Hugging Face's logo

mlfoundations-dev
/
llama3-1_8b_mlfoundations-dev-stackexchange_quantumcomputing

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
EtashGuha commited on
Commit
d5e5fba
·
verified ·
1 Parent(s): 8c0bf6e

Training in progress, epoch 2

Browse files
Files changed (5) 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 +4 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96b6623dbdfcce2c2f81cdbf17e557661baf1a60d478276170044eeea4458643
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907b4b18c4223668c0c5f09fe93f821dfb92207a854507b79f129063d50011ac
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b638390605fd71504bb42cefa13a5474c3635e9f886721a88030a2f0efc333d
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5cafa6e2bbd92fe711ac061db8c85d7df66eed8e511440ad38ed57c5b0d917
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:d89d98e1c0b77e3dd65a44e2ecb26e2f5d9a702a32f36fbea903398a784e7d47
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5543254b1865111a2bea91e663d790ce903e811091e870f3a80f9c4e9f6ad9f
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:de45aae9df896155672fa71a7990c1fff03467ba7437897f013b9ce2a4a353cf
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f3c5712762b88b92169e6bd39bdb2eecbe5665edc6be2664ba0eaa36aae4563
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -4,3 +4,7 @@
4
  {"current_steps": 30, "total_steps": 60, "loss": 0.8464, "lr": 5e-06, "epoch": 1.476923076923077, "percentage": 50.0, "elapsed_time": "1:13:48", "remaining_time": "1:13:48"}
5
  {"current_steps": 40, "total_steps": 60, "loss": 0.8243, "lr": 5e-06, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "1:37:03", "remaining_time": "0:48:31"}
6
  {"current_steps": 40, "total_steps": 60, "eval_loss": 0.840017557144165, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "1:39:25", "remaining_time": "0:49:42"}
 
 
 
 
 
4
  {"current_steps": 30, "total_steps": 60, "loss": 0.8464, "lr": 5e-06, "epoch": 1.476923076923077, "percentage": 50.0, "elapsed_time": "1:13:48", "remaining_time": "1:13:48"}
5
  {"current_steps": 40, "total_steps": 60, "loss": 0.8243, "lr": 5e-06, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "1:37:03", "remaining_time": "0:48:31"}
6
  {"current_steps": 40, "total_steps": 60, "eval_loss": 0.840017557144165, "epoch": 1.9692307692307693, "percentage": 66.67, "elapsed_time": "1:39:25", "remaining_time": "0:49:42"}
7
+ {"current_steps": 50, "total_steps": 60, "loss": 0.7799, "lr": 5e-06, "epoch": 2.4615384615384617, "percentage": 83.33, "elapsed_time": "2:02:36", "remaining_time": "0:24:31"}
8
+ {"current_steps": 60, "total_steps": 60, "loss": 0.7609, "lr": 5e-06, "epoch": 2.953846153846154, "percentage": 100.0, "elapsed_time": "2:25:51", "remaining_time": "0:00:00"}
9
+ {"current_steps": 60, "total_steps": 60, "eval_loss": 0.8229892253875732, "epoch": 2.953846153846154, "percentage": 100.0, "elapsed_time": "2:28:09", "remaining_time": "0:00:00"}
10
+ {"current_steps": 60, "total_steps": 60, "epoch": 2.953846153846154, "percentage": 100.0, "elapsed_time": "2:29:03", "remaining_time": "0:00:00"}