Training in progress, step 50

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/CodeLlama-7b-Instruct-hf",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df09833f347b02053eabab8c51d7622fa800e6547da018ca3b27e743c5422c3d
+size 40036488

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "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_config.json

@@ -0,0 +1,87 @@
+{
+  "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
+    },
+    "32007": {
+      "content": "▁<PRE>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "▁<SUF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "▁<MID>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "▁<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "▁<PRE>",
+    "▁<MID>",
+    "▁<SUF>",
+    "▁<EOT>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if loop.index0 == 0 and system_message is defined %}{% set content = '<<SYS>>\n' + system_message + '\n<</SYS>>\n\n' + message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ '<s>' + '[INST] ' + content + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content + ' ' + '</s>' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "eot_token": "▁<EOT>",
+  "extra_special_tokens": {},
+  "fill_token": "<FILL_ME>",
+  "legacy": null,
+  "middle_token": "▁<MID>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "prefix_token": "▁<PRE>",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "suffix_token": "▁<SUF>",
+  "tokenizer_class": "CodeLlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_log.jsonl

@@ -0,0 +1,6 @@
+{"current_steps": 10, "total_steps": 1500, "loss": 7.3904, "accuracy": 0.550000011920929, "learning_rate": 4.999451708687114e-06, "epoch": 0.007248346470961312, "percentage": 0.67, "elapsed_time": "0:01:20", "remaining_time": "3:18:57", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 20, "total_steps": 1500, "loss": 7.3756, "accuracy": 0.574999988079071, "learning_rate": 4.997807075247147e-06, "epoch": 0.014496692941922623, "percentage": 1.33, "elapsed_time": "0:02:34", "remaining_time": "3:10:59", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 30, "total_steps": 1500, "loss": 7.451, "accuracy": 0.4375, "learning_rate": 4.9950668210706795e-06, "epoch": 0.021745039412883936, "percentage": 2.0, "elapsed_time": "0:03:48", "remaining_time": "3:06:12", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 40, "total_steps": 1500, "loss": 7.3892, "accuracy": 0.6499999761581421, "learning_rate": 4.9912321481237616e-06, "epoch": 0.028993385883845247, "percentage": 2.67, "elapsed_time": "0:05:02", "remaining_time": "3:04:08", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 1500, "loss": 7.5171, "accuracy": 0.512499988079071, "learning_rate": 4.986304738420684e-06, "epoch": 0.03624173235480656, "percentage": 3.33, "elapsed_time": "0:06:19", "remaining_time": "3:03:27", "throughput": "0.00", "total_tokens": 0}
+{"current_steps": 50, "total_steps": 1500, "eval_loss": 0.9120001792907715, "epoch": 0.03624173235480656, "percentage": 3.33, "elapsed_time": "0:06:50", "remaining_time": "3:18:26", "throughput": "0.00", "total_tokens": 0}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91b9d0e6e8c92ae4a2c435b81fedf969ba2fc02907285b004770a8256166d71d
+size 7224