duyphu commited on
Commit
e3a6176
·
verified ·
1 Parent(s): adca234

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 sha256:9fc75617e33b69fd4234fedc6268795bbffe6e488f553c567a95fd4d6f7f6baf
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62066f21d6fa99e089fa5d965b97b661178d8580e955c48bb15b81d4f56468ea
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dff8ad70593592214c2d5a359bedfd5f3208317efda72e3d7999db09b2468f2b
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d94cb2bdfe83e3f53716a083039c5b491b637cbc19cc5735acf31f7624b850e6
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7144b0dce529bd6ff66b9941983b581e0ea1f47f188e811ff4fa48d3921f957f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79860259ff731f0b1c006300fee3fbd1e0fb1cad375751b62eee5d8cabbc13f0
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": 0.0007137464827396884,
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": 2.1106,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4855106151383040.0,
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": 0.0010706197241095326,
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": 2.1106,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0008235536339304097,
72
+ "grad_norm": 2.8816778659820557,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.2125,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0008235536339304097,
79
+ "eval_loss": NaN,
80
+ "eval_runtime": 1014.3743,
81
+ "eval_samples_per_second": 15.121,
82
+ "eval_steps_per_second": 7.56,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0009608125729188114,
87
+ "grad_norm": 2.178051710128784,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.0191,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7259539673972736.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null