0x1202 commited on
Commit
07c6852
·
verified ·
1 Parent(s): 8731b23

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:052b1c98ca08efa3fb4a3c085270d6ca9ddbfa1573a86ab5f1c194525c06da81
3
  size 645975704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48b42e301b7d38bc5bcfe7373712112882099cc7a9073cfc64e90916f5462560
3
  size 645975704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:71c07a17da051af96e362df1ee0fe25c88d8ae2e65364d13bcfe67e1fc2c057c
3
  size 328468404
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d0a331805b51f626ec974f314f7d1d364695d381708d1994068a5995d23a51c
3
  size 328468404
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:866c9c593b8f656306ee8873bbd71813969fc57179480fd14cab9986cca25136
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e7a0cedf434fc23d879f978e02c03de0ccd6047f54e36390d99f47742d1da1b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4c9c807f0681c8b7e53ada9b6ec3dba530d303de7da0d0a0562a3d8d0bbba08
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7417677640914917,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.13882461823229986,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -144,6 +144,49 @@
144
  "eval_samples_per_second": 11.092,
145
  "eval_steps_per_second": 2.773,
146
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
147
  }
148
  ],
149
  "logging_steps": 10,
@@ -167,12 +210,12 @@
167
  "should_evaluate": false,
168
  "should_log": false,
169
  "should_save": true,
170
- "should_training_stop": false
171
  },
172
  "attributes": {}
173
  }
174
  },
175
- "total_flos": 2.6802601718710272e+17,
176
  "train_batch_size": 8,
177
  "trial_name": null,
178
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.7377251386642456,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.18509949097639983,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
144
  "eval_samples_per_second": 11.092,
145
  "eval_steps_per_second": 2.773,
146
  "step": 150
147
+ },
148
+ {
149
+ "epoch": 0.14807959278111985,
150
+ "grad_norm": 0.22447636723518372,
151
+ "learning_rate": 1.1697777844051105e-05,
152
+ "loss": 1.7912,
153
+ "step": 160
154
+ },
155
+ {
156
+ "epoch": 0.15733456732993983,
157
+ "grad_norm": 0.23410490155220032,
158
+ "learning_rate": 6.698729810778065e-06,
159
+ "loss": 1.7734,
160
+ "step": 170
161
+ },
162
+ {
163
+ "epoch": 0.16658954187875982,
164
+ "grad_norm": 0.2778407037258148,
165
+ "learning_rate": 3.0153689607045845e-06,
166
+ "loss": 1.7592,
167
+ "step": 180
168
+ },
169
+ {
170
+ "epoch": 0.1758445164275798,
171
+ "grad_norm": 0.3438330888748169,
172
+ "learning_rate": 7.596123493895991e-07,
173
+ "loss": 1.7603,
174
+ "step": 190
175
+ },
176
+ {
177
+ "epoch": 0.18509949097639983,
178
+ "grad_norm": 0.7146674394607544,
179
+ "learning_rate": 0.0,
180
+ "loss": 1.7467,
181
+ "step": 200
182
+ },
183
+ {
184
+ "epoch": 0.18509949097639983,
185
+ "eval_loss": 1.7377251386642456,
186
+ "eval_runtime": 163.7691,
187
+ "eval_samples_per_second": 11.113,
188
+ "eval_steps_per_second": 2.778,
189
+ "step": 200
190
  }
191
  ],
192
  "logging_steps": 10,
 
210
  "should_evaluate": false,
211
  "should_log": false,
212
  "should_save": true,
213
+ "should_training_stop": true
214
  },
215
  "attributes": {}
216
  }
217
  },
218
+ "total_flos": 3.5796047653502976e+17,
219
  "train_batch_size": 8,
220
  "trial_name": null,
221
  "trial_params": null