duyphu commited on
Commit
f28ba3f
·
verified ·
1 Parent(s): 72490ac

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:f96c3d64ca1ef136fb7657e8770e04883ed1b6cf8657ec74eee3f16aa68a58a7
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79770a4cf85c6b4f990d47ec7f78d07982914cf11bf55d277f415fb0269d7758
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653f09ba4b6de08fa6d9290ec7fdadb3a72203ab66f375876b2e01abb1c00783
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743d83fee4a9aa1b41dcbf4ac2437fa4d56ddd6bd974c3b38683707997228e25
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d792f8c4da4f5332896f6b98b86c01d6d9b4ce6d947eeef4cb23fd3a0745b34e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be8487cf05ea0074174fea05b5c29e640fe072093941da1693aedc4198f5aaaf
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": 0.016521048451151706,
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": 0.9476,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2520810635919360.0,
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": 0.02478157267672756,
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": 0.9476,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.019062748212867357,
72
+ "grad_norm": 1.0646625757217407,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.015,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.019062748212867357,
79
+ "eval_loss": 1.0179016590118408,
80
+ "eval_runtime": 44.1296,
81
+ "eval_samples_per_second": 15.024,
82
+ "eval_steps_per_second": 7.523,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.022239872915011914,
87
+ "grad_norm": 1.02644681930542,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.8815,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3768979009044480.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null