chancharikm commited on
Commit
384d7dc
·
verified ·
1 Parent(s): 3870a4c

Training in progress, step 100

Browse files
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18c16aeaace0dc1d447ca9d0194b7600e6e4b69053c80165c422ec024dde78fb
3
  size 4998056552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bed4480dc618d5c958149a905b27159769a03f3f48747cbc85df65ec875af59
3
  size 4998056552
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10b724aba4d0dfa1b78b76c3fec8cfcc384d2d44200ddf6e7c2653a35c02ce29
3
  size 4915962464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11e702bb5f8eca6805ddbe9ee14453556e2faf2567d389f6951139145dfe8ba
3
  size 4915962464
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c0c6ac4eaf53ce24ed8cfc98c6b5fc719c9a222371f7cf30788abf69a68a820
3
  size 4915962496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e142472c59526c67cd73513fe90b3fad8c125caa8493c1f9f145a50bb229869
3
  size 4915962496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d24b28d0d968b8e7ab6e2cb51cdcdf7f5ba8a5edc51ef7110d44cbfc7466781d
3
  size 2704357976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7483638aacca60c77f95421085f8cb44e640c8410d5d8b2c5e8b4a18fcd05f9
3
  size 2704357976
tokenizer_config.json CHANGED
@@ -234,6 +234,7 @@
234
  "model_max_length": 262144,
235
  "pad_token": "<|endoftext|>",
236
  "padding_side": "right",
 
237
  "split_special_tokens": false,
238
  "tokenizer_class": "Qwen2Tokenizer",
239
  "unk_token": null
 
234
  "model_max_length": 262144,
235
  "pad_token": "<|endoftext|>",
236
  "padding_side": "right",
237
+ "processor_class": "Qwen3VLProcessor",
238
  "split_special_tokens": false,
239
  "tokenizer_class": "Qwen2Tokenizer",
240
  "unk_token": null
trainer_log.jsonl CHANGED
@@ -1,50 +1,100 @@
1
- {"current_steps": 1, "total_steps": 2820, "loss": 2.1209, "lr": 0.0, "epoch": 0.000709471443774388, "percentage": 0.04, "elapsed_time": "0:04:23", "remaining_time": "8 days, 13:58:57"}
2
- {"current_steps": 2, "total_steps": 2820, "loss": 1.9508, "lr": 2.1276595744680852e-07, "epoch": 0.001418942887548776, "percentage": 0.07, "elapsed_time": "0:07:38", "remaining_time": "7 days, 11:21:27"}
3
- {"current_steps": 3, "total_steps": 2820, "loss": 2.2064, "lr": 4.2553191489361704e-07, "epoch": 0.002128414331323164, "percentage": 0.11, "elapsed_time": "0:11:41", "remaining_time": "7 days, 14:51:15"}
4
- {"current_steps": 4, "total_steps": 2820, "loss": 2.003, "lr": 6.382978723404255e-07, "epoch": 0.002837885775097552, "percentage": 0.14, "elapsed_time": "0:16:31", "remaining_time": "8 days, 1:52:27"}
5
- {"current_steps": 5, "total_steps": 2820, "loss": 2.1071, "lr": 8.510638297872341e-07, "epoch": 0.0035473572188719402, "percentage": 0.18, "elapsed_time": "0:20:19", "remaining_time": "7 days, 22:44:48"}
6
- {"current_steps": 6, "total_steps": 2820, "loss": 1.6393, "lr": 1.0638297872340427e-06, "epoch": 0.004256828662646328, "percentage": 0.21, "elapsed_time": "0:24:16", "remaining_time": "7 days, 21:44:59"}
7
- {"current_steps": 7, "total_steps": 2820, "loss": 1.6007, "lr": 1.276595744680851e-06, "epoch": 0.004966300106420717, "percentage": 0.25, "elapsed_time": "0:28:23", "remaining_time": "7 days, 22:09:25"}
8
- {"current_steps": 8, "total_steps": 2820, "loss": 1.0148, "lr": 1.4893617021276596e-06, "epoch": 0.005675771550195104, "percentage": 0.28, "elapsed_time": "0:32:25", "remaining_time": "7 days, 21:58:42"}
9
- {"current_steps": 9, "total_steps": 2820, "loss": 0.8182, "lr": 1.7021276595744682e-06, "epoch": 0.006385242993969493, "percentage": 0.32, "elapsed_time": "0:36:07", "remaining_time": "7 days, 20:03:30"}
10
- {"current_steps": 10, "total_steps": 2820, "loss": 0.3787, "lr": 1.9148936170212763e-06, "epoch": 0.0070947144377438804, "percentage": 0.35, "elapsed_time": "0:40:09", "remaining_time": "7 days, 20:03:25"}
11
- {"current_steps": 11, "total_steps": 2820, "loss": 0.3839, "lr": 2.1276595744680853e-06, "epoch": 0.007804185881518269, "percentage": 0.39, "elapsed_time": "0:44:08", "remaining_time": "7 days, 19:52:12"}
12
- {"current_steps": 12, "total_steps": 2820, "loss": 0.2913, "lr": 2.340425531914894e-06, "epoch": 0.008513657325292657, "percentage": 0.43, "elapsed_time": "0:47:28", "remaining_time": "7 days, 17:07:57"}
