tarabukinivan commited on
Commit
2cbc95b
·
verified ·
1 Parent(s): 0c4c496

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0d9a6cd022ba6b1e720fba33e07c122c98abe9ce8b80f89b587728539deee8ed
3
  size 26008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7da878284afc2ad077756c318f60ca3a858be95bcfe80c75f6d349843f12ed55
3
  size 26008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9677ec2ef0f29f084efd9a1c6f608765d85bb505cd371d711a63c9285c976f8c
3
  size 68874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f498ed63910f7b173ab999cfd6ea66f992fbe595b23ee5511698c60e464eb654
3
  size 68874
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
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": 0.02372479240806643,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 161.428,
53
  "eval_steps_per_second": 80.714,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -71,7 +108,7 @@
71
  "attributes": {}
72
  }
73
  },
74
- "total_flos": 3747348480.0,
75
  "train_batch_size": 2,
76
  "trial_name": null,
77
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04744958481613286,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 161.428,
53
  "eval_steps_per_second": 80.714,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.028469750889679714,
58
+ "grad_norm": 0.03766925632953644,
59
+ "learning_rate": 0.00019510565162951537,
60
+ "loss": 11.9331,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.03558718861209965,
65
+ "grad_norm": 0.06065177544951439,
66
+ "learning_rate": 0.00017071067811865476,
67
+ "loss": 11.9283,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.03558718861209965,
72
+ "eval_loss": 11.931966781616211,
73
+ "eval_runtime": 1.1329,
74
+ "eval_samples_per_second": 157.117,
75
+ "eval_steps_per_second": 78.559,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.042704626334519574,
80
+ "grad_norm": 0.041120365262031555,
81
+ "learning_rate": 0.00013090169943749476,
82
+ "loss": 11.9338,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.04744958481613286,
87
+ "eval_loss": 11.931893348693848,
88
+ "eval_runtime": 1.1032,
89
+ "eval_samples_per_second": 161.354,
90
+ "eval_steps_per_second": 80.677,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
108
  "attributes": {}
109
  }
110
  },
111
+ "total_flos": 7494696960.0,
112
  "train_batch_size": 2,
113
  "trial_name": null,
114
  "trial_params": null