Hugging Face's logo

chancharikm
/
CHAI_SFT_model_8b

Video-Text-to-Text
Transformers
Safetensors
qwen3_vl
image-text-to-text
llama-factory
full
Generated from Trainer
video-language-model
video-captioning
Model card Files
xet
 Community
chancharikm commited on
Commit
af6ff3e
·
verified ·
1 Parent(s): 4ae3c13

Training in progress, step 200, checkpoint

Browse files
Files changed (23) hide show
  1. last-checkpoint/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
  2. last-checkpoint/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
  3. last-checkpoint/global_step200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
  4. last-checkpoint/global_step200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
  5. last-checkpoint/global_step200/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
  6. last-checkpoint/global_step200/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
  7. last-checkpoint/global_step200/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
  8. last-checkpoint/global_step200/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
  9. last-checkpoint/global_step200/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
  10. last-checkpoint/global_step200/zero_pp_rank_1_mp_rank_00_model_states.pt +3 -0
  11. last-checkpoint/global_step200/zero_pp_rank_2_mp_rank_00_model_states.pt +3 -0
  12. last-checkpoint/global_step200/zero_pp_rank_3_mp_rank_00_model_states.pt +3 -0
  13. last-checkpoint/global_step200/zero_pp_rank_4_mp_rank_00_model_states.pt +3 -0
  14. last-checkpoint/global_step200/zero_pp_rank_5_mp_rank_00_model_states.pt +3 -0
  15. last-checkpoint/global_step200/zero_pp_rank_6_mp_rank_00_model_states.pt +3 -0
  16. last-checkpoint/global_step200/zero_pp_rank_7_mp_rank_00_model_states.pt +3 -0
  17. last-checkpoint/latest +1 -1
  18. last-checkpoint/model-00001-of-00004.safetensors +1 -1
  19. last-checkpoint/model-00002-of-00004.safetensors +1 -1
  20. last-checkpoint/model-00003-of-00004.safetensors +1 -1
  21. last-checkpoint/model-00004-of-00004.safetensors +1 -1
  22. last-checkpoint/scheduler.pt +1 -1
  23. last-checkpoint/trainer_state.json +353 -3
last-checkpoint/global_step200/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf9f54e6f88bdf072c7b9a1762bcf303c0c7949f4331e207fddee60ed481574b
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7af90f7dc34597a3e59a7ea76cf1066d9442f0baf59a02531e3029de0e189102
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8953fdbaff00623250da884d3a53f99b00431ac948dcc74762d78df9cd0d0f46
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33cb6d49afd4777ad3bbc533de073afbb42c92b509b38e88250d2ec5e622c293
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3807649e412f1140545659d42da8d0fc1382baa0b20c58dadd0a7c6ca7129d74
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6d39af45c050136f4dff0d11f52028ad953fc788029dc8140016845990ce861
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd26d63b34553aa1d0c0188e3fbb293ea0fba084b110d3ac474fc4284835783d
3
+ size 1558836997
last-checkpoint/global_step200/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28303de30eb7f651d44e0af7e5c7b407c9a37b31217df70e208ac65d979f62ae
3
+ size 1558836997
last-checkpoint/global_step200/zero_pp_rank_0_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba121e45f30461ce098e1e4b32f91bdd333482d1be85dacba2d2ecf89764641f