13
- {"current_steps": 13, "total_steps": 2820, "loss": 0.255, "lr": 2.553191489361702e-06, "epoch": 0.009223128769067045, "percentage": 0.46, "elapsed_time": "0:51:16", "remaining_time": "7 days, 16:31:23"}
14
- {"current_steps": 14, "total_steps": 2820, "loss": 0.1531, "lr": 2.7659574468085106e-06, "epoch": 0.009932600212841433, "percentage": 0.5, "elapsed_time": "0:54:39", "remaining_time": "7 days, 14:36:10"}
15
- {"current_steps": 15, "total_steps": 2820, "loss": 0.1764, "lr": 2.978723404255319e-06, "epoch": 0.010642071656615822, "percentage": 0.53, "elapsed_time": "0:58:35", "remaining_time": "7 days, 14:35:09"}
16
- {"current_steps": 16, "total_steps": 2820, "loss": 0.1404, "lr": 3.1914893617021277e-06, "epoch": 0.011351543100390209, "percentage": 0.57, "elapsed_time": "1:02:48", "remaining_time": "7 days, 15:27:53"}
17
- {"current_steps": 17, "total_steps": 2820, "loss": 0.1568, "lr": 3.4042553191489363e-06, "epoch": 0.012061014544164597, "percentage": 0.6, "elapsed_time": "1:06:30", "remaining_time": "7 days, 14:47:18"}
18
- {"current_steps": 18, "total_steps": 2820, "loss": 0.1627, "lr": 3.6170212765957445e-06, "epoch": 0.012770485987938986, "percentage": 0.64, "elapsed_time": "1:10:00", "remaining_time": "7 days, 13:38:51"}
19
- {"current_steps": 19, "total_steps": 2820, "loss": 0.1692, "lr": 3.829787234042553e-06, "epoch": 0.013479957431713374, "percentage": 0.67, "elapsed_time": "1:13:40", "remaining_time": "7 days, 13:01:02"}
20
- {"current_steps": 20, "total_steps": 2820, "loss": 0.1887, "lr": 4.042553191489362e-06, "epoch": 0.014189428875487761, "percentage": 0.71, "elapsed_time": "1:18:21", "remaining_time": "7 days, 14:49:50"}
21
- {"current_steps": 21, "total_steps": 2820, "loss": 0.2045, "lr": 4.255319148936171e-06, "epoch": 0.01489890031926215, "percentage": 0.74, "elapsed_time": "1:21:59", "remaining_time": "7 days, 14:08:05"}
22
- {"current_steps": 22, "total_steps": 2820, "loss": 0.1875, "lr": 4.468085106382979e-06, "epoch": 0.015608371763036538, "percentage": 0.78, "elapsed_time": "1:25:26", "remaining_time": "7 days, 13:05:49"}
23
- {"current_steps": 23, "total_steps": 2820, "loss": 0.1742, "lr": 4.680851063829788e-06, "epoch": 0.016317843206810925, "percentage": 0.82, "elapsed_time": "1:30:04", "remaining_time": "7 days, 14:33:20"}
24
- {"current_steps": 24, "total_steps": 2820, "loss": 0.1418, "lr": 4.893617021276596e-06, "epoch": 0.017027314650585313, "percentage": 0.85, "elapsed_time": "1:33:40", "remaining_time": "7 days, 13:53:57"}
25
- {"current_steps": 25, "total_steps": 2820, "loss": 0.1617, "lr": 5.106382978723404e-06, "epoch": 0.0177367860943597, "percentage": 0.89, "elapsed_time": "1:37:33", "remaining_time": "7 days, 13:46:37"}
26
- {"current_steps": 26, "total_steps": 2820, "loss": 0.1591, "lr": 5.319148936170213e-06, "epoch": 0.01844625753813409, "percentage": 0.92, "elapsed_time": "1:41:47", "remaining_time": "7 days, 14:19:15"}
27
- {"current_steps": 27, "total_steps": 2820, "loss": 0.1594, "lr": 5.531914893617021e-06, "epoch": 0.01915572898190848, "percentage": 0.96, "elapsed_time": "1:46:23", "remaining_time": "7 days, 15:26:09"}
28
- {"current_steps": 28, "total_steps": 2820, "loss": 0.1455, "lr": 5.74468085106383e-06, "epoch": 0.019865200425682867, "percentage": 0.99, "elapsed_time": "1:50:43", "remaining_time": "7 days, 16:00:39"}
29
- {"current_steps": 29, "total_steps": 2820, "loss": 0.1564, "lr": 5.957446808510638e-06, "epoch": 0.020574671869457255, "percentage": 1.03, "elapsed_time": "1:54:19", "remaining_time": "7 days, 15:22:52"}
30
- {"current_steps": 30, "total_steps": 2820, "loss": 0.1659, "lr": 6.1702127659574465e-06, "epoch": 0.021284143313231644, "percentage": 1.06, "elapsed_time": "1:57:56", "remaining_time": "7 days, 14:48:03"}
31
- {"current_steps": 31, "total_steps": 2820, "loss": 0.1387, "lr": 6.3829787234042555e-06, "epoch": 0.02199361475700603, "percentage": 1.1, "elapsed_time": "2:02:24", "remaining_time": "7 days, 15:32:09"}
32
- {"current_steps": 32, "total_steps": 2820, "loss": 0.19, "lr": 6.5957446808510645e-06, "epoch": 0.022703086200780417, "percentage": 1.13, "elapsed_time": "2:06:37", "remaining_time": "7 days, 15:52:09"}
