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 159967880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e93441689c7530633b90837bc696af3d1ecbf91b5f7381b791ba5de6f9f40ab
|
3 |
size 159967880
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 81730196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:03bac986b3637123f2dae2fdf758a1b4262b7b3762dbcb53d68e14a4e1504300
|
3 |
size 81730196
|
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 sha256:722735c1029efd69806c37c127ea2f5cb712ab8435ed91ccc02751954d952b2c
|
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 sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
|
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": 7.07,
|
82 |
"eval_steps_per_second": 3.536,
|
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": 0.0011556935967351656,
|
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": 7.07,
|
82 |
"eval_steps_per_second": 3.536,
|
83 |
"step": 6
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.0010112318971432699,
|
87 |
+
"grad_norm": 25.792160034179688,
|
88 |
+
"learning_rate": 7e-05,
|
89 |
+
"loss": 22.1435,
|
90 |
+
"step": 7
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.0011556935967351656,
|
94 |
+
"grad_norm": 22.48407745361328,
|
95 |
+
"learning_rate": 8e-05,
|
96 |
+
"loss": 17.8129,
|
97 |
+
"step": 8
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.0011556935967351656,
|
101 |
+
"eval_loss": 3.734724998474121,
|
102 |
+
"eval_runtime": 412.2645,
|
103 |
+
"eval_samples_per_second": 7.071,
|
104 |
+
"eval_steps_per_second": 3.537,
|
105 |
+
"step": 8
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 1,
|
|
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
+
"total_flos": 2613858577416192.0,
|
126 |
"train_batch_size": 2,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|