cwaud commited on
Commit
08c40e0
·
verified ·
1 Parent(s): 25878c4

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 sha256:3c7a6f6edeabec336202683807d27cf59811fd4d8c12ecb3f7288b8537eedc2f
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efff1503c16ebb8627aa07d1db313d3cd2c4d01af105d01926ec7146295f226e
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbc4db7136f606b8f086296a04b412b6f9983cbb3c17eb08de679769e23865fb
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7efd0ad7c08870e9dc8db75b2d3f4f16dcf8e1e5eb429acfa8c260abaf5566
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d26119094700b045e9c480a0c7cf82f1620d9eb1119abdd7291f7017ea443b1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd033918d0ec9be7b0057f0d36df7507acb2080dc148b8d779c63bff8270321
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": 0.001894387875917594,
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": 22.354,
74
  "eval_steps_per_second": 11.177,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 305923620864000.0,
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": 0.0028415818138763913,
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": 22.354,
74
  "eval_steps_per_second": 11.177,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.0022101191885705264,
79
+ "grad_norm": 1.3896536827087402,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.5012,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.0025258505012234586,
86
+ "grad_norm": 1.2694809436798096,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.5385,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0028415818138763913,
93
+ "grad_norm": 2.028712034225464,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.5697,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0028415818138763913,
100
+ "eval_loss": 2.3210620880126953,
101
+ "eval_runtime": 59.7473,
102
+ "eval_samples_per_second": 22.327,
103
+ "eval_steps_per_second": 11.164,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 452766958878720.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null