havinash-ai commited on
Commit
51fd9d8
·
verified ·
1 Parent(s): 33a2d14

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 sha256:8e74faed96cbf9a8f8b100cab94dd9af40d3c598e852ed82d903e54a660a3139
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98696d41ca947de02607c2a5f88c651002e189aad81c5265ce70c3424bb16baa
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1ba4539260cec4b0730718b3e544f4710fe202ed2bc9c023078719a408fa5ac
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8cc624e72c6edd5c8c1ef3fc0b912ba36a84910806d5c6f6a821fa8640308e24
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a427adcb42a5e21efe60aeff1fc331ce48c7ff904cf00d837fab2409ae1ed3f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:702327b551c4e20ef5af863061e25c1972735379504477c4bd2355e08bc4820d
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": 0.004281891168599465,
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": 8.707,
74
  "eval_steps_per_second": 4.354,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 4076840838758400.0,
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": 0.006422836752899197,
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": 8.707,
74
  "eval_steps_per_second": 4.354,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0049955396966993755,
79
+ "grad_norm": 0.31830304861068726,
80
+ "learning_rate": 0.00014,
81
+ "loss": 1.2547,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.005709188224799286,
86
+ "grad_norm": 0.3602185547351837,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.1553,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.006422836752899197,
93
+ "grad_norm": 0.3723427951335907,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.3473,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.006422836752899197,
100
+ "eval_loss": 0.34222760796546936,
101
+ "eval_runtime": 67.6386,
102
+ "eval_samples_per_second": 8.723,
103
+ "eval_steps_per_second": 4.361,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 6115261258137600.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null