Training in progress, step 8, 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 sha256:6782198f26d7090c75ba067cf7a49276545a977660e7e4b002ebf39bf866c4d8
|
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 501028338
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2717f48d2203de257427a8e67c82770c2e438c954b3c679e2267c7b873adc02d
|
3 |
size 501028338
|
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 sha256:9dce83d5e7082d084aabbacccd92be956bcfaead09c5a0116c6978f26e20a645
|
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 sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -81,6 +81,28 @@
|
|
81 |
"eval_samples_per_second": 5.741,
|
82 |
"eval_steps_per_second": 2.87,
|
83 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 1,
|
@@ -100,7 +122,7 @@
|
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.006739679865206402,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 8,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"eval_samples_per_second": 5.741,
|
82 |
"eval_steps_per_second": 2.87,
|
83 |
"step": 6
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.005897219882055603,
|
87 |
+
"grad_norm": 25.561017990112305,
|
88 |
+
"learning_rate": 0.00014,
|
89 |
+
"loss": 12.8493,
|
90 |
+
"step": 7
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.006739679865206402,
|
94 |
+
"grad_norm": 25.24022102355957,
|
95 |
+
"learning_rate": 0.00016,
|
96 |
+
"loss": 9.74,
|
97 |
+
"step": 8
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.006739679865206402,
|
101 |
+
"eval_loss": 1.5246657133102417,
|
102 |
+
"eval_runtime": 87.3812,
|
103 |
+
"eval_samples_per_second": 5.722,
|
104 |
+
"eval_steps_per_second": 2.861,
|
105 |
+
"step": 8
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 1,
|
|
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
+
"total_flos": 5078231757619200.0,
|
126 |
"train_batch_size": 2,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|