Training in progress, step 100

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_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 sha256:93d0c39180108199a73a3a36aab0bb63210e11576be474629935deed05ebc6f6
+size 60599872

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

angle.config

@@ -0,0 +1,27 @@
+{
+  "model_name_or_path": "Qwen/Qwen1.5-0.5B",
+  "max_length": 75,
+  "model_kwargs": {},
+  "pooling_strategy": "avg",
+  "lora_config_kwargs": {
+    "task_type": "CAUSAL_LM",
+    "r": 32,
+    "lora_alpha": 32,
+    "lora_dropout": 0.1,
+    "bias": "none",
+    "target_modules": [
+      "k_proj",
+      "v_proj",
+      "o_proj",
+      "up_proj",
+      "down_proj",
+      "q_proj",
+      "gate_proj"
+    ]
+  },
+  "is_llm": 1,
+  "apply_billm": 1,
+  "billm_model_class": "Qwen2ForCausalLM",
+  "apply_lora": 1,
+  "tokenizer_padding_side": null
+}

runs/Apr24_09-53-03_beta-M12SWA-TF/events.out.tfevents.1713923586.beta-M12SWA-TF.1504211.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fbb8eb5c5a1648101330ab6ba51183c0340c8cbcd133df510fc9b17ab952348
+size 13335

runs/Apr24_10-55-09_beta-M12SWA-TF/events.out.tfevents.1713927310.beta-M12SWA-TF.1506031.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4bf30d3909ad1183ed7c00803e4244bb1b71417dcd757265fe16ceced1210e
+size 4136

runs/Apr24_10-56-07_beta-M12SWA-TF/events.out.tfevents.1713927371.beta-M12SWA-TF.1506519.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3de427cde0881781bc04079f0b5aed3da9ad403d2c7ee5c2278a3d71a2b3c7d5
+size 7248

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c126e947453c98ae2874e51c8a9e30cb4053abdc05af3a74df5c79a95bb7ec42
+size 4539