kostiantynk-out commited on
Commit
77cfe4d
·
verified ·
1 Parent(s): 056bbe4

Training in progress, step 9, 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:ef9fba3bd377c892ac3050334189c7f64b18664d69742af5360f03591cc2c30b
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:674eb0ab03f66863226c973e0df0717b41b0a7c602877f926b71aed8e5c057ac
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa98fe6babb4a99cb3470c25a33caed547b7ae6582b8f7de29201d3d25ff7c0b
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed87b813c3e4e2e054209aa1a7090e9e842c149cf2fc5119b3d553606cdfaa06
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:22bdd3e28a5c5e07dd26fead4e33c39110271736518658f4653b98f61291a497
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53682ca9c6293fe1d7015467a02e0276dfb87c5470ad925caa422514eeb91c91
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.028070175438596492,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 54.59,
74
  "eval_steps_per_second": 27.295,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 306950373900288.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.042105263157894736,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 54.59,
74
  "eval_steps_per_second": 27.295,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.03274853801169591,
79
+ "grad_norm": 0.44060736894607544,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.4808,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.03742690058479532,
86
+ "grad_norm": 0.4031517207622528,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.4764,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.042105263157894736,
93
+ "grad_norm": 0.36345911026000977,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.2561,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.042105263157894736,
100
+ "eval_loss": 2.419855833053589,
101
+ "eval_runtime": 1.6451,
102
+ "eval_samples_per_second": 54.709,
103
+ "eval_steps_per_second": 27.354,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 460425560850432.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null