tuanna08go commited on
Commit
9db2f60
·
verified ·
1 Parent(s): 8875004

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 sha256:18ae88adbe0d43dcdf8bb99336761d6b1e5bc9fac65ee91a39963945e23deac1
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:675a09efa5a487718c6251c24c902159f8b28c5385c39fe87ca76b26ae288869
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9b2bb844a249448f468a82ef400e803dfcd98bbccb0ec3f74999f1c1ff6cda0
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:410f6ab443a1887eadb3512a1da1f4a0ebfe1d674ec55b6993ffa888b5785b8d
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bcd094c31c6302ab0f6b8a0d552c64675298946a65fbc2f7cfe61f1f9a1ad9d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44b2b655181cbd20071e25a8c2ca5953708370f3dc36111fe4dce52cd2f9b572
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": 0.05499735589635114,
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": 0.57,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4778131848167424.0,
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": 0.08249603384452671,
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": 0.57,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.06345848757271286,
72
+ "grad_norm": 1.8820977210998535,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.2061,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.06345848757271286,
79
+ "eval_loss": 0.2232237458229065,
80
+ "eval_runtime": 17.669,
81
+ "eval_samples_per_second": 11.263,
82
+ "eval_steps_per_second": 5.66,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.074034902168165,
87
+ "grad_norm": 1.589575171470642,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.7223,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7189115808251904.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null