kostiantynk1205 commited on
Commit
807a12b
·
verified ·
1 Parent(s): 059fde8

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:ae8c4f1b9e49320a7749ae89bf37cc9fd8a56081c3f6d6facf80d3ae0741585b
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25a03aa4f6e901f0a9b434909fd30fbdff576106963afb1ce10f90d64f948c37
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99b245f8fae7377de992446a7efe53ca78d7e47188b6ece5514ddfd2b6498b57
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:002255a7925410cbe54d306702c76c247ec5986dcb8b45bc3ffec4da3b7dfd9e
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:536f0330362fd09b1961297fffaef7cfae191e63e836fa1143751bbdfe0f3ac6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:157f0b38a83b3746dd7a07fdaa1bfaddd05a6863135cff06f7445a1aa2497e82
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.002245880752370052,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 21.332,
46
  "eval_steps_per_second": 10.668,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 8366449907466240.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003368821128555078,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 21.332,
46
  "eval_steps_per_second": 10.668,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0025914008681192906,
51
+ "grad_norm": 2.327564239501953,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 8.6316,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.003368821128555078,
58
+ "eval_loss": 2.156334400177002,
59
+ "eval_runtime": 228.4604,
60
+ "eval_samples_per_second": 21.338,
61
+ "eval_steps_per_second": 10.671,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.2488456935047168e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null