kostiantynk commited on
Commit
fe52380
·
verified ·
1 Parent(s): da778a7

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 sha256:35622d666b8676cb0e78ac7c159a149ce601f05e7a4fcffb8998bc0619527699
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b19177125d28ed5fd93477ac1adaccaa6b094a99d38e75a7bb40d97b8dcc2f9
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa8d4bf2a54850ddb8df8cc3851d0e580d3b793a6db9e3d345688709a1a1b03d
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0122bd14526ba8816be64a2e3b32087388d63f4c68549a4a663243d2a8a6336e
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:290db72453c0549da48ac2c903de9d8ef739ca7e660c6a1235dab2d77509f626
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc527ae92339ea167c2945496cfde8562215165c21050204ee36547f80f22391
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": 0.0017599178704993767,
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": 36.761,
74
  "eval_steps_per_second": 18.381,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 300058398425088.0,
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": 0.002639876805749065,
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": 36.761,
74
  "eval_steps_per_second": 18.381,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002053237515582606,
79
+ "grad_norm": 0.8693864941596985,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.4923,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0023465571606658357,
86
+ "grad_norm": 1.0759321451187134,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.3972,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.002639876805749065,
93
+ "grad_norm": 0.8064371347427368,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.3029,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002639876805749065,
100
+ "eval_loss": 1.302195429801941,
101
+ "eval_runtime": 38.9221,
102
+ "eval_samples_per_second": 36.894,
103
+ "eval_steps_per_second": 18.447,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 450087597637632.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null