Upload folder using huggingface_hub

config.json

@@ -1,27 +1,62 @@
 {
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": -1,
-  "eos_token_id": -2,
-  "hidden_act": "silu",
-  "hidden_size": 48,
-  "initializer_range": 0.02,
-  "intermediate_size": 48,
-  "max_position_embeddings": 513,
-  "model_type": "llama",
-  "num_attention_heads": 2,
-  "num_hidden_layers": 2,
-  "num_key_value_heads": 2,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.39.0.dev0",
-  "use_cache": true,
-  "vocab_size": 4096
-}
+  "model_config": {
+    "model_type": "llama2",
+    "mamba": null,
+    "llama2": {
+      "attention_bias": false,
+      "attention_dropout": 0.0,
+      "bos_token_id": -1,
+      "eos_token_id": -2,
+      "hidden_act": "silu",
+      "hidden_size": 48,
+      "initializer_range": 0.02,
+      "intermediate_size": 48,
+      "max_position_embeddings": 513,
+      "num_attention_heads": 2,
+      "num_hidden_layers": 2,
+      "num_key_value_heads": 2,
+      "pretraining_tp": 1,
+      "rms_norm_eps": 1e-06,
+      "rope_scaling": null,
+      "rope_theta": 10000.0,
+      "tie_word_embeddings": false,
+      "use_cache": true,
+      "vocab_size": 4096
+    }
+  },
+  "run_name": "debug__2024_03_19_00_25_35",
+  "output_dir": "/Users/jaidhyani/Library/Application Support/delphi/debug__2024_03_19_00_25_35",
+  "huggingface": {
+    "repo_id": null,
+    "save_checkpoints": false
+  },
+  "device": "auto",
+  "eval_interval": 1,
+  "log_interval": 1,
+  "eval_iters": 1,
+  "eval_only": false,
+  "always_save_checkpoint": true,
+  "init_from": "scratch",
+  "wandb_config": {
+    "log": true,
+    "project": "delphi",
+    "entity": "jaiwithani"
+  },
+  "batch_size": 64,
+  "max_seq_len": 512,
+  "max_epochs": 1,
+  "grad_clip": 1.0,
+  "optimizer": {
+    "gradient_accumulation_steps": 4,
+    "learning_rate": 0.0005,
+    "weight_decay": 0.1,
+    "beta1": 0.9,
+    "beta2": 0.95,
+    "grad_clip": 1.0,
+    "decay_lr": true,
+    "warmup_iters": 1000,
+    "min_lr": 0.0
+  },
+  "train_sample_limit": 1024,
+  "val_sample_limit": -1
+}

model/config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": -1,
+  "eos_token_id": -2,
+  "hidden_act": "silu",
+  "hidden_size": 48,
+  "initializer_range": 0.02,
+  "intermediate_size": 48,
+  "max_position_embeddings": 513,
+  "model_type": "llama",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "num_key_value_heads": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 4096
+}

model/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": -1,
+  "eos_token_id": -2,
+  "transformers_version": "4.39.0.dev0"
+}

model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97c293c8012db4e680aafabdd506275753edd5583a014640c1baf76e8e56a536
+size 1705032

opt.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f32e89835c9174e9addbbf7a3b81cf17fabf341a11ff4b6ec8187f6ed4f9049
+size 3422425

run_context.json

@@ -0,0 +1,7 @@
+{
+  "device": "mps",
+  "torch_version": "2.1.2",
+  "delphi_version": "0.1.1",
+  "transformers_version": "4.39.0.dev0",
+  "os": "Darwin Kernel Version 23.2.0: Wed Nov 15 21:53:34 PST 2023; root:xnu-10002.61.3~2/RELEASE_ARM64_T8103"
+}

training_state.json

@@ -0,0 +1,9 @@
+{
+  "iter_num": 1,
+  "local_iter_num": 1,
+  "best_val_loss": 8.323423385620117,
+  "running_mfu": -1.0,
+  "lr": 5e-07,
+  "epoch": 0,
+  "step": 1
+}