Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_epoch3_dcftv1.2

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
sedrickkeh commited on
Commit
e54b08d
·
verified ·
1 Parent(s): 36ea5d8

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 +33 -0
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f997b121e8312a92208c5ba74990cf3ce5273a4427f1e7940a261370706b0b9
3
  size 4903351912
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:532ad72726d5f1c8be77df56851b59c42c74a2491e2be144820fb619b7372541
3
  size 4903351912
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:198089ec9b4c952e4489d58c631a384691e1bbab9152459f5257dd06ff8371f1
3
  size 4947570872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cad05750d48ef87c113f06d2882d249543abb7b298a8da5fd984dfb708f19ab5
3
  size 4947570872
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46d36d201e8529e6e91bd2834b478fa80fc8e8e0cd45efeb67f558d6e178eaa8
3
  size 4962221464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:907564fb4555a5ad241c27384689846a929c5529510b3d9e300f55f6dfce1907
3
  size 4962221464
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81ad43858df73453bb935bc107f2a7ca49d442ca5cb6c9199a0001820a40e913
3
  size 3670322200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:995494e66b59b8015e9323be0d79d481609e02f043011f38c70414597c9b8e60
3
  size 3670322200
trainer_log.jsonl CHANGED
@@ -67,3 +67,36 @@
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5595, "lr": 5e-06, "epoch": 1.9753086419753085, "percentage": 65.87, "elapsed_time": "8:26:52", "remaining_time": "4:22:39"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.615513026714325, "epoch": 1.9992517770295548, "percentage": 66.67, "elapsed_time": "8:37:39", "remaining_time": "4:18:49"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.5957, "lr": 5e-06, "epoch": 2.0052375607931165, "percentage": 66.87, "elapsed_time": "8:40:10", "remaining_time": "4:17:45"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  {"current_steps": 660, "total_steps": 1002, "loss": 0.5595, "lr": 5e-06, "epoch": 1.9753086419753085, "percentage": 65.87, "elapsed_time": "8:26:52", "remaining_time": "4:22:39"}
68
  {"current_steps": 668, "total_steps": 1002, "eval_loss": 0.615513026714325, "epoch": 1.9992517770295548, "percentage": 66.67, "elapsed_time": "8:37:39", "remaining_time": "4:18:49"}
69
  {"current_steps": 670, "total_steps": 1002, "loss": 0.5957, "lr": 5e-06, "epoch": 2.0052375607931165, "percentage": 66.87, "elapsed_time": "8:40:10", "remaining_time": "4:17:45"}
70
+ {"current_steps": 680, "total_steps": 1002, "loss": 0.4851, "lr": 5e-06, "epoch": 2.035166479610924, "percentage": 67.86, "elapsed_time": "8:47:47", "remaining_time": "4:09:55"}
71
+ {"current_steps": 690, "total_steps": 1002, "loss": 0.4799, "lr": 5e-06, "epoch": 2.0650953984287317, "percentage": 68.86, "elapsed_time": "8:55:23", "remaining_time": "4:02:05"}
72
+ {"current_steps": 700, "total_steps": 1002, "loss": 0.4845, "lr": 5e-06, "epoch": 2.0950243172465393, "percentage": 69.86, "elapsed_time": "9:03:00", "remaining_time": "3:54:15"}
73
+ {"current_steps": 710, "total_steps": 1002, "loss": 0.4862, "lr": 5e-06, "epoch": 2.1249532360643473, "percentage": 70.86, "elapsed_time": "9:10:36", "remaining_time": "3:46:26"}
74
+ {"current_steps": 720, "total_steps": 1002, "loss": 0.4882, "lr": 5e-06, "epoch": 2.154882154882155, "percentage": 71.86, "elapsed_time": "9:18:13", "remaining_time": "3:38:38"}
75
+ {"current_steps": 730, "total_steps": 1002, "loss": 0.4894, "lr": 5e-06, "epoch": 2.1848110736999624, "percentage": 72.85, "elapsed_time": "9:25:49", "remaining_time": "3:30:49"}
76
+ {"current_steps": 740, "total_steps": 1002, "loss": 0.4898, "lr": 5e-06, "epoch": 2.2147399925177704, "percentage": 73.85, "elapsed_time": "9:33:25", "remaining_time": "3:23:01"}
77
+ {"current_steps": 750, "total_steps": 1002, "loss": 0.4917, "lr": 5e-06, "epoch": 2.244668911335578, "percentage": 74.85, "elapsed_time": "9:41:02", "remaining_time": "3:15:13"}
78
+ {"current_steps": 760, "total_steps": 1002, "loss": 0.4878, "lr": 5e-06, "epoch": 2.2745978301533856, "percentage": 75.85, "elapsed_time": "9:48:38", "remaining_time": "3:07:26"}
79
+ {"current_steps": 770, "total_steps": 1002, "loss": 0.4936, "lr": 5e-06, "epoch": 2.3045267489711936, "percentage": 76.85, "elapsed_time": "9:56:14", "remaining_time": "2:59:38"}
