Training in progress, step 1400, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a9b2e951f28dd08f8debe68655d5a92a076ce4df20a103ba442bdf6fbddd2366
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 126034975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cc5de2f6bfb0d174bf93aef3448b6eb30c8bcc41eba2be5ba4067149b21c80f7
|
3 |
size 126034975
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad7fc7071961748864dd6f9ca40a1cddc3830abfaa3ac7402a2db33aa199e317
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
|
3 |
size 627
|
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": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -85,13 +85,26 @@
|
|
85 |
"eval_samples_per_second": 4.0,
|
86 |
"eval_steps_per_second": 0.132,
|
87 |
"step": 1200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 200,
|
91 |
"max_steps": 1535,
|
92 |
"num_train_epochs": 5,
|
93 |
"save_steps": 200,
|
94 |
-
"total_flos": 1.
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.5602605863192185,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 1400,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
85 |
"eval_samples_per_second": 4.0,
|
86 |
"eval_steps_per_second": 0.132,
|
87 |
"step": 1200
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 4.56,
|
91 |
+
"learning_rate": 0.0002,
|
92 |
+
"loss": 0.0703,
|
93 |
+
"step": 1400
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 4.56,
|
97 |
+
"eval_runtime": 128.8001,
|
98 |
+
"eval_samples_per_second": 4.006,
|
99 |
+
"eval_steps_per_second": 0.132,
|
100 |
+
"step": 1400
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 200,
|
104 |
"max_steps": 1535,
|
105 |
"num_train_epochs": 5,
|
106 |
"save_steps": 200,
|
107 |
+
"total_flos": 1.77341374660608e+18,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|