duyphu commited on
Commit
4770305
·
verified ·
1 Parent(s): 2db1763

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:ea3701ddade63ff6e7827f8944f7c3282908eb7f0424889ba7cc6fdfdcb8e38b
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fab06ea34f43af4705986620cfb869fd701ccc2708fd23dce4bcb1382de6cd3
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3073e8ee07dab9f32c9b70fb37d69dada35f013b1daec7911161358d6bf0012a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52338f2f8a0528eb49cec35ce5e8af6f7d967c7adce88b3981d173b6218bff47
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:f367a6fef73d23ae488233d596a286d469d8d9b870fe7304bee86a5f40e0d1ea
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee1b249b23d3c7045b61d986525da9475988e143778f6c2587b190ecfa13a70
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": 0.0021938614070245756,
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": 0.6352,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5739993548980224.0,
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": 0.0032907921105368634,
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": 0.6352,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0025313785465668178,
72
+ "grad_norm": 12.149748802185059,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2221,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0025313785465668178,
79
+ "eval_loss": 0.0454639196395874,
80
+ "eval_runtime": 416.6408,
81
+ "eval_samples_per_second": 11.977,
82
+ "eval_steps_per_second": 5.988,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0029532749709946207,
87
+ "grad_norm": 9.316723823547363,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.1035,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 8631898695794688.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null