Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_math_100000_samples

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
gsmyrnis commited on
Commit
edccd1d
·
verified ·
1 Parent(s): 4e09709

Training in progress, epoch 1

Browse files
Files changed (6) hide show
  1. model-00001-of-00004.safetensors +1 -1
  2. model-00002-of-00004.safetensors +1 -1
  3. model-00003-of-00004.safetensors +1 -1
  4. model-00004-of-00004.safetensors +1 -1
  5. trainer_log.jsonl +29 -29
  6. training_args.bin +1 -1
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:48dbef312bbdf5915bcf4467c81cc9d56be9aaf309732d1244fa61a9a45c2de9
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3263965e36f55fb4a5df66cc3e22f268d962fe48daed21f16ed4f1a73e04c6c
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:425fbee60737c189c45d2a16df028cd259938b0d7407cedb6a70f5bcfbc5c74c
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9c686e2be7812969cf894f35fb468d3658ca2a0011d6f3783dceb8c01e53d9
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d2693da3e180a8f828fc78ed333d194ebaea37ebe0f2e84eee476312a4495e21
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bf16fa0ec9fe3182664c98a6e7470fc22f2443bbfea7875814dfaa2a65e0c87
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf001d40dd6d1aceaddf0d2c3073528aa664404c9aba7da3f48a94aa9fa49c1c
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b86a451f809dd292892d004da5bbbb37d55e36261424064cd6d54f1f8afa8145
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,29 +1,29 @@
1
- {"current_steps": 10, "total_steps": 252, "loss": 0.7414, "lr": 5e-06, "epoch": 0.11904761904761904, "percentage": 3.97, "elapsed_time": "0:01:03", "remaining_time": "0:25:28"}
2
- {"current_steps": 20, "total_steps": 252, "loss": 0.6546, "lr": 5e-06, "epoch": 0.23809523809523808, "percentage": 7.94, "elapsed_time": "0:02:03", "remaining_time": "0:23:58"}
3
- {"current_steps": 30, "total_steps": 252, "loss": 0.625, "lr": 5e-06, "epoch": 0.35714285714285715, "percentage": 11.9, "elapsed_time": "0:03:04", "remaining_time": "0:22:42"}
4
- {"current_steps": 40, "total_steps": 252, "loss": 0.6117, "lr": 5e-06, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "0:04:04", "remaining_time": "0:21:36"}
5
- {"current_steps": 50, "total_steps": 252, "loss": 0.6025, "lr": 5e-06, "epoch": 0.5952380952380952, "percentage": 19.84, "elapsed_time": "0:05:05", "remaining_time": "0:20:34"}
6
- {"current_steps": 60, "total_steps": 252, "loss": 0.5934, "lr": 5e-06, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "0:06:06", "remaining_time": "0:19:34"}
7
- {"current_steps": 70, "total_steps": 252, "loss": 0.592, "lr": 5e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:07:08", "remaining_time": "0:18:33"}
8
- {"current_steps": 80, "total_steps": 252, "loss": 0.5845, "lr": 5e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "0:08:09", "remaining_time": "0:17:32"}
9
- {"current_steps": 84, "total_steps": 252, "eval_loss": 0.5790121555328369, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:08:42", "remaining_time": "0:17:24"}
10
- {"current_steps": 90, "total_steps": 252, "loss": 0.5649, "lr": 5e-06, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "0:10:52", "remaining_time": "0:19:34"}
11
- {"current_steps": 100, "total_steps": 252, "loss": 0.5511, "lr": 5e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "0:11:53", "remaining_time": "0:18:04"}
12
- {"current_steps": 110, "total_steps": 252, "loss": 0.5536, "lr": 5e-06, "epoch": 1.3095238095238095, "percentage": 43.65, "elapsed_time": "0:12:54", "remaining_time": "0:16:39"}
13
- {"current_steps": 120, "total_steps": 252, "loss": 0.5516, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:13:56", "remaining_time": "0:15:19"}
14
- {"current_steps": 130, "total_steps": 252, "loss": 0.5455, "lr": 5e-06, "epoch": 1.5476190476190477, "percentage": 51.59, "elapsed_time": "0:14:56", "remaining_time": "0:14:01"}
