Hugging Face's logo

mlfoundations-dev
/
oh_v3-1_only_glaive_code_assistant

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
esfrankel17 commited on
Commit
9cf70a9
·
verified ·
1 Parent(s): 9bba250

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 +13 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b347e7656cb3329f1dc5e252d10969d8d91dfd1b39d67fa706d556dfef2ea944
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875885b51240ad910c657b5240e33e5ff4d676a0422c020b75ccad95845b9efb
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8441a81ae53f602927f7cc608cf5b60828ff51f0385a143c17f83e7ea3067376
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9912bce50c5ddf650fcf309fa9b9f8deb4f5b08e754bf8b0030af4425a388683
3
  size 4999802720
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:143536cdbd9e21bf79fd7363820d31539be7987f0cd3e89115bd517327646db8
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4428f2744e9270b4e5f4000f97cbe83fe29cf8bf281a752b7b6e3d9696803843
3
  size 4915916176
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c5808ddd16216fde11bb479bb5862fc7182bf6b4e6da37e968d6a28a23832e8
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04a88f7fd921b13bbdbfd521b78ab98877288937b9c5d2f383d190ed22a3102d
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -22,3 +22,16 @@
22
  {"current_steps": 210, "total_steps": 330, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 1.8983050847457628, "percentage": 63.64, "elapsed_time": "1:50:29", "remaining_time": "1:03:08"}
23
  {"current_steps": 220, "total_steps": 330, "loss": 0.5574, "learning_rate": 5e-06, "epoch": 1.9887005649717513, "percentage": 66.67, "elapsed_time": "1:55:38", "remaining_time": "0:57:49"}
24
  {"current_steps": 221, "total_steps": 330, "eval_loss": 0.580794095993042, "epoch": 1.9977401129943502, "percentage": 66.97, "elapsed_time": "1:57:27", "remaining_time": "0:57:55"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22
  {"current_steps": 210, "total_steps": 330, "loss": 0.5549, "learning_rate": 5e-06, "epoch": 1.8983050847457628, "percentage": 63.64, "elapsed_time": "1:50:29", "remaining_time": "1:03:08"}
23
  {"current_steps": 220, "total_steps": 330, "loss": 0.5574, "learning_rate": 5e-06, "epoch": 1.9887005649717513, "percentage": 66.67, "elapsed_time": "1:55:38", "remaining_time": "0:57:49"}
24
  {"current_steps": 221, "total_steps": 330, "eval_loss": 0.580794095993042, "epoch": 1.9977401129943502, "percentage": 66.97, "elapsed_time": "1:57:27", "remaining_time": "0:57:55"}
25
+ {"current_steps": 230, "total_steps": 330, "loss": 0.5432, "learning_rate": 5e-06, "epoch": 2.07909604519774, "percentage": 69.7, "elapsed_time": "2:03:09", "remaining_time": "0:53:32"}
26
+ {"current_steps": 240, "total_steps": 330, "loss": 0.5182, "learning_rate": 5e-06, "epoch": 2.169491525423729, "percentage": 72.73, "elapsed_time": "2:08:19", "remaining_time": "0:48:07"}
27
+ {"current_steps": 250, "total_steps": 330, "loss": 0.5201, "learning_rate": 5e-06, "epoch": 2.2598870056497176, "percentage": 75.76, "elapsed_time": "2:13:31", "remaining_time": "0:42:43"}
28
+ {"current_steps": 260, "total_steps": 330, "loss": 0.5186, "learning_rate": 5e-06, "epoch": 2.3502824858757063, "percentage": 78.79, "elapsed_time": "2:18:41", "remaining_time": "0:37:20"}
29
+ {"current_steps": 270, "total_steps": 330, "loss": 0.5193, "learning_rate": 5e-06, "epoch": 2.440677966101695, "percentage": 81.82, "elapsed_time": "2:23:51", "remaining_time": "0:31:58"}
30
+ {"current_steps": 280, "total_steps": 330, "loss": 0.5262, "learning_rate": 5e-06, "epoch": 2.5310734463276834, "percentage": 84.85, "elapsed_time": "2:29:02", "remaining_time": "0:26:36"}
31
+ {"current_steps": 290, "total_steps": 330, "loss": 0.5232, "learning_rate": 5e-06, "epoch": 2.621468926553672, "percentage": 87.88, "elapsed_time": "2:34:12", "remaining_time": "0:21:16"}
32
+ {"current_steps": 300, "total_steps": 330, "loss": 0.5192, "learning_rate": 5e-06, "epoch": 2.711864406779661, "percentage": 90.91, "elapsed_time": "2:39:22", "remaining_time": "0:15:56"}
33
+ {"current_steps": 310, "total_steps": 330, "loss": 0.526, "learning_rate": 5e-06, "epoch": 2.8022598870056497, "percentage": 93.94, "elapsed_time": "2:44:31", "remaining_time": "0:10:36"}
34
+ {"current_steps": 320, "total_steps": 330, "loss": 0.5174, "learning_rate": 5e-06, "epoch": 2.8926553672316384, "percentage": 96.97, "elapsed_time": "2:49:39", "remaining_time": "0:05:18"}
35
+ {"current_steps": 330, "total_steps": 330, "loss": 0.5233, "learning_rate": 5e-06, "epoch": 2.983050847457627, "percentage": 100.0, "elapsed_time": "2:54:48", "remaining_time": "0:00:00"}
36
+ {"current_steps": 330, "total_steps": 330, "eval_loss": 0.5797294974327087, "epoch": 2.983050847457627, "percentage": 100.0, "elapsed_time": "2:57:17", "remaining_time": "0:00:00"}
37
+ {"current_steps": 330, "total_steps": 330, "epoch": 2.983050847457627, "percentage": 100.0, "elapsed_time": "2:58:20", "remaining_time": "0:00:00"}