Hugging Face's logo

pkarypis
/
zephyr-7b-sft-filtered-0.7

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
pkarypis commited on
Commit
55c8a00
·
1 Parent(s): 245d0d5

Model save

Browse files
Files changed (10) hide show
  1. all_results.json +7 -7
  2. eval_results.json +4 -4
  3. model-00001-of-00003.safetensors +1 -1
  4. model-00002-of-00003.safetensors +1 -1
  5. model-00003-of-00003.safetensors +1 -1
  6. runs/Nov16_23-34-29_aga44/events.out.tfevents.1700199363.aga44.653402.0 +3 -0
  7. runs/Nov16_23-34-29_aga44/events.out.tfevents.1700207265.aga44.653402.1 +3 -0
  8. train_results.json +3 -3
  9. trainer_state.json +7 -7
  10. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 0.66,
3
- "eval_loss": 0.9370002746582031,
4
- "eval_runtime": 201.2462,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 114.834,
7
- "eval_steps_per_second": 0.452,
8
- "train_loss": 0.9872982885645724,
9
- "train_runtime": 7675.6494,
10
  "train_samples": 200979,
11
- "train_samples_per_second": 26.184,
12
  "train_steps_per_second": 0.051
13
  }
 
1
  {
2
  "epoch": 0.66,
3
+ "eval_loss": 0.9369996786117554,
4
+ "eval_runtime": 197.3355,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 117.11,
7
+ "eval_steps_per_second": 0.461,
8
+ "train_loss": 0.9872269639566941,
9
+ "train_runtime": 7705.3811,
10
  "train_samples": 200979,
11
+ "train_samples_per_second": 26.083,
12
  "train_steps_per_second": 0.051
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.66,
3
- "eval_loss": 0.9370002746582031,
4
- "eval_runtime": 201.2462,
5
  "eval_samples": 23110,
6
- "eval_samples_per_second": 114.834,
7
- "eval_steps_per_second": 0.452
8
  }
 
1
  {
2
  "epoch": 0.66,
3
+ "eval_loss": 0.9369996786117554,
4
+ "eval_runtime": 197.3355,
5
  "eval_samples": 23110,
6
+ "eval_samples_per_second": 117.11,
7
+ "eval_steps_per_second": 0.461
8
  }
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4011c1adf418c5a47080bb2003b5bb457ab30b253e4c525dfc127e91104cb927
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca04b671100e60fd6c5c7763ee1a39efab1868d6064904f0c03bdec85d139ff7
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:edebd0da5107a8961be0720f9fa57324d4ec4d0907f063773ec93eeb51eac6b3
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e10d993181d2d969ef7fb039ffbb9339e1f7bce8755fe2eab226c21a2efff6c
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5e7397c5d2a68b30e9b5f447fb12c664bb3dffe724434eca54bf23d1aa274cb1
3
  size 4540516344
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a72488d3db8ac37494004a8cad4d9c41331fcf75cecf9f104d1c281bfcca4be8
3
  size 4540516344
runs/Nov16_23-34-29_aga44/events.out.tfevents.1700199363.aga44.653402.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c15877bb9394191a2aa11c4db9e099e12b045ba7cbcb56d9756c019244fe375f
3
+ size 5040
runs/Nov16_23-34-29_aga44/events.out.tfevents.1700207265.aga44.653402.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217068b110e66f0d455103f19ab96f1635b76194df0e6f11ce663edbe7daf4e7
3
+ size 359
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.66,
3
- "train_loss": 0.9872982885645724,
4
- "train_runtime": 7675.6494,
5
  "train_samples": 200979,
6
- "train_samples_per_second": 26.184,
7
  "train_steps_per_second": 0.051
8
  }
 
1
  {
2
  "epoch": 0.66,
3
+ "train_loss": 0.9872269639566941,
4
+ "train_runtime": 7705.3811,
5
  "train_samples": 200979,
6
+ "train_samples_per_second": 26.083,
7
  "train_steps_per_second": 0.051
8
  }
trainer_state.json CHANGED
@@ -16,19 +16,19 @@
16
  },
17
  {
18
  "epoch": 0.66,
19
- "eval_loss": 0.9371677041053772,
20
- "eval_runtime": 201.1342,
21
- "eval_samples_per_second": 114.898,
22
- "eval_steps_per_second": 0.452,
23
  "step": 261
24
  },
25
  {
26
  "epoch": 0.66,
27
  "step": 261,
28
  "total_flos": 436818306662400.0,
29
- "train_loss": 0.9872982885645724,
30
- "train_runtime": 7675.6494,
31
- "train_samples_per_second": 26.184,
32
  "train_steps_per_second": 0.051
33
  }
34
  ],
 
16
  },
17
  {
18
  "epoch": 0.66,
19
+ "eval_loss": 0.9371662735939026,
20
+ "eval_runtime": 200.9763,
21
+ "eval_samples_per_second": 114.989,
22
+ "eval_steps_per_second": 0.453,
23
  "step": 261
24
  },
25
  {
26
  "epoch": 0.66,
27
  "step": 261,
28
  "total_flos": 436818306662400.0,
29
+ "train_loss": 0.9872269639566941,
30
+ "train_runtime": 7705.3811,
31
+ "train_samples_per_second": 26.083,
32
  "train_steps_per_second": 0.051
33
  }
34
  ],
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2466280ec14a7c5eae86f8af39405e9adc8ac3a1ce712e01467f4a9164c2d2a
3
  size 5179
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa6ca9f679e4ea97be68b3366a80221bef18dd03c280ab8642a8b7fe95cbd259
3
  size 5179