33
- {"current_steps": 33, "total_steps": 2820, "loss": 0.1516, "lr": 6.808510638297873e-06, "epoch": 0.023412557644554806, "percentage": 1.17, "elapsed_time": "2:10:20", "remaining_time": "7 days, 15:27:16"}
34
- {"current_steps": 34, "total_steps": 2820, "loss": 0.1468, "lr": 7.021276595744681e-06, "epoch": 0.024122029088329194, "percentage": 1.21, "elapsed_time": "2:14:18", "remaining_time": "7 days, 15:25:20"}
35
- {"current_steps": 35, "total_steps": 2820, "loss": 0.1417, "lr": 7.234042553191489e-06, "epoch": 0.024831500532103583, "percentage": 1.24, "elapsed_time": "2:18:26", "remaining_time": "7 days, 15:35:28"}
36
- {"current_steps": 36, "total_steps": 2820, "loss": 0.1362, "lr": 7.446808510638298e-06, "epoch": 0.02554097197587797, "percentage": 1.28, "elapsed_time": "2:21:21", "remaining_time": "7 days, 14:12:05"}
37
- {"current_steps": 37, "total_steps": 2820, "loss": 0.1438, "lr": 7.659574468085105e-06, "epoch": 0.02625044341965236, "percentage": 1.31, "elapsed_time": "2:24:45", "remaining_time": "7 days, 13:28:13"}
38
- {"current_steps": 38, "total_steps": 2820, "loss": 0.1502, "lr": 7.872340425531914e-06, "epoch": 0.026959914863426748, "percentage": 1.35, "elapsed_time": "2:29:01", "remaining_time": "7 days, 13:49:41"}
39
- {"current_steps": 39, "total_steps": 2820, "loss": 0.1621, "lr": 8.085106382978723e-06, "epoch": 0.027669386307201137, "percentage": 1.38, "elapsed_time": "2:32:50", "remaining_time": "7 days, 13:39:19"}
40
- {"current_steps": 40, "total_steps": 2820, "loss": 0.1553, "lr": 8.297872340425532e-06, "epoch": 0.028378857750975522, "percentage": 1.42, "elapsed_time": "2:36:04", "remaining_time": "7 days, 12:47:28"}
41
- {"current_steps": 41, "total_steps": 2820, "loss": 0.1422, "lr": 8.510638297872341e-06, "epoch": 0.02908832919474991, "percentage": 1.45, "elapsed_time": "2:40:20", "remaining_time": "7 days, 13:08:07"}
42
- {"current_steps": 42, "total_steps": 2820, "loss": 0.1618, "lr": 8.723404255319149e-06, "epoch": 0.0297978006385243, "percentage": 1.49, "elapsed_time": "2:44:12", "remaining_time": "7 days, 13:01:40"}
43
- {"current_steps": 43, "total_steps": 2820, "loss": 0.1563, "lr": 8.936170212765958e-06, "epoch": 0.030507272082298687, "percentage": 1.52, "elapsed_time": "2:48:28", "remaining_time": "7 days, 13:20:50"}
44
- {"current_steps": 44, "total_steps": 2820, "loss": 0.1603, "lr": 9.148936170212767e-06, "epoch": 0.031216743526073076, "percentage": 1.56, "elapsed_time": "2:51:58", "remaining_time": "7 days, 12:50:02"}
45
- {"current_steps": 45, "total_steps": 2820, "loss": 0.1649, "lr": 9.361702127659576e-06, "epoch": 0.03192621496984746, "percentage": 1.6, "elapsed_time": "2:55:49", "remaining_time": "7 days, 12:42:28"}
46
- {"current_steps": 46, "total_steps": 2820, "loss": 0.1658, "lr": 9.574468085106385e-06, "epoch": 0.03263568641362185, "percentage": 1.63, "elapsed_time": "2:59:21", "remaining_time": "7 days, 12:16:30"}
47
- {"current_steps": 47, "total_steps": 2820, "loss": 0.1661, "lr": 9.787234042553192e-06, "epoch": 0.03334515785739624, "percentage": 1.67, "elapsed_time": "3:02:39", "remaining_time": "7 days, 11:36:46"}
48
- {"current_steps": 48, "total_steps": 2820, "loss": 0.1618, "lr": 9.999999999999999e-06, "epoch": 0.034054629301170626, "percentage": 1.7, "elapsed_time": "3:06:59", "remaining_time": "7 days, 11:58:17"}
49
- {"current_steps": 49, "total_steps": 2820, "loss": 0.1404, "lr": 1.0212765957446808e-05, "epoch": 0.034764100744945015, "percentage": 1.74, "elapsed_time": "3:10:58", "remaining_time": "7 days, 12:00:17"}
50
- {"current_steps": 50, "total_steps": 2820, "loss": 0.1692, "lr": 1.0425531914893617e-05, "epoch": 0.0354735721887194, "percentage": 1.77, "elapsed_time": "3:16:16", "remaining_time": "7 days, 13:13:12"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {"current_steps": 1, "total_steps": 2820, "loss": 2.1209, "lr": 0.0, "epoch": 0.000709471443774388, "percentage": 0.04, "elapsed_time": "0:04:15", "remaining_time": "8 days, 8:03:07"}
2
