Model save

README.md

@@ -3,15 +3,12 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
 datasets:
-- HuggingFaceH4/ultrachat_200k
+- generator
 model-index:
 - name: zephyr-7b-sft-full
   results: []
@@ -22,9 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.9420
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
 
 ## Model description
 
@@ -51,21 +46,18 @@ The following hyperparameters were used during training:
 - num_devices: 8
 - total_train_batch_size: 128
 - total_eval_batch_size: 64
-- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
 - num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 0.9183        | 1.0   | 1084 | 0.9420          |
 
 
 ### Framework versions
 
-- Transformers 4.47.1
+- Transformers 4.45.2
 - Pytorch 2.2.2+rocm5.7
 - Datasets 3.2.0
-- Tokenizers 0.21.0
+- Tokenizers 0.20.3

all_results.json

@@ -6,9 +6,9 @@
     "eval_samples_per_second": 17.836,
     "eval_steps_per_second": 0.279,
     "total_flos": 453935093514240.0,
-    "train_loss": 0.9848188322408613,
-    "train_runtime": 34384.388,
+    "train_loss": 0.0,
+    "train_runtime": 0.0102,
     "train_samples": 207864,
-    "train_samples_per_second": 4.033,
-    "train_steps_per_second": 0.032
+    "train_samples_per_second": 13581178.092,
+    "train_steps_per_second": 106152.682
 }

config.json

@@ -21,7 +21,7 @@
   "sliding_window": 4096,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.47.1",
-  "use_cache": true,
+  "transformers_version": "4.45.2",
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.47.1"
+  "transformers_version": "4.45.2"
 }

runs/Jan06_13-29-45_nid002982/events.out.tfevents.1736142626.nid002982.1881012.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab50543af028bbd682a41ae742d225d04468aaf14b9472d78ea73af8292459a
+size 5872

tokenizer_config.json

@@ -33,7 +33,6 @@
   "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": "</s>",
-  "extra_special_tokens": {},
   "legacy": false,
   "model_max_length": 2048,
   "pad_token": "</s>",

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
     "total_flos": 453935093514240.0,
-    "train_loss": 0.9848188322408613,
-    "train_runtime": 34384.388,
+    "train_loss": 0.0,
+    "train_runtime": 0.0102,
     "train_samples": 207864,
-    "train_samples_per_second": 4.033,
-    "train_steps_per_second": 0.032
+    "train_samples_per_second": 13581178.092,
+    "train_steps_per_second": 106152.682
 }

trainer_state.json

@@ -1527,22 +1527,14 @@
       "loss": 0.9183,
       "step": 1080
     },
-    {
-      "epoch": 1.0,
-      "eval_loss": 0.9419716000556946,
-      "eval_runtime": 896.1794,
-      "eval_samples_per_second": 17.128,
-      "eval_steps_per_second": 0.268,
-      "step": 1084
-    },
     {
       "epoch": 1.0,
       "step": 1084,
       "total_flos": 453935093514240.0,
-      "train_loss": 0.9848188322408613,
-      "train_runtime": 34384.388,
-      "train_samples_per_second": 4.033,
-      "train_steps_per_second": 0.032
+      "train_loss": 0.0,
+      "train_runtime": 0.0102,
+      "train_samples_per_second": 13581178.092,
+      "train_steps_per_second": 106152.682
     }
   ],
   "logging_steps": 5,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fb7b163f0f2760ee586d53670c0b581adf6604a94b96f942bb89e81c5d0ea87
-size 7160
+oid sha256:334a53df05940f5e0bacaf2f760dcc46ccd9e16ee2d1e3852cbcffc37806bf1f
+size 7032