Training in progress, step 30

added_tokens.json

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

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Qwen/Qwen1.5-1.8B",
+  "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": "4.39.3",
+  "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 sha256:55c79e77860816fc69e2fec4cb5801afdd1af0a33532210ea4c187a507b9e991
+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": "{% 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 +1,5 @@
+{"current_steps": 10, "total_steps": 129, "loss": 1.6271, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0000000000000002e-06, "epoch": 0.08, "percentage": 7.75, "elapsed_time": "0:01:49", "remaining_time": "0:21:47"}
+{"current_steps": 20, "total_steps": 129, "loss": 1.5888, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0000000000000003e-06, "epoch": 0.16, "percentage": 15.5, "elapsed_time": "0:02:02", "remaining_time": "0:11:10"}
+{"current_steps": 30, "total_steps": 129, "loss": 1.6088, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-06, "epoch": 0.23, "percentage": 23.26, "elapsed_time": "0:02:16", "remaining_time": "0:07:28"}
+{"current_steps": 30, "total_steps": 129, "loss": null, "eval_loss": 1.6200140714645386, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.23, "percentage": 23.26, "elapsed_time": "0:02:16", "remaining_time": "0:07:28"}
+{"current_steps": 40, "total_steps": 129, "loss": 1.557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.000000000000001e-06, "epoch": 0.31, "percentage": 31.01, "elapsed_time": "0:02:45", "remaining_time": "0:06:08"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02bb292edf81b3301abec77493d5e806a61450dc4760dc264c424c9878fd1bd5
+size 4603