Nexspear commited on
Commit
43cbb6b
·
verified ·
1 Parent(s): 6c2ce18

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:fe13b6f1bbdfd66402bf9677bf3a150e17cc1de847da4a1a4c480e09740155f1
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eec857b9ea12eaabf2d0b23dcf15198f146668afc44f53d70f043121f8d3dbc3
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8c7fa07bfc83ac5fef3626428701e44ada1944b97335074121c46e14ff6a98e
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:96dd4930bdbaf3eabdecfee0db4168d33be108db483343c685de30a583cdf07e
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb68ca91ee60d94458763e6e49cbbe5d5a84e740dd8d6996e285ee8f567d027e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5abcee414ef1d24e3d92c4f6d6e4e10ed3a8bed448da343406c47f1ca300c19
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": 0.13600697471665213,
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": 20.759,
89
  "eval_steps_per_second": 10.465,
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": 7085059202875392.0,
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": 0.17436791630340018,
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": 20.759,
89
  "eval_steps_per_second": 10.465,
90
  "step": 39
91
+ },
92
+ {
93
+ "epoch": 0.13949433304272013,
94
+ "grad_norm": 0.008936063386499882,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.0007,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.15693112467306017,
101
+ "grad_norm": 2.6619582176208496,
102
+ "learning_rate": 3.8060233744356633e-06,
103
+ "loss": 0.0188,
104
+ "step": 45
105
+ },
106
+ {
107
+ "epoch": 0.17436791630340018,
108
+ "grad_norm": 0.007761336863040924,
109
+ "learning_rate": 0.0,
110
+ "loss": 0.0014,
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": 9243151948578816.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null