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
f3d9fb4
·
verified ·
1 Parent(s): 389beac

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 +3 -3
  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": 1.2132670879364014,
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
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.2132965326309204,
4
+ "eval_runtime": 0.4369,
5
+ "eval_samples_per_second": 1419.149,
6
+ "eval_steps_per_second": 11.445,
7
  "total_flos": 3.742438758599885e+16,
8
+ "train_loss": 1.3028600319572117,
9
+ "train_runtime": 47.4803,
10
+ "train_samples_per_second": 247.766,
11
+ "train_steps_per_second": 0.484
12
  }
eval_results.json CHANGED
@@ -1,7 +1,7 @@
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
  }
 
1
  {
2
  "epoch": 1.0,
3
+ "eval_loss": 1.2132965326309204,
4
+ "eval_runtime": 0.4369,
5
+ "eval_samples_per_second": 1419.149,
6
+ "eval_steps_per_second": 11.445
7
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:530fa995def746d56bfcdd02bf27ad60b458bc046fc2abe6fc4601d8e7505796
3
  size 2200119864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09c7b3d225500aceefc7ab2ac4711a0aaffc704916f903bc84e6fe46866c6a55
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": 1.3028676406196926,
5
- "train_runtime": 44.8785,
6
- "train_samples_per_second": 262.13,
7
- "train_steps_per_second": 0.512
8
  }
 
1
  {
2
  "epoch": 1.0,
3
  "total_flos": 3.742438758599885e+16,
4
+ "train_loss": 1.3028600319572117,
5
+ "train_runtime": 47.4803,
6
+ "train_samples_per_second": 247.766,
7
+ "train_steps_per_second": 0.484
8
  }
trainer_log.jsonl CHANGED
@@ -1,4 +1,4 @@
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"}
 
1
+ {"current_steps": 10, "total_steps": 23, "loss": 1.3741, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:16", "remaining_time": "0:00:21"}
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": 1.2132965326309204, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:40", "remaining_time": "0:00:00"}
4
+ {"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:46", "remaining_time": "0:00:00"}
trainer_state.json CHANGED
@@ -10,34 +10,34 @@
10
  "log_history": [
11
  {
12
  "epoch": 0.43478260869565216,
13
- "grad_norm": 0.8424881100654602,
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,
 
10
  "log_history": [
11
  {
12
  "epoch": 0.43478260869565216,
13
+ "grad_norm": 0.8429296612739563,
14
  "learning_rate": 1.4539904997395468e-05,
15
+ "loss": 1.3741,
16
  "step": 10
17
  },
18
  {
19
  "epoch": 0.8695652173913043,
20
+ "grad_norm": 0.5978645086288452,
21
  "learning_rate": 1.0899347581163222e-06,
22
  "loss": 1.2457,
23
  "step": 20
24
  },
25
  {
26
  "epoch": 1.0,
27
+ "eval_loss": 1.2132965326309204,
28
+ "eval_runtime": 0.5878,
29
+ "eval_samples_per_second": 1054.768,
30
+ "eval_steps_per_second": 8.506,
31
  "step": 23
32
  },
33
  {
34
  "epoch": 1.0,
35
  "step": 23,
36
  "total_flos": 3.742438758599885e+16,
37
+ "train_loss": 1.3028600319572117,
38
+ "train_runtime": 47.4803,
39
+ "train_samples_per_second": 247.766,
40
+ "train_steps_per_second": 0.484
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 sha256:3264d490cd0375748e1d7e3a6741b66700101ec5d171854643e9d302f3c7b66e
3
  size 6712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:143a0712bbd5de3cacbf2c90bf42bd432f6eafad3ec0090dd9646d6743f09936
3
  size 6712