Hugging Face's logo

hllj
/
non-qa-sft-zephyr-7b-beta-v1

Text Generation
Transformers
TensorBoard
Safetensors
mistral
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Metrics Community
hllj commited on
Commit
adc5339
·
1 Parent(s): 5699431

Training in progress, step 25

Browse files
Files changed (8) hide show
  1. adapter_config.json +1 -1
  2. adapter_model.bin +1 -1
  3. adapter_model.safetensors +1 -1
  4. all_results.json +6 -6
  5. eval_results.json +3 -3
  6. train_results.json +3 -3
  7. trainer_state.json +9 -9
  8. training_args.bin +1 -1
adapter_config.json CHANGED
@@ -16,8 +16,8 @@
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
19
- "q_proj",
20
  "o_proj",
 
21
  "k_proj",
22
  "v_proj"
23
  ],
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
19
  "o_proj",
20
+ "q_proj",
21
  "k_proj",
22
  "v_proj"
23
  ],
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b83398fcd1f83b2b4645df1bdbeebc94b55adf84df4f531c41d4da50278bd54e
3
  size 872508554
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a65b50967390cfef35f29c0c558040200984c1dc16570052ecad9979dae852d
3
  size 872508554
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4507cecfab4aed7b850ede3e6b20862e39e7aafc5cefba9750cc95b8301e63a4
3
  size 872450448
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0db23340a233d6a10240667d8ba287a38e66b15ecd1d863fee3447be11638b8
3
  size 872450448
all_results.json CHANGED
@@ -1,13 +1,13 @@
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
- "eval_runtime": 113.1958,
5
  "eval_samples": 650,
6
- "eval_samples_per_second": 5.742,
7
- "eval_steps_per_second": 1.44,
8
  "train_loss": 1.0970729541778566,
9
- "train_runtime": 344.8794,
10
  "train_samples": 5845,
11
- "train_samples_per_second": 0.58,
12
- "train_steps_per_second": 0.145
13
  }
 
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
+ "eval_runtime": 112.9915,
5
  "eval_samples": 650,
6
+ "eval_samples_per_second": 5.753,
7
+ "eval_steps_per_second": 1.443,
8
  "train_loss": 1.0970729541778566,
9
+ "train_runtime": 356.1922,
10
  "train_samples": 5845,
11
+ "train_samples_per_second": 0.561,
12
+ "train_steps_per_second": 0.14
13
  }
eval_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
- "eval_runtime": 113.1958,
5
  "eval_samples": 650,
6
- "eval_samples_per_second": 5.742,
7
- "eval_steps_per_second": 1.44
8
  }
 
1
  {
2
  "epoch": 0.03,
3
  "eval_loss": 0.8876652717590332,
4
+ "eval_runtime": 112.9915,
5
  "eval_samples": 650,
6
+ "eval_samples_per_second": 5.753,
7
+ "eval_steps_per_second": 1.443
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 0.03,
3
  "train_loss": 1.0970729541778566,
4
- "train_runtime": 344.8794,
5
  "train_samples": 5845,
6
- "train_samples_per_second": 0.58,
7
- "train_steps_per_second": 0.145
8
  }
 
1
  {
2
  "epoch": 0.03,
3
  "train_loss": 1.0970729541778566,
4
+ "train_runtime": 356.1922,
5
  "train_samples": 5845,
6
+ "train_samples_per_second": 0.561,
7
+ "train_steps_per_second": 0.14
8
  }
trainer_state.json CHANGED
@@ -29,9 +29,9 @@
29
  {
30
  "epoch": 0.02,
31
  "eval_loss": 0.9467611908912659,
32
- "eval_runtime": 113.1765,
33
- "eval_samples_per_second": 5.743,
34
- "eval_steps_per_second": 1.44,
35
  "step": 25
36
  },
37
  {
@@ -55,9 +55,9 @@
55
  {
56
  "epoch": 0.03,
57
  "eval_loss": 0.8876652717590332,
58
- "eval_runtime": 114.0148,
59
- "eval_samples_per_second": 5.701,
60
- "eval_steps_per_second": 1.43,
61
  "step": 50
62
  },
63
  {
@@ -65,9 +65,9 @@
65
  "step": 50,
66
  "total_flos": 4008716634423296.0,
67
  "train_loss": 1.0970729541778566,
68
- "train_runtime": 344.8794,
69
- "train_samples_per_second": 0.58,
70
- "train_steps_per_second": 0.145
71
  }
72
  ],
73
  "logging_steps": 10,
 
29
  {
30
  "epoch": 0.02,
31
  "eval_loss": 0.9467611908912659,
32
+ "eval_runtime": 113.3532,
33
+ "eval_samples_per_second": 5.734,
34
+ "eval_steps_per_second": 1.438,
35
  "step": 25
36
  },
37
  {
 
55
  {
56
  "epoch": 0.03,
57
  "eval_loss": 0.8876652717590332,
58
+ "eval_runtime": 114.2498,
59
+ "eval_samples_per_second": 5.689,
60
+ "eval_steps_per_second": 1.427,
61
  "step": 50
62
  },
63
  {
 
65
  "step": 50,
66
  "total_flos": 4008716634423296.0,
67
  "train_loss": 1.0970729541778566,
68
+ "train_runtime": 356.1922,
69
+ "train_samples_per_second": 0.561,
70
+ "train_steps_per_second": 0.14
71
  }
72
  ],
73
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ce4fc530190fc50faa5c41b7996377ae6495a8c82a8243129b1546cca66170e8
3
  size 4664
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bfbbe611ebadd32f93b7dc4ee103872d24668c7eff310a8b7fe4ca99b2448042
3
  size 4664