Hugging Face's logo

anhdai312
/
Math18

Transformers
Safetensors
Generated from Trainer
sft
trl
unsloth
Model card Files
xet
 Community
anhdai312 commited on
Commit
7b60be3
·
verified ·
1 Parent(s): 90afc78

Training in progress, step 20, checkpoint

Browse files
Files changed (6) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +84 -6
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:792f6b5e409b467eed26818b8cbb468dd96971ad834cad6c8c13f5f81b0ae81b
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af064472ba1b66a0575444234d02f9dcd3eb1acb13792dd72998569aff56ae79
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8bfe19cfb751a7f68acd64fa56524804d81c76c232793bad701a5f7ee86fc3f
3
  size 18813829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f49e83fc7f7340236d54355fd19fc0404a2938d423705b03111c002b57a6e4f9
3
  size 18813829
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1259278ffa940e75456fa75c1f3f81fbad820adb0ccb5da97ce9130e9bbb6829
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec0cb1682171af50e84ef108a2acc2a5a9a5225ee807dd0ee1a230865af9ad1
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33523e96ce52dff0f29ec9e7ae1f032a7b33c5c5c6ccdfcac4547633f9274c58
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b374f525f261516982436cbdd52f264a2fa16b745265e4769916ed5719b55e
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17536e14144b500faa2a6ac809e5499560283606faa52a592337b7d3bcbf81e3
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd72775bbfa5902abce63e0562cae984d05beeb75fe20a28d89e581e86edcc1
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 10,
3
- "best_metric": 2.172542095184326,
4
- "best_model_checkpoint": "/tmp/checkpoints_/job_2cd1f599-85bf-4aa0-a3cf-f84970e4883a/checkpoint-10",
5
- "epoch": 0.2222222222222222,
6
  "eval_steps": 10,
7
- "global_step": 10,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -86,6 +86,84 @@
86
  "eval_samples_per_second": 13.892,
87
  "eval_steps_per_second": 3.473,
88
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  }
90
  ],
91
  "logging_steps": 1,
@@ -105,7 +183,7 @@
105
  "attributes": {}
106
  }
107
  },
108
- "total_flos": 9009728582400.0,
109
  "train_batch_size": 1,
110
  "trial_name": null,
111
  "trial_params": null
 
1
  {
2
+ "best_global_step": 20,
3
+ "best_metric": 0.6980130076408386,
4
+ "best_model_checkpoint": "/tmp/checkpoints_/job_2cd1f599-85bf-4aa0-a3cf-f84970e4883a/checkpoint-20",
5
+ "epoch": 0.4444444444444444,
6
  "eval_steps": 10,
7
+ "global_step": 20,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
86
  "eval_samples_per_second": 13.892,
87
  "eval_steps_per_second": 3.473,
88
  "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.24444444444444444,
92
+ "grad_norm": 8.405779838562012,
93
+ "learning_rate": 4.923076923076924e-05,
94
+ "loss": 2.295246124267578,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.26666666666666666,
99
+ "grad_norm": 7.363292217254639,
100
+ "learning_rate": 4.884615384615385e-05,
101
+ "loss": 2.2567129135131836,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.28888888888888886,
106
+ "grad_norm": 7.1502790451049805,
107
+ "learning_rate": 4.846153846153846e-05,
108
+ "loss": 1.823792815208435,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.3111111111111111,
113
+ "grad_norm": 6.763433933258057,
114
+ "learning_rate": 4.8076923076923084e-05,
115
+ "loss": 1.5706839561462402,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.3333333333333333,
120
+ "grad_norm": 6.633345127105713,
121
+ "learning_rate": 4.76923076923077e-05,
122
+ "loss": 1.5136253833770752,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.35555555555555557,
127
+ "grad_norm": 6.369776248931885,
128
+ "learning_rate": 4.730769230769231e-05,
129
+ "loss": 1.6171478033065796,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.37777777777777777,
134
+ "grad_norm": 6.243237018585205,
135
+ "learning_rate": 4.692307692307693e-05,
136
+ "loss": 1.0360909700393677,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.4,
141
+ "grad_norm": 7.544528484344482,
142
+ "learning_rate": 4.653846153846154e-05,
143
+ "loss": 1.2657012939453125,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.4222222222222222,
148
+ "grad_norm": 5.462157726287842,
149
+ "learning_rate": 4.615384615384616e-05,
150
+ "loss": 0.9959335327148438,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.4444444444444444,
155
+ "grad_norm": 5.940985679626465,
156
+ "learning_rate": 4.576923076923077e-05,
157
+ "loss": 1.0224928855895996,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.4444444444444444,
162
+ "eval_loss": 0.6980130076408386,
163
+ "eval_runtime": 0.746,
164
+ "eval_samples_per_second": 26.808,
165
+ "eval_steps_per_second": 6.702,
166
+ "step": 20
167
  }
168
  ],
169
  "logging_steps": 1,
 
183
  "attributes": {}
184
  }
185
  },
186
+ "total_flos": 18219673355520.0,
187
  "train_batch_size": 1,
188
  "trial_name": null,
189
  "trial_params": null