avsolatorio commited on
Commit
f7387a9
1 Parent(s): b27cceb

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ce19c672be0d8e93a7fa34f22da21019af73a72b352a65bdfa8a3d06b1c6a9e
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27bb833041adfed42b6a3ef2a35959c1b1b7ec6fac87c9be3548d8be65091b43
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3f1fa73ea7a5820ec872caa2a1dcbe4434a262fc31339d2a61a280dcaae0398
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:769c965d71315065d6a2bf11b3587d15c515c2ddccef1e3c359b7c3985c89ed3
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34649568145f465443beb487f2295ab3dad9e5f49f758646dd823029413e18fe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69797e619b7f76fc3c65d1346887cd92f6a036b8a8ff866da9ca1a335d274133
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e136870ce715682b288c29fb4d05a0aec61f1a74b2cc393d7fb9e66e4965261
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de10e3ea9e9f590bd00b7f01055683747e52076430fd0eff98a7f3083d4ae0fc
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.09118108451366425,
3
- "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-1000",
4
- "epoch": 0.4930966469428008,
5
  "eval_steps": 1000,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -33,6 +33,32 @@
33
  "eval_samples_per_second": 669.709,
34
  "eval_steps_per_second": 2.642,
35
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
36
  }
37
  ],
38
  "logging_steps": 500,
@@ -61,7 +87,7 @@
61
  "attributes": {}
62
  }
63
  },
64
- "total_flos": 22568907250224.0,
65
  "train_batch_size": 4,
66
  "trial_name": null,
67
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.07077465206384659,
3
+ "best_model_checkpoint": "doc-topic-model_eval-02_train-00/checkpoint-2000",
4
+ "epoch": 0.9861932938856016,
5
  "eval_steps": 1000,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
33
  "eval_samples_per_second": 669.709,
34
  "eval_steps_per_second": 2.642,
35
  "step": 1000
36
+ },
37
+ {
38
+ "epoch": 0.7396449704142012,
39
+ "grad_norm": 0.33391374349594116,
40
+ "learning_rate": 1.9852071005917162e-05,
41
+ "loss": 0.0874,
42
+ "step": 1500
43
+ },
44
+ {
45
+ "epoch": 0.9861932938856016,
46
+ "grad_norm": 0.3162483870983124,
47
+ "learning_rate": 1.980276134122288e-05,
48
+ "loss": 0.0785,
49
+ "step": 2000
50
+ },
51
+ {
52
+ "epoch": 0.9861932938856016,
53
+ "eval_accuracy": 0.9813654208653996,
54
+ "eval_f1": 0.0,
55
+ "eval_loss": 0.07077465206384659,
56
+ "eval_precision": 0.0,
57
+ "eval_recall": 0.0,
58
+ "eval_runtime": 12.1773,
59
+ "eval_samples_per_second": 665.993,
60
+ "eval_steps_per_second": 2.628,
61
+ "step": 2000
62
  }
63
  ],
64
  "logging_steps": 500,
 
87
  "attributes": {}
88
  }
89
  },
90
+ "total_flos": 45292254069672.0,
91
  "train_batch_size": 4,
92
  "trial_name": null,
93
  "trial_params": null