kostiantynk-out commited on
Commit
bcc49b7
·
verified ·
1 Parent(s): 7299e4b

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bc797a1477cdcdf12274ffb5c0261ad56e89e29d0f19d877eef8aff6f6ec9eb
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:514e7a9867dcc1e2cdad9f6cc39946bcb0cba6072579a216511ec5a032fc2553
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7494252886296cb85df73e5bc786db2dd8ca17a20a26249d17efccc3cc733cbe
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b850902d02af03824952d0bc078262631b055c849e85b101eff65dad55b6fb4
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d29470828d895d58a07ba3e17290d308a68112a553e7a0f7d273c07e5e6b0bff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b976fe13df9d590838338fd3331460eb1554057da1cd4564745a089b6e6b692
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.04153354632587859,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 24.116,
61
  "eval_steps_per_second": 12.058,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.0033886046191616e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05324813631522897,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 24.116,
61
  "eval_steps_per_second": 12.058,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.042598509052183174,
66
+ "grad_norm": 0.9870797991752625,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.272,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.05324813631522897,
73
+ "grad_norm": 1.6510009765625,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.3372,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.2530797781188608e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null