sedrickkeh commited on
Commit
5af5347
·
verified ·
1 Parent(s): 54d7877

Training in progress, epoch 2

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:868fe5fa9fe0eae9eb90012bea6ad6f41c35afdee2e812fcb068f4107c7dc956
3
  size 4877660776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c119b2a1f3f1e65c2e30fb4fee97052008a1c3b2f10e3fb19e40b615176bdf7c
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:c116d13c6628f4c3ea37cd0411c41b354a93f1da413019a56cbfe092c24da04e
3
  size 4932751008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:472f399d0cbc501df8399cfea7ab18377cd065b5a055917b604e526a6b2d6e3e
3
  size 4932751008
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ff7fcc2e25ab4eed7a9ad988927c9e2eb4b50613ddc89fe0bf968a7c03c019b
3
  size 4330865200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68b32a2193fb4098402129214838a92d19085000693b6ede1c9f82e8537a2489
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:ac7af2a95ab8cfcaac78d5eb2c6baf1d175a2f1e4ae303555797f42130d9d1a9
3
  size 1089994880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:026b505390d66ac4bcd7c64208918d4bf66358ad666ddc6e5a01c7b68d1957de
3
  size 1089994880
trainer_log.jsonl CHANGED
@@ -62,3 +62,33 @@
62
  {"current_steps": 62, "total_steps": 93, "loss": 0.8321, "lr": 3.0647485139889145e-06, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:57:15", "remaining_time": "0:28:37"}
63
  {"current_steps": 63, "total_steps": 93, "loss": 1.5436, "lr": 2.89167433274908e-06, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "0:59:20", "remaining_time": "0:28:15"}
64
  {"current_steps": 64, "total_steps": 93, "loss": 0.8582, "lr": 2.721620307718793e-06, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "1:00:15", "remaining_time": "0:27:18"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62
  {"current_steps": 62, "total_steps": 93, "loss": 0.8321, "lr": 3.0647485139889145e-06, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:57:15", "remaining_time": "0:28:37"}
63
  {"current_steps": 63, "total_steps": 93, "loss": 1.5436, "lr": 2.89167433274908e-06, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "0:59:20", "remaining_time": "0:28:15"}
64
  {"current_steps": 64, "total_steps": 93, "loss": 0.8582, "lr": 2.721620307718793e-06, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "1:00:15", "remaining_time": "0:27:18"}
65
+ {"current_steps": 65, "total_steps": 93, "loss": 0.8665, "lr": 2.554830039650834e-06, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "1:01:14", "remaining_time": "0:26:22"}
66
+ {"current_steps": 66, "total_steps": 93, "loss": 0.8705, "lr": 2.391542453997578e-06, "epoch": 2.112, "percentage": 70.97, "elapsed_time": "1:02:06", "remaining_time": "0:25:24"}
67
+ {"current_steps": 67, "total_steps": 93, "loss": 0.7992, "lr": 2.2319914586525776e-06, "epoch": 2.144, "percentage": 72.04, "elapsed_time": "1:02:56", "remaining_time": "0:24:25"}
68
+ {"current_steps": 68, "total_steps": 93, "loss": 0.8735, "lr": 2.0764056088797646e-06, "epoch": 2.176, "percentage": 73.12, "elapsed_time": "1:03:54", "remaining_time": "0:23:29"}
69
+ {"current_steps": 69, "total_steps": 93, "loss": 0.8379, "lr": 1.9250077799102323e-06, "epoch": 2.208, "percentage": 74.19, "elapsed_time": "1:04:40", "remaining_time": "0:22:29"}
70
+ {"current_steps": 70, "total_steps": 93, "loss": 0.8338, "lr": 1.7780148476756148e-06, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "1:05:35", "remaining_time": "0:21:33"}
71
+ {"current_steps": 71, "total_steps": 93, "loss": 0.7843, "lr": 1.6356373781354058e-06, "epoch": 2.2720000000000002, "percentage": 76.34, "elapsed_time": "1:06:36", "remaining_time": "0:20:38"}
72
+ {"current_steps": 72, "total_steps": 93, "loss": 0.8256, "lr": 1.4980793256432474e-06, "epoch": 2.304, "percentage": 77.42, "elapsed_time": "1:07:28", "remaining_time": "0:19:40"}
73
