Hugging Face's logo

BaoLocTown
/
sft-mistral-7b-v01-v1

Text Generation
Transformers
Safetensors
mistral
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
BaoLocTown commited on
Commit
30bce3d
•
1 Parent(s): accfa1a

Model save

Browse files
Files changed (5) hide show
  1. adapter_model.safetensors +1 -1
  2. all_results.json +6 -6
  3. eval_results.json +3 -3
  4. train_results.json +3 -3
  5. trainer_state.json +12 -12
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed3d959cc6ff0319ebeb80281e439f2cba867f20ea34b65ae440688b5b8c75ef
3
  size 872450448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f9f18326b14f78e6e5baa1cd8a08bf2c26653a7be354015978e694797c82eb
3
  size 872450448
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 1.45,
3
  "eval_loss": 0.491791695356369,
4
- "eval_runtime": 105.74,
5
  "eval_samples": 852,
6
- "eval_samples_per_second": 8.058,
7
- "eval_steps_per_second": 2.014,
8
  "train_loss": 0.305820442848905,
9
- "train_runtime": 6666.1209,
10
  "train_samples": 7665,
11
- "train_samples_per_second": 2.3,
12
- "train_steps_per_second": 0.575
13
  }
 
1
  {
2
  "epoch": 1.45,
3
  "eval_loss": 0.491791695356369,
4
+ "eval_runtime": 106.5509,
5
  "eval_samples": 852,
6
+ "eval_samples_per_second": 7.996,
7
+ "eval_steps_per_second": 1.999,
8
  "train_loss": 0.305820442848905,
9
+ "train_runtime": 6698.0985,
10
  "train_samples": 7665,
11
+ "train_samples_per_second": 2.289,
12
+ "train_steps_per_second": 0.572
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.45,
3
  "eval_loss": 0.491791695356369,
4
- "eval_runtime": 105.74,
5
  "eval_samples": 852,
6
- "eval_samples_per_second": 8.058,
7
- "eval_steps_per_second": 2.014
8
  }
 
1
  {
2
  "epoch": 1.45,
3
  "eval_loss": 0.491791695356369,
4
+ "eval_runtime": 106.5509,
5
  "eval_samples": 852,
6
+ "eval_samples_per_second": 7.996,
7
+ "eval_steps_per_second": 1.999
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.45,
3
  "train_loss": 0.305820442848905,
4
- "train_runtime": 6666.1209,
5
  "train_samples": 7665,
6
- "train_samples_per_second": 2.3,
7
- "train_steps_per_second": 0.575
8
  }
 
1
  {
2
  "epoch": 1.45,
3
  "train_loss": 0.305820442848905,
4
+ "train_runtime": 6698.0985,
5
  "train_samples": 7665,
6
+ "train_samples_per_second": 2.289,
7
+ "train_steps_per_second": 0.572
8
  }
trainer_state.json CHANGED
@@ -317,9 +317,9 @@
317
  {
318
  "epoch": 0.26,
319
  "eval_loss": 0.5063315629959106,
320
- "eval_runtime": 105.7257,
321
- "eval_samples_per_second": 8.059,
322
- "eval_steps_per_second": 2.015,
323
  "step": 500
324
  },
325
  {
@@ -625,9 +625,9 @@
625
  {
626
  "epoch": 1.07,
627
  "eval_loss": 0.48916903138160706,
628
- "eval_runtime": 106.4721,
629
- "eval_samples_per_second": 8.002,
630
- "eval_steps_per_second": 2.001,
631
  "step": 1000
632
  },
633
  {
@@ -933,9 +933,9 @@
933
  {
934
  "epoch": 1.33,
935
  "eval_loss": 0.4950372576713562,
936
- "eval_runtime": 105.7937,
937
- "eval_samples_per_second": 8.053,
938
- "eval_steps_per_second": 2.013,
939
  "step": 1500
940
  },
941
  {
@@ -1069,9 +1069,9 @@
1069
  "step": 1718,
1070
  "total_flos": 3.091617473007452e+17,
1071
  "train_loss": 0.305820442848905,
1072
- "train_runtime": 6666.1209,
1073
- "train_samples_per_second": 2.3,
1074
- "train_steps_per_second": 0.575
1075
  }
1076
  ],
1077
  "logging_steps": 10,
 
317
  {
318
  "epoch": 0.26,
319
  "eval_loss": 0.5063315629959106,
320
+ "eval_runtime": 106.6235,
321
+ "eval_samples_per_second": 7.991,
322
+ "eval_steps_per_second": 1.998,
323
  "step": 500
324
  },
325
  {
 
625
  {
626
  "epoch": 1.07,
627
  "eval_loss": 0.48916903138160706,
628
+ "eval_runtime": 106.511,
629
+ "eval_samples_per_second": 7.999,
630
+ "eval_steps_per_second": 2.0,
631
  "step": 1000
632
  },
633
  {
 
933
  {
934
  "epoch": 1.33,
935
  "eval_loss": 0.4950372576713562,
936
+ "eval_runtime": 106.6983,
937
+ "eval_samples_per_second": 7.985,
938
+ "eval_steps_per_second": 1.996,
939
  "step": 1500
940
  },
941
  {
 
1069
  "step": 1718,
1070
  "total_flos": 3.091617473007452e+17,
1071
  "train_loss": 0.305820442848905,
1072
+ "train_runtime": 6698.0985,
1073
+ "train_samples_per_second": 2.289,
1074
+ "train_steps_per_second": 0.572
1075
  }
1076
  ],
1077
  "logging_steps": 10,