ccore commited on
Commit
0f499a9
·
verified ·
1 Parent(s): e593e09

Training in progress, epoch 8, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24e28a52ef229ba6d8ed71fec15bff705f2501a7e9bd14e4bb54029c74045d56
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a30ebbd6657e1cab4ec2b03e03655f4cb11cc943457a8a4467091f0030d5d6
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:332a0dba68d3a65274c093ef9fc6ebceede2b5d048c9bfdaa10b0f40c94e497c
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5599f756b658d54d746a9242579f1e01ebe343bfce18681a57bbe6c9ed1e081f
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93cb2a9e1c10d9abbebe7c7a138c2f0ba5fcefafc2c50079c366e35cb5be33d1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ee4971414a0520b88b927c694c19903060200592189a0a539c94170dd4f40b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30c198d40e01946dd435e0b3025e9ad1b5a21b75875c7b39f672157105ea2ab6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b747a0dae9cc690ae54725ad77f1bc3e848725dcbbaa4ba117f697b1bc16ee0a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.354698896408081,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-110",
4
- "epoch": 7.0,
5
  "eval_steps": 500,
6
- "global_step": 154,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -63,6 +63,14 @@
63
  "eval_samples_per_second": 37.071,
64
  "eval_steps_per_second": 9.268,
65
  "step": 154
 
 
 
 
 
 
 
 
66
  }
67
  ],
68
  "logging_steps": 500,
@@ -82,7 +90,7 @@
82
  "attributes": {}
83
  }
84
  },
85
- "total_flos": 4965940804608000.0,
86
  "train_batch_size": 16,
87
  "trial_name": null,
88
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.350898027420044,
3
+ "best_model_checkpoint": "./opt_trained/checkpoint-176",
4
+ "epoch": 8.0,
5
  "eval_steps": 500,
6
+ "global_step": 176,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
63
  "eval_samples_per_second": 37.071,
64
  "eval_steps_per_second": 9.268,
65
  "step": 154
66
+ },
67
+ {
68
+ "epoch": 8.0,
69
+ "eval_loss": 1.350898027420044,
70
+ "eval_runtime": 8.0696,
71
+ "eval_samples_per_second": 37.177,
72
+ "eval_steps_per_second": 9.294,
73
+ "step": 176
74
  }
75
  ],
76
  "logging_steps": 500,
 
90
  "attributes": {}
91
  }
92
  },
93
+ "total_flos": 5675360919552000.0,
94
  "train_batch_size": 16,
95
  "trial_name": null,
96
  "trial_params": null