leixa commited on
Commit
be4b335
·
verified ·
1 Parent(s): c0b8633

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f382ad7236c3f538fc7e8cfcd9b3a2cbf0999c16e45297a65fe281ba98224f1
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:893189980328b7343dfabeaa68d6539aed525990d53c410c274a9725cddaf66a
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe210eaefd96a7e614ea3ab2b776d290e5bf396533231f95eb4cd8b729fbef52
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:695772ce8d99daff3093a575413951dd4743e94d7535e76c4f0e410603987c0f
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8167a96dc4a0b700271fb769c80662658cb5db8db82c0d6060f5e230fd90b238
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2c1d5a97dae61d9453fafd03f4c7d8eea28e16ba48efd0c4f825b9e78ee9a7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.024671832990668986,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,27 @@
88
  "eval_samples_per_second": 13.011,
89
  "eval_steps_per_second": 6.505,
90
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +123,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 1.3592561159503872e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03163055511624229,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "eval_samples_per_second": 13.011,
89
  "eval_steps_per_second": 6.505,
90
  "step": 39
91
+ },
92
+ {
93
+ "epoch": 0.025304444092993834,
94
+ "grad_norm": 0.35025447607040405,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.5634,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.02846749960461806,
101
+ "grad_norm": 0.36843404173851013,
102
+ "learning_rate": 3.8060233744356633e-06,
103
+ "loss": 0.5792,
104
+ "step": 45
105
+ },
106
+ {
107
+ "epoch": 0.03163055511624229,
108
+ "grad_norm": 0.3375423848628998,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.5554,
111
+ "step": 50
112
  }
113
  ],
114
  "logging_steps": 5,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1.74263604609024e+16,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null