15
- {"current_steps": 140, "total_steps": 252, "loss": 0.5463, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:15:58", "remaining_time": "0:12:46"}
16
- {"current_steps": 150, "total_steps": 252, "loss": 0.5453, "lr": 5e-06, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "0:16:59", "remaining_time": "0:11:33"}
17
- {"current_steps": 160, "total_steps": 252, "loss": 0.5425, "lr": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "0:18:00", "remaining_time": "0:10:21"}
18
- {"current_steps": 168, "total_steps": 252, "eval_loss": 0.5688955783843994, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:58", "remaining_time": "0:09:29"}
19
- {"current_steps": 170, "total_steps": 252, "loss": 0.5384, "lr": 5e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "0:20:36", "remaining_time": "0:09:56"}
20
- {"current_steps": 180, "total_steps": 252, "loss": 0.5145, "lr": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "0:21:36", "remaining_time": "0:08:38"}
21
- {"current_steps": 190, "total_steps": 252, "loss": 0.51, "lr": 5e-06, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "0:22:37", "remaining_time": "0:07:22"}
22
- {"current_steps": 200, "total_steps": 252, "loss": 0.5076, "lr": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "0:23:38", "remaining_time": "0:06:08"}
23
- {"current_steps": 210, "total_steps": 252, "loss": 0.511, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:24:38", "remaining_time": "0:04:55"}
24
- {"current_steps": 220, "total_steps": 252, "loss": 0.5114, "lr": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "0:25:40", "remaining_time": "0:03:44"}
25
- {"current_steps": 230, "total_steps": 252, "loss": 0.5088, "lr": 5e-06, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "0:26:41", "remaining_time": "0:02:33"}
26
- {"current_steps": 240, "total_steps": 252, "loss": 0.5145, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:27:41", "remaining_time": "0:01:23"}
27
- {"current_steps": 250, "total_steps": 252, "loss": 0.5111, "lr": 5e-06, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "0:28:43", "remaining_time": "0:00:13"}
28
- {"current_steps": 252, "total_steps": 252, "eval_loss": 0.5703586935997009, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:30:31", "remaining_time": "0:00:00"}
29
- {"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:32:07", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 10, "total_steps": 252, "loss": 0.7508, "lr": 5e-06, "epoch": 0.11904761904761904, "percentage": 3.97, "elapsed_time": "0:01:02", "remaining_time": "0:25:04"}
2
+ {"current_steps": 20, "total_steps": 252, "loss": 0.6727, "lr": 5e-06, "epoch": 0.23809523809523808, "percentage": 7.94, "elapsed_time": "0:02:02", "remaining_time": "0:23:39"}
3
+ {"current_steps": 30, "total_steps": 252, "loss": 0.633, "lr": 5e-06, "epoch": 0.35714285714285715, "percentage": 11.9, "elapsed_time": "0:03:03", "remaining_time": "0:22:36"}
4
+ {"current_steps": 40, "total_steps": 252, "loss": 0.6164, "lr": 5e-06, "epoch": 0.47619047619047616, "percentage": 15.87, "elapsed_time": "0:04:04", "remaining_time": "0:21:37"}
5
+ {"current_steps": 50, "total_steps": 252, "loss": 0.6066, "lr": 5e-06, "epoch": 0.5952380952380952, "percentage": 19.84, "elapsed_time": "0:05:05", "remaining_time": "0:20:34"}
6
+ {"current_steps": 60, "total_steps": 252, "loss": 0.5966, "lr": 5e-06, "epoch": 0.7142857142857143, "percentage": 23.81, "elapsed_time": "0:06:06", "remaining_time": "0:19:31"}
7
+ {"current_steps": 70, "total_steps": 252, "loss": 0.5944, "lr": 5e-06, "epoch": 0.8333333333333334, "percentage": 27.78, "elapsed_time": "0:07:07", "remaining_time": "0:18:31"}
8
+ {"current_steps": 80, "total_steps": 252, "loss": 0.5861, "lr": 5e-06, "epoch": 0.9523809523809523, "percentage": 31.75, "elapsed_time": "0:08:09", "remaining_time": "0:17:32"}
9
