Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_physics_50000_samples

Safetensors
llama
Model card Files Community
gsmyrnis commited on
Commit
fcb5450
·
verified ·
1 Parent(s): 3ca6141

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 +15 -15
  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 sha256:0a7652e8494d7dff749f96f9916d535ed5301f4f0daaad66d879d8fd40c3beeb
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e5058214314fed27c078e19c00b2fd853c59f89c6d050e3f6a3f2de19ec2c5a
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:ef2d32ea84cc798731fc7af68465059d9b562de8e959b13eeef9717fd65dc736
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f9c61fa20b7c4e3fd4de3a5d7eb9650151a0cb38ba28a9816425b17728bd13e
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:ad75e231332bdb629b5651a2acab3593c54e3bcca372682b50bc273f3b2ac2d1
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e637807b3c09acc5c85117001a1fa16c7861eca513251953d291873326ab2b2a
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:da156f1a75f2c0dbb9dfbdb941ec9de4f2a84271997628257e04d81d8cf01b40
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36afc88490ad6ecb25ac54e09e8fbb4109430db2ff49fae6a714f411f7ce856
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,15 +1,15 @@
1
- {"current_steps": 10, "total_steps": 111, "loss": 1.0405, "lr": 5e-06, "epoch": 0.2702702702702703, "percentage": 9.01, "elapsed_time": "0:00:59", "remaining_time": "0:09:56"}
2
- {"current_steps": 20, "total_steps": 111, "loss": 0.932, "lr": 5e-06, "epoch": 0.5405405405405406, "percentage": 18.02, "elapsed_time": "0:01:56", "remaining_time": "0:08:51"}
3
- {"current_steps": 30, "total_steps": 111, "loss": 0.8995, "lr": 5e-06, "epoch": 0.8108108108108109, "percentage": 27.03, "elapsed_time": "0:02:54", "remaining_time": "0:07:52"}
4
- {"current_steps": 37, "total_steps": 111, "eval_loss": 0.8795487880706787, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:03:38", "remaining_time": "0:07:17"}
5
- {"current_steps": 40, "total_steps": 111, "loss": 0.8701, "lr": 5e-06, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "0:05:23", "remaining_time": "0:09:33"}
6
- {"current_steps": 50, "total_steps": 111, "loss": 0.8382, "lr": 5e-06, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "0:06:21", "remaining_time": "0:07:44"}
7
- {"current_steps": 60, "total_steps": 111, "loss": 0.8199, "lr": 5e-06, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "0:07:18", "remaining_time": "0:06:13"}
8
- {"current_steps": 70, "total_steps": 111, "loss": 0.8164, "lr": 5e-06, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "0:08:16", "remaining_time": "0:04:50"}
9
- {"current_steps": 74, "total_steps": 111, "eval_loss": 0.8546912670135498, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:08:43", "remaining_time": "0:04:21"}
10
- {"current_steps": 80, "total_steps": 111, "loss": 0.7771, "lr": 5e-06, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "0:10:44", "remaining_time": "0:04:09"}
11
- {"current_steps": 90, "total_steps": 111, "loss": 0.7618, "lr": 5e-06, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "0:11:42", "remaining_time": "0:02:43"}
12
- {"current_steps": 100, "total_steps": 111, "loss": 0.759, "lr": 5e-06, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "0:12:40", "remaining_time": "0:01:23"}
13
- {"current_steps": 110, "total_steps": 111, "loss": 0.7525, "lr": 5e-06, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "0:13:38", "remaining_time": "0:00:07"}
14
- {"current_steps": 111, "total_steps": 111, "eval_loss": 0.8525012135505676, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:15", "remaining_time": "0:00:00"}
15
- {"current_steps": 111, "total_steps": 111, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:16:42", "remaining_time": "0:00:00"}
 
1
+ {"current_steps": 10, "total_steps": 111, "loss": 1.0353, "lr": 5e-06, "epoch": 0.2702702702702703, "percentage": 9.01, "elapsed_time": "0:01:00", "remaining_time": "0:10:08"}
2
+ {"current_steps": 20, "total_steps": 111, "loss": 0.9337, "lr": 5e-06, "epoch": 0.5405405405405406, "percentage": 18.02, "elapsed_time": "0:01:59", "remaining_time": "0:09:03"}
3
+ {"current_steps": 30, "total_steps": 111, "loss": 0.9077, "lr": 5e-06, "epoch": 0.8108108108108109, "percentage": 27.03, "elapsed_time": "0:02:58", "remaining_time": "0:08:03"}
4
+ {"current_steps": 37, "total_steps": 111, "eval_loss": 0.8829638957977295, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:03:43", "remaining_time": "0:07:27"}
5
+ {"current_steps": 40, "total_steps": 111, "loss": 0.8749, "lr": 5e-06, "epoch": 1.0810810810810811, "percentage": 36.04, "elapsed_time": "0:05:26", "remaining_time": "0:09:40"}
6
+ {"current_steps": 50, "total_steps": 111, "loss": 0.8444, "lr": 5e-06, "epoch": 1.3513513513513513, "percentage": 45.05, "elapsed_time": "0:06:27", "remaining_time": "0:07:53"}
7
+ {"current_steps": 60, "total_steps": 111, "loss": 0.825, "lr": 5e-06, "epoch": 1.6216216216216215, "percentage": 54.05, "elapsed_time": "0:07:27", "remaining_time": "0:06:20"}
8
+ {"current_steps": 70, "total_steps": 111, "loss": 0.8201, "lr": 5e-06, "epoch": 1.8918918918918919, "percentage": 63.06, "elapsed_time": "0:08:26", "remaining_time": "0:04:56"}
9
+ {"current_steps": 74, "total_steps": 111, "eval_loss": 0.854485809803009, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:08:53", "remaining_time": "0:04:26"}
10
+ {"current_steps": 80, "total_steps": 111, "loss": 0.7804, "lr": 5e-06, "epoch": 2.1621621621621623, "percentage": 72.07, "elapsed_time": "0:10:54", "remaining_time": "0:04:13"}
11
+ {"current_steps": 90, "total_steps": 111, "loss": 0.7645, "lr": 5e-06, "epoch": 2.4324324324324325, "percentage": 81.08, "elapsed_time": "0:11:53", "remaining_time": "0:02:46"}
12
+ {"current_steps": 100, "total_steps": 111, "loss": 0.7623, "lr": 5e-06, "epoch": 2.7027027027027026, "percentage": 90.09, "elapsed_time": "0:12:53", "remaining_time": "0:01:25"}
13
+ {"current_steps": 110, "total_steps": 111, "loss": 0.7564, "lr": 5e-06, "epoch": 2.972972972972973, "percentage": 99.1, "elapsed_time": "0:13:52", "remaining_time": "0:00:07"}
14
+ {"current_steps": 111, "total_steps": 111, "eval_loss": 0.8543545603752136, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:15:21", "remaining_time": "0:00:00"}
15
+ {"current_steps": 111, "total_steps": 111, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:16:49", "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:f4d9d619683378107c0c742f0d01c02ed94b8918711ee9657c5590fcbb4d9a16
3
  size 7288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8b08ea45b225ff80f34cefbf378ac44929750c60ce40cfddaff84492b91c08
3
  size 7288