+ {"current_steps": 2, "total_steps": 2820, "loss": 1.9508, "lr": 2.1276595744680852e-07, "epoch": 0.001418942887548776, "percentage": 0.07, "elapsed_time": "0:07:38", "remaining_time": "7 days, 11:26:12"}
3
+ {"current_steps": 3, "total_steps": 2820, "loss": 2.1995, "lr": 4.2553191489361704e-07, "epoch": 0.002128414331323164, "percentage": 0.11, "elapsed_time": "0:11:56", "remaining_time": "7 days, 18:47:30"}
4
+ {"current_steps": 4, "total_steps": 2820, "loss": 2.0081, "lr": 6.382978723404255e-07, "epoch": 0.002837885775097552, "percentage": 0.14, "elapsed_time": "0:16:14", "remaining_time": "7 days, 22:33:06"}
5
+ {"current_steps": 5, "total_steps": 2820, "loss": 2.0828, "lr": 8.510638297872341e-07, "epoch": 0.0035473572188719402, "percentage": 0.18, "elapsed_time": "0:20:14", "remaining_time": "7 days, 21:52:09"}
6
+ {"current_steps": 6, "total_steps": 2820, "loss": 1.6403, "lr": 1.0638297872340427e-06, "epoch": 0.004256828662646328, "percentage": 0.21, "elapsed_time": "0:24:34", "remaining_time": "8 days, 0:08:46"}
7
+ {"current_steps": 7, "total_steps": 2820, "loss": 1.6037, "lr": 1.276595744680851e-06, "epoch": 0.004966300106420717, "percentage": 0.25, "elapsed_time": "0:29:03", "remaining_time": "8 days, 2:38:10"}
8
+ {"current_steps": 8, "total_steps": 2820, "loss": 1.0155, "lr": 1.4893617021276596e-06, "epoch": 0.005675771550195104, "percentage": 0.28, "elapsed_time": "0:33:39", "remaining_time": "8 days, 5:09:23"}
9
+ {"current_steps": 9, "total_steps": 2820, "loss": 0.8153, "lr": 1.7021276595744682e-06, "epoch": 0.006385242993969493, "percentage": 0.32, "elapsed_time": "0:37:34", "remaining_time": "8 days, 3:34:23"}
10
+ {"current_steps": 10, "total_steps": 2820, "loss": 0.3811, "lr": 1.9148936170212763e-06, "epoch": 0.0070947144377438804, "percentage": 0.35, "elapsed_time": "0:41:17", "remaining_time": "8 days, 1:20:38"}
11
+ {"current_steps": 11, "total_steps": 2820, "loss": 0.3851, "lr": 2.1276595744680853e-06, "epoch": 0.007804185881518269, "percentage": 0.39, "elapsed_time": "0:45:29", "remaining_time": "8 days, 1:38:28"}
12
+ {"current_steps": 12, "total_steps": 2820, "loss": 0.2891, "lr": 2.340425531914894e-06, "epoch": 0.008513657325292657, "percentage": 0.43, "elapsed_time": "0:49:10", "remaining_time": "7 days, 23:48:41"}
13
+ {"current_steps": 13, "total_steps": 2820, "loss": 0.2528, "lr": 2.553191489361702e-06, "epoch": 0.009223128769067045, "percentage": 0.46, "elapsed_time": "0:53:24", "remaining_time": "8 days, 0:11:37"}
14
+ {"current_steps": 14, "total_steps": 2820, "loss": 0.1542, "lr": 2.7659574468085106e-06, "epoch": 0.009932600212841433, "percentage": 0.5, "elapsed_time": "0:56:51", "remaining_time": "7 days, 21:56:02"}
15
+ {"current_steps": 15, "total_steps": 2820, "loss": 0.1762, "lr": 2.978723404255319e-06, "epoch": 0.010642071656615822, "percentage": 0.53, "elapsed_time": "1:00:38", "remaining_time": "7 days, 20:58:33"}
16
+ {"current_steps": 16, "total_steps": 2820, "loss": 0.1403, "lr": 3.1914893617021277e-06, "epoch": 0.011351543100390209, "percentage": 0.57, "elapsed_time": "1:05:06", "remaining_time": "7 days, 22:09:18"}
17
+ {"current_steps": 17, "total_steps": 2820, "loss": 0.1561, "lr": 3.4042553191489363e-06, "epoch": 0.012061014544164597, "percentage": 0.6, "elapsed_time": "1:08:54", "remaining_time": "7 days, 21:22:44"}
18
+ {"current_steps": 18, "total_steps": 2820, "loss": 0.1632, "lr": 3.6170212765957445e-06, "epoch": 0.012770485987938986, "percentage": 0.64, "elapsed_time": "1:11:58", "remaining_time": "7 days, 18:43:34"}
19
+ {"current_steps": 19, "total_steps": 2820, "loss": 0.1667, "lr": 3.829787234042553e-06, "epoch": 0.013479957431713374, "percentage": 0.67, "elapsed_time": "1:15:52", "remaining_time": "7 days, 18:24:49"}
20
+ {"current_steps": 20, "total_steps": 2820, "loss": 0.1893, "lr": 4.042553191489362e-06, "epoch": 0.014189428875487761, "percentage": 0.71, "elapsed_time": "1:20:01", "remaining_time": "7 days, 18:43:36"}
21
+ {"current_steps": 21, "total_steps": 2820, "loss": 0.2085, "lr": 4.255319148936171e-06, "epoch": 0.01489890031926215, "percentage": 0.74, "elapsed_time": "1:24:04", "remaining_time": "7 days, 18:44:59"}
22
