phungkhaccuong
commited on
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:
|
3 |
size 1579352
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ab4d2967715b2abbb99dd704677aa886dc455f40d204e9eb81f68ec7bd8ba93
|
3 |
size 1579352
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 857338
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8f0e37f5be8322c665a7f08f9ff455d91bf419009dcdeda02f3ba78a067e6d1
|
3 |
size 857338
|
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:f743fc887c1cdfa63d4df1e8e53f9f2db34a0b31fc622cb4f35850cc91ce315d
|
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: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.
|
5 |
"eval_steps": 10,
|
6 |
-
"global_step":
|
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": 60.0403,
|
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":
|
106 |
},
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
-
"total_flos":
|
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": 0.03073140749846343,
|
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": 60.0403,
|
90 |
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.024585125998770743,
|
94 |
+
"grad_norm": 5726.9609375,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 177.8988,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.024585125998770743,
|
101 |
+
"eval_loss": 32.00729751586914,
|
102 |
+
"eval_runtime": 7.9572,
|
103 |
+
"eval_samples_per_second": 86.086,
|
104 |
+
"eval_steps_per_second": 43.106,
|
105 |
+
"step": 40
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.027658266748617086,
|
109 |
+
"grad_norm": 1328.4888916015625,
|
110 |
+
"learning_rate": 3.8060233744356633e-06,
|
111 |
+
"loss": 125.6105,
|
112 |
+
"step": 45
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.03073140749846343,
|
116 |
+
"grad_norm": 929.8414306640625,
|
117 |
+
"learning_rate": 0.0,
|
118 |
+
"loss": 61.2684,
|
119 |
+
"step": 50
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.03073140749846343,
|
123 |
+
"eval_loss": 31.988927841186523,
|
124 |
+
"eval_runtime": 7.9558,
|
125 |
+
"eval_samples_per_second": 86.101,
|
126 |
+
"eval_steps_per_second": 43.113,
|
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": 92199173750784.0,
|
148 |
"train_batch_size": 2,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|