Upload 12 files

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/home/joe/Downloads/so_much",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 31,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.0.dev0",
+  "unsloth_version": "2024.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef32ccef672d5de3e5f2be43e0a1be3cb7061cc11bd8751c0c818f751415bfe8
+size 2992926176

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c6a9e7b695f7687e731b7a15386f2a736e885cb744ab237ee84633b183ff84
+size 5454522

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:386fcc8cc1089aade9450d86fb239ea3483f455fd2d78d8378645feecfec9d69
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9625c4bd6137497fdc071f2ef3c6109f815959a4f84d167e89493c9fe28650
+size 1064

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "max_length": 2048,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,203 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.056700482783555585,
+  "eval_steps": 500,
+  "global_step": 2666,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.9096835851669312,
+      "learning_rate": 4.989366000978328e-05,
+      "loss": 0.5573,
+      "step": 100
+    },
+    {
+      "epoch": 0.0,
+      "grad_norm": 0.8342915177345276,
+      "learning_rate": 4.978732001956656e-05,
+      "loss": 0.5416,
+      "step": 200
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 1.401437759399414,
+      "learning_rate": 4.968098002934984e-05,
+      "loss": 0.5475,
+      "step": 300
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.7456225156784058,
+      "learning_rate": 4.957464003913312e-05,
+      "loss": 0.5302,
+      "step": 400
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.966705858707428,
+      "learning_rate": 4.94683000489164e-05,
+      "loss": 0.5257,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.8829948902130127,
+      "learning_rate": 4.936302345860184e-05,
+      "loss": 0.5185,
+      "step": 600
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 0.8967320322990417,
+      "learning_rate": 4.925668346838512e-05,
+      "loss": 0.5195,
+      "step": 700
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.8852934241294861,
+      "learning_rate": 4.9151406878070574e-05,
+      "loss": 0.5117,
+      "step": 800
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.0393266677856445,
+      "learning_rate": 4.9045066887853846e-05,
+      "loss": 0.5027,
+      "step": 900
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.016802191734314,
+      "learning_rate": 4.8938726897637125e-05,
+      "loss": 0.5099,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 1.0666687488555908,
+      "learning_rate": 4.8832386907420405e-05,
+      "loss": 0.5129,
+      "step": 1100
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.0762836933135986,
+      "learning_rate": 4.872604691720369e-05,
+      "loss": 0.5277,
+      "step": 1200
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.8559880256652832,
+      "learning_rate": 4.861970692698696e-05,
+      "loss": 0.4987,
+      "step": 1300
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.0834448337554932,
+      "learning_rate": 4.851336693677024e-05,
+      "loss": 0.5171,
+      "step": 1400
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9118117690086365,
+      "learning_rate": 4.840702694655352e-05,
+      "loss": 0.5073,
+      "step": 1500
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.029111623764038,
+      "learning_rate": 4.830068695633681e-05,
+      "loss": 0.5085,
+      "step": 1600
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.9440446496009827,
+      "learning_rate": 4.819434696612008e-05,
+      "loss": 0.4978,
+      "step": 1700
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8061498403549194,
+      "learning_rate": 4.808800697590336e-05,
+      "loss": 0.4859,
+      "step": 1800
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.1587491035461426,
+      "learning_rate": 4.798166698568664e-05,
+      "loss": 0.5029,
+      "step": 1900
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 0.8422715067863464,
+      "learning_rate": 4.787532699546992e-05,
+      "loss": 0.507,
+      "step": 2000
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.0634592771530151,
+      "learning_rate": 4.77689870052532e-05,
+      "loss": 0.4967,
+      "step": 2100
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.1594743728637695,
+      "learning_rate": 4.7662647015036477e-05,
+      "loss": 0.4993,
+      "step": 2200
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.0729972124099731,
+      "learning_rate": 4.7556307024819756e-05,
+      "loss": 0.496,
+      "step": 2300
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.0069080591201782,
+      "learning_rate": 4.7449967034603035e-05,
+      "loss": 0.5016,
+      "step": 2400
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.9722279906272888,
+      "learning_rate": 4.7343627044386314e-05,
+      "loss": 0.4883,
+      "step": 2500
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.760681688785553,
+      "learning_rate": 4.7237287054169594e-05,
+      "loss": 0.4899,
+      "step": 2600
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 47019,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1333,
+  "total_flos": 7.500219014216417e+17,
+  "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:e57c4dc9131f9bf65b5c29340629c4a87fa288a08d427753cdc7fbe9a295c893
+size 4920