Model save

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 1.0686
+- Loss: 1.0683
 
 ## Model description
 
@@ -51,7 +51,7 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| 1.0775        | 0.26  | 31   | 1.0669          |
+| 1.0771        | 0.26  | 31   | 1.0666          |
 
 
 ### Framework versions

all_results.json

@@ -1,13 +1,13 @@
 {
     "epoch": 0.26,
-    "eval_loss": 1.06858229637146,
-    "eval_runtime": 6.5753,
+    "eval_loss": 1.0683468580245972,
+    "eval_runtime": 6.6188,
     "eval_samples": 1000,
-    "eval_samples_per_second": 152.085,
-    "eval_steps_per_second": 1.217,
-    "train_loss": 1.2061054245118172,
-    "train_runtime": 1488.8374,
+    "eval_samples_per_second": 151.085,
+    "eval_steps_per_second": 1.209,
+    "train_loss": 1.2071462215915802,
+    "train_runtime": 1490.1678,
     "train_samples": 61966,
-    "train_samples_per_second": 41.62,
+    "train_samples_per_second": 41.583,
     "train_steps_per_second": 0.081
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.26,
-    "eval_loss": 1.06858229637146,
-    "eval_runtime": 6.5753,
+    "eval_loss": 1.0683468580245972,
+    "eval_runtime": 6.6188,
     "eval_samples": 1000,
-    "eval_samples_per_second": 152.085,
-    "eval_steps_per_second": 1.217
+    "eval_samples_per_second": 151.085,
+    "eval_steps_per_second": 1.209
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7090011f379d2f31fe315762a1504972627a1d26862424eecd5e3fa12acd1ef
+oid sha256:b9807e76613b2db37f0898e9a732f39ec4491d65735a97423d0e7bfed386b4ef
 size 4943162336

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6317d911d6fe78d7147461b42b87028ba4ad576c8b41439ac8b83da846a64c3
+oid sha256:9e0abde6f22f4baadb136891b425b532d77c7c8fc09a10d5dec6441ce659c73c
 size 4999819336

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f6e3325ff22f5396df10a092b349d9ac56a5299f1f4fb0ae31a3d9368d8568e
+oid sha256:c6a2b4b503bc04ae15796eba94e15b1a94a44bd44c594d49015382134ee46383
 size 4540516344

runs/Nov18_08-54-00_j004-ds/events.out.tfevents.1700319321.j004-ds.1903041.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd536d3a0a5002fcd2c3c04ba7087d35dc6518ad8005111094efab8ab7a9ef7
+size 5921

runs/Nov18_08-54-00_j004-ds/events.out.tfevents.1700320817.j004-ds.1903041.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eb2163a1dc8a6abd142d51a2b57573820d34fec8b39027c452e7cc1d2bffbe6
+size 354

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.26,
-    "train_loss": 1.2061054245118172,
-    "train_runtime": 1488.8374,
+    "train_loss": 1.2071462215915802,
+    "train_runtime": 1490.1678,
     "train_samples": 61966,
-    "train_samples_per_second": 41.62,
+    "train_samples_per_second": 41.583,
     "train_steps_per_second": 0.081
 }

trainer_state.json

@@ -23,55 +23,55 @@
     {
       "epoch": 0.08,
       "learning_rate": 1.966483553946637e-05,
-      "loss": 1.2967,
+      "loss": 1.3001,
       "step": 10
     },
     {
       "epoch": 0.12,
       "learning_rate": 1.9251166435386837e-05,
-      "loss": 1.1809,
+      "loss": 1.1836,
       "step": 15
     },
     {
       "epoch": 0.16,
       "learning_rate": 1.868180920098644e-05,
-      "loss": 1.1281,
+      "loss": 1.1287,
       "step": 20
     },
     {
       "epoch": 0.21,
       "learning_rate": 1.796634556457236e-05,
-      "loss": 1.0929,
+      "loss": 1.093,
       "step": 25
     },
     {
       "epoch": 0.25,
       "learning_rate": 1.7116816083045603e-05,
-      "loss": 1.0775,
+      "loss": 1.0771,
       "step": 30
     },
     {
       "epoch": 0.26,
-      "eval_loss": 1.066861629486084,
-      "eval_runtime": 6.7745,
-      "eval_samples_per_second": 147.613,
-      "eval_steps_per_second": 1.181,
+      "eval_loss": 1.0666340589523315,
+      "eval_runtime": 6.8061,
+      "eval_samples_per_second": 146.926,
+      "eval_steps_per_second": 1.175,
       "step": 31
     },
     {
       "epoch": 0.26,
       "step": 31,
       "total_flos": 50905428787200.0,
-      "train_loss": 1.2061054245118172,
-      "train_runtime": 1488.8374,
-      "train_samples_per_second": 41.62,
+      "train_loss": 1.2071462215915802,
+      "train_runtime": 1490.1678,
+      "train_samples_per_second": 41.583,
       "train_steps_per_second": 0.081
     }
   ],
   "logging_steps": 5,
   "max_steps": 121,
   "num_train_epochs": 1,
-  "save_steps": 500,
+  "save_steps": 50,
   "total_flos": 50905428787200.0,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39cc359ce3258b2e63e327c39e82644b160cae8a11afa9e752dd762b8c47d000
+oid sha256:a76446f98f2efebc3742cb697a455c19f8e656d97426c4e9ce3a189d1b2c484c
 size 5624