Training in progress, step 3000

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "MathSymbol/BasicSFT_1.8_Pretrain_Lightning",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5504,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 16,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcb9e249858be8cd1761d787a5eab4c07eeae570ff35e838e331a6da03f1806b
+size 3673690696

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 +1,44 @@
+{
+  "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": "{% set system_message = 'You are a Math Teacher.Your goal is to understand a math word problem. Then recognize and distinguish which problem it is and then define the variables (if needed) and formulate the problem as it kind then transform it to Symbolic Form.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Question: ' + content + ' \\n Answer: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,12 @@
+{"current_steps": 300, "total_steps": 9120, "loss": 0.7143, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3e-05, "epoch": 0.03289383514706285, "percentage": 3.29, "elapsed_time": "0:11:46", "remaining_time": "5:46:15"}
+{"current_steps": 600, "total_steps": 9120, "loss": 0.2219, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.998339850669331e-05, "epoch": 0.0657876702941257, "percentage": 6.58, "elapsed_time": "0:21:56", "remaining_time": "5:11:39"}
+{"current_steps": 900, "total_steps": 9120, "loss": 0.2074, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9734816848192624e-05, "epoch": 0.09868150544118856, "percentage": 9.87, "elapsed_time": "0:33:43", "remaining_time": "5:08:02"}
+{"current_steps": 1200, "total_steps": 9120, "loss": 0.1906, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.9190839785031474e-05, "epoch": 0.1315753405882514, "percentage": 13.16, "elapsed_time": "0:43:50", "remaining_time": "4:49:22"}
+{"current_steps": 1500, "total_steps": 9120, "loss": 0.1923, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.835796376008569e-05, "epoch": 0.16446917573531428, "percentage": 16.45, "elapsed_time": "0:55:43", "remaining_time": "4:43:07"}
+{"current_steps": 1500, "total_steps": 9120, "loss": null, "eval_loss": 0.1849033087491989, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.16446917573531428, "percentage": 16.45, "elapsed_time": "0:55:43", "remaining_time": "4:43:07"}
+{"current_steps": 1800, "total_steps": 9120, "loss": 0.1839, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.7246135390382216e-05, "epoch": 0.19736301088237712, "percentage": 19.74, "elapsed_time": "1:07:10", "remaining_time": "4:33:08"}
+{"current_steps": 2100, "total_steps": 9120, "loss": 0.1938, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.586863267968384e-05, "epoch": 0.23025684602944, "percentage": 23.03, "elapsed_time": "1:19:01", "remaining_time": "4:24:08"}
+{"current_steps": 2400, "total_steps": 9120, "loss": 0.1863, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.4241906446007296e-05, "epoch": 0.2631506811765028, "percentage": 26.32, "elapsed_time": "1:29:09", "remaining_time": "4:09:38"}
+{"current_steps": 2700, "total_steps": 9120, "loss": 0.1797, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.238538385782601e-05, "epoch": 0.2960445163235657, "percentage": 29.61, "elapsed_time": "1:40:55", "remaining_time": "3:59:59"}
+{"current_steps": 3000, "total_steps": 9120, "loss": 0.176, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.032123642522486e-05, "epoch": 0.32893835147062855, "percentage": 32.89, "elapsed_time": "1:51:07", "remaining_time": "3:46:41"}
+{"current_steps": 3000, "total_steps": 9120, "loss": null, "eval_loss": 0.1760552078485489, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.32893835147062855, "percentage": 32.89, "elapsed_time": "1:51:07", "remaining_time": "3:46:41"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e87d1dec697e26f8674bebb378e7add472d9862f152df6bbd1c35b83737657ec
+size 5176