+ {"current_steps": 22, "total_steps": 2820, "loss": 0.1913, "lr": 4.468085106382979e-06, "epoch": 0.015608371763036538, "percentage": 0.78, "elapsed_time": "1:27:45", "remaining_time": "7 days, 18:01:24"}
23
+ {"current_steps": 23, "total_steps": 2820, "loss": 0.1741, "lr": 4.680851063829788e-06, "epoch": 0.016317843206810925, "percentage": 0.82, "elapsed_time": "1:31:34", "remaining_time": "7 days, 17:37:03"}
24
+ {"current_steps": 24, "total_steps": 2820, "loss": 0.1408, "lr": 4.893617021276596e-06, "epoch": 0.017027314650585313, "percentage": 0.85, "elapsed_time": "1:35:13", "remaining_time": "7 days, 16:54:27"}
25
+ {"current_steps": 25, "total_steps": 2820, "loss": 0.1632, "lr": 5.106382978723404e-06, "epoch": 0.0177367860943597, "percentage": 0.89, "elapsed_time": "1:39:09", "remaining_time": "7 days, 16:45:28"}
26
+ {"current_steps": 26, "total_steps": 2820, "loss": 0.1563, "lr": 5.319148936170213e-06, "epoch": 0.01844625753813409, "percentage": 0.92, "elapsed_time": "1:43:31", "remaining_time": "7 days, 17:24:36"}
27
+ {"current_steps": 27, "total_steps": 2820, "loss": 0.1582, "lr": 5.531914893617021e-06, "epoch": 0.01915572898190848, "percentage": 0.96, "elapsed_time": "1:47:50", "remaining_time": "7 days, 17:56:16"}
28
+ {"current_steps": 28, "total_steps": 2820, "loss": 0.1451, "lr": 5.74468085106383e-06, "epoch": 0.019865200425682867, "percentage": 0.99, "elapsed_time": "1:51:32", "remaining_time": "7 days, 17:21:29"}
29
+ {"current_steps": 29, "total_steps": 2820, "loss": 0.157, "lr": 5.957446808510638e-06, "epoch": 0.020574671869457255, "percentage": 1.03, "elapsed_time": "1:55:33", "remaining_time": "7 days, 17:21:13"}
30
+ {"current_steps": 30, "total_steps": 2820, "loss": 0.1725, "lr": 6.1702127659574465e-06, "epoch": 0.021284143313231644, "percentage": 1.06, "elapsed_time": "1:58:48", "remaining_time": "7 days, 16:09:51"}
31
+ {"current_steps": 31, "total_steps": 2820, "loss": 0.1318, "lr": 6.3829787234042555e-06, "epoch": 0.02199361475700603, "percentage": 1.1, "elapsed_time": "2:03:44", "remaining_time": "7 days, 17:33:24"}
32
+ {"current_steps": 32, "total_steps": 2820, "loss": 0.1795, "lr": 6.5957446808510645e-06, "epoch": 0.022703086200780417, "percentage": 1.13, "elapsed_time": "2:07:56", "remaining_time": "7 days, 17:46:56"}
33
+ {"current_steps": 33, "total_steps": 2820, "loss": 0.1586, "lr": 6.808510638297873e-06, "epoch": 0.023412557644554806, "percentage": 1.17, "elapsed_time": "2:11:27", "remaining_time": "7 days, 17:01:50"}
34
+ {"current_steps": 34, "total_steps": 2820, "loss": 0.1552, "lr": 7.021276595744681e-06, "epoch": 0.024122029088329194, "percentage": 1.21, "elapsed_time": "2:15:27", "remaining_time": "7 days, 16:59:22"}
35
+ {"current_steps": 35, "total_steps": 2820, "loss": 0.1573, "lr": 7.234042553191489e-06, "epoch": 0.024831500532103583, "percentage": 1.24, "elapsed_time": "2:20:43", "remaining_time": "7 days, 18:37:04"}
36
+ {"current_steps": 36, "total_steps": 2820, "loss": 0.149, "lr": 7.446808510638298e-06, "epoch": 0.02554097197587797, "percentage": 1.28, "elapsed_time": "2:23:51", "remaining_time": "7 days, 17:24:53"}
37
+ {"current_steps": 37, "total_steps": 2820, "loss": 0.154, "lr": 7.659574468085105e-06, "epoch": 0.02625044341965236, "percentage": 1.31, "elapsed_time": "2:27:06", "remaining_time": "7 days, 16:25:20"}
38
+ {"current_steps": 38, "total_steps": 2820, "loss": 0.1563, "lr": 7.872340425531914e-06, "epoch": 0.026959914863426748, "percentage": 1.35, "elapsed_time": "2:31:13", "remaining_time": "7 days, 16:30:45"}
39
+ {"current_steps": 39, "total_steps": 2820, "loss": 0.1568, "lr": 8.085106382978723e-06, "epoch": 0.027669386307201137, "percentage": 1.38, "elapsed_time": "2:34:57", "remaining_time": "7 days, 16:10:02"}
40
+ {"current_steps": 40, "total_steps": 2820, "loss": 0.1608, "lr": 8.297872340425532e-06, "epoch": 0.028378857750975522, "percentage": 1.42, "elapsed_time": "2:38:16", "remaining_time": "7 days, 15:20:06"}
41
+ {"current_steps": 41, "total_steps": 2820, "loss": 0.1495, "lr": 8.510638297872341e-06, "epoch": 0.02908832919474991, "percentage": 1.45, "elapsed_time": "2:42:36", "remaining_time": "7 days, 15:41:47"}
42
