chauhoang commited on
Commit
dfe354d
·
verified ·
1 Parent(s): f288191

Training in progress, step 39, 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:cd4b250856ee5455aa9455579adfc144b20ca64f4f86cc31277e22fd7ccb13b2
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e3f155170b2e17057b7217e2bfeb8697e115cae6642ad212ff92fdd58b35a13
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dbdd581fce24e0541afb1ff09d27ef801de3bb17aeee1c8f4e559563c2d40fb
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a7e70600e03400972f367ba4c0d573ac62fadd3ea2ed6e028bdb67aa41d0022
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8b13df26bddb3c70b41dbe531e063a6e553c93965d731263f3f8cc687e7afb6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0a69897655d6335f40565e13c6d562938736cf3824c45eb132524b68b5b2ee5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.00897015697774711,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.634,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2545284525588480.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.013455235466620665,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.634,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.010350181128169742,
72
+ "grad_norm": 1.740796446800232,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.4755,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.010350181128169742,
79
+ "eval_loss": 0.5024950504302979,
80
+ "eval_runtime": 81.8931,
81
+ "eval_samples_per_second": 14.91,
82
+ "eval_steps_per_second": 7.461,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.012075211316198034,
87
+ "grad_norm": 1.8068922758102417,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.721,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3817926788382720.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null