havinash-ai commited on
Commit
c73083c
·
verified ·
1 Parent(s): 2ec0d74

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 sha256:8f6ce35e23b27fd6e8d1d435b62502338591f11531a5f8a43f0234c840188472
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a915023c7f8bdd17464c741226f972fe5b268cd370ae32f9e451dd707bf8226
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d1803d7ed40b584bcc9f71c2bb29e9cf16ac34d3d187a78c084a9dbd530b5650
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89c8b56c3bf31711649e9096743ffcda7656110afe58002de0e8ccf081d1e1b5
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5c3c915a3bb8b4192b1fe9ab2e40a6b8012bb6b2e4c94a894df47ee8a987a0e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:88861b17d557d63b349882c3778027603bbfce23e2152d04a0a61bc48795d1d0
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": 0.025423728813559324,
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": 7.961,
74
  "eval_steps_per_second": 3.981,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1359453911777280.0,
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": 0.038135593220338986,
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": 7.961,
74
  "eval_steps_per_second": 3.981,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.029661016949152543,
79
+ "grad_norm": 0.37393781542778015,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.0564,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.03389830508474576,
86
+ "grad_norm": 0.42129209637641907,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.9499,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.038135593220338986,
93
+ "grad_norm": 0.3632056713104248,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.9532,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.038135593220338986,
100
+ "eval_loss": 1.7135396003723145,
101
+ "eval_runtime": 12.5871,
102
+ "eval_samples_per_second": 7.945,
103
+ "eval_steps_per_second": 3.972,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2059778654208000.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null