first commit

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.2"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7868fc9abbb6931f6e4a8c39f8bd390056c35e70ae78c263251a66dac473ee12
+size 649705097

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,38 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.92,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 2e-05,
+      "loss": 3.0266,
+      "step": 1
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.9594929736144978e-05,
+      "loss": 3.0107,
+      "step": 2
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.8412535328311813e-05,
+      "loss": 2.6686,
+      "step": 3
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.6548607339452853e-05,
+      "loss": 2.741,
+      "step": 4
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.4154150130018867e-05,
+      "loss": 2.3865,
+      "step": 5
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.1423148382732854e-05,
+      "loss": 2.4957,
+      "step": 6
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.576851617267151e-06,
+      "loss": 2.425,
+      "step": 7
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.845849869981137e-06,
+      "loss": 2.4254,
+      "step": 8
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.4513926605471504e-06,
+      "loss": 2.2729,
+      "step": 9
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.587464671688187e-06,
+      "loss": 2.2357,
+      "step": 10
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 4.0507026385502747e-07,
+      "loss": 2.2729,
+      "step": 11
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0,
+      "loss": 2.2377,
+      "step": 12
+    },
+    {
+      "epoch": 1.92,
+      "step": 12,
+      "total_flos": 2601669460230144.0,
+      "train_loss": 2.5165560046831765,
+      "train_runtime": 131.5492,
+      "train_samples_per_second": 12.163,
+      "train_steps_per_second": 0.091
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 12,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 2601669460230144.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:323984dbdccc7514d4d9652fd33de19cfd8d2abceb7578764960b514e87a5ba1
+size 4027