duyphu commited on
Commit
930273a
·
verified ·
1 Parent(s): f29b2e5

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:c1ba3805b69906bf7d225fa9f97d4954fb1d57ab3453966ec95435f5a5f55e09
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8034066eab84385c925f8d5cb7dfaac1a9310cd520ef42543c10ecb68356f02b
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8936d730a6652c39f99e2fca3bd590959e0ffc15e0f9c60c348450c9e28369b
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50c1dd1e7f5c32e67e8beda7ac94af84589283a31635d51cbb5771bc4ec16f98
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3e0188c36bf4bc0a57d33fa822edfdddef13a1992525ff541c6389d56823cb0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f497f2a858c936111630bbf34f23fec2b0221ce321dcb916b0ed6dfb1c17ee4
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": 0.004396533502430776,
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": 0.2481,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 8974575637364736.0,
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": 0.006594800253646164,
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": 0.2481,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0050729232720355105,
72
+ "grad_norm": 0.10945611447095871,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.2563,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0050729232720355105,
79
+ "eval_loss": 0.26252034306526184,
80
+ "eval_runtime": 304.3401,
81
+ "eval_samples_per_second": 8.182,
82
+ "eval_steps_per_second": 4.091,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.005918410484041429,
87
+ "grad_norm": 0.11487659066915512,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.2584,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.3461863456047104e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null