Save benchmark: stable-run-sft-step-40

checkpoints/stable-run-sft-step-40/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-40/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-40/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-40/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d740ab1a53a65f90f2c80b414fdc73bbb81b7372099ac79b50562d38ab8fa09
+size 327657928

checkpoints/stable-run-sft-step-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828b8ea811b717fee3cf1acc522be760e9cd93c74ecbcd351f48b917a4403638
+size 655362635

checkpoints/stable-run-sft-step-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ced5ad6c6d957131b672d283057f6ecb5d6550f1a457d538205586246e3408
+size 1401

checkpoints/stable-run-sft-step-40/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-40/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|>"
+}

checkpoints/stable-run-sft-step-40/training_state.json

@@ -0,0 +1,407 @@
+{
+    "phase": "SFT",
+    "total_optimizer_steps": 40,
+    "metrics": [
+        {
+            "Step": 1,
+            "Metric": "SFT Loss",
+            "Value": 10.806696891784668
+        },
+        {
+            "Step": 1,
+            "Metric": "Learning Rate",
+            "Value": 4.0000000000000003e-07
+        },
+        {
+            "Step": 2,
+            "Metric": "SFT Loss",
+            "Value": 20.197086334228516
+        },
+        {
+            "Step": 2,
+            "Metric": "Learning Rate",
+            "Value": 8.000000000000001e-07
+        },
+        {
+            "Step": 3,
+            "Metric": "SFT Loss",
+            "Value": 13.669203758239746
+        },
+        {
+            "Step": 3,
+            "Metric": "Learning Rate",
+            "Value": 1.2000000000000002e-06
+        },
+        {
+            "Step": 4,
+            "Metric": "SFT Loss",
+            "Value": 19.52617835998535
+        },
+        {
+            "Step": 4,
+            "Metric": "Learning Rate",
+            "Value": 1.6000000000000001e-06
+        },
+        {
+            "Step": 5,
+            "Metric": "SFT Loss",
+            "Value": 14.46614933013916
+        },
+        {
+            "Step": 5,
+            "Metric": "Learning Rate",
+            "Value": 2.0000000000000003e-06
+        },
+        {
+            "Step": 6,
+            "Metric": "SFT Loss",
+            "Value": 11.709370613098145
+        },
+        {
+            "Step": 6,
+            "Metric": "Learning Rate",
+            "Value": 2.4000000000000003e-06
+        },
+        {
+            "Step": 7,
+            "Metric": "SFT Loss",
+            "Value": 14.79263687133789
+        },
+        {
+            "Step": 7,
+            "Metric": "Learning Rate",
+            "Value": 2.8000000000000003e-06
+        },
+        {
+            "Step": 8,
+            "Metric": "SFT Loss",
+            "Value": 16.564573287963867
+        },
+        {
+            "Step": 8,
+            "Metric": "Learning Rate",
+            "Value": 3.2000000000000003e-06
+        },
+        {
+            "Step": 9,
+            "Metric": "SFT Loss",
+            "Value": 16.437776565551758
+        },
+        {
+            "Step": 9,
+            "Metric": "Learning Rate",
+            "Value": 3.6000000000000003e-06
+        },
+        {
+            "Step": 10,
+            "Metric": "SFT Loss",
+            "Value": 14.215919494628906
+        },
+        {
+            "Step": 10,
+            "Metric": "Learning Rate",
+            "Value": 4.000000000000001e-06
+        },
+        {
+            "Step": 11,
+            "Metric": "SFT Loss",
+            "Value": 13.728559494018555
+        },
+        {
+            "Step": 11,
+            "Metric": "Learning Rate",
+            "Value": 4.4e-06
+        },
+        {
+            "Step": 12,
+            "Metric": "SFT Loss",
+            "Value": 17.120494842529297
+        },
+        {
+            "Step": 12,
+            "Metric": "Learning Rate",
+            "Value": 4.800000000000001e-06
+        },
+        {
+            "Step": 13,
+            "Metric": "SFT Loss",
+            "Value": 12.443873405456543
+        },
+        {
+            "Step": 13,
+            "Metric": "Learning Rate",
+            "Value": 5.2e-06
+        },
+        {
+            "Step": 14,
+            "Metric": "SFT Loss",
+            "Value": 10.322935104370117
+        },
+        {
+            "Step": 14,
+            "Metric": "Learning Rate",
+            "Value": 5.600000000000001e-06
+        },
+        {
+            "Step": 15,
+            "Metric": "SFT Loss",
+            "Value": 10.010440826416016
+        },
+        {
+            "Step": 15,
+            "Metric": "Learning Rate",
+            "Value": 6e-06
+        },
+        {
+            "Step": 16,
+            "Metric": "SFT Loss",
+            "Value": 9.959354400634766
+        },
+        {
+            "Step": 16,
+            "Metric": "Learning Rate",
+            "Value": 6.4000000000000006e-06
+        },
+        {
+            "Step": 17,
+            "Metric": "SFT Loss",
+            "Value": 9.42132568359375
+        },
+        {
+            "Step": 17,
+            "Metric": "Learning Rate",
+            "Value": 6.800000000000001e-06
+        },
+        {
+            "Step": 18,
+            "Metric": "SFT Loss",
+            "Value": 10.809995651245117
+        },
+        {
+            "Step": 18,
+            "Metric": "Learning Rate",
+            "Value": 7.2000000000000005e-06
+        },
