havinash-ai commited on
Commit
1442bd1
·
verified ·
1 Parent(s): 3310bf2

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 sha256:4a7e2086005e3e94774a4eab33694d4c30e04325419481b86d0573804503c146
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00116626013e9105e01652c93ceafdffb03807d1cc2643fbd39b2c1b7cc487cc
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8c3d5e12d992ea98938a3902185a4d9fde5997a2f34d63f59fad5680603c6605
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd5f85e656642ec8902b29776b3cd54b15c427d8fb27cca0a7e04eab970d4723
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d57765ccdbd3b79c135f681da7122fdba173117294579537d75e298a46d06671
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c722d78ec7068537fd499039e77673cf31f3270136d8ce21088267ffb4d3ec54
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": 0.016183412002697236,
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": 38.341,
74
  "eval_steps_per_second": 19.293,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 389157910216704.0,
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": 0.024275118004045852,
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": 38.341,
74
  "eval_steps_per_second": 19.293,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.018880647336480108,
79
+ "grad_norm": 0.20136234164237976,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.1399,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.02157788267026298,
86
+ "grad_norm": 0.20706254243850708,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.1876,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.024275118004045852,
93
+ "grad_norm": 0.18600346148014069,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.1218,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.024275118004045852,
100
+ "eval_loss": 1.2926275730133057,
101
+ "eval_runtime": 4.1348,
102
+ "eval_samples_per_second": 37.971,
103
+ "eval_steps_per_second": 19.106,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 567521952399360.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null