Hugging Face's logo

mlfoundations-dev
/
stackexchange_astronomy

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
sedrickkeh commited on
Commit
c7656db
·
verified ·
1 Parent(s): a7696f4

Training in progress, epoch 1

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 +3 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:657be1bfded62b841a1e769ecd60f2c3027dfa2ad74369d3deec8017c37994cd
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87a9bebf99a12d846d8accd01a5e667b4678cd0795ef22a497d4250a8def8b78
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4438d7928ec9af04d96f0b2815b25dbcdd7404da01c9a8bde48f1a7305ed171a
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed8fb818c662bf7f752cdc934bcaf217d8c97e42f49b0f51a4124601e3f84b33
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cf74072a330f4b5081e0778816d1942e6790656a161767aa5edaad7dc09d1d2
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cff79f7bbd0831776168b8f177d580837f64668af3f3a96405204c889cf54269
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2663c8c77b188d9055dcaa070be145348ac85da8b5d506d37d3e1b559507d081
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6aa56d70608a7852cb0b8cbb49e9656ec9db92342a500b9f5a1d899fdcf6d2e4
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -1,3 +1,6 @@
1
  {"current_steps": 10, "total_steps": 60, "loss": 1.1263, "lr": 5e-06, "epoch": 0.48484848484848486, "percentage": 16.67, "elapsed_time": "0:09:38", "remaining_time": "0:48:13"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 1.0663, "lr": 5e-06, "epoch": 0.9696969696969697, "percentage": 33.33, "elapsed_time": "0:19:12", "remaining_time": "0:38:24"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 1.1175479888916016, "epoch": 0.9696969696969697, "percentage": 33.33, "elapsed_time": "0:20:09", "remaining_time": "0:40:19"}
 
 
 
 
1
  {"current_steps": 10, "total_steps": 60, "loss": 1.1263, "lr": 5e-06, "epoch": 0.48484848484848486, "percentage": 16.67, "elapsed_time": "0:09:38", "remaining_time": "0:48:13"}
2
  {"current_steps": 20, "total_steps": 60, "loss": 1.0663, "lr": 5e-06, "epoch": 0.9696969696969697, "percentage": 33.33, "elapsed_time": "0:19:12", "remaining_time": "0:38:24"}
3
  {"current_steps": 20, "total_steps": 60, "eval_loss": 1.1175479888916016, "epoch": 0.9696969696969697, "percentage": 33.33, "elapsed_time": "0:20:09", "remaining_time": "0:40:19"}
4
+ {"current_steps": 30, "total_steps": 60, "loss": 1.0693, "lr": 5e-06, "epoch": 1.4545454545454546, "percentage": 50.0, "elapsed_time": "0:30:20", "remaining_time": "0:30:20"}
5
+ {"current_steps": 40, "total_steps": 60, "loss": 0.9594, "lr": 5e-06, "epoch": 1.9393939393939394, "percentage": 66.67, "elapsed_time": "0:39:54", "remaining_time": "0:19:57"}
6
+ {"current_steps": 41, "total_steps": 60, "eval_loss": 0.9644138813018799, "epoch": 1.9878787878787878, "percentage": 68.33, "elapsed_time": "0:41:23", "remaining_time": "0:19:11"}