joboffer commited on
Commit
5dc0494
·
verified ·
1 Parent(s): 9a2a98f

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2851b5401934ef3a039d8b121cb026ae2cd487722b5b5607be716b8d4cfe66ce
3
  size 95402480
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f38ad1926844bd4e8778799df4a3fd38c29501aca568a0d60c45d865ace7f591
3
  size 95402480
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6634bbcea65ac4f0b13cb57e5e6f65b3bcdea8a4185178a362048e7bdfc4cad
3
  size 191012170
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d54c6e8e1b9a7e49d99b02d001e123f217111e53c5387447a11c027fa0e097
3
  size 191012170
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0133ad863b144f8eaead13b3a3bc2bb37df48d6abc7222d3edabe9dfc51f6ed0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e16bdf370742716a02b73cdc1cc08bf8c26688d8e390eced9a1803f36ab354eb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.9294590950012207,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.00038642116042274477,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 7.935,
53
  "eval_steps_per_second": 3.968,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 2925325990232064.0,
84
  "train_batch_size": 2,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.82761812210083,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.0007728423208454895,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 7.935,
53
  "eval_steps_per_second": 3.968,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.0004637053925072937,
58
+ "grad_norm": 13.129424095153809,
59
+ "learning_rate": 8.18711994874345e-05,
60
+ "loss": 14.6658,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.0005796317406341171,
65
+ "grad_norm": 11.06294059753418,
66
+ "learning_rate": 6.545084971874738e-05,
67
+ "loss": 13.741,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.0005796317406341171,
72
+ "eval_loss": 1.861341953277588,
73
+ "eval_runtime": 1378.0059,
74
+ "eval_samples_per_second": 7.908,
75
+ "eval_steps_per_second": 3.954,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.0006955580887609405,
80
+ "grad_norm": 7.217223167419434,
81
+ "learning_rate": 4.6860474023534335e-05,
82
+ "loss": 13.4053,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.0007728423208454895,
87
+ "eval_loss": 1.82761812210083,
88
+ "eval_runtime": 1378.5654,
89
+ "eval_samples_per_second": 7.905,
90
+ "eval_steps_per_second": 3.953,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 5779302566068224.0,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null