Hugging Face's logo

Azrail
/
smallm_70

Text Generation
Transformers
Safetensors
English
smallm
transformer
language-model
experimental
conversational
custom_code
Model card Files
xet
 Community
Azrail commited on
Commit
9561004
·
verified ·
1 Parent(s): 5838d3f

Training in progress, step 35000, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +182 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a6b173b549e9d3319645826a9f24c43c83f85f0e4eb63106d17d813597efd32
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a855920f124e3b4014e03b8c3b2f6f6aadfeef34dd9cdfa8a470be61a1f52396
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:318dc4beaeec065907f21b0996915041ab17bf3f8a094d80b20e22236127e478
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed6213da76cf0e650dec0313cef1a284a57573141f65d8eef45850182380cfa
3
  size 602335994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b93f64c9a6269745acb7384d7354dcfadb94dacfa9ca2a2196b8150f90e2180
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6edbca0184a8ecdfa680b47d18610592e612689fbab9a38d48545fb022b69be
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14f558fa3ebdf8eded534006aef123b31a5895b4203fad741964c0be3f8e2ef2
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c432826b41d4d9850a94ad79c80845280b64911bf27c831beef66a783066385f
3
  size 1064
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": 0.1621808555040128,
6
  "eval_steps": 500,
7
- "global_step": 34000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -6060,11 +6060,189 @@
6060
  "eval_steps_per_second": 24.608,
6061
  "num_input_tokens_seen": 8912896000,
6062
  "step": 34000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6063
  }
6064
  ],
6065
  "logging_steps": 50,
6066
  "max_steps": 70000,
6067
- "num_input_tokens_seen": 8912896000,
6068
  "num_train_epochs": 1,
6069
  "save_steps": 1000,
6070
  "stateful_callbacks": {
@@ -6079,7 +6257,7 @@
6079
  "attributes": {}
6080
  }
6081
  },
6082
- "total_flos": 2.38428666986496e+18,
6083
  "train_batch_size": 64,
6084
  "trial_name": null,
6085
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.1669508806658955,
6
  "eval_steps": 500,
7
+ "global_step": 35000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
6060
  "eval_steps_per_second": 24.608,
6061
  "num_input_tokens_seen": 8912896000,
6062
  "step": 34000
6063
+ },
6064
+ {
6065
+ "epoch": 0.16241935676210692,
6066
+ "grad_norm": 0.1935052126646042,
6067
+ "learning_rate": 0.001,
6068
+ "loss": 2.6583,
6069
+ "num_input_tokens_seen": 8926003200,
6070
+ "step": 34050
6071
+ },
6072
+ {
6073
+ "epoch": 0.16265785802020105,
6074
+ "grad_norm": 0.7825157642364502,
6075
+ "learning_rate": 0.001,
6076
+ "loss": 2.6481,
6077
+ "num_input_tokens_seen": 8939110400,
6078
+ "step": 34100
6079
+ },
6080
+ {
6081
+ "epoch": 0.16289635927829518,
6082
+ "grad_norm": 0.23290683329105377,
6083
+ "learning_rate": 0.001,
6084
+ "loss": 2.6925,
6085
+ "num_input_tokens_seen": 8952217600,
6086
+ "step": 34150
6087
+ },
6088
+ {
6089
+ "epoch": 0.16313486053638934,
6090
+ "grad_norm": 0.23564130067825317,
6091
+ "learning_rate": 0.001,
6092
+ "loss": 2.6495,
6093
+ "num_input_tokens_seen": 8965324800,
6094
+ "step": 34200
6095
+ },
6096
+ {
6097
+ "epoch": 0.16337336179448347,
6098
+ "grad_norm": 0.19592130184173584,
6099
+ "learning_rate": 0.001,
6100
+ "loss": 2.6536,
6101
+ "num_input_tokens_seen": 8978432000,
6102
+ "step": 34250
6103
+ },
6104
+ {
6105
+ "epoch": 0.1636118630525776,
6106
+ "grad_norm": 0.23535041511058807,
6107
+ "learning_rate": 0.001,
6108
+ "loss": 2.6608,
6109
+ "num_input_tokens_seen": 8991539200,
6110
+ "step": 34300
6111
+ },
6112
+ {
6113
+ "epoch": 0.16385036431067174,
6114
+ "grad_norm": 0.1991938352584839,
6115
+ "learning_rate": 0.001,
6116
+ "loss": 2.6458,
6117