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_1_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fedc68cb76d5183f998cf10aeda3a25b8f6f9a11502ea9b384851ba913a9bbc5
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_2_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48079e379806d1e1442aa0a86a7f9ed2cfa353d07f7e9157f3d8ea3551fac6fb
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_3_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d93dc7f08e6e79347dffd1ddcffde87470e5214e5ebd778a86a1f875bdc6f20c
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_4_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9275dc1e1d47d6171536930fb18131dd99612bc0b0415b70fa9c2fdd0a602248
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_5_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d7db7f51b0295748d0448376bb4881a1a1f32efc5e1e20eeacb516424cf90d5
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_6_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fec4c83d1b347fd1d6e189314a433e231a0c7da514b1e76437b7ea8d63fec354
3
+ size 14662941
last-checkpoint/global_step200/zero_pp_rank_7_mp_rank_00_model_states.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45a4fb2f5dc000f5cc88c82f1ee8c4ee5726c495c6c5926d62a1635f5a8b3778
3
+ size 14662941
last-checkpoint/latest CHANGED
@@ -1 +1 @@
1
- global_step150
 
1
+ global_step200
last-checkpoint/model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93cf36b428ad873d16519d98fac95e165c1f5903d4924b90da24e0d6b217e2cd
3
  size 4998056552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8548fda29c2fcaa5503f4886ef33eab279e0138dda533d8e0cd77eb0983560fc
3
  size 4998056552
last-checkpoint/model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2dc7ac2907f6a93e48d0cff05e14775431c61780303fe311a68f664ed72451a6
3
  size 4915962464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:830041c1492e9bbf049fa48e810bcb70c4c350304770f8375dc8c65e94cd5c8d
3
  size 4915962464
last-checkpoint/model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c99143d02bdc7200d11845fc6c722451842ae4352c35c73b03864d9d1dac6ac2
3
  size 4915962496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7645ebdf7d3a8a1698ae1c2e91ff6cf46717190304f9f84b85c4438b20c1291
3
  size 4915962496
last-checkpoint/model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7aba28b15170cd25381c6e63ef31c627abc26fe1296fedefe3ef752e8091a4a5
3
  size 2704357976
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1190648df1ee0aab52c000d24285170bacbb99923a87e47cd8fcf44b2a270c76
3
  size 2704357976
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbe06634a55d8dd3790f8c0d82a7af4e61775c8a115e3c9f6dce61003e06fb39
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84577b38b315425b3b00a1f7d28ec4217062075371f6c91ac68dc3cf5f77005f
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.6085192697768763,
6
  "eval_steps": 500,
7
- "global_step": 150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -1058,6 +1058,356 @@
1058
  "learning_rate": 2.8192106268097336e-05,
1059
  "loss": 0.1848,
1060
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1061
  }
1062
  ],
1063
  "logging_steps": 1,
@@ -1077,7 +1427,7 @@
1077
  "attributes": {}
