Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/datastor1/shared_resources/nlp-models/hf/models--meta-llama--Llama-2-7b-hf/snapshots/8cca527612d856d7d32bd94f8103728d614eb852",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.41.2"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e5981e58245e636382d6943cd1abbb027d1a1f21b4e349ebac6e99e1acb5dc5
+size 4840649992

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5223007d15b2c6e97ca2ad7ce0f26a95dfde7597121a312fcbd168c41d888ee
+size 4857443920

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae3d2b52dce41859d765cd0b43755dcd8c4944f5bdb57a4f3ac1d2953dfea07
+size 4857444480

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41cf19f480b7a13e14943896aa983a5cec90eee3c24488433d37a84ed5ee7ce1
+size 4857444480

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d89990b9f8136128eb4d4a6760557ad6a3c003e7c7840188f7fbb215cd2cab82
+size 4857444480

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd3b4123fae6363aab674965ac676a90507ae72009d1d71748b96026478d00af
+size 2684567688

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7111de7e18602e47b32f5e8ec7aef2bc6ff2806b40f0bc94e34de263b49adcd
+size 177914

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd4c00f24c2045443d42cad82627a0b052cf2e33e952e18e93bae1f262d24da
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4ec1e67514c244d459fe0b2ac65c35d4543801c1925cd62965589c57c8be38b
+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": "[PAD]",
+    "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 +1,49 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,188 @@
+{
+  "best_metric": 0.3008906841278076,
+  "best_model_checkpoint": "/datastor1/fcyin/finetuned_checkpoints/truthfulqa/llama2_7B_truthfulqa_lofit_seed42_96heads/checkpoint-123",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 205,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6008107662200928,
+      "learning_rate": 0.004,
+      "logits/chosen": -2.5561070442199707,
+      "logits/rejected": -2.650902271270752,
+      "logps/chosen": -29.893611907958984,
+      "logps/rejected": -31.828697204589844,
+      "loss": 0.2945,
+      "rewards/accuracies": 0.8597561120986938,
+      "rewards/chosen": -0.5662117004394531,
+      "rewards/margins": 2.810072422027588,
+      "rewards/rejected": -3.376283884048462,
+      "step": 41
+    },
+    {
+      "epoch": 1.0,
+      "eval_logits/chosen": -3.046513319015503,
+      "eval_logits/rejected": -3.213273048400879,
+      "eval_logps/chosen": -30.533157348632812,
+      "eval_logps/rejected": -33.57004165649414,
+      "eval_loss": 0.6931471228599548,
+      "eval_rewards/accuracies": 0.0,
+      "eval_rewards/chosen": 0.0,
+      "eval_rewards/margins": 0.0,
+      "eval_rewards/rejected": 0.0,
+      "eval_runtime": 7.6196,
+      "eval_samples_per_second": 10.762,
+      "eval_steps_per_second": 0.394,
+      "step": 41
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.98629230260849,
+      "learning_rate": 0.003,
+      "logits/chosen": -2.6476099491119385,
+      "logits/rejected": -2.767660140991211,
+      "logps/chosen": -29.75066375732422,
+      "logps/rejected": -38.1750602722168,
+      "loss": 0.0504,
+      "rewards/accuracies": 0.9969512224197388,
+      "rewards/chosen": -0.5129372477531433,
+      "rewards/margins": 6.039527893066406,
+      "rewards/rejected": -6.552464962005615,
+      "step": 82
+    },
+    {
+      "epoch": 2.0,
+      "eval_logits/chosen": -2.8705577850341797,
+      "eval_logits/rejected": -3.025930166244507,
+      "eval_logps/chosen": -30.89835548400879,
+      "eval_logps/rejected": -37.61328887939453,
+      "eval_loss": 0.3324950039386749,
+      "eval_rewards/accuracies": 0.8530092239379883,