+        {
+            "Step": 19,
+            "Metric": "SFT Loss",
+            "Value": 11.641499519348145
+        },
+        {
+            "Step": 19,
+            "Metric": "Learning Rate",
+            "Value": 7.600000000000001e-06
+        },
+        {
+            "Step": 20,
+            "Metric": "SFT Loss",
+            "Value": 8.137388229370117
+        },
+        {
+            "Step": 20,
+            "Metric": "Learning Rate",
+            "Value": 8.000000000000001e-06
+        },
+        {
+            "Step": 21,
+            "Metric": "SFT Loss",
+            "Value": 11.187762260437012
+        },
+        {
+            "Step": 21,
+            "Metric": "Learning Rate",
+            "Value": 8.400000000000001e-06
+        },
+        {
+            "Step": 22,
+            "Metric": "SFT Loss",
+            "Value": 6.696204662322998
+        },
+        {
+            "Step": 22,
+            "Metric": "Learning Rate",
+            "Value": 8.8e-06
+        },
+        {
+            "Step": 23,
+            "Metric": "SFT Loss",
+            "Value": 9.350967407226562
+        },
+        {
+            "Step": 23,
+            "Metric": "Learning Rate",
+            "Value": 9.200000000000002e-06
+        },
+        {
+            "Step": 24,
+            "Metric": "SFT Loss",
+            "Value": 7.601217269897461
+        },
+        {
+            "Step": 24,
+            "Metric": "Learning Rate",
+            "Value": 9.600000000000001e-06
+        },
+        {
+            "Step": 25,
+            "Metric": "SFT Loss",
+            "Value": 7.671919345855713
+        },
+        {
+            "Step": 25,
+            "Metric": "Learning Rate",
+            "Value": 1e-05
+        },
+        {
+            "Step": 26,
+            "Metric": "SFT Loss",
+            "Value": 5.797372341156006
+        },
+        {
+            "Step": 26,
+            "Metric": "Learning Rate",
+            "Value": 1.04e-05
+        },
+        {
+            "Step": 27,
+            "Metric": "SFT Loss",
+            "Value": 7.414616107940674
+        },
+        {
+            "Step": 27,
+            "Metric": "Learning Rate",
+            "Value": 1.0800000000000002e-05
+        },
+        {
+            "Step": 28,
+            "Metric": "SFT Loss",
+            "Value": 7.067437171936035
+        },
+        {
+            "Step": 28,
+            "Metric": "Learning Rate",
+            "Value": 1.1200000000000001e-05
+        },
+        {
+            "Step": 29,
+            "Metric": "SFT Loss",
+            "Value": 6.7167463302612305
+        },
+        {
+            "Step": 29,
+            "Metric": "Learning Rate",
+            "Value": 1.16e-05
+        },
+        {
+            "Step": 30,
+            "Metric": "SFT Loss",
+            "Value": 6.630039691925049
+        },
+        {
+            "Step": 30,
+            "Metric": "Learning Rate",
+            "Value": 1.2e-05
+        },
+        {
+            "Step": 31,
+            "Metric": "SFT Loss",
+            "Value": 6.276569366455078
+        },
+        {
+            "Step": 31,
+            "Metric": "Learning Rate",
+            "Value": 1.2400000000000002e-05
+        },
+        {
+            "Step": 32,
+            "Metric": "SFT Loss",
+            "Value": 7.236689567565918
+        },
+        {
+            "Step": 32,
+            "Metric": "Learning Rate",
+            "Value": 1.2800000000000001e-05
+        },
+        {
+            "Step": 33,
+            "Metric": "SFT Loss",
+            "Value": 6.829200267791748
+        },
+        {
+            "Step": 33,
+            "Metric": "Learning Rate",
+            "Value": 1.3200000000000002e-05
+        },
+        {
+            "Step": 34,
+            "Metric": "SFT Loss",
+            "Value": 6.348658561706543
+        },
+        {
+            "Step": 34,
+            "Metric": "Learning Rate",
+            "Value": 1.3600000000000002e-05
+        },
+        {
+            "Step": 35,
+            "Metric": "SFT Loss",
+            "Value": 6.114589691162109
+        },
+        {
+            "Step": 35,
+            "Metric": "Learning Rate",
+            "Value": 1.4e-05
+        },
+        {
+            "Step": 36,
+            "Metric": "SFT Loss",
+            "Value": 5.820864677429199
+        },
+        {
+            "Step": 36,
+            "Metric": "Learning Rate",
+            "Value": 1.4400000000000001e-05
+        },
+        {
+            "Step": 37,
+            "Metric": "SFT Loss",
+            "Value": 6.093341827392578
+        },
+        {
+            "Step": 37,
+            "Metric": "Learning Rate",
+            "Value": 1.48e-05
+        },
+        {
+            "Step": 38,
+            "Metric": "SFT Loss",
+            "Value": 6.195661544799805
+        },
+        {
+            "Step": 38,
+            "Metric": "Learning Rate",
+            "Value": 1.5200000000000002e-05
+        },
+        {
+            "Step": 39,
+            "Metric": "SFT Loss",
+            "Value": 7.604869365692139
+        },
+        {
+            "Step": 39,
+            "Metric": "Learning Rate",
+            "Value": 1.5600000000000003e-05
+        },
+        {
+            "Step": 40,
+            "Metric": "SFT Loss",
+            "Value": 5.295370101928711
+        },
+        {
+            "Step": 40,
+            "Metric": "Learning Rate",
+            "Value": 1.6000000000000003e-05
+        }
+    ],
+    "sft_complete": false
+}