phungkhaccuong
commited on
Training in progress, step 42, 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 17640136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:507d13fd012650c83bfb67d5356355b6abf82dddf4b0ce4116c2ed3c8af85036
|
3 |
size 17640136
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9568884
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd671f86bdbdd26131c590a7e009ab94f6bdd8ac15c10d787dbc4ed724bf138a
|
3 |
size 9568884
|
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 sha256:746c5e4860eb646207dc9434946139a962cceac00e3f3cdafdcbd2c78a113d3e
|
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 sha256:1d29324a0d5877763002861a44f469da99d01dae7b8684c45bb1b74d6def2b49
|
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":
|
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,
|
@@ -81,6 +81,28 @@
|
|
81 |
"learning_rate": 3.086582838174551e-05,
|
82 |
"loss": 0.0013,
|
83 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 5,
|
@@ -95,12 +117,12 @@
|
|
95 |
"should_evaluate": false,
|
96 |
"should_log": false,
|
97 |
"should_save": true,
|
98 |
-
"should_training_stop":
|
99 |
},
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0179640718562875,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 42,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"learning_rate": 3.086582838174551e-05,
|
82 |
"loss": 0.0013,
|
83 |
"step": 30
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.8383233532934131,
|
87 |
+
"grad_norm": 0.023674650117754936,
|
88 |
+
"learning_rate": 1.134947733186315e-05,
|
89 |
+
"loss": 0.0011,
|
90 |
+
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.8622754491017964,
|
94 |
+
"eval_loss": 0.0010952703887596726,
|
95 |
+
"eval_runtime": 0.616,
|
96 |
+
"eval_samples_per_second": 29.221,
|
97 |
+
"eval_steps_per_second": 14.61,
|
98 |
+
"step": 36
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.9580838323353293,
|
102 |
+
"grad_norm": 0.020750371739268303,
|
103 |
+
"learning_rate": 9.607359798384785e-07,
|
104 |
+
"loss": 0.0013,
|
105 |
+
"step": 40
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 5,
|
|
|
117 |
"should_evaluate": false,
|
118 |
"should_log": false,
|
119 |
"should_save": true,
|
120 |
+
"should_training_stop": true
|
121 |
},
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
+
"total_flos": 373960287977472.0,
|
126 |
"train_batch_size": 2,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|