kostiantynk1205 commited on
Commit
6cd99dc
·
verified ·
1 Parent(s): 148bb10

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:ea941fd17fe02aac215439ae91f907211ef49fa786b9f52570725336394b8c23
3
  size 12609312
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d403ad317dd8a933cdf8bc4c51d482dbd4216f62511eaa2fa428fe02ee544311
3
  size 12609312
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccbe7c65257f068a9ad10be8b0b75b80eb39deff1722da97642649ffc4efa7dd
3
  size 6615034
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9a3f5e2fec662d52e06b23d92a434b1dff560011b67e77dadd04e1fab35bc56
3
  size 6615034
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f740901ed64f5f8faba4c4399f748c6779503ac7c16ef83516dab3603a5a5402
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:399171def2779bd0a4edea00ec815fe9bfd7f86cec979b7ea47ed048203a9783
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": 0.0031189083820662767,
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": 77.774,
74
  "eval_steps_per_second": 38.935,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 105274278936576.0,
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": 0.004678362573099415,
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": 77.774,
74
  "eval_steps_per_second": 38.935,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0036387264457439896,
79
+ "grad_norm": 23.673173904418945,
80
+ "learning_rate": 0.00014,
81
+ "loss": 7.4469,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.004158544509421702,
86
+ "grad_norm": 17.75699234008789,
87
+ "learning_rate": 0.00016,
88
+ "loss": 6.9898,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.004678362573099415,
93
+ "grad_norm": 29.242324829101562,
94
+ "learning_rate": 0.00018,
95
+ "loss": 6.5794,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.004678362573099415,
100
+ "eval_loss": 1.6873035430908203,
101
+ "eval_runtime": 10.2979,
102
+ "eval_samples_per_second": 78.754,
103
+ "eval_steps_per_second": 39.425,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 157911418404864.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null