+ {"current_steps": 42, "total_steps": 2820, "loss": 0.1746, "lr": 8.723404255319149e-06, "epoch": 0.0297978006385243, "percentage": 1.49, "elapsed_time": "2:46:35", "remaining_time": "7 days, 15:38:20"}
43
+ {"current_steps": 43, "total_steps": 2820, "loss": 0.1501, "lr": 8.936170212765958e-06, "epoch": 0.030507272082298687, "percentage": 1.52, "elapsed_time": "2:50:39", "remaining_time": "7 days, 15:41:45"}
44
+ {"current_steps": 44, "total_steps": 2820, "loss": 0.1614, "lr": 9.148936170212767e-06, "epoch": 0.031216743526073076, "percentage": 1.56, "elapsed_time": "2:54:30", "remaining_time": "7 days, 15:30:22"}
45
+ {"current_steps": 45, "total_steps": 2820, "loss": 0.1649, "lr": 9.361702127659576e-06, "epoch": 0.03192621496984746, "percentage": 1.6, "elapsed_time": "2:58:43", "remaining_time": "7 days, 15:41:01"}
46
+ {"current_steps": 46, "total_steps": 2820, "loss": 0.1528, "lr": 9.574468085106385e-06, "epoch": 0.03263568641362185, "percentage": 1.63, "elapsed_time": "3:02:41", "remaining_time": "7 days, 15:36:50"}
47
+ {"current_steps": 47, "total_steps": 2820, "loss": 0.151, "lr": 9.787234042553192e-06, "epoch": 0.03334515785739624, "percentage": 1.67, "elapsed_time": "3:06:15", "remaining_time": "7 days, 15:09:09"}
48
+ {"current_steps": 48, "total_steps": 2820, "loss": 0.15, "lr": 9.999999999999999e-06, "epoch": 0.034054629301170626, "percentage": 1.7, "elapsed_time": "3:10:14", "remaining_time": "7 days, 15:06:13"}
49
+ {"current_steps": 49, "total_steps": 2820, "loss": 0.1385, "lr": 1.0212765957446808e-05, "epoch": 0.034764100744945015, "percentage": 1.74, "elapsed_time": "3:14:46", "remaining_time": "7 days, 15:34:54"}
50
+ {"current_steps": 50, "total_steps": 2820, "loss": 0.1822, "lr": 1.0425531914893617e-05, "epoch": 0.0354735721887194, "percentage": 1.77, "elapsed_time": "3:19:54", "remaining_time": "7 days, 16:34:28"}
51
+ {"current_steps": 51, "total_steps": 2820, "loss": 0.1465, "lr": 1.0638297872340426e-05, "epoch": 0.03618304363249379, "percentage": 1.81, "elapsed_time": "3:24:56", "remaining_time": "7 days, 17:27:16"}
52
+ {"current_steps": 52, "total_steps": 2820, "loss": 0.1301, "lr": 1.0851063829787235e-05, "epoch": 0.03689251507626818, "percentage": 1.84, "elapsed_time": "3:28:43", "remaining_time": "7 days, 17:10:38"}
53
+ {"current_steps": 53, "total_steps": 2820, "loss": 0.1495, "lr": 1.1063829787234042e-05, "epoch": 0.03760198652004257, "percentage": 1.88, "elapsed_time": "3:33:32", "remaining_time": "7 days, 17:48:26"}
54
+ {"current_steps": 54, "total_steps": 2820, "loss": 0.1686, "lr": 1.1276595744680851e-05, "epoch": 0.03831145796381696, "percentage": 1.91, "elapsed_time": "3:37:39", "remaining_time": "7 days, 17:49:03"}
55
+ {"current_steps": 55, "total_steps": 2820, "loss": 0.1567, "lr": 1.148936170212766e-05, "epoch": 0.039020929407591345, "percentage": 1.95, "elapsed_time": "3:41:24", "remaining_time": "7 days, 17:30:40"}
56
+ {"current_steps": 56, "total_steps": 2820, "loss": 0.1444, "lr": 1.170212765957447e-05, "epoch": 0.039730400851365734, "percentage": 1.99, "elapsed_time": "3:45:16", "remaining_time": "7 days, 17:19:05"}
57
+ {"current_steps": 57, "total_steps": 2820, "loss": 0.1484, "lr": 1.1914893617021277e-05, "epoch": 0.04043987229514012, "percentage": 2.02, "elapsed_time": "3:48:50", "remaining_time": "7 days, 16:52:28"}
58
+ {"current_steps": 58, "total_steps": 2820, "loss": 0.1502, "lr": 1.2127659574468084e-05, "epoch": 0.04114934373891451, "percentage": 2.06, "elapsed_time": "3:53:04", "remaining_time": "7 days, 16:59:07"}
59
+ {"current_steps": 59, "total_steps": 2820, "loss": 0.1473, "lr": 1.2340425531914893e-05, "epoch": 0.0418588151826889, "percentage": 2.09, "elapsed_time": "3:57:09", "remaining_time": "7 days, 16:58:14"}
60
+ {"current_steps": 60, "total_steps": 2820, "loss": 0.1415, "lr": 1.2553191489361702e-05, "epoch": 0.04256828662646329, "percentage": 2.13, "elapsed_time": "4:00:51", "remaining_time": "7 days, 16:39:24"}
61
+ {"current_steps": 61, "total_steps": 2820, "loss": 0.1528, "lr": 1.2765957446808511e-05, "epoch": 0.043277758070237676, "percentage": 2.16, "elapsed_time": "4:04:47", "remaining_time": "7 days, 16:32:05"}
62
