tuanna08go
commited on
Training in progress, step 45, 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:
|
3 |
size 80792096
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:72090e0b7a82fb9036f64ae54bc27c216149239a7c4c630044b04acf4b0f1d6e
|
3 |
size 80792096
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41459700
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49655b56fb7e231874793dab02a813f8c2803a36c5f8dd7596c06af450a116c5
|
3 |
size 41459700
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:059bbe1d12465ee75da00d8c8586ae56dd6c1db13436c63b23bba2dbaf17c845
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e263c1ebbfad3b137dc95d038c7d450a9c91a9eea444a4a6b3bd99ae958ae3a
|
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
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -68,6 +68,21 @@
|
|
68 |
"eval_samples_per_second": 19.283,
|
69 |
"eval_steps_per_second": 2.418,
|
70 |
"step": 36
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
71 |
}
|
72 |
],
|
73 |
"logging_steps": 10,
|
@@ -82,12 +97,12 @@
|
|
82 |
"should_evaluate": false,
|
83 |
"should_log": false,
|
84 |
"should_save": true,
|
85 |
-
"should_training_stop":
|
86 |
},
|
87 |
"attributes": {}
|
88 |
}
|
89 |
},
|
90 |
-
"total_flos": 1.
|
91 |
"train_batch_size": 8,
|
92 |
"trial_name": null,
|
93 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 45,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
68 |
"eval_samples_per_second": 19.283,
|
69 |
"eval_steps_per_second": 2.418,
|
70 |
"step": 36
|
71 |
+
},
|
72 |
+
{
|
73 |
+
"epoch": 0.8888888888888888,
|
74 |
+
"grad_norm": 0.3237155079841614,
|
75 |
+
"learning_rate": 3.299194563372604e-06,
|
76 |
+
"loss": 0.443,
|
77 |
+
"step": 40
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 1.0,
|
81 |
+
"eval_loss": 0.4497634768486023,
|
82 |
+
"eval_runtime": 15.6856,
|
83 |
+
"eval_samples_per_second": 19.317,
|
84 |
+
"eval_steps_per_second": 2.423,
|
85 |
+
"step": 45
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 10,
|
|
|
97 |
"should_evaluate": false,
|
98 |
"should_log": false,
|
99 |
"should_save": true,
|
100 |
+
"should_training_stop": true
|
101 |
},
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
+
"total_flos": 1.254044464667689e+17,
|
106 |
"train_batch_size": 8,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|