+      "eval_rewards/chosen": -0.18259893357753754,
+      "eval_rewards/margins": 1.8390239477157593,
+      "eval_rewards/rejected": -2.021622896194458,
+      "eval_runtime": 7.4476,
+      "eval_samples_per_second": 11.01,
+      "eval_steps_per_second": 0.403,
+      "step": 82
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 2.8237621784210205,
+      "learning_rate": 0.002,
+      "logits/chosen": -2.4965312480926514,
+      "logits/rejected": -2.600482940673828,
+      "logps/chosen": -30.458192825317383,
+      "logps/rejected": -42.681915283203125,
+      "loss": 0.0133,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -0.8702911734580994,
+      "rewards/margins": 7.938199520111084,
+      "rewards/rejected": -8.808490753173828,
+      "step": 123
+    },
+    {
+      "epoch": 3.0,
+      "eval_logits/chosen": -2.774709701538086,
+      "eval_logits/rejected": -2.927616834640503,
+      "eval_logps/chosen": -32.284488677978516,
+      "eval_logps/rejected": -40.45302200317383,
+      "eval_loss": 0.3008906841278076,
+      "eval_rewards/accuracies": 0.8611111044883728,
+      "eval_rewards/chosen": -0.875666081905365,
+      "eval_rewards/margins": 2.5658228397369385,
+      "eval_rewards/rejected": -3.4414889812469482,
+      "eval_runtime": 7.444,
+      "eval_samples_per_second": 11.016,
+      "eval_steps_per_second": 0.403,
+      "step": 123
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.09415304660797119,
+      "learning_rate": 0.001,
+      "logits/chosen": -2.4607629776000977,
+      "logits/rejected": -2.572495222091675,
+      "logps/chosen": -30.935243606567383,
+      "logps/rejected": -44.62324905395508,
+      "loss": 0.0063,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.088704228401184,
+      "rewards/margins": 8.673280715942383,
+      "rewards/rejected": -9.761984825134277,
+      "step": 164
+    },
+    {
+      "epoch": 4.0,
+      "eval_logits/chosen": -2.737975835800171,
+      "eval_logits/rejected": -2.888521432876587,
+      "eval_logps/chosen": -32.865299224853516,
+      "eval_logps/rejected": -41.451168060302734,
+      "eval_loss": 0.3184911608695984,
+      "eval_rewards/accuracies": 0.8611111044883728,
+      "eval_rewards/chosen": -1.1660696268081665,
+      "eval_rewards/margins": 2.774491310119629,
+      "eval_rewards/rejected": -3.940561056137085,
+      "eval_runtime": 7.5099,
+      "eval_samples_per_second": 10.919,
+      "eval_steps_per_second": 0.399,
+      "step": 164
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.0271140243858099,
+      "learning_rate": 0.0,
+      "logits/chosen": -2.4665253162384033,
+      "logits/rejected": -2.5754239559173584,
+      "logps/chosen": -31.26015853881836,
+      "logps/rejected": -45.692237854003906,
+      "loss": 0.0041,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": -1.2341755628585815,
+      "rewards/margins": 9.071220397949219,
+      "rewards/rejected": -10.305395126342773,
+      "step": 205
+    },
+    {
+      "epoch": 5.0,
+      "eval_logits/chosen": -2.723881959915161,
+      "eval_logits/rejected": -2.8738536834716797,
+      "eval_logps/chosen": -33.00375747680664,
+      "eval_logps/rejected": -41.7939453125,
+      "eval_loss": 0.32048389315605164,
+      "eval_rewards/accuracies": 0.8715277314186096,
+      "eval_rewards/chosen": -1.2353010177612305,
+      "eval_rewards/margins": 2.8766491413116455,
+      "eval_rewards/rejected": -4.111950397491455,
+      "eval_runtime": 7.4592,
+      "eval_samples_per_second": 10.993,
+      "eval_steps_per_second": 0.402,
+      "step": 205
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 205,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b6887ed4dd1aecc280a6d68992d497c8884204e24271c7b8fb53fc17eabf4dd
+size 5240