Model save

README.md

@@ -1,16 +1,12 @@
 ---
 license: apache-2.0
-base_model: mistralai/Mistral-7B-v0.1
+base_model: TinyLlama/TinyLlama-1.1B-step-50K-105b
 tags:
-- alignment-handbook
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- HuggingFaceH4/ultrachat_200k
+- generator
 model-index:
 - name: zephyr-7b-sft-full
   results: []
@@ -21,9 +17,9 @@ 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.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-step-50K-105b](https://huggingface.co/TinyLlama/TinyLlama-1.1B-step-50K-105b) on the generator dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0320
+- Loss: 1.3203
 
 ## Model description
 
@@ -59,7 +55,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0197        | 1.0   | 3488 | 1.0320          |
+| 1.3518        | 1.0   | 3653 | 1.3203          |
 
 
 ### Framework versions

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.0320301055908203,
-    "eval_runtime": 4528.944,
-    "eval_samples": 124719,
-    "eval_samples_per_second": 18.466,
-    "eval_steps_per_second": 1.154,
-    "total_flos": 182579059752960.0,
-    "train_loss": 0.025541797006895784,
-    "train_runtime": 4827.4873,
+    "total_flos": 66190143651840.0,
+    "train_loss": 1.3573657579367173,
+    "train_runtime": 8062.8425,
     "train_samples": 83145,
-    "train_samples_per_second": 11.557,
-    "train_steps_per_second": 0.723
+    "train_samples_per_second": 7.249,
+    "train_steps_per_second": 0.453
 }

generation_config.json

@@ -1,6 +1,7 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.41.2"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd1cc3ab3138978cfaabb13b4c070fdf8abcd5746d969d43dcdeb7894d456d8d
+oid sha256:255ed0475eb2e61e886a1e01ffff1f186d6d7e3b2a2a6ade35fdd64222d797d8
 size 2200119864

runs/Jul02_08-04-09_ishant-gpu/events.out.tfevents.1719908314.ishant-gpu.55464.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57cba252731d0f3ade0b6f9746c0b9686cdcdd7afd93215501edf8041131a582
-size 155689
+oid sha256:85986aec543252f2f13c69541395d5fae79ba83dabfb45ad655140da39f539f8
+size 159690

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 1.0,
-    "total_flos": 182579059752960.0,
-    "train_loss": 0.025541797006895784,
-    "train_runtime": 4827.4873,
+    "total_flos": 66190143651840.0,
+    "train_loss": 1.3573657579367173,
+    "train_runtime": 8062.8425,
     "train_samples": 83145,
-    "train_samples_per_second": 11.557,
-    "train_steps_per_second": 0.723
+    "train_samples_per_second": 7.249,
+    "train_steps_per_second": 0.453
 }