run-sft-step-480/tokenizer_config.json

@@ -0,0 +1,21 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}