1078
  }
1079
  },
1080
- "total_flos": 1012863152947200.0,
1081
  "train_batch_size": 10,
1082
  "trial_name": null,
1083
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.8113590263691683,
6
  "eval_steps": 500,
7
+ "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
1058
  "learning_rate": 2.8192106268097336e-05,
1059
  "loss": 0.1848,
1060
  "step": 150
1061
+ },
1062
+ {
1063
+ "epoch": 0.6125760649087221,
1064
+ "grad_norm": 0.6000865550277297,
1065
+ "learning_rate": 2.8160070675715038e-05,
1066
+ "loss": 0.1938,
1067
+ "step": 151
1068
+ },
1069
+ {
1070
+ "epoch": 0.6166328600405679,
1071
+ "grad_norm": 0.5791492060921085,
1072
+ "learning_rate": 2.8127772270483714e-05,
1073
+ "loss": 0.2085,
1074
+ "step": 152
1075
+ },
1076
+ {
1077
+ "epoch": 0.6206896551724138,
1078
+ "grad_norm": 0.6023954274654707,
1079
+ "learning_rate": 2.8095211697417823e-05,
1080
+ "loss": 0.2237,
1081
+ "step": 153
1082
+ },
1083
+ {
1084
+ "epoch": 0.6247464503042597,
1085
+ "grad_norm": 0.6536097341613256,
1086
+ "learning_rate": 2.8062389606767445e-05,
1087
+ "loss": 0.2123,
1088
+ "step": 154
1089
+ },
1090
+ {
1091
+ "epoch": 0.6288032454361054,
1092
+ "grad_norm": 0.5127334450984861,
1093
+ "learning_rate": 2.8029306654005288e-05,
1094
+ "loss": 0.1829,
1095
+ "step": 155
1096
+ },
1097
+ {
1098
+ "epoch": 0.6328600405679513,
1099
+ "grad_norm": 0.5624075392241792,
1100
+ "learning_rate": 2.7995963499813596e-05,
1101
+ "loss": 0.2025,
1102
+ "step": 156
1103
+ },
1104
+ {
1105
+ "epoch": 0.6369168356997972,
1106
+ "grad_norm": 0.6449150568592729,
1107
+ "learning_rate": 2.796236081007096e-05,
1108
+ "loss": 0.1949,
1109
+ "step": 157
1110
+ },
1111
+ {
1112
+ "epoch": 0.640973630831643,
1113
+ "grad_norm": 0.701187654484129,
1114
+ "learning_rate": 2.7928499255839033e-05,
1115
+ "loss": 0.2151,
1116
+ "step": 158
1117
+ },
1118
+ {
1119
+ "epoch": 0.6450304259634888,
1120
+ "grad_norm": 0.6431071185310107,
1121
+ "learning_rate": 2.789437951334909e-05,
1122
+ "loss": 0.1695,
1123
+ "step": 159
1124
+ },
1125
+ {
1126
+ "epoch": 0.6490872210953347,
1127
+ "grad_norm": 0.883066522041192,
1128
+ "learning_rate": 2.7860002263988565e-05,
1129
+ "loss": 0.2035,
1130
+ "step": 160
1131
+ },
1132
+ {
1133
+ "epoch": 0.6531440162271805,
1134
+ "grad_norm": 0.8635932764225648,
1135
+ "learning_rate": 2.7825368194287425e-05,
1136
+ "loss": 0.1695,
1137
+ "step": 161
1138
+ },
1139
+ {
1140
+ "epoch": 0.6572008113590264,
1141
+ "grad_norm": 0.6782443532910216,
1142
+ "learning_rate": 2.7790477995904454e-05,
1143
+ "loss": 0.1865,
1144
+ "step": 162
1145
+ },
1146
+ {
1147
+ "epoch": 0.6612576064908722,
1148
+ "grad_norm": 0.5924664424714287,
1149
+ "learning_rate": 2.7755332365613453e-05,
1150
+ "loss": 0.202,
1151
+ "step": 163
1152
+ },
1153
+ {
1154
+ "epoch": 0.665314401622718,
1155
+ "grad_norm": 0.519362457725557,
1156
+ "learning_rate": 2.7719932005289317e-05,
1157
+ "loss": 0.1877,
1158
+ "step": 164
1159
+ },
1160
+ {
1161
+ "epoch": 0.6693711967545639,
1162
+ "grad_norm": 0.567689209781307,
1163
+ "learning_rate": 2.768427762189402e-05,
1164
+ "loss": 0.1943,
1165
+ "step": 165
1166
+ },
1167
+ {
1168
+ "epoch": 0.6734279918864098,
1169
+ "grad_norm": 0.5265646643108667,
1170
+ "learning_rate": 2.7648369927462503e-05,
