tuantmdev commited on
Commit
e518a89
·
verified ·
1 Parent(s): 4066a60

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:07d576f44960ee50c7b5c410926b2877d9d947e1001a7bc925a4c43b5a0906f1
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9e6ca91dd7139afe1de28258a6bf89573f95d1d60cb3e878c46c310ef11366b
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:342a7eddb67fb91234085ee861ceaff6d928aad6d8bf765bc31c537b4abc0118
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d59b7aa9ef273c359f0edebe78acf1d365ccdc59275f7f6ae72fef87a8259ca
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a11026151701891f1e51da87b129435ea3f0c8a57006941ff93af609e5428fd
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4dfab981a31aa7cc3ba55071696c4004ea8c14650f4097d8f8d20ecdaedc437
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:500b1c78c9d3af1c55fbf9cc6e380394ac567579f265e54ad9607c3dc9f74108
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb148ad6cd6502048dc3eee274a6708e5b4f6b72c0d56ebc272935446c220acd
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": 0.017534606875483742,
5
  "eval_steps": 40,
6
- "global_step": 160,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -75,6 +75,21 @@
75
  "eval_samples_per_second": 15.315,
76
  "eval_steps_per_second": 7.658,
77
  "step": 160
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  }
79
  ],
80
  "logging_steps": 40,
@@ -89,12 +104,12 @@
89
  "should_evaluate": false,
90
  "should_log": false,
91
  "should_save": true,
92
- "should_training_stop": false
93
  },
94
  "attributes": {}
95
  }
96
  },
97
- "total_flos": 1.0423892069842944e+17,
98
  "train_batch_size": 2,
99
  "trial_name": null,
100
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.02191825859435468,
5
  "eval_steps": 40,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
75
  "eval_samples_per_second": 15.315,
76
  "eval_steps_per_second": 7.658,
77
  "step": 160
78
+ },
79
+ {
80
+ "epoch": 0.02191825859435468,
81
+ "grad_norm": 17.095829010009766,
82
+ "learning_rate": 0.0,
83
+ "loss": 27.6745,
84
+ "step": 200
85
+ },
86
+ {
87
+ "epoch": 0.02191825859435468,
88
+ "eval_loss": 1.7235428094863892,
89
+ "eval_runtime": 1005.4389,
90
+ "eval_samples_per_second": 15.286,
91
+ "eval_steps_per_second": 7.643,
92
+ "step": 200
93
  }
94
  ],
95
  "logging_steps": 40,
 
104
  "should_evaluate": false,
105
  "should_log": false,
106
  "should_save": true,
107
+ "should_training_stop": true
108
  },
109
  "attributes": {}
110
  }
111
  },
112
+ "total_flos": 1.302986508730368e+17,
113
  "train_batch_size": 2,
114
  "trial_name": null,
115
  "trial_params": null