+ {"current_steps": 62, "total_steps": 2820, "loss": 0.1659, "lr": 1.297872340425532e-05, "epoch": 0.04398722951401206, "percentage": 2.2, "elapsed_time": "4:08:34", "remaining_time": "7 days, 16:17:26"}
63
+ {"current_steps": 63, "total_steps": 2820, "loss": 0.1318, "lr": 1.3191489361702129e-05, "epoch": 0.044696700957786446, "percentage": 2.23, "elapsed_time": "4:12:15", "remaining_time": "7 days, 15:59:24"}
64
+ {"current_steps": 64, "total_steps": 2820, "loss": 0.1444, "lr": 1.3404255319148936e-05, "epoch": 0.045406172401560835, "percentage": 2.27, "elapsed_time": "4:16:40", "remaining_time": "7 days, 16:12:53"}
65
+ {"current_steps": 65, "total_steps": 2820, "loss": 0.1534, "lr": 1.3617021276595745e-05, "epoch": 0.04611564384533522, "percentage": 2.3, "elapsed_time": "4:20:41", "remaining_time": "7 days, 16:09:20"}
66
+ {"current_steps": 66, "total_steps": 2820, "loss": 0.1402, "lr": 1.3829787234042554e-05, "epoch": 0.04682511528910961, "percentage": 2.34, "elapsed_time": "4:24:30", "remaining_time": "7 days, 15:57:15"}
67
+ {"current_steps": 67, "total_steps": 2820, "loss": 0.1425, "lr": 1.4042553191489362e-05, "epoch": 0.047534586732884, "percentage": 2.38, "elapsed_time": "4:28:01", "remaining_time": "7 days, 15:32:49"}
68
+ {"current_steps": 68, "total_steps": 2820, "loss": 0.1441, "lr": 1.425531914893617e-05, "epoch": 0.04824405817665839, "percentage": 2.41, "elapsed_time": "4:31:49", "remaining_time": "7 days, 15:21:13"}
69
+ {"current_steps": 69, "total_steps": 2820, "loss": 0.1209, "lr": 1.4468085106382978e-05, "epoch": 0.04895352962043278, "percentage": 2.45, "elapsed_time": "4:35:38", "remaining_time": "7 days, 15:09:54"}
70
+ {"current_steps": 70, "total_steps": 2820, "loss": 0.1368, "lr": 1.4680851063829787e-05, "epoch": 0.049663001064207166, "percentage": 2.48, "elapsed_time": "4:39:33", "remaining_time": "7 days, 15:02:24"}
71
+ {"current_steps": 71, "total_steps": 2820, "loss": 0.1228, "lr": 1.4893617021276596e-05, "epoch": 0.050372472507981554, "percentage": 2.52, "elapsed_time": "4:43:16", "remaining_time": "7 days, 14:47:48"}
72
+ {"current_steps": 72, "total_steps": 2820, "loss": 0.1504, "lr": 1.5106382978723403e-05, "epoch": 0.05108194395175594, "percentage": 2.55, "elapsed_time": "4:47:04", "remaining_time": "7 days, 14:36:48"}
73
+ {"current_steps": 73, "total_steps": 2820, "loss": 0.1354, "lr": 1.531914893617021e-05, "epoch": 0.05179141539553033, "percentage": 2.59, "elapsed_time": "4:51:41", "remaining_time": "7 days, 14:56:13"}
74
+ {"current_steps": 74, "total_steps": 2820, "loss": 0.1272, "lr": 1.553191489361702e-05, "epoch": 0.05250088683930472, "percentage": 2.62, "elapsed_time": "4:55:46", "remaining_time": "7 days, 14:55:31"}
75
+ {"current_steps": 75, "total_steps": 2820, "loss": 0.1307, "lr": 1.574468085106383e-05, "epoch": 0.05321035828307911, "percentage": 2.66, "elapsed_time": "5:00:01", "remaining_time": "7 days, 15:00:57"}
76
+ {"current_steps": 76, "total_steps": 2820, "loss": 0.1215, "lr": 1.5957446808510637e-05, "epoch": 0.053919829726853497, "percentage": 2.7, "elapsed_time": "5:03:43", "remaining_time": "7 days, 14:46:12"}
77
+ {"current_steps": 77, "total_steps": 2820, "loss": 0.1362, "lr": 1.6170212765957446e-05, "epoch": 0.054629301170627885, "percentage": 2.73, "elapsed_time": "5:07:40", "remaining_time": "7 days, 14:40:32"}
78
+ {"current_steps": 78, "total_steps": 2820, "loss": 0.1899, "lr": 1.6382978723404255e-05, "epoch": 0.05533877261440227, "percentage": 2.77, "elapsed_time": "5:12:14", "remaining_time": "7 days, 14:56:30"}
79
+ {"current_steps": 79, "total_steps": 2820, "loss": 0.1611, "lr": 1.6595744680851064e-05, "epoch": 0.056048244058176655, "percentage": 2.8, "elapsed_time": "5:16:25", "remaining_time": "7 days, 14:58:31"}
80
+ {"current_steps": 80, "total_steps": 2820, "loss": 0.1514, "lr": 1.6808510638297873e-05, "epoch": 0.056757715501951043, "percentage": 2.84, "elapsed_time": "5:21:02", "remaining_time": "7 days, 15:15:31"}
81
+ {"current_steps": 81, "total_steps": 2820, "loss": 0.1468, "lr": 1.7021276595744682e-05, "epoch": 0.05746718694572543, "percentage": 2.87, "elapsed_time": "5:26:09", "remaining_time": "7 days, 15:49:15"}
82
