kostiantynk commited on
Commit
f188b68
·
verified ·
1 Parent(s): 8f3c587

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:d0453d0ed010c20359a55f163ad7b5469ffbaade88b91964d626a1abbad96a6f
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:301767e54e8519964a0bf777ccff1446f5d554d0d04e2bad2c9b66481f9a9af3
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:700f1e025a6b9ca5e4a62bac2a09a5a462050d468da17e3bcb832d073ed33b80
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:467a56c5398c91854ab4096a0b434d7ddc9db3102df765975cfabe69af9ec0bf
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:049ef9d402621f8d67191fa7981b9705ec1748fcb4431765ca3a28fee3882315
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b70f29a81cab5749b7acb47c2046572b3022dd01b41109c8e1baa88cfd573b4b
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": 0.00024168210746797713,
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": 28.405,
74
  "eval_steps_per_second": 14.202,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1146654849761280.0,
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": 0.0003625231612019657,
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": 28.405,
74
  "eval_steps_per_second": 14.202,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00028196245871264,
79
+ "grad_norm": 2.818126678466797,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.0842,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0003222428099573028,
86
+ "grad_norm": 2.949310779571533,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.9708,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003625231612019657,
93
+ "grad_norm": 2.6062393188476562,
94
+ "learning_rate": 0.00018,
95
+ "loss": 0.7602,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003625231612019657,
100
+ "eval_loss": 0.5603215098381042,
101
+ "eval_runtime": 367.7961,
102
+ "eval_samples_per_second": 28.423,
103
+ "eval_steps_per_second": 14.212,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1719982274641920.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null