tuanna08go commited on
Commit
a3835b9
1 Parent(s): 6387d14

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:acdeefd06da21aec06877f32a58c2cfc9d8ed89edd4577be6d382338353f5685
3
  size 25192688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4d688b2f8a5542dc643ced12c82c46d14e6d6a1e0cfcb377ad01a086872c38a
3
  size 25192688
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:943e80a16406ae2250b5199db9532de636b79b9ac71d0a4e4d8d4c7fbad0ed6a
3
  size 13005178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e801f6ff75d282115f19870fad40a5b035ec58dc3f130a43b013d06ba3d3bca
3
  size 13005178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22560de8d5c5627120056c9da75748885a03451755734cf94fb6753df46da956
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04bd6c27f858a0013b27fc2a14ee28ac0f8deacab33d7b314aab38ab4b18a1d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
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": 0.08960573476702509,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -58,6 +58,49 @@
58
  "eval_samples_per_second": 5.368,
59
  "eval_steps_per_second": 5.368,
60
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  }
62
  ],
63
  "logging_steps": 5,
@@ -72,12 +115,12 @@
72
  "should_evaluate": false,
73
  "should_log": false,
74
  "should_save": true,
75
- "should_training_stop": false
76
  },
77
  "attributes": {}
78
  }
79
  },
80
- "total_flos": 94803433881600.0,
81
  "train_batch_size": 1,
82
  "trial_name": null,
83
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.17921146953405018,
5
  "eval_steps": 25,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
58
  "eval_samples_per_second": 5.368,
59
  "eval_steps_per_second": 5.368,
60
  "step": 25
61
+ },
62
+ {
63
+ "epoch": 0.10752688172043011,
64
+ "grad_norm": 0.0,
65
+ "learning_rate": 5e-05,
66
+ "loss": 0.0,
67
+ "step": 30
68
+ },
69
+ {
70
+ "epoch": 0.12544802867383512,
71
+ "grad_norm": 0.0,
72
+ "learning_rate": 3.086582838174551e-05,
73
+ "loss": 0.0,
74
+ "step": 35
75
+ },
76
+ {
77
+ "epoch": 0.14336917562724014,
78
+ "grad_norm": 0.0,
79
+ "learning_rate": 1.4644660940672627e-05,
80
+ "loss": 0.0,
81
+ "step": 40
82
+ },
83
+ {
84
+ "epoch": 0.16129032258064516,
85
+ "grad_norm": 0.0,
86
+ "learning_rate": 3.8060233744356633e-06,
87
+ "loss": 0.0,
88
+ "step": 45
89
+ },
90
+ {
91
+ "epoch": 0.17921146953405018,
92
+ "grad_norm": 0.0,
93
+ "learning_rate": 0.0,
94
+ "loss": 0.0,
95
+ "step": 50
96
+ },
97
+ {
98
+ "epoch": 0.17921146953405018,
99
+ "eval_loss": NaN,
100
+ "eval_runtime": 5.7108,
101
+ "eval_samples_per_second": 5.428,
102
+ "eval_steps_per_second": 5.428,
103
+ "step": 50
104
  }
105
  ],
106
  "logging_steps": 5,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 189606867763200.0,
124
  "train_batch_size": 1,
125
  "trial_name": null,
126
  "trial_params": null