chauhoang commited on
Commit
300fbe3
·
verified ·
1 Parent(s): 00f65d4

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:a194fe1771316d69b942b026afaa9348f9d68b42deff1657d4491ac7e2260fae
3
  size 47235968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:306a8a7e54973801fd6ad56c59597fc3d526d2c00955e3043ae048a8d184e599
3
  size 47235968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a371d9aa69dbeb05d016651305d4f48d3c60e008518836898e52dd22efd9acca
3
  size 24410836
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ffb5394229b0195f27605f79c1e114e4888db38ca381ee363ca292bb145840d
3
  size 24410836
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:859560405fadc46aa10c3525b31585fba36ff636518d72b63aeb6c6a91c53b2c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a448c761d231bc0fb3f5b9140d4d36c6d5f57b2bc38a054844f026f5b0ed811b
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": 0.003612114476243401,
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": 1.278,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 3269109743616000.0,
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": 0.005418171714365101,
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": 1.278,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.004167824395665463,
72
+ "grad_norm": 3.263500690460205,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.2457,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.004167824395665463,
79
+ "eval_loss": 1.187597632408142,
80
+ "eval_runtime": 246.9745,
81
+ "eval_samples_per_second": 12.273,
82
+ "eval_steps_per_second": 6.138,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0048624617949430396,
87
+ "grad_norm": 2.6320784091949463,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.117,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 4903664615424000.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null