+ {"current_steps": 84, "total_steps": 252, "eval_loss": 0.5798346996307373, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:08:41", "remaining_time": "0:17:23"}
10
+ {"current_steps": 90, "total_steps": 252, "loss": 0.5663, "lr": 5e-06, "epoch": 1.0714285714285714, "percentage": 35.71, "elapsed_time": "0:10:34", "remaining_time": "0:19:02"}
11
+ {"current_steps": 100, "total_steps": 252, "loss": 0.5517, "lr": 5e-06, "epoch": 1.1904761904761905, "percentage": 39.68, "elapsed_time": "0:11:35", "remaining_time": "0:17:37"}
12
+ {"current_steps": 110, "total_steps": 252, "loss": 0.5546, "lr": 5e-06, "epoch": 1.3095238095238095, "percentage": 43.65, "elapsed_time": "0:12:35", "remaining_time": "0:16:15"}
13
+ {"current_steps": 120, "total_steps": 252, "loss": 0.5526, "lr": 5e-06, "epoch": 1.4285714285714286, "percentage": 47.62, "elapsed_time": "0:13:36", "remaining_time": "0:14:57"}
14
+ {"current_steps": 130, "total_steps": 252, "loss": 0.5466, "lr": 5e-06, "epoch": 1.5476190476190477, "percentage": 51.59, "elapsed_time": "0:14:36", "remaining_time": "0:13:42"}
15
+ {"current_steps": 140, "total_steps": 252, "loss": 0.5472, "lr": 5e-06, "epoch": 1.6666666666666665, "percentage": 55.56, "elapsed_time": "0:15:38", "remaining_time": "0:12:30"}
16
+ {"current_steps": 150, "total_steps": 252, "loss": 0.5464, "lr": 5e-06, "epoch": 1.7857142857142856, "percentage": 59.52, "elapsed_time": "0:16:40", "remaining_time": "0:11:20"}
17
+ {"current_steps": 160, "total_steps": 252, "loss": 0.543, "lr": 5e-06, "epoch": 1.9047619047619047, "percentage": 63.49, "elapsed_time": "0:17:40", "remaining_time": "0:10:09"}
18
+ {"current_steps": 168, "total_steps": 252, "eval_loss": 0.5688267946243286, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:18:37", "remaining_time": "0:09:18"}
19
+ {"current_steps": 170, "total_steps": 252, "loss": 0.5387, "lr": 5e-06, "epoch": 2.0238095238095237, "percentage": 67.46, "elapsed_time": "0:20:07", "remaining_time": "0:09:42"}
20
+ {"current_steps": 180, "total_steps": 252, "loss": 0.513, "lr": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "0:21:07", "remaining_time": "0:08:27"}
21
+ {"current_steps": 190, "total_steps": 252, "loss": 0.5084, "lr": 5e-06, "epoch": 2.261904761904762, "percentage": 75.4, "elapsed_time": "0:22:08", "remaining_time": "0:07:13"}
22
+ {"current_steps": 200, "total_steps": 252, "loss": 0.5065, "lr": 5e-06, "epoch": 2.380952380952381, "percentage": 79.37, "elapsed_time": "0:23:09", "remaining_time": "0:06:01"}
23
+ {"current_steps": 210, "total_steps": 252, "loss": 0.5096, "lr": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "0:24:10", "remaining_time": "0:04:50"}
24
+ {"current_steps": 220, "total_steps": 252, "loss": 0.51, "lr": 5e-06, "epoch": 2.619047619047619, "percentage": 87.3, "elapsed_time": "0:25:10", "remaining_time": "0:03:39"}
25
+ {"current_steps": 230, "total_steps": 252, "loss": 0.5075, "lr": 5e-06, "epoch": 2.738095238095238, "percentage": 91.27, "elapsed_time": "0:26:11", "remaining_time": "0:02:30"}
26
+ {"current_steps": 240, "total_steps": 252, "loss": 0.5129, "lr": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "0:27:13", "remaining_time": "0:01:21"}
27
+ {"current_steps": 250, "total_steps": 252, "loss": 0.51, "lr": 5e-06, "epoch": 2.9761904761904763, "percentage": 99.21, "elapsed_time": "0:28:13", "remaining_time": "0:00:13"}
28
+ {"current_steps": 252, "total_steps": 252, "eval_loss": 0.5704450607299805, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:29:50", "remaining_time": "0:00:00"}
29
+ {"current_steps": 252, "total_steps": 252, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:31:08", "remaining_time": "0:00:00"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6d947651e330a36c3c1f79f44e455869d99bd597650c11f7bc99a51de27ceaf
3
  size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a50b2d5fc5bc6fdab863d576ce99d547b2aa768f2601958b7f661882f23088d2
3
  size 7288