Training in progress, epoch 1
Browse files
model-00001-of-00004.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4877660776
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c014cf493882e8343bd82432d25d5780a3b91c684fdd1ddb853c075bcf7293e4
|
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:
|
3 |
size 4932751008
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11423c429d4f917452f98bb3a7b83e74417c1221bf4b1f36db708ba034239e86
|
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:
|
3 |
size 4330865200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08874ae21b38628dabdcc21c5f37aa17cfa33795b5cc804e91d9cbfc16978d70
|
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:
|
3 |
size 1089994880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90eb55a72ca1e574b50fbfed9585cb331962613dd9f185a924edac0ad72bd9cf
|
3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
@@ -32,3 +32,35 @@
|
|
32 |
{"current_steps": 32, "total_steps": 224, "loss": 0.713, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:04:59", "remaining_time": "6:29:55"}
|
33 |
{"current_steps": 33, "total_steps": 224, "loss": 0.707, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:07:37", "remaining_time": "6:31:26"}
|
34 |
{"current_steps": 34, "total_steps": 224, "loss": 0.679, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:09:33", "remaining_time": "6:28:45"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
32 |
{"current_steps": 32, "total_steps": 224, "loss": 0.713, "lr": 1.990122514534651e-05, "epoch": 0.9721518987341772, "percentage": 14.29, "elapsed_time": "1:04:59", "remaining_time": "6:29:55"}
|
33 |
{"current_steps": 33, "total_steps": 224, "loss": 0.707, "lr": 1.9878102910595097e-05, "epoch": 1.010126582278481, "percentage": 14.73, "elapsed_time": "1:07:37", "remaining_time": "6:31:26"}
|
34 |
{"current_steps": 34, "total_steps": 224, "loss": 0.679, "lr": 1.985256759242359e-05, "epoch": 1.040506329113924, "percentage": 15.18, "elapsed_time": "1:09:33", "remaining_time": "6:28:45"}
|
35 |
+
{"current_steps": 35, "total_steps": 224, "loss": 0.6817, "lr": 1.982462542875576e-05, "epoch": 1.070886075949367, "percentage": 15.62, "elapsed_time": "1:11:33", "remaining_time": "6:26:22"}
|
36 |
+
{"current_steps": 36, "total_steps": 224, "loss": 0.6638, "lr": 1.979428324547432e-05, "epoch": 1.1012658227848102, "percentage": 16.07, "elapsed_time": "1:13:24", "remaining_time": "6:23:22"}
|
37 |
+
{"current_steps": 37, "total_steps": 224, "loss": 0.6612, "lr": 1.9761548454753455e-05, "epoch": 1.1316455696202532, "percentage": 16.52, "elapsed_time": "1:15:24", "remaining_time": "6:21:07"}
|
38 |
+
{"current_steps": 38, "total_steps": 224, "loss": 0.6698, "lr": 1.972642905324813e-05, "epoch": 1.1620253164556962, "percentage": 16.96, "elapsed_time": "1:17:23", "remaining_time": "6:18:49"}
|
39 |
+
{"current_steps": 39, "total_steps": 224, "loss": 0.7059, "lr": 1.9688933620140638e-05, "epoch": 1.1924050632911392, "percentage": 17.41, "elapsed_time": "1:19:17", "remaining_time": "6:16:05"}
|
40 |
+
{"current_steps": 40, "total_steps": 224, "loss": 0.6519, "lr": 1.96490713150448e-05, "epoch": 1.2227848101265824, "percentage": 17.86, "elapsed_time": "1:21:20", "remaining_time": "6:14:10"}
|
41 |
+
{"current_steps": 41, "total_steps": 224, "loss": 0.6575, "lr": 1.9606851875768404e-05, "epoch": 1.2531645569620253, "percentage": 18.3, "elapsed_time": "1:23:34", "remaining_time": "6:13:03"}
|
42 |
+
{"current_steps": 42, "total_steps": 224, "loss": 0.6557, "lr": 1.956228561593441e-05, "epoch": 1.2835443037974683, "percentage": 18.75, "elapsed_time": "1:25:33", "remaining_time": "6:10:44"}
|
43 |
+
{"current_steps": 43, "total_steps": 224, "loss": 0.6426, "lr": 1.9515383422461457e-05, "epoch": 1.3139240506329113, "percentage": 19.2, "elapsed_time": "1:27:32", "remaining_time": "6:08:27"}
|
44 |
+
{"current_steps": 44, "total_steps": 224, "loss": 0.631, "lr": 1.9466156752904344e-05, "epoch": 1.3443037974683545, "percentage": 19.64, "elapsed_time": "1:29:28", "remaining_time": "6:06:03"}
|
45 |
+
{"current_steps": 45, "total_steps": 224, "loss": 0.648, "lr": 1.9414617632655114e-05, "epoch": 1.3746835443037975, "percentage": 20.09, "elapsed_time": "1:31:30", "remaining_time": "6:04:01"}
