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 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5396e594e5a5c5dc163cb17d0b1928cfb60cc543712b47908542702e451f09f3
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c819f5a72e24f4bf78be7f0aa2ff82a84d3347afc0c8a846ec80ae7a7cb8125
|
3 |
size 43122580
|
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 sha256:09fda1c21f459bad4fee9b6536753c5e4e23ec986d82b550a153673b2a5a397e
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -88,6 +88,27 @@
|
|
88 |
"eval_samples_per_second": 22.037,
|
89 |
"eval_steps_per_second": 11.019,
|
90 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
@@ -102,12 +123,12 @@
|
|
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": 0.0008415312502629785,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
88 |
"eval_samples_per_second": 22.037,
|
89 |
"eval_steps_per_second": 11.019,
|
90 |
"step": 39
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.0006732250002103828,
|
94 |
+
"grad_norm": 1.8676096200942993,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 2.2087,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.0007573781252366807,
|
101 |
+
"grad_norm": 5.003595352172852,
|
102 |
+
"learning_rate": 3.8060233744356633e-06,
|
103 |
+
"loss": 2.5483,
|
104 |
+
"step": 45
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.0008415312502629785,
|
108 |
+
"grad_norm": 3.329429864883423,
|
109 |
+
"learning_rate": 0.0,
|
110 |
+
"loss": 2.2177,
|
111 |
+
"step": 50
|
112 |
}
|
113 |
],
|
114 |
"logging_steps": 5,
|
|
|
123 |
"should_evaluate": false,
|
124 |
"should_log": false,
|
125 |
"should_save": true,
|
126 |
+
"should_training_stop": true
|
127 |
},
|
128 |
"attributes": {}
|
129 |
}
|
130 |
},
|
131 |
+
"total_flos": 9432777665544192.0,
|
132 |
"train_batch_size": 2,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|