lesso commited on
Commit
b807d58
·
verified ·
1 Parent(s): de38487

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:fb34842dd9d51ce6c938e8efbc6f49475ccdebcf37b37fcb699e170a18771564
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2e848244af448da7a2d1c4d9688540c28184d38e92e64d11021ca90e6fd714
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c9b87f5e79618b0bfcdadaaf31c42610e7d7aa93cd212a5672ac08c3ef23c33
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ccce0b864bfcc116927a7d35e1852218b269730b1fc38a2343123aaf954741
3
  size 168037178
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a60def06e8d16b47623b67a4aae8194c19582b3e85d8800ca2e3bc17092d1bb5
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce8441b6f44f4e2fa1d2c030527340ac0218aae059aebad5b78181cb84cf26fe
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbbfd43de7fb2acc21f9de1871048cc58018d000e5907250651f158a613d62d3
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc75c68691d11d10bcc57bd372463d3e0df9a0caca3bec2a2287a78f782bdcb7
3
  size 14512
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": 0.00788436268068331,
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": 14.38,
45
  "eval_steps_per_second": 7.235,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1109738548887552.0,
67
  "train_batch_size": 1,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.01576872536136662,
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": 14.38,
45
  "eval_steps_per_second": 7.235,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.010512483574244415,
50
+ "grad_norm": 1.6191483736038208,
51
+ "learning_rate": 8e-05,
52
+ "loss": 3.4872,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.013140604467805518,
57
+ "grad_norm": 1.4146218299865723,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.1748,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.01576872536136662,
64
+ "grad_norm": 1.7842243909835815,
65
+ "learning_rate": 0.00012,
66
+ "loss": 3.2239,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.01576872536136662,
71
+ "eval_loss": 3.25826358795166,
72
+ "eval_runtime": 11.3071,
73
+ "eval_samples_per_second": 14.239,
74
+ "eval_steps_per_second": 7.164,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2219477097775104.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null