trenden commited on
Commit
6f6acdf
·
verified ·
1 Parent(s): 3b8f979

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 sha256:9e9b27b775cbd94d25d42ee33fcf5c3d5dd786cfd9e5b3ca663b108daeb9e4c3
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c05618421679010ace69b6aa82c39fa972cc9d4041cb14be4cca6b26f42f886c
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0afbf9b5e2688bac3d7c784dad33e0b64d1e07f8769bbfcd534c7d5f50c1f2d
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef12d91ddf0e715152a41cda1c3506a38b2bb527150cb2ba2d696223ee456c0e
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59dfd7e3c5f47e9c59dd82d5934b354dca1792ccd6d53d936783c3e96fc445c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fda5437f05e2eaed0597b85f69532d5c06b3025917ba7357f9b3d1d946872746
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": 0.00031702419951389624,
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": 52.601,
74
  "eval_steps_per_second": 26.304,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 53422898282496.0,
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": 0.00047553629927084436,
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": 52.601,
74
  "eval_steps_per_second": 26.304,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0003698615660995456,
79
+ "grad_norm": 15.76357650756836,
80
+ "learning_rate": 0.00014,
81
+ "loss": 6.056,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00042269893268519497,
86
+ "grad_norm": 13.875348091125488,
87
+ "learning_rate": 0.00016,
88
+ "loss": 4.9629,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.00047553629927084436,
93
+ "grad_norm": 15.756418228149414,
94
+ "learning_rate": 0.00018,
95
+ "loss": 3.7258,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00047553629927084436,
100
+ "eval_loss": 3.4606802463531494,
101
+ "eval_runtime": 151.5311,
102
+ "eval_samples_per_second": 52.59,
103
+ "eval_steps_per_second": 26.298,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 80134347423744.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null