+ "num_input_tokens_seen": 9004641856,
6118
+ "step": 34350
6119
+ },
6120
+ {
6121
+ "epoch": 0.16408886556876587,
6122
+ "grad_norm": 0.19363388419151306,
6123
+ "learning_rate": 0.001,
6124
+ "loss": 2.6531,
6125
+ "num_input_tokens_seen": 9017749056,
6126
+ "step": 34400
6127
+ },
6128
+ {
6129
+ "epoch": 0.16432736682686,
6130
+ "grad_norm": 0.18500390648841858,
6131
+ "learning_rate": 0.001,
6132
+ "loss": 2.6391,
6133
+ "num_input_tokens_seen": 9030856256,
6134
+ "step": 34450
6135
+ },
6136
+ {
6137
+ "epoch": 0.16456586808495416,
6138
+ "grad_norm": 0.2774065434932709,
6139
+ "learning_rate": 0.001,
6140
+ "loss": 2.6619,
6141
+ "num_input_tokens_seen": 9043963456,
6142
+ "step": 34500
6143
+ },
6144
+ {
6145
+ "epoch": 0.16456586808495416,
6146
+ "eval_loss": 2.5325100421905518,
6147
+ "eval_runtime": 51.5954,
6148
+ "eval_samples_per_second": 96.908,
6149
+ "eval_steps_per_second": 24.227,
6150
+ "num_input_tokens_seen": 9043963456,
6151
+ "step": 34500
6152
+ },
6153
+ {
6154
+ "epoch": 0.1648043693430483,
6155
+ "grad_norm": 0.1957511603832245,
6156
+ "learning_rate": 0.001,
6157
+ "loss": 2.6456,
6158
+ "num_input_tokens_seen": 9057070656,
6159
+ "step": 34550
6160
+ },
6161
+ {
6162
+ "epoch": 0.16504287060114242,
6163
+ "grad_norm": 0.20958378911018372,
6164
+ "learning_rate": 0.001,
6165
+ "loss": 2.6452,
6166
+ "num_input_tokens_seen": 9070177856,
6167
+ "step": 34600
6168
+ },
6169
+ {
6170
+ "epoch": 0.16528137185923655,
6171
+ "grad_norm": 0.206208735704422,
6172
+ "learning_rate": 0.001,
6173
+ "loss": 2.6548,
6174
+ "num_input_tokens_seen": 9083285056,
6175
+ "step": 34650
6176
+ },
6177
+ {
6178
+ "epoch": 0.16551987311733068,
6179
+ "grad_norm": 0.22349481284618378,
6180
+ "learning_rate": 0.001,
6181
+ "loss": 2.6653,
6182
+ "num_input_tokens_seen": 9096392256,
6183
+ "step": 34700
6184
+ },
6185
+ {
6186
+ "epoch": 0.16575837437542484,
6187
+ "grad_norm": 0.22599968314170837,
6188
+ "learning_rate": 0.001,
6189
+ "loss": 2.6329,
6190
+ "num_input_tokens_seen": 9109499456,
6191
+ "step": 34750
6192
+ },
6193
+ {
6194
+ "epoch": 0.16599687563351898,
6195
+ "grad_norm": 0.19219790399074554,
6196
+ "learning_rate": 0.001,
6197
+ "loss": 2.6404,
6198
+ "num_input_tokens_seen": 9122606656,
6199
+ "step": 34800
6200
+ },
6201
+ {
6202
+ "epoch": 0.1662353768916131,
6203
+ "grad_norm": 0.2006351351737976,
6204
+ "learning_rate": 0.001,
6205
+ "loss": 2.6522,
6206
+ "num_input_tokens_seen": 9135713856,
6207
+ "step": 34850
6208
+ },
6209
+ {
6210
+ "epoch": 0.16647387814970724,
6211
+ "grad_norm": 0.18393316864967346,
6212
+ "learning_rate": 0.001,
6213
+ "loss": 2.6464,
6214
+ "num_input_tokens_seen": 9148821056,
6215
+ "step": 34900
6216
+ },
6217
+ {
6218
+ "epoch": 0.16671237940780137,
6219
+ "grad_norm": 0.19820146262645721,
6220
+ "learning_rate": 0.001,
6221
+ "loss": 2.6402,
6222
+ "num_input_tokens_seen": 9161928256,
6223
+ "step": 34950
6224
+ },
6225
+ {
6226
+ "epoch": 0.1669508806658955,
6227
+ "grad_norm": 0.1995670199394226,
6228
+ "learning_rate": 0.001,
6229
+ "loss": 2.652,
6230
+ "num_input_tokens_seen": 9175035456,
6231
+ "step": 35000
6232
+ },
6233
+ {
6234
+ "epoch": 0.1669508806658955,
6235
+ "eval_loss": 2.5248045921325684,
6236
+ "eval_runtime": 50.8205,
6237
+ "eval_samples_per_second": 98.386,
6238
+ "eval_steps_per_second": 24.596,
6239
+ "num_input_tokens_seen": 9175035456,
6240
+ "step": 35000
6241
  }
6242
  ],
6243
  "logging_steps": 50,
6244
  "max_steps": 70000,
6245
+ "num_input_tokens_seen": 9175035456,
6246
  "num_train_epochs": 1,
6247
  "save_steps": 1000,
6248
  "stateful_callbacks": {
 
6257
  "attributes": {}
6258
  }
6259
  },
6260
+ "total_flos": 2.4544115328260506e+18,
6261
  "train_batch_size": 64,
6262
  "trial_name": null,
6263
  "trial_params": null