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 sha256:00bb426ca13f282dadb75eb36fab59f6fa5b1397add550ef7ad48fdb7a63d6e0
+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 +1,244 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.92,
+  "eval_steps": 500,
+  "global_step": 36,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 1e-05,
+      "loss": 3.0296,
+      "step": 1
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 2e-05,
+      "loss": 3.0742,
+      "step": 2
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.9957341762950346e-05,
+      "loss": 2.8934,
+      "step": 3
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.982973099683902e-05,
+      "loss": 2.6232,
+      "step": 4
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.961825643172819e-05,
+      "loss": 2.702,
+      "step": 5
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.932472229404356e-05,
+      "loss": 2.6369,
+      "step": 6
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.8951632913550625e-05,
+      "loss": 2.3979,
+      "step": 7
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.8502171357296144e-05,
+      "loss": 2.4416,
+      "step": 8
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.7980172272802398e-05,
+      "loss": 2.4504,
+      "step": 9
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 1.7390089172206594e-05,
+      "loss": 2.3466,
+      "step": 10
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 1.6736956436465573e-05,
+      "loss": 2.1911,
+      "step": 11
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.6026346363792565e-05,
+      "loss": 2.1612,
+      "step": 12
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.526432162877356e-05,
+      "loss": 2.3012,
+      "step": 13
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.4457383557765385e-05,
+      "loss": 2.1788,
+      "step": 14
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1.3612416661871532e-05,
+      "loss": 1.9259,
+      "step": 15
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.2736629900720832e-05,
+      "loss": 2.0095,
+      "step": 16
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 1.1837495178165706e-05,
+      "loss": 2.0258,
+      "step": 17
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.092268359463302e-05,
+      "loss": 2.1327,
+      "step": 18
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1e-05,
+      "loss": 1.9709,
+      "step": 19
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 9.07731640536698e-06,
+      "loss": 2.0154,
+      "step": 20
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 8.162504821834296e-06,
+      "loss": 1.9757,
+      "step": 21
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 7.263370099279173e-06,
+      "loss": 2.041,
+      "step": 22
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 6.387583338128471e-06,
+      "loss": 1.979,
+      "step": 23
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 5.542616442234618e-06,
+      "loss": 1.864,
+      "step": 24
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 4.7356783712264405e-06,
+      "loss": 1.7513,
+      "step": 25
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 3.973653636207437e-06,
+      "loss": 1.9203,
+      "step": 26
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.2630435635344283e-06,
+      "loss": 1.7979,
+      "step": 27
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 2.6099108277934105e-06,
+      "loss": 1.7382,
+      "step": 28
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 2.019827727197605e-06,
+      "loss": 1.8576,
+      "step": 29
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 1.4978286427038602e-06,
+      "loss": 1.8706,
+      "step": 30
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 1.0483670864493777e-06,
+      "loss": 1.7878,
+      "step": 31
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 6.752777059564431e-07,
+      "loss": 1.8523,
+      "step": 32
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 3.817435682718096e-07,
+      "loss": 1.8966,
+      "step": 33
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.7026900316098217e-07,
+      "loss": 1.8256,
+      "step": 34
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 4.2658237049655325e-08,
+      "loss": 1.8652,
+      "step": 35
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 0.0,
+      "loss": 1.9459,
+      "step": 36
+    },
+    {
+      "epoch": 1.92,
+      "step": 36,
+      "total_flos": 7805008380690432.0,
+      "train_loss": 2.152141014734904,
+      "train_runtime": 364.8773,
+      "train_samples_per_second": 13.155,
+      "train_steps_per_second": 0.099
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 36,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 7805008380690432.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8541483038d96c8279b41adf8633fa1f27b30ec128b380b694ce1dc760112686
+size 4027