Hugging Face's logo

mlfoundations-dev
/
316_globalbatchsize32_lr2e5_epochs15

Text Generation
Transformers
Safetensors
qwen2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files Community
1
sedrickkeh commited on
Commit
fe55a2f
·
verified ·
1 Parent(s): 24c805c

Training in progress, epoch 15

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 +7 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55226e334e1ffe583af3617947b57704b9087f6333e251a3ee25288004830e38
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:338521dcfb47e6bbd8946ece63fd97d293b792028666af2f305b13d499d77252
3
  size 4877660776
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dcb9b088406209e229ad31217b86393084bd1a43dd9ee6f3eebb962de1a925b
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0283e5ba861d954190834e96218815845476bebc20e50ade117377fb4274bade
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e0400352678351b2b3b518b163326c1bdae5fe0c1a92387a04692b7c17d9e239
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9193cdeb9413078767030d534840c6f18b0469ac57c3434a1319d95a9177297d
3
  size 4330865200
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:046868b21a077e62a28041bd0939d002d6ef037a2a6e83eb1dd90cfb46a9f1f3
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d47569c84f8e7d0eeffd0ac75f2cff41804170774d6ebba4c1f4bdc3c2609e3d
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -142,3 +142,10 @@
142
  {"current_steps": 142, "total_steps": 150, "loss": 0.0008, "lr": 1.7279353293586765e-07, "epoch": 14.2, "percentage": 94.67, "elapsed_time": "1:36:48", "remaining_time": "0:05:27"}
143
  {"current_steps": 143, "total_steps": 150, "loss": 0.0009, "lr": 1.323846788742078e-07, "epoch": 14.3, "percentage": 95.33, "elapsed_time": "1:37:25", "remaining_time": "0:04:46"}
144
  {"current_steps": 144, "total_steps": 150, "loss": 0.0007, "lr": 9.731931258429638e-08, "epoch": 14.4, "percentage": 96.0, "elapsed_time": "1:37:48", "remaining_time": "0:04:04"}
 
 
 
 
 
 
 
 
142
  {"current_steps": 142, "total_steps": 150, "loss": 0.0008, "lr": 1.7279353293586765e-07, "epoch": 14.2, "percentage": 94.67, "elapsed_time": "1:36:48", "remaining_time": "0:05:27"}
143
  {"current_steps": 143, "total_steps": 150, "loss": 0.0009, "lr": 1.323846788742078e-07, "epoch": 14.3, "percentage": 95.33, "elapsed_time": "1:37:25", "remaining_time": "0:04:46"}
144
  {"current_steps": 144, "total_steps": 150, "loss": 0.0007, "lr": 9.731931258429638e-08, "epoch": 14.4, "percentage": 96.0, "elapsed_time": "1:37:48", "remaining_time": "0:04:04"}
145
+ {"current_steps": 145, "total_steps": 150, "loss": 0.0007, "lr": 6.761642258056977e-08, "epoch": 14.5, "percentage": 96.67, "elapsed_time": "1:38:27", "remaining_time": "0:03:23"}
146
+ {"current_steps": 146, "total_steps": 150, "loss": 0.0007, "lr": 4.329209350195651e-08, "epoch": 14.6, "percentage": 97.33, "elapsed_time": "1:39:03", "remaining_time": "0:02:42"}
147
+ {"current_steps": 147, "total_steps": 150, "loss": 0.001, "lr": 2.4359497401758026e-08, "epoch": 14.7, "percentage": 98.0, "elapsed_time": "1:39:38", "remaining_time": "0:02:02"}
148
+ {"current_steps": 148, "total_steps": 150, "loss": 0.0008, "lr": 1.0828886614754342e-08, "epoch": 14.8, "percentage": 98.67, "elapsed_time": "1:40:08", "remaining_time": "0:01:21"}
149
+ {"current_steps": 149, "total_steps": 150, "loss": 0.0008, "lr": 2.7075882053828605e-09, "epoch": 14.9, "percentage": 99.33, "elapsed_time": "1:40:49", "remaining_time": "0:00:40"}
150
+ {"current_steps": 150, "total_steps": 150, "loss": 0.0008, "lr": 0.0, "epoch": 15.0, "percentage": 100.0, "elapsed_time": "1:41:25", "remaining_time": "0:00:00"}
151
+ {"current_steps": 150, "total_steps": 150, "epoch": 15.0, "percentage": 100.0, "elapsed_time": "1:44:01", "remaining_time": "0:00:00"}