|
46 |
+
{"current_steps": 46, "total_steps": 224, "loss": 0.6361, "lr": 1.9360778652005416e-05, "epoch": 1.4050632911392404, "percentage": 20.54, "elapsed_time": "1:33:27", "remaining_time": "6:01:38"}
|
47 |
+
{"current_steps": 47, "total_steps": 224, "loss": 0.6379, "lr": 1.9304652963070868e-05, "epoch": 1.4354430379746836, "percentage": 20.98, "elapsed_time": "1:35:33", "remaining_time": "5:59:53"}
|
48 |
+
{"current_steps": 48, "total_steps": 224, "loss": 0.6443, "lr": 1.9246254276578175e-05, "epoch": 1.4658227848101266, "percentage": 21.43, "elapsed_time": "1:37:32", "remaining_time": "5:57:37"}
|
49 |
+
{"current_steps": 49, "total_steps": 224, "loss": 0.6603, "lr": 1.9185596858515797e-05, "epoch": 1.4962025316455696, "percentage": 21.88, "elapsed_time": "1:39:33", "remaining_time": "5:55:33"}
|
50 |
+
{"current_steps": 50, "total_steps": 224, "loss": 0.6473, "lr": 1.9122695526648968e-05, "epoch": 1.5265822784810128, "percentage": 22.32, "elapsed_time": "1:41:41", "remaining_time": "5:53:54"}
|
51 |
+
{"current_steps": 51, "total_steps": 224, "loss": 0.6371, "lr": 1.905756564689991e-05, "epoch": 1.5569620253164556, "percentage": 22.77, "elapsed_time": "1:43:49", "remaining_time": "5:52:11"}
|
52 |
+
{"current_steps": 52, "total_steps": 224, "loss": 0.6316, "lr": 1.8990223129594146e-05, "epoch": 1.5873417721518988, "percentage": 23.21, "elapsed_time": "1:45:48", "remaining_time": "5:49:59"}
|
53 |
+
{"current_steps": 53, "total_steps": 224, "loss": 0.6399, "lr": 1.8920684425573865e-05, "epoch": 1.6177215189873417, "percentage": 23.66, "elapsed_time": "1:47:58", "remaining_time": "5:48:23"}
|
54 |
+
{"current_steps": 54, "total_steps": 224, "loss": 0.6423, "lr": 1.884896652217917e-05, "epoch": 1.6481012658227847, "percentage": 24.11, "elapsed_time": "1:49:51", "remaining_time": "5:45:50"}
|
55 |
+
{"current_steps": 55, "total_steps": 224, "loss": 0.6354, "lr": 1.877508693909831e-05, "epoch": 1.678481012658228, "percentage": 24.55, "elapsed_time": "1:51:52", "remaining_time": "5:43:45"}
|
56 |
+
{"current_steps": 56, "total_steps": 224, "loss": 0.6495, "lr": 1.8699063724087905e-05, "epoch": 1.7088607594936709, "percentage": 25.0, "elapsed_time": "1:53:56", "remaining_time": "5:41:50"}
|
57 |
+
{"current_steps": 57, "total_steps": 224, "loss": 0.6539, "lr": 1.862091544856407e-05, "epoch": 1.7392405063291139, "percentage": 25.45, "elapsed_time": "1:55:58", "remaining_time": "5:39:46"}
|
58 |
+
{"current_steps": 58, "total_steps": 224, "loss": 0.6376, "lr": 1.854066120306571e-05, "epoch": 1.769620253164557, "percentage": 25.89, "elapsed_time": "1:57:52", "remaining_time": "5:37:21"}
|
59 |
+
{"current_steps": 59, "total_steps": 224, "loss": 0.6212, "lr": 1.8458320592590976e-05, "epoch": 1.8, "percentage": 26.34, "elapsed_time": "2:00:09", "remaining_time": "5:36:01"}
|
60 |
+
{"current_steps": 60, "total_steps": 224, "loss": 0.6368, "lr": 1.837391373180801e-05, "epoch": 1.830379746835443, "percentage": 26.79, "elapsed_time": "2:02:08", "remaining_time": "5:33:52"}
|
61 |
+
{"current_steps": 61, "total_steps": 224, "loss": 0.6265, "lr": 1.8287461240141217e-05, "epoch": 1.8607594936708862, "percentage": 27.23, "elapsed_time": "2:04:13", "remaining_time": "5:31:55"}
|
62 |
+
{"current_steps": 62, "total_steps": 224, "loss": 0.631, "lr": 1.8198984236734246e-05, "epoch": 1.891139240506329, "percentage": 27.68, "elapsed_time": "2:06:15", "remaining_time": "5:29:53"}
|
63 |
+
{"current_steps": 63, "total_steps": 224, "loss": 0.6156, "lr": 1.8108504335290852e-05, "epoch": 1.9215189873417722, "percentage": 28.12, "elapsed_time": "2:08:24", "remaining_time": "5:28:10"}
|
64 |
+
{"current_steps": 64, "total_steps": 224, "loss": 0.6216, "lr": 1.8016043638794975e-05, "epoch": 1.9518987341772152, "percentage": 28.57, "elapsed_time": "2:10:25", "remaining_time": "5:26:04"}
|
65 |
+
{"current_steps": 65, "total_steps": 224, "loss": 0.612, "lr": 1.7921624734111292e-05, "epoch": 1.9822784810126581, "percentage": 29.02, "elapsed_time": "2:12:39", "remaining_time": "5:24:30"}
|
66 |
+
{"current_steps": 66, "total_steps": 224, "loss": 0.6075, "lr": 1.7825270686467567e-05, "epoch": 2.020253164556962, "percentage": 29.46, "elapsed_time": "2:15:39", "remaining_time": "5:24:45"}
|