+ {"current_steps": 73, "total_steps": 93, "loss": 0.8289, "lr": 1.3655377407842813e-06, "epoch": 2.336, "percentage": 78.49, "elapsed_time": "1:08:17", "remaining_time": "0:18:42"}
74
+ {"current_steps": 74, "total_steps": 93, "loss": 0.8025, "lr": 1.2382024881020937e-06, "epoch": 2.368, "percentage": 79.57, "elapsed_time": "1:09:09", "remaining_time": "0:17:45"}
75
+ {"current_steps": 75, "total_steps": 93, "loss": 0.9191, "lr": 1.1162559741195733e-06, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "1:10:06", "remaining_time": "0:16:49"}
76
+ {"current_steps": 76, "total_steps": 93, "loss": 0.8216, "lr": 9.998728860433277e-07, "epoch": 2.432, "percentage": 81.72, "elapsed_time": "1:10:59", "remaining_time": "0:15:52"}
77
+ {"current_steps": 77, "total_steps": 93, "loss": 0.8265, "lr": 8.892199415259501e-07, "epoch": 2.464, "percentage": 82.8, "elapsed_time": "1:11:59", "remaining_time": "0:14:57"}
78
+ {"current_steps": 78, "total_steps": 93, "loss": 0.8353, "lr": 7.844556498445788e-07, "epoch": 2.496, "percentage": 83.87, "elapsed_time": "1:12:49", "remaining_time": "0:14:00"}
79
+ {"current_steps": 79, "total_steps": 93, "loss": 0.8233, "lr": 6.857300848378857e-07, "epoch": 2.528, "percentage": 84.95, "elapsed_time": "1:13:41", "remaining_time": "0:13:03"}
80
+ {"current_steps": 80, "total_steps": 93, "loss": 0.918, "lr": 5.931846699267558e-07, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "1:14:33", "remaining_time": "0:12:06"}
81
+ {"current_steps": 81, "total_steps": 93, "loss": 0.7847, "lr": 5.0695197552659e-07, "epoch": 2.592, "percentage": 87.1, "elapsed_time": "1:15:23", "remaining_time": "0:11:10"}
82
+ {"current_steps": 82, "total_steps": 93, "loss": 0.8077, "lr": 4.271555291414636e-07, "epoch": 2.624, "percentage": 88.17, "elapsed_time": "1:16:19", "remaining_time": "0:10:14"}
83
+ {"current_steps": 83, "total_steps": 93, "loss": 0.8602, "lr": 3.539096384121743e-07, "epoch": 2.656, "percentage": 89.25, "elapsed_time": "1:17:10", "remaining_time": "0:09:17"}
84
+ {"current_steps": 84, "total_steps": 93, "loss": 0.846, "lr": 2.873192273716369e-07, "epoch": 2.6879999999999997, "percentage": 90.32, "elapsed_time": "1:18:09", "remaining_time": "0:08:22"}
85
+ {"current_steps": 85, "total_steps": 93, "loss": 0.808, "lr": 2.274796861422246e-07, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "1:19:10", "remaining_time": "0:07:27"}
86
+ {"current_steps": 86, "total_steps": 93, "loss": 0.8078, "lr": 1.7447673429033361e-07, "epoch": 2.752, "percentage": 92.47, "elapsed_time": "1:20:09", "remaining_time": "0:06:31"}
87
+ {"current_steps": 87, "total_steps": 93, "loss": 0.8601, "lr": 1.2838629803393343e-07, "epoch": 2.784, "percentage": 93.55, "elapsed_time": "1:21:01", "remaining_time": "0:05:35"}
88
+ {"current_steps": 88, "total_steps": 93, "loss": 0.8478, "lr": 8.927440147898703e-08, "epoch": 2.816, "percentage": 94.62, "elapsed_time": "1:21:45", "remaining_time": "0:04:38"}
89
+ {"current_steps": 89, "total_steps": 93, "loss": 0.9191, "lr": 5.7197072040557356e-08, "epoch": 2.848, "percentage": 95.7, "elapsed_time": "1:22:47", "remaining_time": "0:03:43"}
90
+ {"current_steps": 90, "total_steps": 93, "loss": 0.7321, "lr": 3.220026018407541e-08, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "1:23:34", "remaining_time": "0:02:47"}
91
+ {"current_steps": 91, "total_steps": 93, "loss": 0.8163, "lr": 1.431977360173975e-08, "epoch": 2.912, "percentage": 97.85, "elapsed_time": "1:24:30", "remaining_time": "0:01:51"}
92
+ {"current_steps": 92, "total_steps": 93, "loss": 0.8683, "lr": 3.5812259183426457e-09, "epoch": 2.944, "percentage": 98.92, "elapsed_time": "1:25:28", "remaining_time": "0:00:55"}
93
+ {"current_steps": 93, "total_steps": 93, "loss": 0.8822, "lr": 0.0, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "1:26:27", "remaining_time": "0:00:00"}
94
+ {"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "1:28:37", "remaining_time": "0:00:00"}