Training in progress, step 27, 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 50503544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de6a1de0d6419f97a132b387798ebb2154fe6a5d5ebec5f49f0f087a9412e62e
|
3 |
size 50503544
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25986148
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db769c1d57803d4b074aa776a31373c94f47c24a5bcdb625016574f2db422a7a
|
3 |
size 25986148
|
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 sha256:0b0f69563309dc958f9c21e989482a40608995709ae1979e8f697efcafe269a6
|
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:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
|
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,
|
@@ -73,6 +73,35 @@
|
|
73 |
"eval_samples_per_second": 27.872,
|
74 |
"eval_steps_per_second": 3.484,
|
75 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 3,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 8,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.009457921008844907,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 27,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"eval_samples_per_second": 27.872,
|
74 |
"eval_steps_per_second": 3.484,
|
75 |
"step": 18
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.0073561607846571505,
|
79 |
+
"grad_norm": 0.23280549049377441,
|
80 |
+
"learning_rate": 9.635919272833938e-05,
|
81 |
+
"loss": 1.1913,
|
82 |
+
"step": 21
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.008407040896751029,
|
86 |
+
"grad_norm": 0.2081017643213272,
|
87 |
+
"learning_rate": 9.414737964294636e-05,
|
88 |
+
"loss": 1.1646,
|
89 |
+
"step": 24
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.009457921008844907,
|
93 |
+
"grad_norm": 0.22857177257537842,
|
94 |
+
"learning_rate": 9.145187862775209e-05,
|
95 |
+
"loss": 1.1644,
|
96 |
+
"step": 27
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.009457921008844907,
|
100 |
+
"eval_loss": 1.1528327465057373,
|
101 |
+
"eval_runtime": 172.5822,
|
102 |
+
"eval_samples_per_second": 27.859,
|
103 |
+
"eval_steps_per_second": 3.482,
|
104 |
+
"step": 27
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 1.1117182737973248e+16,
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|