Hugging Face's logo

havinash-ai
/
377d8250-51d3-4829-b83f-26d1ea9dfb50

PEFT
Safetensors
phi3
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
havinash-ai commited on
Commit
b92edaf
·
verified ·
1 Parent(s): 9212777

Training in progress, step 9, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:754eee834726db920500b35beb8c483f8d0c181fef4ddbde02f8c1d852a7dea2
3
  size 50365768
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a504bc728f76da32a35d38b4ac4b76c3376003b6a5d250f150d386c896eb729
3
  size 50365768
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c2dacf16cc9821f234020abb1e2967cf10564b8b44a1b90db42c4687267aff8
3
  size 25859156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97ef57b500639b30ca726958685c50a4d057d187aae40be5dbdc03614d696faa
3
  size 25859156
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08313bc423e4e749b1be6f1d16ebae8bf798fe463157da525e99306fd0b9592
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ce404e87fcfa8b39c59ce102013231e7cdc3750402766ab47e6fc98888814f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0045994633959371405,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 32.86,
74
  "eval_steps_per_second": 16.43,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 550772026638336.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006899195093905711,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 32.86,
74
  "eval_steps_per_second": 16.43,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.005366040628593331,
79
+ "grad_norm": 2.7698333263397217,
80
+ "learning_rate": 0.00014,
81
+ "loss": 4.302,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006132617861249521,
86
+ "grad_norm": 3.5623602867126465,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.4733,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006899195093905711,
93
+ "grad_norm": 2.596081256866455,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.3853,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006899195093905711,
100
+ "eval_loss": 0.7518635988235474,
101
+ "eval_runtime": 16.5706,
102
+ "eval_samples_per_second": 33.191,
103
+ "eval_steps_per_second": 16.596,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 826158039957504.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null