1171
+ "loss": 0.1953,
1172
+ "step": 166
1173
+ },
1174
+ {
1175
+ "epoch": 0.6774847870182555,
1176
+ "grad_norm": 0.6457809658154948,
1177
+ "learning_rate": 2.7612209639088433e-05,
1178
+ "loss": 0.2075,
1179
+ "step": 167
1180
+ },
1181
+ {
1182
+ "epoch": 0.6815415821501014,
1183
+ "grad_norm": 0.6522533222938539,
1184
+ "learning_rate": 2.7575797478909914e-05,
1185
+ "loss": 0.2209,
1186
+ "step": 168
1187
+ },
1188
+ {
1189
+ "epoch": 0.6855983772819473,
1190
+ "grad_norm": 0.5926208068621334,
1191
+ "learning_rate": 2.7539134174095047e-05,
1192
+ "loss": 0.1833,
1193
+ "step": 169
1194
+ },
1195
+ {
1196
+ "epoch": 0.6896551724137931,
1197
+ "grad_norm": 0.6215684101485875,
1198
+ "learning_rate": 2.75022204568274e-05,
1199
+ "loss": 0.1849,
1200
+ "step": 170
1201
+ },
1202
+ {
1203
+ "epoch": 0.6937119675456389,
1204
+ "grad_norm": 0.7621052736863643,
1205
+ "learning_rate": 2.7465057064291405e-05,
1206
+ "loss": 0.1666,
1207
+ "step": 171
1208
+ },
1209
+ {
1210
+ "epoch": 0.6977687626774848,
1211
+ "grad_norm": 0.5424544870247899,
1212
+ "learning_rate": 2.7427644738657635e-05,
1213
+ "loss": 0.1672,
1214
+ "step": 172
1215
+ },
1216
+ {
1217
+ "epoch": 0.7018255578093306,
1218
+ "grad_norm": 0.5762207841432611,
1219
+ "learning_rate": 2.738998422706795e-05,
1220
+ "loss": 0.1725,
1221
+ "step": 173
1222
+ },
1223
+ {
1224
+ "epoch": 0.7058823529411765,
1225
+ "grad_norm": 0.5414406787384946,
1226
+ "learning_rate": 2.735207628162063e-05,
1227
+ "loss": 0.1631,
1228
+ "step": 174
1229
+ },
1230
+ {
1231
+ "epoch": 0.7099391480730223,
1232
+ "grad_norm": 0.6368334896233788,
1233
+ "learning_rate": 2.7313921659355305e-05,
1234
+ "loss": 0.1774,
1235
+ "step": 175
1236
+ },
1237
+ {
1238
+ "epoch": 0.7139959432048681,
1239
+ "grad_norm": 0.5101994046433813,
1240
+ "learning_rate": 2.727552112223787e-05,
1241
+ "loss": 0.1776,
1242
+ "step": 176
1243
+ },
1244
+ {
1245
+ "epoch": 0.718052738336714,
1246
+ "grad_norm": 0.6797950370510993,
1247
+ "learning_rate": 2.7236875437145256e-05,
1248
+ "loss": 0.165,
1249
+ "step": 177
1250
+ },
1251
+ {
1252
+ "epoch": 0.7221095334685599,
1253
+ "grad_norm": 0.6280142554651347,
1254
+ "learning_rate": 2.71979853758501e-05,
1255
+ "loss": 0.1904,
1256
+ "step": 178
1257
+ },
1258
+ {
1259
+ "epoch": 0.7261663286004056,
1260
+ "grad_norm": 0.5597196718491728,
1261
+ "learning_rate": 2.715885171500537e-05,
1262
+ "loss": 0.1679,
1263
+ "step": 179
1264
+ },
1265
+ {
1266
+ "epoch": 0.7302231237322515,
1267
+ "grad_norm": 0.49009801560261895,
1268
+ "learning_rate": 2.7119475236128816e-05,
1269
+ "loss": 0.1567,
1270
+ "step": 180
1271
+ },
1272
+ {
1273
+ "epoch": 0.7342799188640974,
1274
+ "grad_norm": 0.6563071312139116,
1275
+ "learning_rate": 2.707985672558739e-05,
1276
+ "loss": 0.1891,
1277
+ "step": 181
1278
+ },
1279
+ {
1280
+ "epoch": 0.7383367139959433,
1281
+ "grad_norm": 0.5376302977824341,
1282
+ "learning_rate": 2.7039996974581524e-05,
1283
+ "loss": 0.156,
1284
+ "step": 182
1285
+ },
1286
+ {
1287
+ "epoch": 0.742393509127789,
1288
+ "grad_norm": 0.5105263903567433,
1289
+ "learning_rate": 2.6999896779129333e-05,
1290
+ "loss": 0.157,
1291
+ "step": 183
1292
+ },
1293
+ {
1294
+ "epoch": 0.7464503042596349,
1295
+ "grad_norm": 0.5799467332504898,
