Hugging Face's logo

VERSIL91
/
8c1d4c55-69a3-4be4-a876-d3098c74c1a5

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
VERSIL91 commited on
Commit
7debca2
·
verified ·
1 Parent(s): b091f7c

Training in progress, step 5, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:455cce95b25b41384665d1321996434c2d35f23a339d06d5d3b4103723a52e85
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baeab59fdd9a79b90fac23801cb3fe248d5eedcbcf37d80ebbd9c005ba8f837b
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41beea363afce3cec8a294b6995962c46d3e1ff4a2c7189a6a7a1a1f77befd2c
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9fc002eddb3a897c368b459e42100793ffea207f8a7c7a415caeb5514ac6e9
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ec3e8d1151e495ffa96386ee76aba3a8b7f1d47f34b3ad5155db54f403701f08
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33908394b59fe7a7ebaedb8be68ef4df972a1fe5650cf558cfa0d7fa8625c2e6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
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": 0.02952029520295203,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 26.925,
60
  "eval_steps_per_second": 13.521,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 5435787785011200.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03690036900369004,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 26.925,
60
  "eval_steps_per_second": 13.521,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.03690036900369004,
65
+ "grad_norm": 42.30099868774414,
66
+ "learning_rate": 5e-05,
67
+ "loss": 125.4018,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 6794734731264000.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null