Upload folder using huggingface_hub

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "hidden_act": "silu",
+  "hidden_size": 12,
+  "initializer_range": 0.02,
+  "intermediate_size": 48,
+  "max_position_embeddings": 512,
+  "model_type": "llama",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 1,
+  "num_key_value_heads": 1,
+  "pad_token_id": 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": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 4096
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 2,
+  "transformers_version": "4.40.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea6d2f409eb01bcb03bb4f21ff3cc7d12463810c2ded3ba70c12a15be209c965
+size 403216

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1f31bf8dba98637205d3ead8f53e54987aaba212244df5819ef4e5c07b6a5e0
+size 813674

run_context.json

@@ -0,0 +1,8 @@
+{
+  "device": "cuda",
+  "gpu_name": "Quadro M4000",
+  "torch_version": "2.1.2+cu121",
+  "delphi_version": "0.2",
+  "transformers_version": "4.40.0",
+  "os": "#164-Ubuntu SMP Tue Mar 21 14:23:17 UTC 2023"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

training_config.json

@@ -0,0 +1,72 @@
+{
+  "model_config": {
+    "model_class": "LlamaForCausalLM",
+    "vocab_size": 4096,
+    "hidden_act": "silu",
+    "max_position_embeddings": 512,
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-06,
+    "bos_token_id": 0,
+    "eos_token_id": 1,
+    "pad_token_id": 2,
+    "tie_word_embeddings": false,
+    "rope_theta": 10000.0,
+    "rope_scaling": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "hidden_size": 12,
+    "intermediate_size": 48,
+    "num_attention_heads": 2,
+    "num_hidden_layers": 1,
+    "num_key_value_heads": 1
+  },
+  "max_seq_len": 512,
+  "run_name": "2024_05_25_09_15_16",
+  "out_dir": "/home/paperspace/.local/share/delphi/2024_05_25_09_15_16",
+  "device": "auto",
+  "checkpoint_interval": 400,
+  "extra_checkpoint_iters": [
+    1,
+    2,
+    4,
+    8,
+    16,
+    32,
+    64,
+    128,
+    256,
+    512
+  ],
+  "log_interval": 40,
+  "eval_iters": 10,
+  "resume_from_path": null,
+  "batch_size": 256,
+  "max_epochs": 1,
+  "grad_clip": 1.0,
+  "gradient_accumulation_steps": 4,
+  "adam": {
+    "learning_rate": 0.0005,
+    "weight_decay": 0.1,
+    "beta1": 0.9,
+    "beta2": 0.95,
+    "decay_lr": true,
+    "warmup_iters": 1000,
+    "min_lr": 0.0
+  },
+  "batch_ordering_seed": 1337,
+  "torch_seed": 42,
+  "save_optimizer": true,
+  "dataset": {
+    "path": "delphi-suite/stories-tokenized",
+    "feature": "tokens",
+    "train_split": "train[:3%]",
+    "validation_split": "validation"
+  },
+  "tokenizer": "delphi-suite/stories-tokenizer",
+  "wandb": "jettjaniak/delphi",
+  "out_repo": "jettjaniak/stories-llama2-100k-v02-test3",
+  "debug_config": {
+    "no_training": false,
+    "no_eval": false
+  }
+}

training_state.json

@@ -0,0 +1,6 @@
+{
+  "iter_num": 125,
+  "lr": 6.2e-05,
+  "epoch": 0,
+  "step": 124
+}