VERSIL91 commited on
Commit
6f28331
·
verified ·
1 Parent(s): 1b71a87

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 sha256:33540693de33624f11e647f105b6e9987824cae45d7b0932aecc0c767f84cba5
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cd5613ef0051165929245077acf89b14796ac9fbe816c182a91b13c9ef53438
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8a405c25f903db0bb133359e26615861473ea567f25821336a024b862e66549
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88333c467c4da6d4513cc121aed294bef79ccab2038801a8a7545aae62947ad1
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:435b272928b7d864a2c0322cd0f99f1494b6d6f71fa2a94061c152a136c75e0d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b550eddb1fd0b6c7745761b04141bf71e2f5f8aef394e37d964f7d28953bcf3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
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": 0.2874251497005988,
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": 20.153,
45
  "eval_steps_per_second": 10.076,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 1101544053276672.0,
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": 0.5748502994011976,
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": 20.153,
45
  "eval_steps_per_second": 10.076,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.38323353293413176,
50
+ "grad_norm": 18.877365112304688,
51
+ "learning_rate": 4e-05,
52
+ "loss": 8.279,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.47904191616766467,
57
+ "grad_norm": 18.81561851501465,
58
+ "learning_rate": 5e-05,
59
+ "loss": 7.9473,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.5748502994011976,
64
+ "grad_norm": 19.72781753540039,
65
+ "learning_rate": 6e-05,
66
+ "loss": 7.7265,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.5748502994011976,
71
+ "eval_loss": 0.3338497579097748,
72
+ "eval_runtime": 0.8954,
73
+ "eval_samples_per_second": 20.102,
74
+ "eval_steps_per_second": 10.051,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 2203088106553344.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null