duyphu commited on
Commit
08883b9
·
verified ·
1 Parent(s): 4f493b2

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 sha256:556ce7f43e70abb0479fd721a69187f74471c80475099f1225a2eace46d740ee
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bd85719cdc8700a227dfd8e834c91497f6b6df56b4d864d25cd4d3b3be3e3ee
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5689c6e5e8160c799262b45d9ebce394dc883e5ca918d6bc50ede5e2e087dcb
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed4ac4c6302067b26f4316b922c0c5b4260691ef0aefc3966c25a83b2da8c8d7
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c994100bc200c9ca152561ad09e094f177f66ff43cd35ce2f03c388104c11909
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca739bde5f78892be94decf671d5c70c2e122047115b43a00c738da6fe3eaf52
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": 0.0063399170933918555,
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": 1.8158,
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": 1816070247677952.0,
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": 0.008128098837681867,
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": 1.8158,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.006502479070145493,
94
+ "grad_norm": 0.8678587079048157,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 2.1344,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.006502479070145493,
101
+ "eval_loss": 2.0176761150360107,
102
+ "eval_runtime": 107.1394,
103
+ "eval_samples_per_second": 24.183,
104
+ "eval_steps_per_second": 12.096,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0073152889539136795,
109
+ "grad_norm": 0.9728282690048218,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.7753,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.008128098837681867,
116
+ "grad_norm": 1.2071011066436768,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.7788,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.008128098837681867,
123
+ "eval_loss": 2.01554012298584,
124
+ "eval_runtime": 106.6185,
125
+ "eval_samples_per_second": 24.302,
126
+ "eval_steps_per_second": 12.155,
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": 2326840004837376.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null