robiual-awal commited on
Commit
c78bdd6
·
verified ·
1 Parent(s): 887e5d7

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 sha256:78f300fadb86d60b83ed9edfc2de1bcb1bc30a23f003b2c34f85c037275798ab
3
  size 5752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af4f4089bbdc3b10df56a585cb700179b830dada0e2180711319f2f337878fb3
3
  size 5752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bededaa14fb1cfa55d162de7048d50bc3b00eab968ab6656b45ee326ce30e5da
3
  size 15814
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e58b0b48383b0239bcf33a3ed82de70f8e49e0c73108507a1ebf183a6f130e23
3
  size 15814
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9264abfa6d2cc5145363bf71d2fb16332b1ac4e60642a70827881d9a447c36a4
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af82c1f1d4ec999545a290f8875f59e0434314b9e98a3c2553c0c541daf4cdfa
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": 0.0010814708002883922,
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": 162.343,
45
  "eval_steps_per_second": 81.241,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 109575831552.0,
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": 0.0021629416005767843,
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": 162.343,
45
  "eval_steps_per_second": 81.241,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0014419610670511895,
50
+ "grad_norm": 1.0569451660558116e-05,
51
+ "learning_rate": 8e-05,
52
+ "loss": 46.0,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.001802451333813987,
57
+ "grad_norm": 1.8572542103356682e-05,
58
+ "learning_rate": 0.0001,
59
+ "loss": 46.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0021629416005767843,
64
+ "grad_norm": 1.435636750102276e-05,
65
+ "learning_rate": 0.00012,
66
+ "loss": 46.0,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0021629416005767843,
71
+ "eval_loss": 11.5,
72
+ "eval_runtime": 7.3833,
73
+ "eval_samples_per_second": 158.329,
74
+ "eval_steps_per_second": 79.232,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 224132382720.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null