tuanna08go commited on
Commit
9033458
·
verified ·
1 Parent(s): efbc6e4

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:ca8ee4888bdc2e3300b20d3f04aff8d25354481d5bcdad9f6cdcb16d42319e99
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd82b9f709db934d194de20ca53b678f8eab20e29124710d65026d19c8d186c8
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61a7e9ab6990e277b1e7e11472964ef8ec9bf0226fca2882f94914f71f334380
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41f62d606ec747856652f8b853d84483ba7359fe65cb0f3d9fc704947fb73962
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f7c2901c8f247ffc6047aac6a8696da943c248de791c80b7c61460e14e4a823
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2754112ba4bf0b24ea7bba3dafb4e4d8bcdb84cd2b6baeabdacd60495750e552
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": 0.0029547133359849992,
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": 0.4691,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4993823469993984.0,
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": 0.004432070003977499,
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": 0.4691,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0034092846184442297,
72
+ "grad_norm": 2.198410749435425,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.3828,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0034092846184442297,
79
+ "eval_loss": 0.3945086598396301,
80
+ "eval_runtime": 257.4771,
81
+ "eval_samples_per_second": 14.39,
82
+ "eval_steps_per_second": 7.197,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.003977498721518268,
87
+ "grad_norm": 1.758271336555481,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.4105,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7444496098787328.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null