Hugging Face's logo

mlfoundations-dev
/
c1_science_10d_16s

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
Community
1
neginr commited on
Commit
012f4cf
·
verified ·
1 Parent(s): 1cdab44

Model save

Browse files
Files changed (5) hide show
  1. all_results.json +4 -4
  2. train_results.json +4 -4
  3. trainer_log.jsonl +1 -0
  4. trainer_state.json +4 -4
  5. training_args.bin +1 -1
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.982278481012658,
3
  "total_flos": 2.512601771310121e+18,
4
- "train_loss": 0.37841837799888317,
5
- "train_runtime": 39311.6395,
6
- "train_samples_per_second": 4.018,
7
- "train_steps_per_second": 0.031
8
  }
 
1
  {
2
  "epoch": 4.982278481012658,
3
  "total_flos": 2.512601771310121e+18,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 1.5658,
6
+ "train_samples_per_second": 100903.723,
7
+ "train_steps_per_second": 785.516
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "epoch": 4.982278481012658,
3
  "total_flos": 2.512601771310121e+18,
4
- "train_loss": 0.37841837799888317,
5
- "train_runtime": 39311.6395,
6
- "train_samples_per_second": 4.018,
7
- "train_steps_per_second": 0.031
8
  }
 
1
  {
2
  "epoch": 4.982278481012658,
3
  "total_flos": 2.512601771310121e+18,
4
+ "train_loss": 0.0,
5
+ "train_runtime": 1.5658,
6
+ "train_samples_per_second": 100903.723,
7
+ "train_steps_per_second": 785.516
8
  }
trainer_log.jsonl CHANGED
@@ -1230,3 +1230,4 @@
1230
  {"current_steps": 1230, "total_steps": 1230, "loss": 0.1621, "lr": 0.0, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "10:51:50", "remaining_time": "0:00:00"}
1231
  {"current_steps": 1230, "total_steps": 1230, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "10:55:09", "remaining_time": "0:00:00"}
1232
  {"current_steps": 1230, "total_steps": 1230, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
 
 
1230
  {"current_steps": 1230, "total_steps": 1230, "loss": 0.1621, "lr": 0.0, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "10:51:50", "remaining_time": "0:00:00"}
1231
  {"current_steps": 1230, "total_steps": 1230, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "10:55:09", "remaining_time": "0:00:00"}
1232
  {"current_steps": 1230, "total_steps": 1230, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
1233
+ {"current_steps": 1230, "total_steps": 1230, "epoch": 4.982278481012658, "percentage": 100.0, "elapsed_time": "0:00:00", "remaining_time": "0:00:00"}
trainer_state.json CHANGED
@@ -8622,10 +8622,10 @@
8622
  "epoch": 4.982278481012658,
8623
  "step": 1230,
8624
  "total_flos": 2.512601771310121e+18,
8625
- "train_loss": 0.37841837799888317,
8626
- "train_runtime": 39311.6395,
8627
- "train_samples_per_second": 4.018,
8628
- "train_steps_per_second": 0.031
8629
  }
8630
  ],
8631
  "logging_steps": 1,
 
8622
  "epoch": 4.982278481012658,
8623
  "step": 1230,
8624
  "total_flos": 2.512601771310121e+18,
8625
+ "train_loss": 0.0,
8626
+ "train_runtime": 1.5658,
8627
+ "train_samples_per_second": 100903.723,
8628
+ "train_steps_per_second": 785.516
8629
  }
8630
  ],
8631
  "logging_steps": 1,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed3962dd196a8889d069af265c5548a1b22814cf84ffce9795b907ea93c6cbbe
3
  size 7352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab3c8bad7d11fa66d01778fdb767187bfe6f7183443d9d8c39070b9bc65e81c4
3
  size 7352