havinash-ai commited on
Commit
50d8226
·
verified ·
1 Parent(s): 11e10f5

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:dc1e578cfb7d0edddd5ada756b4336d6eb4a3b1a071cf36d46013335ab3eb656
3
  size 15182728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4911c86f00ad773fbd09f19c5888c5e6ca12b60ea526ae45a63e5a2e208a4a25
3
  size 15182728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ebabb1b85de7afed92a80e11277192733c931a023a1fad2f909eaa4c86019c2
3
  size 8075796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3363010531329e70b18e53e46f70fd8d996d0b45c4942f1100b852de8a6f483
3
  size 8075796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f12e0141b87e11410da9c14ba63f6f1dc556001470fe156f0138fe4aaf9f84f3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a317c97ee29e1eccbcb46ad3a29e23ffe3723d73c3c0911642fc6a37b5e2a32e
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": 0.011019283746556474,
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": 54.415,
45
  "eval_steps_per_second": 27.444,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 24935235846144.0,
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": 0.02203856749311295,
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": 54.415,
45
  "eval_steps_per_second": 27.444,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.014692378328741965,
50
+ "grad_norm": 2.394775867462158,
51
+ "learning_rate": 8e-05,
52
+ "loss": 3.3265,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.018365472910927456,
57
+ "grad_norm": 2.141361951828003,
58
+ "learning_rate": 0.0001,
59
+ "loss": 3.1668,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.02203856749311295,
64
+ "grad_norm": 1.9102329015731812,
65
+ "learning_rate": 0.00012,
66
+ "loss": 3.4038,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.02203856749311295,
71
+ "eval_loss": 3.2603423595428467,
72
+ "eval_runtime": 2.1406,
73
+ "eval_samples_per_second": 53.722,
74
+ "eval_steps_per_second": 27.095,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 49870471692288.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null