Hugging Face's logo

mlfoundations-dev
/
tinyllama_alpaca_sft_sample

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
marianna13 commited on
Commit
0adb350
·
verified ·
1 Parent(s): 7629f20

Upload folder using huggingface_hub

Browse files
Files changed (7) hide show
  1. all_results.json +8 -8
  2. eval_results.json +4 -4
  3. model.safetensors +1 -1
  4. train_results.json +4 -4
  5. trainer_log.jsonl +4 -4
  6. trainer_state.json +11 -11
  7. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,12 +1,12 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 1.213269829750061,
4
- "eval_runtime": 0.4248,
5
- "eval_samples_per_second": 1459.349,
6
- "eval_steps_per_second": 11.769,
7
  "total_flos": 3.742438758599885e+16,
8
- "train_loss": 1.3028167019719663,
9
- "train_runtime": 44.733,
10
- "train_samples_per_second": 262.982,
11
- "train_steps_per_second": 0.514
12
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.2132670879364014,
4
+ "eval_runtime": 0.4489,
5
+ "eval_samples_per_second": 1381.058,
6
+ "eval_steps_per_second": 11.138,
7
  "total_flos": 3.742438758599885e+16,
8
+ "train_loss": 1.3028676406196926,
9
+ "train_runtime": 44.8785,
10
+ "train_samples_per_second": 262.13,
11
+ "train_steps_per_second": 0.512
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "epoch": 1.0,
3
- "eval_loss": 1.213269829750061,
4
- "eval_runtime": 0.4248,
5
- "eval_samples_per_second": 1459.349,
6
- "eval_steps_per_second": 11.769
7
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.2132670879364014,
4
+ "eval_runtime": 0.4489,
5
+ "eval_samples_per_second": 1381.058,
6
+ "eval_steps_per_second": 11.138
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:822d351ab9e5b178191168caac8ebca0483dc2e8147d7b14ddd1348808d5f2c9
3
  size 2200119864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530fa995def746d56bfcdd02bf27ad60b458bc046fc2abe6fc4601d8e7505796
3
  size 2200119864
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 3.742438758599885e+16,
4
- "train_loss": 1.3028167019719663,
5
- "train_runtime": 44.733,
6
- "train_samples_per_second": 262.982,
7
- "train_steps_per_second": 0.514
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 3.742438758599885e+16,
4
+ "train_loss": 1.3028676406196926,
5
+ "train_runtime": 44.8785,
6
+ "train_samples_per_second": 262.13,
7
+ "train_steps_per_second": 0.512
8
  }
trainer_log.jsonl CHANGED
@@ -1,4 +1,4 @@
1
- {"current_steps": 10, "total_steps": 23, "loss": 1.3741, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:15", "remaining_time": "0:00:20"}
2
- {"current_steps": 20, "total_steps": 23, "loss": 1.2457, "learning_rate": 1.0899347581163222e-06, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "0:00:28", "remaining_time": "0:00:04"}
3
- {"current_steps": 23, "total_steps": 23, "eval_loss": 1.213269829750061, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:38", "remaining_time": "0:00:00"}
4
- {"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:42", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 10, "total_steps": 23, "loss": 1.3742, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:16", "remaining_time": "0:00:20"}
2
+ {"current_steps": 20, "total_steps": 23, "loss": 1.2457, "learning_rate": 1.0899347581163222e-06, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "0:00:29", "remaining_time": "0:00:04"}
3
+ {"current_steps": 23, "total_steps": 23, "eval_loss": 1.2132670879364014, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:38", "remaining_time": "0:00:00"}
4
+ {"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:41", "remaining_time": "0:00:00"}
trainer_state.json CHANGED
@@ -10,34 +10,34 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.43478260869565216,
13
- "grad_norm": 0.8424785137176514,
14
  "learning_rate": 1.4539904997395468e-05,
15
- "loss": 1.3741,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8695652173913043,
20
- "grad_norm": 0.5969947576522827,
21
  "learning_rate": 1.0899347581163222e-06,
22
  "loss": 1.2457,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 1.0,
27
- "eval_loss": 1.213269829750061,
28
- "eval_runtime": 0.5855,
29
- "eval_samples_per_second": 1058.923,
30
- "eval_steps_per_second": 8.54,
31
  "step": 23
32
  },
33
  {
34
  "epoch": 1.0,
35
  "step": 23,
36
  "total_flos": 3.742438758599885e+16,
37
- "train_loss": 1.3028167019719663,
38
- "train_runtime": 44.733,
39
- "train_samples_per_second": 262.982,
40
- "train_steps_per_second": 0.514
41
  }
42
  ],
43
  "logging_steps": 10,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.43478260869565216,
13
+ "grad_norm": 0.8424881100654602,
14
  "learning_rate": 1.4539904997395468e-05,
15
+ "loss": 1.3742,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8695652173913043,
20
+ "grad_norm": 0.5980207324028015,
21
  "learning_rate": 1.0899347581163222e-06,
22
  "loss": 1.2457,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 1.0,
27
+ "eval_loss": 1.2132670879364014,
28
+ "eval_runtime": 0.5126,
29
+ "eval_samples_per_second": 1209.62,
30
+ "eval_steps_per_second": 9.755,
31
  "step": 23
32
  },
33
  {
34
  "epoch": 1.0,
35
  "step": 23,
36
  "total_flos": 3.742438758599885e+16,
37
+ "train_loss": 1.3028676406196926,
38
+ "train_runtime": 44.8785,
39
+ "train_samples_per_second": 262.13,
40
+ "train_steps_per_second": 0.512
41
  }
42
  ],
43
  "logging_steps": 10,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c75513711763921d31ccd0a80a2df55625ceb63b637b01a07232c9b78fa841a3
3
  size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3264d490cd0375748e1d7e3a6741b66700101ec5d171854643e9d302f3c7b66e
3
  size 6712