nblinh63 commited on
Commit
7052e23
·
verified ·
1 Parent(s): a046542

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79b505f3aa54c15b17c2d918bab8b1bb08893568fe3762dbf43a0d95faa89d7f
3
  size 50503544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd2ff0a1ea77107bc0ff9abc718f43b5c390a3d7d86146e4696c6ee13a26b003
3
  size 50503544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c110479f74b0bad0f2216846702b9aad6b89cf1fef4d4900bef3a542e25c98f3
3
  size 25986148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8dfae8c5a8aded5989063a707e862dea252008ac0590ef0b0adad0388eba483d
3
  size 25986148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e60e08514843cd33eaf7ceebe02437d99ec8a00041ba6418bb40b89a1c5cd556
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17180c52a3bd518e0ef3a6c2b2af2da2fdbe09eb8ac3c2cdeb7acff9012e0f39
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0006160322390205088,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 6.415,
74
  "eval_steps_per_second": 3.208,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1235242526441472.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009240483585307631,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 6.415,
74
  "eval_steps_per_second": 3.208,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0007187042788572602,
79
+ "grad_norm": 0.35570693016052246,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.0329,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0008213763186940117,
86
+ "grad_norm": 0.2799961566925049,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.1908,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0009240483585307631,
93
+ "grad_norm": 0.37302330136299133,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.034,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0009240483585307631,
100
+ "eval_loss": 2.0924861431121826,
101
+ "eval_runtime": 639.2343,
102
+ "eval_samples_per_second": 6.415,
103
+ "eval_steps_per_second": 3.209,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1852863789662208.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null