chauhoang commited on
Commit
3d20a41
·
verified ·
1 Parent(s): 0dffd23

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:777ec5415b5ef9c9d5d4681c66e85a22160c7550ae63c1ce43b4722c458a83f0
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0365cfa7d8db98d6ba8a1f7d7b784845e6e8f64ded1a4f6088d96f750a5500a8
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff4231f9907ec776ae8c5f7c8f0dcfdf79002dcc389e8b8d2a1bad2d67c22167
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3dadd849d470ecc88936fc364ce14422c1448668c692c482a9153b0dae60a4a
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d52990953d1b8a81a00b7cecfd9c211b1ca6db6b881889b76e3a32894320cdb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:529c9e51cf346c9538de8a198d0e350de38ac30f5061dd3c6b0f0716ac464501
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.034346103038309116,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.2336,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 6426509401128960.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.044033465433729636,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.2336,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.03522677234698371,
94
+ "grad_norm": 1.8625359535217285,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.2459,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.03522677234698371,
101
+ "eval_loss": 1.205720067024231,
102
+ "eval_runtime": 28.8541,
103
+ "eval_samples_per_second": 16.601,
104
+ "eval_steps_per_second": 8.318,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.03963011889035667,
109
+ "grad_norm": 1.2852716445922852,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.2529,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.044033465433729636,
116
+ "grad_norm": 1.3766034841537476,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.2934,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.044033465433729636,
123
+ "eval_loss": 1.2010602951049805,
124
+ "eval_runtime": 28.412,
125
+ "eval_samples_per_second": 16.859,
126
+ "eval_steps_per_second": 8.447,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 8239114616832000.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null