Training in progress, step 600, 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 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f57691dcd7e933b52c5d9a5166dd8caf267ed92a968a040b9f470eb982b7c27
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 21689885
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec84ae944a4cc142d3f93478ccc0616a338cda7251f06ce0a53b35001b957960
|
3 |
size 21689885
|
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 sha256:664719eaa329cdcebc74bdfaf903302609da1e0efb1bc47661be48112583bcc7
|
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 sha256:1200aa065149a5c4bcf6d6753675764c297af325981700a57cc5d1430df50525
|
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": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -72,13 +72,26 @@
|
|
72 |
"eval_samples_per_second": 1.781,
|
73 |
"eval_steps_per_second": 0.223,
|
74 |
"step": 500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 100,
|
78 |
"max_steps": 1686,
|
79 |
"num_train_epochs": 3,
|
80 |
"save_steps": 100,
|
81 |
-
"total_flos":
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0666666666666667,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
72 |
"eval_samples_per_second": 1.781,
|
73 |
"eval_steps_per_second": 0.223,
|
74 |
"step": 500
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.07,
|
78 |
+
"learning_rate": 0.0001,
|
79 |
+
"loss": 0.5993,
|
80 |
+
"step": 600
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.07,
|
84 |
+
"eval_runtime": 1401.9739,
|
85 |
+
"eval_samples_per_second": 1.783,
|
86 |
+
"eval_steps_per_second": 0.223,
|
87 |
+
"step": 600
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 100,
|
91 |
"max_steps": 1686,
|
92 |
"num_train_epochs": 3,
|
93 |
"save_steps": 100,
|
94 |
+
"total_flos": 2.013975621402624e+17,
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|