havinash-ai commited on
Commit
30dc6c5
·
verified ·
1 Parent(s): 5428697

Training in progress, step 9, 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:d29389ed1fef58e32e4835f075fc4aa9865e6a5d8e9bb433f34b167cbfd4d35d
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a9d3244c3ca3a91474f8403d711f841ec366af4a96509129bfd8a8e501e4709
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0b2866d08bb06b336200df9941ef4bd58d0b178262eccef10475435fc8f87ed
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:555b83bedab0b20ddaca93a5ef3467c76b2545d965a9d1269251653d96e976a7
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b39fdae61621695240489a162bf4b64348d41d273005deffccbb200d274a34d6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2223d09f8cf8811fe50e9173354ece84e24973d7a08105c6e3293c6cd494fecc
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": 0.00013865298623869112,
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": 68.511,
74
  "eval_steps_per_second": 34.257,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 31720701689856.0,
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": 0.00020797947935803667,
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": 68.511,
74
  "eval_steps_per_second": 34.257,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00016176181727847296,
79
+ "grad_norm": 0.2417832463979721,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.0405,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00018487064831825483,
86
+ "grad_norm": 0.2619391977787018,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.0379,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00020797947935803667,
93
+ "grad_norm": 0.2710992395877838,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.6747,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00020797947935803667,
100
+ "eval_loss": 2.761340856552124,
101
+ "eval_runtime": 265.6473,
102
+ "eval_samples_per_second": 68.591,
103
+ "eval_steps_per_second": 34.297,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 47152394403840.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null