+ {"current_steps": 82, "total_steps": 2820, "loss": 0.1445, "lr": 1.723404255319149e-05, "epoch": 0.05817665838949982, "percentage": 2.91, "elapsed_time": "5:30:38", "remaining_time": "7 days, 16:00:03"}
83
+ {"current_steps": 83, "total_steps": 2820, "loss": 0.158, "lr": 1.7446808510638297e-05, "epoch": 0.05888612983327421, "percentage": 2.94, "elapsed_time": "5:34:30", "remaining_time": "7 days, 15:50:50"}
84
+ {"current_steps": 84, "total_steps": 2820, "loss": 0.1253, "lr": 1.7659574468085106e-05, "epoch": 0.0595956012770486, "percentage": 2.98, "elapsed_time": "5:38:27", "remaining_time": "7 days, 15:43:51"}
85
+ {"current_steps": 85, "total_steps": 2820, "loss": 0.1418, "lr": 1.7872340425531915e-05, "epoch": 0.060305072720822986, "percentage": 3.01, "elapsed_time": "5:42:51", "remaining_time": "7 days, 15:51:51"}
86
+ {"current_steps": 86, "total_steps": 2820, "loss": 0.1455, "lr": 1.8085106382978724e-05, "epoch": 0.061014544164597374, "percentage": 3.05, "elapsed_time": "5:47:09", "remaining_time": "7 days, 15:56:34"}
87
+ {"current_steps": 87, "total_steps": 2820, "loss": 0.139, "lr": 1.8297872340425533e-05, "epoch": 0.06172401560837176, "percentage": 3.09, "elapsed_time": "5:50:52", "remaining_time": "7 days, 15:42:10"}
88
+ {"current_steps": 88, "total_steps": 2820, "loss": 0.1396, "lr": 1.8510638297872342e-05, "epoch": 0.06243348705214615, "percentage": 3.12, "elapsed_time": "5:54:49", "remaining_time": "7 days, 15:35:45"}
89
+ {"current_steps": 89, "total_steps": 2820, "loss": 0.1568, "lr": 1.872340425531915e-05, "epoch": 0.06314295849592054, "percentage": 3.16, "elapsed_time": "5:58:09", "remaining_time": "7 days, 15:10:04"}
90
+ {"current_steps": 90, "total_steps": 2820, "loss": 0.147, "lr": 1.893617021276596e-05, "epoch": 0.06385242993969492, "percentage": 3.19, "elapsed_time": "6:02:11", "remaining_time": "7 days, 15:06:23"}
91
+ {"current_steps": 91, "total_steps": 2820, "loss": 0.1603, "lr": 1.914893617021277e-05, "epoch": 0.06456190138346932, "percentage": 3.23, "elapsed_time": "6:05:53", "remaining_time": "7 days, 14:52:47"}
92
+ {"current_steps": 92, "total_steps": 2820, "loss": 0.1731, "lr": 1.9361702127659575e-05, "epoch": 0.0652713728272437, "percentage": 3.26, "elapsed_time": "6:10:01", "remaining_time": "7 days, 14:52:00"}
93
+ {"current_steps": 93, "total_steps": 2820, "loss": 0.1323, "lr": 1.9574468085106384e-05, "epoch": 0.0659808442710181, "percentage": 3.3, "elapsed_time": "6:14:16", "remaining_time": "7 days, 14:54:57"}
94
+ {"current_steps": 94, "total_steps": 2820, "loss": 0.123, "lr": 1.978723404255319e-05, "epoch": 0.06669031571479248, "percentage": 3.33, "elapsed_time": "6:18:02", "remaining_time": "7 days, 14:43:18"}
95
+ {"current_steps": 95, "total_steps": 2820, "loss": 0.1492, "lr": 1.9999999999999998e-05, "epoch": 0.06739978715856687, "percentage": 3.37, "elapsed_time": "6:21:57", "remaining_time": "7 days, 14:36:07"}
96
+ {"current_steps": 96, "total_steps": 2820, "loss": 0.1422, "lr": 2.0212765957446807e-05, "epoch": 0.06810925860234125, "percentage": 3.4, "elapsed_time": "6:26:03", "remaining_time": "7 days, 14:34:31"}
97
+ {"current_steps": 97, "total_steps": 2820, "loss": 0.1263, "lr": 2.0425531914893616e-05, "epoch": 0.06881873004611565, "percentage": 3.44, "elapsed_time": "6:29:55", "remaining_time": "7 days, 14:25:50"}
98
+ {"current_steps": 98, "total_steps": 2820, "loss": 0.1027, "lr": 2.0638297872340425e-05, "epoch": 0.06952820148989003, "percentage": 3.48, "elapsed_time": "6:33:39", "remaining_time": "7 days, 14:14:03"}
99
+ {"current_steps": 99, "total_steps": 2820, "loss": 0.1315, "lr": 2.0851063829787234e-05, "epoch": 0.07023767293366442, "percentage": 3.51, "elapsed_time": "6:37:29", "remaining_time": "7 days, 14:04:51"}
100
+ {"current_steps": 100, "total_steps": 2820, "loss": 0.1971, "lr": 2.1063829787234043e-05, "epoch": 0.0709471443774388, "percentage": 3.55, "elapsed_time": "6:41:26", "remaining_time": "7 days, 13:59:14"}
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59690dec2de0315e951e84e970a3e21faeab8de9ac11de6607c8728b4bc47b50
3
- size 8017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:def4d75ea319d525641ec3446da18695a7865c879bc733e7cf5fa86aa02e3106
3
+ size 7953