Model save

README.md

@@ -1,6 +1,5 @@
 ---
-license: other
-base_model: Qwen/Qwen1.5-0.5B-Chat
+base_model: HuggingFaceH4/qwen-1.5-0.5b-ift
 tags:
 - generated_from_trainer
 model-index:
@@ -13,7 +12,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # dummy-model
 
-This model is a fine-tuned version of [Qwen/Qwen1.5-0.5B-Chat](https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat) on the None dataset.
+This model is a fine-tuned version of [HuggingFaceH4/qwen-1.5-0.5b-ift](https://huggingface.co/HuggingFaceH4/qwen-1.5-0.5b-ift) on the None dataset.
 
 ## Model description
 
@@ -37,9 +36,9 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 42
 - distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 16
-- total_eval_batch_size: 16
+- num_devices: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - lr_scheduler_warmup_ratio: 0.1

all_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.0,
     "train_loss": 0.6931471824645996,
-    "train_runtime": 10.6478,
-    "train_samples_per_second": 1.503,
-    "train_steps_per_second": 0.094
+    "train_runtime": 22.1254,
+    "train_samples_per_second": 2.893,
+    "train_steps_per_second": 0.045
 }

config.json

@@ -1,11 +1,11 @@
 {
-  "_name_or_path": "Qwen/Qwen1.5-0.5B-Chat",
+  "_name_or_path": "HuggingFaceH4/qwen-1.5-0.5b-ift",
   "architectures": [
     "Qwen2ForCausalLM"
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 151643,
-  "eos_token_id": 151645,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
   "hidden_size": 1024,
   "initializer_range": 0.02,

generation_config.json

@@ -1,11 +1,6 @@
 {
   "bos_token_id": 151643,
-  "do_sample": true,
-  "eos_token_id": [
-    151645,
-    151643
-  ],
-  "repetition_penalty": 1.1,
-  "top_p": 0.8,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
   "transformers_version": "4.37.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae33e290572bff9d1123269a1d8344f47b1b46c2ce43e057553a7a6da3f2ebc
+oid sha256:17a9586a6a3cf563746cd9081937545a92e46ed2a0edaa8b7ea7386f4d3785cb
 size 928008104

special_tokens_map.json

@@ -4,7 +4,7 @@
     "<|im_end|>"
   ],
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "<|endoftext|>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer_config.json

@@ -31,9 +31,9 @@
     "<|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']}}{% if (loop.last and add_generation_prompt) or not loop.last %}{{ '<|im_end|>' + '\n'}}{% endif %}{% endfor %}{% if add_generation_prompt and messages[-1]['role'] != 'assistant' %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "<|endoftext|>",
   "errors": "replace",
   "model_max_length": 32768,
   "pad_token": "<|endoftext|>",

train_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.0,
     "train_loss": 0.6931471824645996,
-    "train_runtime": 10.6478,
-    "train_samples_per_second": 1.503,
-    "train_steps_per_second": 0.094
+    "train_runtime": 22.1254,
+    "train_samples_per_second": 2.893,
+    "train_steps_per_second": 0.045
 }

trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00032133676092544985,
+  "epoch": 0.0012853470437017994,
   "eval_steps": 500,
   "global_step": 1,
   "is_hyper_param_search": false,
@@ -11,10 +11,10 @@
     {
       "epoch": 0.0,
       "learning_rate": 0.0,
-      "logits/generated": -1.854715347290039,
-      "logits/real": -1.7835123538970947,
-      "logps/generated": -667.4280395507812,
-      "logps/real": -384.09954833984375,
+      "logits/generated": -1.3129560947418213,
+      "logits/real": -0.6997354626655579,
+      "logps/generated": -609.5880126953125,
+      "logps/real": -542.52783203125,
       "loss": 0.6931,
       "rewards/accuracies": 0.0,
       "rewards/generated": 0.0,
@@ -27,9 +27,9 @@
       "step": 1,
       "total_flos": 0.0,
       "train_loss": 0.6931471824645996,
-      "train_runtime": 10.6478,
-      "train_samples_per_second": 1.503,
-      "train_steps_per_second": 0.094
+      "train_runtime": 22.1254,
+      "train_samples_per_second": 2.893,
+      "train_steps_per_second": 0.045
     }
   ],
   "logging_steps": 10,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:167e5554608d0755ce3da2e17f4ed94b3e74641b26d088bb4c0fefde26f4c2d5
-size 5880
+oid sha256:3b9cec95750bdee2bcf6a04a483459188304950ed8dc641aec56433fae8350ad
+size 5944