Hugging Face's logo

mlfoundations-dev
/
stackexchange_robotics

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
sedrickkeh commited on
Commit
a79d50b
·
verified ·
1 Parent(s): 640443b

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 +5 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0edd1b7161bcc37e6b69dd5025b2956ad2b800fc4496cbd011e070a4b774c26
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43af9d123603bd015830c202e1371aaf12a91172cff40ac049c54ca5abe69a58
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:d7562037cc44cca0c0b435e5e48d002cb4cdb62f7133db2d51f38b1f65b2cd82
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:584b955d4bcbaaf2de2019d64fd67972660a88fd90ef7a246a7adf379b0ee009
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02ccfa068d81019d2eda65913635842275c284f66f3bfe742a70144f532c3f22
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9462bfc17600793aa2abb0449465f03f53d969f1956eaecd5640843416133814
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95dadafaf75d373f86bd3f39384ee26ef86ee44407a293e1f9168cb66dbcd300
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480ec12f092798b945cf178bd53a6c5b96d081e8d202394a2023ca4f246653b1
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -3,3 +3,8 @@
3
  {"current_steps": 30, "total_steps": 126, "loss": 0.9027, "lr": 5e-06, "epoch": 0.7058823529411765, "percentage": 23.81, "elapsed_time": "0:16:01", "remaining_time": "0:51:16"}
4
  {"current_steps": 40, "total_steps": 126, "loss": 0.8767, "lr": 5e-06, "epoch": 0.9411764705882353, "percentage": 31.75, "elapsed_time": "0:21:17", "remaining_time": "0:45:46"}
5
  {"current_steps": 42, "total_steps": 126, "eval_loss": 0.8602203726768494, "epoch": 0.9882352941176471, "percentage": 33.33, "elapsed_time": "0:23:04", "remaining_time": "0:46:09"}
 
 
 
 
 
 
3
  {"current_steps": 30, "total_steps": 126, "loss": 0.9027, "lr": 5e-06, "epoch": 0.7058823529411765, "percentage": 23.81, "elapsed_time": "0:16:01", "remaining_time": "0:51:16"}
4
  {"current_steps": 40, "total_steps": 126, "loss": 0.8767, "lr": 5e-06, "epoch": 0.9411764705882353, "percentage": 31.75, "elapsed_time": "0:21:17", "remaining_time": "0:45:46"}
5
  {"current_steps": 42, "total_steps": 126, "eval_loss": 0.8602203726768494, "epoch": 0.9882352941176471, "percentage": 33.33, "elapsed_time": "0:23:04", "remaining_time": "0:46:09"}
6
+ {"current_steps": 50, "total_steps": 126, "loss": 0.8788, "lr": 5e-06, "epoch": 1.1764705882352942, "percentage": 39.68, "elapsed_time": "0:28:16", "remaining_time": "0:42:58"}
7
+ {"current_steps": 60, "total_steps": 126, "loss": 0.8148, "lr": 5e-06, "epoch": 1.4117647058823528, "percentage": 47.62, "elapsed_time": "0:33:34", "remaining_time": "0:36:55"}
8
+ {"current_steps": 70, "total_steps": 126, "loss": 0.8062, "lr": 5e-06, "epoch": 1.6470588235294117, "percentage": 55.56, "elapsed_time": "0:38:51", "remaining_time": "0:31:05"}
9
+ {"current_steps": 80, "total_steps": 126, "loss": 0.7964, "lr": 5e-06, "epoch": 1.8823529411764706, "percentage": 63.49, "elapsed_time": "0:44:07", "remaining_time": "0:25:22"}
10
+ {"current_steps": 85, "total_steps": 126, "eval_loss": 0.8092531561851501, "epoch": 2.0, "percentage": 67.46, "elapsed_time": "0:47:08", "remaining_time": "0:22:44"}