Hugging Face's logo

DLCS
/
contract-clause-phi3-lora

Text Classification
PEFT
Safetensors
English
lora
legal
contract-analysis
Model card Files
xet
 Community
DLCS commited on
Commit
3f91e84
·
verified ·
1 Parent(s): 5ef7eb3

Training in progress, step 150, checkpoint

Browse files
Files changed (5) 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/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +24 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:892468f6179aa10c1a7733bba59d75eb334d5f24b772b1779adab8dda9b64ab3
3
  size 50366280
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dcc03faff60c88187d193d577cb074f7b887352b1d8d0044f027b8b7434cb2b
3
  size 50366280
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8ee2d1b71e335700c85e7c58eedd0b37704635b9a0a9b94ec63aa14ef3b3d763
3
  size 51423589
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8fe46463f94afbb7df6a2c63de8998de252334e1031f63ce36abe9e77ee7ccf
3
  size 51423589
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0efd08727776fc9c70e3b518c4b5e7fa9a2c8f6e47f0d3709e7229aa5ce45521
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:203d8905e943b46c8e72ae2945349c735f85b24536f3be5e4997e93af1f994c2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feb807aff7b8d57984e264d5d2e6eec87b5558747a4ac826b8b8f88f5ac5c21b
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56a7fa4a93dbd8112336bf69dd77955c95bfe5afe563e5b75d8b00190ba21fa6
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": 75,
3
  "best_metric": 0.4165111482143402,
4
  "best_model_checkpoint": "./outputs/phi3-clause-lora/checkpoint-75",
5
- "epoch": 0.6680026720106881,
6
  "eval_steps": 25,
7
- "global_step": 125,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -113,6 +113,27 @@
113
  "eval_samples_per_second": 6.609,
114
  "eval_steps_per_second": 0.826,
115
  "step": 125
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
116
  }
117
  ],
118
  "logging_steps": 25,
@@ -132,7 +153,7 @@
132
  "attributes": {}
133
  }
134
  },
135
- "total_flos": 7647468081831936.0,
136
  "train_batch_size": 2,
137
  "trial_name": null,
138
  "trial_params": null
 
2
  "best_global_step": 75,
3
  "best_metric": 0.4165111482143402,
4
  "best_model_checkpoint": "./outputs/phi3-clause-lora/checkpoint-75",
5
+ "epoch": 0.8016032064128257,
6
  "eval_steps": 25,
7
+ "global_step": 150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
113
  "eval_samples_per_second": 6.609,
114
  "eval_steps_per_second": 0.826,
115
  "step": 125
116
+ },
117
+ {
118
+ "entropy": 0.16219462169799953,
119
+ "epoch": 0.8016032064128257,
120
+ "grad_norm": 0.6875,
121
+ "learning_rate": 0.0001373719714790469,
122
+ "loss": 0.16621768951416016,
123
+ "mean_token_accuracy": 0.9463053244352341,
124
+ "num_tokens": 317494.0,
125
+ "step": 150
126
+ },
127
+ {
128
+ "epoch": 0.8016032064128257,
129
+ "eval_entropy": 0.4183137859454599,
130
+ "eval_loss": 0.427802175283432,
131
+ "eval_mean_token_accuracy": 0.8620235504066877,
132
+ "eval_num_tokens": 317494.0,
133
+ "eval_runtime": 428.9572,
134
+ "eval_samples_per_second": 6.602,
135
+ "eval_steps_per_second": 0.825,
136
+ "step": 150
137
  }
138
  ],
139
  "logging_steps": 25,
 
153
  "attributes": {}
154
  }
155
  },
156
+ "total_flos": 9176907730673664.0,
157
  "train_batch_size": 2,
158
  "trial_name": null,
159
  "trial_params": null