Hugging Face's logo

anhdai312
/
math

Transformers
Safetensors
Generated from Trainer
unsloth
sft
trl
Model card Files
xet
 Community
anhdai312 commited on
Commit
d97f4cd
·
verified ·
1 Parent(s): d576983

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:f9f0021979b6cdf5f022417c3800dfdb5c51ec6b7ac3228bbe0f98142ddef9d5
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fd1899e54d143d2f81a5da6bd49edd5f123dd02dff09c374b6433ffd510a41e
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5321ddddef2a96f4d59762067250b61bc0564f1915575df12b264680f3530690
3
  size 18813829
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6798a884992637f8fd86ae35c1a2f7f20b19173e66d55c0d2aa0360d93d740d
3
  size 18813829
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c800b778fa7e115e4c34de8529902de8b61c9a1b4bab3eb8295d06dafff030e
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:181c5f0270cf39930062ddfa3767a2481d0c360f120b11f8e25dbf533a1cdaba
3
  size 14645
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f573b9f7149922ed73a27c9028f6f2cbdca1c0ef23c998ef777ef3be95e566d
3
  size 1383
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fee0874fa9afae54661807fadac685c3d3f843473b6af99cc43d812ec6e1b36
3
  size 1383
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:579c3a8590564ed7e91a6b14a7e35d84de8539e45b9a2dc709c0b7ead5628675
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:142330f2274e6971505182827bf85a03f6f751d0c7c41a1bed02d084e8c2ed30
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -1,10 +1,10 @@
1
  {
2
- "best_global_step": 10,
3
- "best_metric": 2.18822979927063,
4
- "best_model_checkpoint": "/tmp/checkpoints_/job_0d4521ef-134d-4da5-986e-64cc35a0beaa/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": 32.162,
87
  "eval_steps_per_second": 8.04,
88
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
89
  }
90
  ],
91
  "logging_steps": 1,
@@ -105,7 +183,7 @@
105
  "attributes": {}
106
  }
107
  },
108
- "total_flos": 10910682305280.0,
109
  "train_batch_size": 1,
110
  "trial_name": null,
111
  "trial_params": null
 
1
  {
2
+ "best_global_step": 20,
3
+ "best_metric": 0.9114124178886414,
4
+ "best_model_checkpoint": "/tmp/checkpoints_/job_0d4521ef-134d-4da5-986e-64cc35a0beaa/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": 32.162,
87
  "eval_steps_per_second": 8.04,
88
  "step": 10
89
+ },
90
+ {
91
+ "epoch": 0.24444444444444444,
92
+ "grad_norm": 5.783756732940674,
93
+ "learning_rate": 4.981772185245135e-05,
94
+ "loss": 2.302637815475464,
95
+ "step": 11
96
+ },
97
+ {
98
+ "epoch": 0.26666666666666666,
99
+ "grad_norm": 5.778560638427734,
100
+ "learning_rate": 4.973765998627628e-05,
101
+ "loss": 2.1610288619995117,
102
+ "step": 12
103
+ },
104
+ {
105
+ "epoch": 0.28888888888888886,
106
+ "grad_norm": 5.138077735900879,
107
+ "learning_rate": 4.964315202329127e-05,
108
+ "loss": 1.8655757904052734,
109
+ "step": 13
110
+ },
111
+ {
112
+ "epoch": 0.3111111111111111,
113
+ "grad_norm": 5.479531764984131,
114
+ "learning_rate": 4.953425315348534e-05,
115
+ "loss": 1.749828815460205,
116
+ "step": 14
117
+ },
118
+ {
119
+ "epoch": 0.3333333333333333,
120
+ "grad_norm": 5.30877161026001,
121
+ "learning_rate": 4.9411026970731805e-05,
122
+ "loss": 1.5302460193634033,
123
+ "step": 15
124
+ },
125
+ {
126
+ "epoch": 0.35555555555555557,
127
+ "grad_norm": 5.6600260734558105,
128
+ "learning_rate": 4.92735454356513e-05,
129
+ "loss": 1.394092082977295,
130
+ "step": 16
131
+ },
132
+ {
133
+ "epoch": 0.37777777777777777,
134
+ "grad_norm": 4.990982532501221,
135
+ "learning_rate": 4.9121888833588795e-05,
136
+ "loss": 1.2497376203536987,
137
+ "step": 17
138
+ },
139
+ {
140
+ "epoch": 0.4,
141
+ "grad_norm": 5.325894832611084,
142
+ "learning_rate": 4.8956145727729156e-05,
143
+ "loss": 1.2083749771118164,
144
+ "step": 18
145
+ },
146
+ {
147
+ "epoch": 0.4222222222222222,
148
+ "grad_norm": 5.7776618003845215,
149
+ "learning_rate": 4.877641290737884e-05,
150
+ "loss": 1.1976934671401978,
151
+ "step": 19
152
+ },
153
+ {
154
+ "epoch": 0.4444444444444444,
155
+ "grad_norm": 5.4699249267578125,
156
+ "learning_rate": 4.858279533144358e-05,
157
+ "loss": 0.9608996510505676,
158
+ "step": 20
159
+ },
160
+ {
161
+ "epoch": 0.4444444444444444,
162
+ "eval_loss": 0.9114124178886414,
163
+ "eval_runtime": 0.6193,
164
+ "eval_samples_per_second": 32.293,
165
+ "eval_steps_per_second": 8.073,
166
+ "step": 20
167
  }
168
  ],
169
  "logging_steps": 1,
 
183
  "attributes": {}
184
  }
185
  },
186
+ "total_flos": 21898370837760.0,
187
  "train_batch_size": 1,
188
  "trial_name": null,
189
  "trial_params": null