great0001 commited on
Commit
695ab70
·
verified ·
1 Parent(s): eb76e97

Training in progress, step 6, 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:ad640a97c3a6354dbb0a2ee7e6d718a73bc096efad83746a8c57fad593f59bec
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7eceb5ab7d268e6f0220a69ab1b53903e6fc4c356bbb4a4c759ad630461d94e
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:757fd63446d573982d9edb571b12b86e6e9f33dde38d02f7d99c2906bdb996cd
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10efc2d54d0e1ab1e1d1c7f3f6bde01b3d0039a6ddf68c44b45f054ca18d7af7
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07dcab63c2688c6a677a021ac12864386eaa503924c1151e4b00c1ce7eee7d14
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2de705390d283bbd81a5e93dee1b31313fa27cc6d82af844c64763adad18b049
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.007134363852556481,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 35.761,
45
  "eval_steps_per_second": 17.88,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 239962322632704.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.014268727705112961,
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,
 
44
  "eval_samples_per_second": 35.761,
45
  "eval_steps_per_second": 17.88,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.009512485136741973,
50
+ "grad_norm": 0.2574818730354309,
51
+ "learning_rate": 8e-05,
52
+ "loss": 2.0286,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.011890606420927468,
57
+ "grad_norm": 0.4121098518371582,
58
+ "learning_rate": 0.0001,
59
+ "loss": 1.9101,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.014268727705112961,
64
+ "grad_norm": 0.3913452923297882,
65
+ "learning_rate": 0.00012,
66
+ "loss": 1.9592,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.014268727705112961,
71
+ "eval_loss": 2.049959421157837,
72
+ "eval_runtime": 4.955,
73
+ "eval_samples_per_second": 35.923,
74
+ "eval_steps_per_second": 17.962,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 497064811167744.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null