Hugging Face's logo

mlfoundations-dev
/
oh-dcft-v1.2_no-curation_gpt-4o-mini_wo_camel_chemistry

Text Generation
Transformers
Safetensors
llama
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
gsmyrnis commited on
Commit
924bf67
·
verified ·
1 Parent(s): ea8894d

Training in progress, epoch 3

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 +30 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99c3461104f1eda4529847ba3550fbac4a5fd606d7b4d08b8ad809837287ff01
3
  size 4976698672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d06ae95e4fd27c5c254063ce5d550c63ae1f18008927a472a8740590c18e2e
3
  size 4976698672
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0736655a15c11c239406ee5f772a3ec9eb926eb168ea900462bd18d257a3b2d5
3
  size 4999802720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ec429c60626f1685f5c49ab1e5c5f6abfd6116151d1555ee5a837c2b3dbe50e
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:b745d6684363ed754080619cfc073150685ad4fd699d20eaac041ee4105b215b
3
  size 4915916176
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f9d28b3da61bb38af478aae95399cac5889e971ee7e80a61e61356da213ac33
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:f0f9c2235eae5b1238ef2b0b557cfaf16c9beed2c2a367dcd25fad6f07dedf84
3
  size 1168138808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c207eb5c98af306d34859c5a8b4aa7c0740c3fc1ab9bfa9c3987bc74803f8a9b
3
  size 1168138808
trainer_log.jsonl CHANGED
@@ -64,3 +64,33 @@
64
  {"current_steps": 620, "total_steps": 924, "loss": 0.5894, "learning_rate": 5e-06, "epoch": 2.012987012987013, "percentage": 67.1, "elapsed_time": "1:04:47", "remaining_time": "0:31:46"}
65
  {"current_steps": 630, "total_steps": 924, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.0454545454545454, "percentage": 68.18, "elapsed_time": "1:05:46", "remaining_time": "0:30:41"}
66
  {"current_steps": 640, "total_steps": 924, "loss": 0.5669, "learning_rate": 5e-06, "epoch": 2.0779220779220777, "percentage": 69.26, "elapsed_time": "1:06:45", "remaining_time": "0:29:37"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
64
  {"current_steps": 620, "total_steps": 924, "loss": 0.5894, "learning_rate": 5e-06, "epoch": 2.012987012987013, "percentage": 67.1, "elapsed_time": "1:04:47", "remaining_time": "0:31:46"}
65
  {"current_steps": 630, "total_steps": 924, "loss": 0.5677, "learning_rate": 5e-06, "epoch": 2.0454545454545454, "percentage": 68.18, "elapsed_time": "1:05:46", "remaining_time": "0:30:41"}
66
  {"current_steps": 640, "total_steps": 924, "loss": 0.5669, "learning_rate": 5e-06, "epoch": 2.0779220779220777, "percentage": 69.26, "elapsed_time": "1:06:45", "remaining_time": "0:29:37"}
67
+ {"current_steps": 650, "total_steps": 924, "loss": 0.5697, "learning_rate": 5e-06, "epoch": 2.1103896103896105, "percentage": 70.35, "elapsed_time": "1:07:44", "remaining_time": "0:28:33"}
68
+ {"current_steps": 660, "total_steps": 924, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.142857142857143, "percentage": 71.43, "elapsed_time": "1:08:44", "remaining_time": "0:27:29"}
69
+ {"current_steps": 670, "total_steps": 924, "loss": 0.577, "learning_rate": 5e-06, "epoch": 2.175324675324675, "percentage": 72.51, "elapsed_time": "1:09:43", "remaining_time": "0:26:25"}
70
+ {"current_steps": 680, "total_steps": 924, "loss": 0.5724, "learning_rate": 5e-06, "epoch": 2.207792207792208, "percentage": 73.59, "elapsed_time": "1:10:43", "remaining_time": "0:25:22"}
71
+ {"current_steps": 690, "total_steps": 924, "loss": 0.5663, "learning_rate": 5e-06, "epoch": 2.24025974025974, "percentage": 74.68, "elapsed_time": "1:11:42", "remaining_time": "0:24:19"}
72
+ {"current_steps": 700, "total_steps": 924, "loss": 0.5721, "learning_rate": 5e-06, "epoch": 2.2727272727272725, "percentage": 75.76, "elapsed_time": "1:12:40", "remaining_time": "0:23:15"}
73
+ {"current_steps": 710, "total_steps": 924, "loss": 0.5718, "learning_rate": 5e-06, "epoch": 2.3051948051948052, "percentage": 76.84, "elapsed_time": "1:13:40", "remaining_time": "0:22:12"}
74
+ {"current_steps": 720, "total_steps": 924, "loss": 0.5681, "learning_rate": 5e-06, "epoch": 2.3376623376623376, "percentage": 77.92, "elapsed_time": "1:14:40", "remaining_time": "0:21:09"}
