lesso01 commited on
Commit
f6855c1
·
verified ·
1 Parent(s): 29e2cbf

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3256445ad884dd7e3690f852ff0535905d2b5ca8de75bb405f00f27f37a0b876
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e7ad47b7c403631e928089b7609e516f8f654e4dc4ddc7742f95856ee62a6f90
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b64aa789118b1f89db26a085285377ca3c184b558e0ce825ca43c01c7d59c218
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e05de80bb099f25139ed3f692696033689aa81a24627a0d24006ce0494cb26cc
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:771aba8a4e8fb219bd14601087487c802e830687ae8ba870683f0a0c56d57221
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49de370ac54225c7243186cc559aced1036fab31ef98861b24fe84d7ec44bd0b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.4689041078090668,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.022922636103151862,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -101,6 +101,92 @@
101
  "eval_samples_per_second": 3.301,
102
  "eval_steps_per_second": 1.65,
103
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
104
  }
105
  ],
106
  "logging_steps": 1,
@@ -129,7 +215,7 @@
129
  "attributes": {}
130
  }
131
  },
132
- "total_flos": 3505343598428160.0,
133
  "train_batch_size": 2,
134
  "trial_name": null,
135
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.3850732743740082,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.045845272206303724,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
101
  "eval_samples_per_second": 3.301,
102
  "eval_steps_per_second": 1.65,
103
  "step": 10
104
+ },
105
+ {
106
+ "epoch": 0.02521489971346705,
107
+ "grad_norm": 4.579631328582764,
108
+ "learning_rate": 0.00019781476007338058,
109
+ "loss": 2.0219,
110
+ "step": 11
111
+ },
112
+ {
113
+ "epoch": 0.027507163323782235,
114
+ "grad_norm": 6.482594966888428,
115
+ "learning_rate": 0.0001913545457642601,
116
+ "loss": 2.1928,
117
+ "step": 12
118
+ },
119
+ {
120
+ "epoch": 0.02979942693409742,
121
+ "grad_norm": 4.32263708114624,
122
+ "learning_rate": 0.00018090169943749476,
123
+ "loss": 1.7855,
124
+ "step": 13
125
+ },
126
+ {
127
+ "epoch": 0.032091690544412604,
128
+ "grad_norm": 4.8766188621521,
129
+ "learning_rate": 0.00016691306063588583,
130
+ "loss": 1.6799,
131
+ "step": 14
132
+ },
133
+ {
134
+ "epoch": 0.034383954154727794,
135
+ "grad_norm": 4.413567066192627,
136
+ "learning_rate": 0.00015000000000000001,
137
+ "loss": 1.6611,
138
+ "step": 15
139
+ },
140
+ {
141
+ "epoch": 0.034383954154727794,
142
+ "eval_loss": 0.40960490703582764,
143
+ "eval_runtime": 55.4446,
144
+ "eval_samples_per_second": 3.319,
145
+ "eval_steps_per_second": 1.659,
146
+ "step": 15
147
+ },
148
+ {
149
+ "epoch": 0.03667621776504298,
150
+ "grad_norm": 4.532293319702148,
151
+ "learning_rate": 0.00013090169943749476,
152
+ "loss": 1.7058,
153
+ "step": 16
154
+ },
155
+ {
156
+ "epoch": 0.03896848137535817,
157
+ "grad_norm": 4.254657745361328,
158
+ "learning_rate": 0.00011045284632676536,
159
+ "loss": 1.7261,
160
+ "step": 17
161
+ },
162
+ {
163
+ "epoch": 0.04126074498567335,
164
+ "grad_norm": 3.960785388946533,
165
+ "learning_rate": 8.954715367323468e-05,
166
+ "loss": 1.5435,
167
+ "step": 18
168
+ },
169
+ {
170
+ "epoch": 0.04355300859598854,
171
+ "grad_norm": 4.079868316650391,
172
+ "learning_rate": 6.909830056250527e-05,
173
+ "loss": 1.6584,
174
+ "step": 19
175
+ },
176
+ {
177
+ "epoch": 0.045845272206303724,
178
+ "grad_norm": 3.6767802238464355,
179
+ "learning_rate": 5.000000000000002e-05,
180
+ "loss": 1.5751,
181
+ "step": 20
182
+ },
183
+ {
184
+ "epoch": 0.045845272206303724,
185
+ "eval_loss": 0.3850732743740082,
186
+ "eval_runtime": 55.6159,
187
+ "eval_samples_per_second": 3.308,
188
+ "eval_steps_per_second": 1.654,
189
+ "step": 20
190
  }
191
  ],
192
  "logging_steps": 1,
 
215
  "attributes": {}
216
  }
217
  },
218
+ "total_flos": 7010687196856320.0,
219
  "train_batch_size": 2,
220
  "trial_name": null,
221
  "trial_params": null