tuanna08go commited on
Commit
c2ab570
·
verified ·
1 Parent(s): 6d77b51

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 sha256:9f3ff81779ab0c06a627ea9b247ba53791789b0bb104eb59ba079aaf86cfce86
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f068d5669c53449fe332da5c94685d42f988385554047ad6da79b7fb04240c31
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9280148741fec4b7fe3563ffadce99b4a88b398d19daccbb9ea9490d1173ab6f
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34ab9ae395827a859cb1db4f69453e1384fd0031f9c3f4004890f548573f92b5
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e557af93914c894de252ad5739c858bc8be67dba19068d91502dd049001e333e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da57a3a869ac100e03e854428cb96b9fe176c6ed5065d0878032c78bdd0f415e
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": 0.02364711232378354,
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": 1.6847,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2132126528962560.0,
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": 0.03547066848567531,
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": 1.6847,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.027285129604365622,
72
+ "grad_norm": 1.6155500411987305,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9678,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.027285129604365622,
79
+ "eval_loss": 1.909964919090271,
80
+ "eval_runtime": 17.9512,
81
+ "eval_samples_per_second": 25.792,
82
+ "eval_steps_per_second": 12.924,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.031832651205093224,
87
+ "grad_norm": 2.7540478706359863,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.1482,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3198189793443840.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null