Hugging Face's logo

mlfoundations-dev
/
evol_tt_2s

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
6b01ff8
•
1 Parent(s): 7923c61

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:ef1d77589f38e4b0b62ac3966dbdffaf887a8170f3cd04047f72dbf3f3be3c1a
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6166669ffa636a1b237d6d3296cd70c0209fd37551d08397f8f4f02b17226067
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:124ce9954e9f901bf6d0b7e72f374dfe450bdebbc739e79d6dccc583dca9e55e
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:272f29c8bb07497f9663934bdb1221bef96c4c48d44da5367eb8242f84595c0f
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:a571e8b5953df8a2653398556f994dd8980bbfd7d581b99b33e46ccccd68b254
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ba246757f5b518af28cb6929c7a75a867dfdddbbe479d0efad67a9c8f305a9
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b5a4b047029b36251403d2042afdccee266e59ccb21f1f5993d6cd7ddbb4740
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72506eb3671c52051cf81249d89d1554c915f76b002646503229ae3bfdda9583
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -6,3 +6,7 @@
6
  {"current_steps": 50, "total_steps": 87, "loss": 1.015, "lr": 5e-06, "epoch": 1.694915254237288, "percentage": 57.47, "elapsed_time": "0:49:27", "remaining_time": "0:36:35"}
7
  {"current_steps": 59, "total_steps": 87, "eval_loss": 1.044095754623413, "epoch": 2.0, "percentage": 67.82, "elapsed_time": "0:58:28", "remaining_time": "0:27:45"}
8
  {"current_steps": 60, "total_steps": 87, "loss": 1.0548, "lr": 5e-06, "epoch": 2.0338983050847457, "percentage": 68.97, "elapsed_time": "1:00:36", "remaining_time": "0:27:16"}
 
 
 
 
 
6
  {"current_steps": 50, "total_steps": 87, "loss": 1.015, "lr": 5e-06, "epoch": 1.694915254237288, "percentage": 57.47, "elapsed_time": "0:49:27", "remaining_time": "0:36:35"}
7
  {"current_steps": 59, "total_steps": 87, "eval_loss": 1.044095754623413, "epoch": 2.0, "percentage": 67.82, "elapsed_time": "0:58:28", "remaining_time": "0:27:45"}
8
  {"current_steps": 60, "total_steps": 87, "loss": 1.0548, "lr": 5e-06, "epoch": 2.0338983050847457, "percentage": 68.97, "elapsed_time": "1:00:36", "remaining_time": "0:27:16"}
9
+ {"current_steps": 70, "total_steps": 87, "loss": 0.9598, "lr": 5e-06, "epoch": 2.3728813559322033, "percentage": 80.46, "elapsed_time": "1:10:09", "remaining_time": "0:17:02"}
10
+ {"current_steps": 80, "total_steps": 87, "loss": 0.9549, "lr": 5e-06, "epoch": 2.711864406779661, "percentage": 91.95, "elapsed_time": "1:19:42", "remaining_time": "0:06:58"}
11
+ {"current_steps": 87, "total_steps": 87, "eval_loss": 1.0310115814208984, "epoch": 2.9491525423728815, "percentage": 100.0, "elapsed_time": "1:28:07", "remaining_time": "0:00:00"}
12
+ {"current_steps": 87, "total_steps": 87, "epoch": 2.9491525423728815, "percentage": 100.0, "elapsed_time": "1:29:19", "remaining_time": "0:00:00"}