Upload 12 files

config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 512,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47cac36e9c1ad84ddcfe7758dfc56ace1b8e265fec1d8ab0e226aa949942b1ea
+size 6485383922

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14044b2262797869783420de01d3f3eff0a936b5d61daed15b33c544e1115ec6
+size 3242672438

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff264f99d31b522cc7e2a4eac9d38606d0c58a34c0adc74d71e0ca8b371dc36
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27b630be30fb88e8f9c6be05fedc42b5c4d5f370e484c12b1aea7c801707b91c
+size 1064

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.04325558862204997,
+  "eval_steps": 100000000,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.0000000000000001e-07,
+      "loss": 10.7586,
+      "step": 1
+    },
+    {
+      "epoch": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 6.5292,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.99998214600225e-05,
+      "loss": 4.7262,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.9999285842640105e-05,
+      "loss": 4.1997,
+      "step": 1500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 4.999839315550315e-05,
+      "loss": 3.8892,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9997143411362066e-05,
+      "loss": 3.6618,
+      "step": 2500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9995536628067196e-05,
+      "loss": 3.5132,
+      "step": 3000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.9993572828568536e-05,
+      "loss": 3.4092,
+      "step": 3500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.999125204091544e-05,
+      "loss": 3.3295,
+      "step": 4000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.998857429825615e-05,
+      "loss": 3.2596,
+      "step": 4500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9985539638837424e-05,
+      "loss": 3.2068,
+      "step": 5000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.998214810600389e-05,
+      "loss": 3.163,
+      "step": 5500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.997839974819749e-05,
+      "loss": 3.1256,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 416130,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 3000,
+  "total_flos": 2.197429420032e+18,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9d0d01338b60b1be222619b79ea3b0ae2fdbdadaf777c837223a484daa9c2b4
+size 4728