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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a5a571129871eb60cf2ffe8498568adf6757208650b1005f617806249da880d4
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f406dd35c2b4b13985236b819acbb1c53768c538bd203986aacdc5fcc4d2791
|
3 |
size 37965300
|
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:ff1496a3a9d5a79bd03f8efa281ecf200546f06b22096d14072acfb8e8d2cff0
|
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 sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
|
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": 36.153,
|
74 |
"eval_steps_per_second": 4.845,
|
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": 0.46956521739130436,
|
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": 36.153,
|
74 |
"eval_steps_per_second": 4.845,
|
75 |
"step": 18
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.3652173913043478,
|
79 |
+
"grad_norm": 0.4831562042236328,
|
80 |
+
"learning_rate": 4.817959636416969e-05,
|
81 |
+
"loss": 1.7264,
|
82 |
+
"step": 21
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.41739130434782606,
|
86 |
+
"grad_norm": 0.56829833984375,
|
87 |
+
"learning_rate": 4.707368982147318e-05,
|
88 |
+
"loss": 1.7197,
|
89 |
+
"step": 24
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.46956521739130436,
|
93 |
+
"grad_norm": 0.5362353920936584,
|
94 |
+
"learning_rate": 4.572593931387604e-05,
|
95 |
+
"loss": 1.5556,
|
96 |
+
"step": 27
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.46956521739130436,
|
100 |
+
"eval_loss": 1.2610658407211304,
|
101 |
+
"eval_runtime": 2.6707,
|
102 |
+
"eval_samples_per_second": 36.32,
|
103 |
+
"eval_steps_per_second": 4.868,
|
104 |
+
"step": 27
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 7119165160685568.0,
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|