80
+ {"current_steps": 780, "total_steps": 1002, "loss": 0.4885, "lr": 5e-06, "epoch": 2.334455667789001, "percentage": 77.84, "elapsed_time": "10:03:50", "remaining_time": "2:51:51"}
81
+ {"current_steps": 790, "total_steps": 1002, "loss": 0.4902, "lr": 5e-06, "epoch": 2.3643845866068087, "percentage": 78.84, "elapsed_time": "10:11:26", "remaining_time": "2:44:05"}
82
+ {"current_steps": 800, "total_steps": 1002, "loss": 0.4947, "lr": 5e-06, "epoch": 2.3943135054246163, "percentage": 79.84, "elapsed_time": "10:19:03", "remaining_time": "2:36:18"}
83
+ {"current_steps": 810, "total_steps": 1002, "loss": 0.4995, "lr": 5e-06, "epoch": 2.4242424242424243, "percentage": 80.84, "elapsed_time": "10:26:39", "remaining_time": "2:28:32"}
84
+ {"current_steps": 820, "total_steps": 1002, "loss": 0.4979, "lr": 5e-06, "epoch": 2.454171343060232, "percentage": 81.84, "elapsed_time": "10:34:15", "remaining_time": "2:20:46"}
85
+ {"current_steps": 830, "total_steps": 1002, "loss": 0.4968, "lr": 5e-06, "epoch": 2.48410026187804, "percentage": 82.83, "elapsed_time": "10:41:51", "remaining_time": "2:13:00"}
86
+ {"current_steps": 840, "total_steps": 1002, "loss": 0.4951, "lr": 5e-06, "epoch": 2.5140291806958475, "percentage": 83.83, "elapsed_time": "10:49:27", "remaining_time": "2:05:15"}
87
+ {"current_steps": 850, "total_steps": 1002, "loss": 0.498, "lr": 5e-06, "epoch": 2.543958099513655, "percentage": 84.83, "elapsed_time": "10:57:04", "remaining_time": "1:57:29"}
88
+ {"current_steps": 860, "total_steps": 1002, "loss": 0.4959, "lr": 5e-06, "epoch": 2.5738870183314626, "percentage": 85.83, "elapsed_time": "11:04:40", "remaining_time": "1:49:44"}
89
+ {"current_steps": 870, "total_steps": 1002, "loss": 0.4938, "lr": 5e-06, "epoch": 2.6038159371492706, "percentage": 86.83, "elapsed_time": "11:12:16", "remaining_time": "1:41:59"}
90
+ {"current_steps": 880, "total_steps": 1002, "loss": 0.4921, "lr": 5e-06, "epoch": 2.633744855967078, "percentage": 87.82, "elapsed_time": "11:19:52", "remaining_time": "1:34:15"}
91
+ {"current_steps": 890, "total_steps": 1002, "loss": 0.4977, "lr": 5e-06, "epoch": 2.6636737747848858, "percentage": 88.82, "elapsed_time": "11:27:28", "remaining_time": "1:26:30"}
92
+ {"current_steps": 900, "total_steps": 1002, "loss": 0.5011, "lr": 5e-06, "epoch": 2.6936026936026938, "percentage": 89.82, "elapsed_time": "11:35:04", "remaining_time": "1:18:46"}
93
+ {"current_steps": 910, "total_steps": 1002, "loss": 0.4947, "lr": 5e-06, "epoch": 2.7235316124205013, "percentage": 90.82, "elapsed_time": "11:42:40", "remaining_time": "1:11:02"}
94
+ {"current_steps": 920, "total_steps": 1002, "loss": 0.4959, "lr": 5e-06, "epoch": 2.753460531238309, "percentage": 91.82, "elapsed_time": "11:50:17", "remaining_time": "1:03:18"}
95
+ {"current_steps": 930, "total_steps": 1002, "loss": 0.5016, "lr": 5e-06, "epoch": 2.7833894500561165, "percentage": 92.81, "elapsed_time": "11:57:53", "remaining_time": "0:55:34"}
96
+ {"current_steps": 940, "total_steps": 1002, "loss": 0.4985, "lr": 5e-06, "epoch": 2.8133183688739245, "percentage": 93.81, "elapsed_time": "12:05:30", "remaining_time": "0:47:51"}
97
+ {"current_steps": 950, "total_steps": 1002, "loss": 0.4986, "lr": 5e-06, "epoch": 2.843247287691732, "percentage": 94.81, "elapsed_time": "12:13:06", "remaining_time": "0:40:07"}
98
+ {"current_steps": 960, "total_steps": 1002, "loss": 0.502, "lr": 5e-06, "epoch": 2.87317620650954, "percentage": 95.81, "elapsed_time": "12:20:43", "remaining_time": "0:32:24"}
99
+ {"current_steps": 970, "total_steps": 1002, "loss": 0.4959, "lr": 5e-06, "epoch": 2.9031051253273477, "percentage": 96.81, "elapsed_time": "12:28:18", "remaining_time": "0:24:41"}
100
+ {"current_steps": 980, "total_steps": 1002, "loss": 0.5023, "lr": 5e-06, "epoch": 2.9330340441451552, "percentage": 97.8, "elapsed_time": "12:35:55", "remaining_time": "0:16:58"}
101
+ {"current_steps": 990, "total_steps": 1002, "loss": 0.5048, "lr": 5e-06, "epoch": 2.962962962962963, "percentage": 98.8, "elapsed_time": "12:43:31", "remaining_time": "0:09:15"}
102
+ {"current_steps": 1000, "total_steps": 1002, "loss": 0.5047, "lr": 5e-06, "epoch": 2.992891881780771, "percentage": 99.8, "elapsed_time": "12:51:07", "remaining_time": "0:01:32"}