75
+ {"current_steps": 730, "total_steps": 924, "loss": 0.5722, "learning_rate": 5e-06, "epoch": 2.3701298701298703, "percentage": 79.0, "elapsed_time": "1:15:39", "remaining_time": "0:20:06"}
76
+ {"current_steps": 740, "total_steps": 924, "loss": 0.578, "learning_rate": 5e-06, "epoch": 2.4025974025974026, "percentage": 80.09, "elapsed_time": "1:16:37", "remaining_time": "0:19:03"}
77
+ {"current_steps": 750, "total_steps": 924, "loss": 0.57, "learning_rate": 5e-06, "epoch": 2.435064935064935, "percentage": 81.17, "elapsed_time": "1:17:38", "remaining_time": "0:18:00"}
78
+ {"current_steps": 760, "total_steps": 924, "loss": 0.5726, "learning_rate": 5e-06, "epoch": 2.4675324675324677, "percentage": 82.25, "elapsed_time": "1:18:37", "remaining_time": "0:16:57"}
79
+ {"current_steps": 770, "total_steps": 924, "loss": 0.5693, "learning_rate": 5e-06, "epoch": 2.5, "percentage": 83.33, "elapsed_time": "1:19:35", "remaining_time": "0:15:55"}
80
+ {"current_steps": 780, "total_steps": 924, "loss": 0.5714, "learning_rate": 5e-06, "epoch": 2.5324675324675323, "percentage": 84.42, "elapsed_time": "1:20:35", "remaining_time": "0:14:52"}
81
+ {"current_steps": 790, "total_steps": 924, "loss": 0.5689, "learning_rate": 5e-06, "epoch": 2.564935064935065, "percentage": 85.5, "elapsed_time": "1:21:34", "remaining_time": "0:13:50"}
82
+ {"current_steps": 800, "total_steps": 924, "loss": 0.5742, "learning_rate": 5e-06, "epoch": 2.5974025974025974, "percentage": 86.58, "elapsed_time": "1:22:33", "remaining_time": "0:12:47"}
83
+ {"current_steps": 810, "total_steps": 924, "loss": 0.5687, "learning_rate": 5e-06, "epoch": 2.62987012987013, "percentage": 87.66, "elapsed_time": "1:23:33", "remaining_time": "0:11:45"}
84
+ {"current_steps": 820, "total_steps": 924, "loss": 0.5763, "learning_rate": 5e-06, "epoch": 2.6623376623376624, "percentage": 88.74, "elapsed_time": "1:24:31", "remaining_time": "0:10:43"}
85
+ {"current_steps": 830, "total_steps": 924, "loss": 0.5747, "learning_rate": 5e-06, "epoch": 2.6948051948051948, "percentage": 89.83, "elapsed_time": "1:25:31", "remaining_time": "0:09:41"}
86
+ {"current_steps": 840, "total_steps": 924, "loss": 0.5711, "learning_rate": 5e-06, "epoch": 2.7272727272727275, "percentage": 90.91, "elapsed_time": "1:26:31", "remaining_time": "0:08:39"}
87
+ {"current_steps": 850, "total_steps": 924, "loss": 0.5701, "learning_rate": 5e-06, "epoch": 2.75974025974026, "percentage": 91.99, "elapsed_time": "1:27:30", "remaining_time": "0:07:37"}
88
+ {"current_steps": 860, "total_steps": 924, "loss": 0.5673, "learning_rate": 5e-06, "epoch": 2.792207792207792, "percentage": 93.07, "elapsed_time": "1:28:28", "remaining_time": "0:06:35"}
89
+ {"current_steps": 870, "total_steps": 924, "loss": 0.5713, "learning_rate": 5e-06, "epoch": 2.824675324675325, "percentage": 94.16, "elapsed_time": "1:29:29", "remaining_time": "0:05:33"}
90
+ {"current_steps": 880, "total_steps": 924, "loss": 0.5749, "learning_rate": 5e-06, "epoch": 2.857142857142857, "percentage": 95.24, "elapsed_time": "1:30:27", "remaining_time": "0:04:31"}
91
+ {"current_steps": 890, "total_steps": 924, "loss": 0.5671, "learning_rate": 5e-06, "epoch": 2.8896103896103895, "percentage": 96.32, "elapsed_time": "1:31:27", "remaining_time": "0:03:29"}
92
+ {"current_steps": 900, "total_steps": 924, "loss": 0.5694, "learning_rate": 5e-06, "epoch": 2.9220779220779223, "percentage": 97.4, "elapsed_time": "1:32:27", "remaining_time": "0:02:27"}
93
+ {"current_steps": 910, "total_steps": 924, "loss": 0.5691, "learning_rate": 5e-06, "epoch": 2.9545454545454546, "percentage": 98.48, "elapsed_time": "1:33:25", "remaining_time": "0:01:26"}
94
+ {"current_steps": 920, "total_steps": 924, "loss": 0.568, "learning_rate": 5e-06, "epoch": 2.987012987012987, "percentage": 99.57, "elapsed_time": "1:34:25", "remaining_time": "0:00:24"}
95
+ {"current_steps": 924, "total_steps": 924, "eval_loss": 0.6653555631637573, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:36:40", "remaining_time": "0:00:00"}
96
+ {"current_steps": 924, "total_steps": 924, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:38:08", "remaining_time": "0:00:00"}