chauhoang commited on
Commit
e9926b1
·
verified ·
1 Parent(s): 0fd1edb

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:edcb7faa486c73f95147d2c5573f2a60123527e294df2dc5153492f573086c05
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba437e8d607bf35bde9fd9510a19fd719c9ae9eafbee3fd2e8538466d32834c
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:703557a07e59eb745661fb89bc31a54c6f5f36b4c324ab32bf8bd4dbedf06f42
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2555e32867013ae56fdd1addd1a0429719b67e08332916cd1d598292a250be39
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c22b2175a2a47d6b4a165ba96176044e357c7704eefe53ddb51f284586337029
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809dcdff3234f9152331d97451dd9535031f15f06b34f3dc13a8639c11fb865b
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": 0.03399803857469761,
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": 2.2194,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8074361233735680.0,
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": 0.05099705786204642,
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": 2.2194,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.03922850604772801,
72
+ "grad_norm": 2.625696897506714,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9821,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.03922850604772801,
79
+ "eval_loss": 2.027791738510132,
80
+ "eval_runtime": 37.9951,
81
+ "eval_samples_per_second": 8.475,
82
+ "eval_steps_per_second": 4.237,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.04576659038901602,
87
+ "grad_norm": 2.2278287410736084,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.0424,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.213543049330688e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null