duyphu commited on
Commit
48571b1
·
verified ·
1 Parent(s): 2c132ee

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 sha256:9652545dfd699162b5b6b847223e3aacfb04b822f6036e449e1099591aa93b20
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cee7030de506f158e7660e7b3747e193cc7110321191a1a3bfd188b50b5b562
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3debee0c1840c287a3ecc578fae14f3f28cb0ed9df6480a494ef81542d294c43
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ee06ee5608ebe0d6b6c38d6119007af2a1fbad6a502268a3f0ed609a1dfb7a
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.029612756264236904,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 7.3182,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2900965588992.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.04441913439635535,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 7.3182,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03416856492027335,
72
+ "grad_norm": 2.4453885555267334,
73
+ "learning_rate": 5e-05,
74
+ "loss": 7.4379,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03416856492027335,
79
+ "eval_loss": 7.355154037475586,
80
+ "eval_runtime": 5.0816,
81
+ "eval_samples_per_second": 72.812,
82
+ "eval_steps_per_second": 36.406,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.03986332574031891,
87
+ "grad_norm": 1.6234405040740967,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 7.5061,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4376032837632.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null