avsolatorio commited on
Commit
fe1b071
1 Parent(s): 132a4de

Training in progress, step 6000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a21612915d6048919c6c6fa540383add9560f3e355dabb28be9845e4fba73a80
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:041ce8f32ce552119e7b1d4237f62d551c007214b038e2e85e9201a6801f1604
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4d3b24a54a28fc1b501395caa28685b2dbe3f72b3754fd34c574c93993e2ab37
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eccf747ca8c8c8db9575b2956c6dd997a8eb4b5311ef905ec24ee3407e8cf61
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.04676121473312378,
3
- "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-5000",
4
- "epoch": 2.465483234714004,
5
  "eval_steps": 1000,
6
- "global_step": 5000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -137,6 +137,32 @@
137
  "eval_samples_per_second": 563.675,
138
  "eval_steps_per_second": 2.224,
139
  "step": 5000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
140
  }
141
  ],
142
  "logging_steps": 500,
@@ -165,7 +191,7 @@
165
  "attributes": {}
166
  }
167
  },
168
- "total_flos": 112700461753656.0,
169
  "train_batch_size": 4,
170
  "trial_name": null,
171
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.04347195476293564,
3
+ "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-6000",
4
+ "epoch": 2.9585798816568047,
5
  "eval_steps": 1000,
6
+ "global_step": 6000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
137
  "eval_samples_per_second": 563.675,
138
  "eval_steps_per_second": 2.224,
139
  "step": 5000
140
+ },
141
+ {
142
+ "epoch": 2.712031558185404,
143
+ "grad_norm": 0.39123860001564026,
144
+ "learning_rate": 1.9457593688362923e-05,
145
+ "loss": 0.0456,
146
+ "step": 5500
147
+ },
148
+ {
149
+ "epoch": 2.9585798816568047,
150
+ "grad_norm": 0.4525609016418457,
151
+ "learning_rate": 1.940828402366864e-05,
152
+ "loss": 0.0441,
153
+ "step": 6000
154
+ },
155
+ {
156
+ "epoch": 2.9585798816568047,
157
+ "eval_accuracy": 0.9861062686905623,
158
+ "eval_f1": 0.4897725498360485,
159
+ "eval_loss": 0.04347195476293564,
160
+ "eval_precision": 0.774103323461665,
161
+ "eval_recall": 0.35820327369623145,
162
+ "eval_runtime": 14.2071,
163
+ "eval_samples_per_second": 570.842,
164
+ "eval_steps_per_second": 2.252,
165
+ "step": 6000
166
  }
167
  ],
168
  "logging_steps": 500,
 
191
  "attributes": {}
192
  }
193
  },
194
+ "total_flos": 135256930917768.0,
195
  "train_batch_size": 4,
196
  "trial_name": null,
197
  "trial_params": null