Upload folder using huggingface_hub

adapter_config.json

@@ -0,0 +1,21 @@
+{
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data/lizongyue/llm_factory/model/meta-llama/Llama-2-7b-chat-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 80.0,
+    "train_loss": 0.4674161618947983,
+    "train_runtime": 1650.9942,
+    "train_samples_per_second": 4.846,
+    "train_steps_per_second": 0.121
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "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 +1,35 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' '  + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 80.0,
+    "train_loss": 0.4674161618947983,
+    "train_runtime": 1650.9942,
+    "train_samples_per_second": 4.846,
+    "train_steps_per_second": 0.121
+}

trainer_log.jsonl

@@ -0,0 +1,21 @@
+{"current_steps": 10, "total_steps": 200, "loss": 2.4048, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9692208514878444e-05, "epoch": 4.0, "percentage": 5.0, "elapsed_time": "0:01:23", "remaining_time": "0:26:25"}
+{"current_steps": 20, "total_steps": 200, "loss": 1.6571, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.877641290737884e-05, "epoch": 8.0, "percentage": 10.0, "elapsed_time": "0:02:47", "remaining_time": "0:25:03"}
+{"current_steps": 30, "total_steps": 200, "loss": 1.088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.72751631047092e-05, "epoch": 12.0, "percentage": 15.0, "elapsed_time": "0:04:09", "remaining_time": "0:23:34"}
+{"current_steps": 40, "total_steps": 200, "loss": 0.7735, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.522542485937369e-05, "epoch": 16.0, "percentage": 20.0, "elapsed_time": "0:05:31", "remaining_time": "0:22:07"}
+{"current_steps": 50, "total_steps": 200, "loss": 0.6017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.267766952966369e-05, "epoch": 20.0, "percentage": 25.0, "elapsed_time": "0:06:54", "remaining_time": "0:20:44"}
+{"current_steps": 60, "total_steps": 200, "loss": 0.4956, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.969463130731183e-05, "epoch": 24.0, "percentage": 30.0, "elapsed_time": "0:08:16", "remaining_time": "0:19:17"}
+{"current_steps": 70, "total_steps": 200, "loss": 0.4105, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.634976249348867e-05, "epoch": 28.0, "percentage": 35.0, "elapsed_time": "0:09:38", "remaining_time": "0:17:53"}
+{"current_steps": 80, "total_steps": 200, "loss": 0.3463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.272542485937369e-05, "epoch": 32.0, "percentage": 40.0, "elapsed_time": "0:11:00", "remaining_time": "0:16:31"}
+{"current_steps": 90, "total_steps": 200, "loss": 0.2862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8910861626005776e-05, "epoch": 36.0, "percentage": 45.0, "elapsed_time": "0:12:24", "remaining_time": "0:15:09"}
+{"current_steps": 100, "total_steps": 200, "loss": 0.2345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 40.0, "percentage": 50.0, "elapsed_time": "0:13:46", "remaining_time": "0:13:46"}
+{"current_steps": 110, "total_steps": 200, "loss": 0.1905, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1089138373994223e-05, "epoch": 44.0, "percentage": 55.0, "elapsed_time": "0:15:08", "remaining_time": "0:12:23"}
+{"current_steps": 120, "total_steps": 200, "loss": 0.1554, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7274575140626318e-05, "epoch": 48.0, "percentage": 60.0, "elapsed_time": "0:16:30", "remaining_time": "0:11:00"}
+{"current_steps": 130, "total_steps": 200, "loss": 0.1269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3650237506511331e-05, "epoch": 52.0, "percentage": 65.0, "elapsed_time": "0:17:53", "remaining_time": "0:09:37"}
+{"current_steps": 140, "total_steps": 200, "loss": 0.1071, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0305368692688174e-05, "epoch": 56.0, "percentage": 70.0, "elapsed_time": "0:19:15", "remaining_time": "0:08:15"}
+{"current_steps": 150, "total_steps": 200, "loss": 0.0921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.3223304703363135e-06, "epoch": 60.0, "percentage": 75.0, "elapsed_time": "0:20:38", "remaining_time": "0:06:52"}
+{"current_steps": 160, "total_steps": 200, "loss": 0.0832, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7745751406263165e-06, "epoch": 64.0, "percentage": 80.0, "elapsed_time": "0:22:01", "remaining_time": "0:05:30"}
+{"current_steps": 170, "total_steps": 200, "loss": 0.0777, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7248368952908053e-06, "epoch": 68.0, "percentage": 85.0, "elapsed_time": "0:23:24", "remaining_time": "0:04:07"}
+{"current_steps": 180, "total_steps": 200, "loss": 0.0739, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2235870926211619e-06, "epoch": 72.0, "percentage": 90.0, "elapsed_time": "0:24:46", "remaining_time": "0:02:45"}
+{"current_steps": 190, "total_steps": 200, "loss": 0.0714, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.077914851215585e-07, "epoch": 76.0, "percentage": 95.0, "elapsed_time": "0:26:08", "remaining_time": "0:01:22"}
+{"current_steps": 200, "total_steps": 200, "loss": 0.072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 80.0, "percentage": 100.0, "elapsed_time": "0:27:30", "remaining_time": "0:00:00"}
+{"current_steps": 200, "total_steps": 200, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 80.0, "percentage": 100.0, "elapsed_time": "0:27:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 80.0,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.9692208514878444e-05,
+      "loss": 2.4048,
+      "step": 10
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 1.6571,
+      "step": 20
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 1.088,
+      "step": 30
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.7735,
+      "step": 40
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.6017,
+      "step": 50
+    },
+    {
+      "epoch": 24.0,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.4956,
+      "step": 60
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.4105,
+      "step": 70
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.3463,
+      "step": 80
+    },
+    {
+      "epoch": 36.0,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 0.2862,
+      "step": 90
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.2345,
+      "step": 100
+    },
+    {
+      "epoch": 44.0,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 0.1905,
+      "step": 110
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 0.1554,
+      "step": 120
+    },
+    {
+      "epoch": 52.0,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 0.1269,
+      "step": 130
+    },
+    {
+      "epoch": 56.0,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 0.1071,
+      "step": 140
+    },
+    {
+      "epoch": 60.0,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0921,
+      "step": 150
+    },
+    {
+      "epoch": 64.0,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.0832,
+      "step": 160
+    },
+    {
+      "epoch": 68.0,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.0777,
+      "step": 170
+    },
+    {
+      "epoch": 72.0,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.0739,
+      "step": 180
+    },
+    {
+      "epoch": 76.0,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.0714,
+      "step": 190
+    },
+    {
+      "epoch": 80.0,
+      "learning_rate": 0.0,
+      "loss": 0.072,
+      "step": 200
+    },
+    {
+      "epoch": 80.0,
+      "step": 200,
+      "total_flos": 3.758484756417741e+16,
+      "train_loss": 0.4674161618947983,
+      "train_runtime": 1650.9942,
+      "train_samples_per_second": 4.846,
+      "train_steps_per_second": 0.121
+    }
+  ],
+  "max_steps": 200,
+  "num_train_epochs": 100,
+  "total_flos": 3.758484756417741e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04af69d64033227c400b4e671a8f03858f8738666ac1b19e83577ed306cf5f52
+size 4219