1296
+ "learning_rate": 2.6959556940050736e-05,
1297
+ "loss": 0.169,
1298
+ "step": 184
1299
+ },
1300
+ {
1301
+ "epoch": 0.7505070993914807,
1302
+ "grad_norm": 0.59461838466469,
1303
+ "learning_rate": 2.691897826295143e-05,
1304
+ "loss": 0.1666,
1305
+ "step": 185
1306
+ },
1307
+ {
1308
+ "epoch": 0.7545638945233266,
1309
+ "grad_norm": 0.5812562725844442,
1310
+ "learning_rate": 2.6878161558206845e-05,
1311
+ "loss": 0.1757,
1312
+ "step": 186
1313
+ },
1314
+ {
1315
+ "epoch": 0.7586206896551724,
1316
+ "grad_norm": 0.5570290569403675,
1317
+ "learning_rate": 2.6837107640945904e-05,
1318
+ "loss": 0.1557,
1319
+ "step": 187
1320
+ },
1321
+ {
1322
+ "epoch": 0.7626774847870182,
1323
+ "grad_norm": 0.5210782779050981,
1324
+ "learning_rate": 2.6795817331034803e-05,
1325
+ "loss": 0.1681,
1326
+ "step": 188
1327
+ },
1328
+ {
1329
+ "epoch": 0.7667342799188641,
1330
+ "grad_norm": 0.8814030705223431,
1331
+ "learning_rate": 2.6754291453060598e-05,
1332
+ "loss": 0.1892,
1333
+ "step": 189
1334
+ },
1335
+ {
1336
+ "epoch": 0.77079107505071,
1337
+ "grad_norm": 0.5918031831634013,
1338
+ "learning_rate": 2.6712530836314763e-05,
1339
+ "loss": 0.1574,
1340
+ "step": 190
1341
+ },
1342
+ {
1343
+ "epoch": 0.7748478701825557,
1344
+ "grad_norm": 0.7326389750531642,
1345
+ "learning_rate": 2.6670536314776593e-05,
1346
+ "loss": 0.1544,
1347
+ "step": 191
1348
+ },
1349
+ {
1350
+ "epoch": 0.7789046653144016,
1351
+ "grad_norm": 0.5086355741172542,
1352
+ "learning_rate": 2.66283087270966e-05,
1353
+ "loss": 0.1572,
1354
+ "step": 192
1355
+ },
1356
+ {
1357
+ "epoch": 0.7829614604462475,
1358
+ "grad_norm": 0.5965212460678235,
1359
+ "learning_rate": 2.6585848916579723e-05,
1360
+ "loss": 0.1497,
1361
+ "step": 193
1362
+ },
1363
+ {
1364
+ "epoch": 0.7870182555780934,
1365
+ "grad_norm": 0.5692689362307511,
1366
+ "learning_rate": 2.6543157731168502e-05,
1367
+ "loss": 0.1618,
1368
+ "step": 194
1369
+ },
1370
+ {
1371
+ "epoch": 0.7910750507099391,
1372
+ "grad_norm": 0.516188907315308,
1373
+ "learning_rate": 2.650023602342614e-05,
1374
+ "loss": 0.1456,
1375
+ "step": 195
1376
+ },
1377
+ {
1378
+ "epoch": 0.795131845841785,
1379
+ "grad_norm": 0.7593371898283678,
1380
+ "learning_rate": 2.645708465051949e-05,
1381
+ "loss": 0.1809,
1382
+ "step": 196
1383
+ },
1384
+ {
1385
+ "epoch": 0.7991886409736308,
1386
+ "grad_norm": 0.5366328407002237,
1387
+ "learning_rate": 2.6413704474201924e-05,
1388
+ "loss": 0.1572,
1389
+ "step": 197
1390
+ },
1391
+ {
1392
+ "epoch": 0.8032454361054767,
1393
+ "grad_norm": 0.5277744342808298,
1394
+ "learning_rate": 2.6370096360796116e-05,
1395
+ "loss": 0.1593,
1396
+ "step": 198
1397
+ },
1398
+ {
1399
+ "epoch": 0.8073022312373225,
1400
+ "grad_norm": 0.5609600455428916,
1401
+ "learning_rate": 2.6326261181176772e-05,
1402
+ "loss": 0.1428,
1403
+ "step": 199
1404
+ },
1405
+ {
1406
+ "epoch": 0.8113590263691683,
1407
+ "grad_norm": 0.5420590413429403,
1408
+ "learning_rate": 2.6282199810753192e-05,
1409
+ "loss": 0.1407,
1410
+ "step": 200
1411
  }
1412
  ],
1413
  "logging_steps": 1,
 
1427
  "attributes": {}
1428
  }
1429
  },
1430
+ "total_flos": 1353718179561472.0,
1431
  "train_batch_size": 10,
1432
  "trial_name": null,
1433
  "trial_params": null