Upload 9 files

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "eqhylxx/vicuna-160m",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a63124c1a0d6123d64b9cfd48ffa6984efb3bd45afaf0fa575647687b0fda450
+size 649681952

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 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 256,
+  "pad_token": "<unk>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,88 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7391304347826086,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 2e-05,
+      "loss": 1.4856,
+      "step": 1
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.4885,
+      "step": 2
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.458,
+      "step": 3
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.4399,
+      "step": 4
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 1.474,
+      "step": 5
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.4138,
+      "step": 6
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.3794,
+      "step": 7
+    },
+    {
+      "epoch": 1.39,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 1.3599,
+      "step": 8
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 1.343,
+      "step": 9
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0,
+      "loss": 1.3461,
+      "step": 10
+    },
+    {
+      "epoch": 1.74,
+      "step": 10,
+      "total_flos": 269101715816448.0,
+      "train_loss": 1.4188124775886535,
+      "train_runtime": 11.4392,
+      "train_samples_per_second": 127.106,
+      "train_steps_per_second": 0.874
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 10,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 269101715816448.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c464bc8c9dfe015e295371677782b673166c21d07d7b471ce81479a1bacb2ff
+size 4600