Training in progress, step 9, 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 17640136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:480e7a6df6735ee7d257328cf719bff9b5dfe7641dc0767ecca6547fa6464d71
|
3 |
size 17640136
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9568884
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ce7b4f077c75d3b69f9366b68630b7b69d3f95eb4f403be0d6d8f2d52a391a1
|
3 |
size 9568884
|
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:d0653e8a75fe77c1fcabde2c807162496351ba6a4d66095809e7fef93d73801f
|
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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -65,6 +65,35 @@
|
|
65 |
"eval_samples_per_second": 21.645,
|
66 |
"eval_steps_per_second": 10.839,
|
67 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 1,
|
@@ -84,7 +113,7 @@
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
-
"total_flos":
|
88 |
"train_batch_size": 2,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.005565002318750966,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
65 |
"eval_samples_per_second": 21.645,
|
66 |
"eval_steps_per_second": 10.839,
|
67 |
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.004328335136806307,
|
71 |
+
"grad_norm": 1.5643634796142578,
|
72 |
+
"learning_rate": 0.00014,
|
73 |
+
"loss": 2.3483,
|
74 |
+
"step": 7
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.004946668727778636,
|
78 |
+
"grad_norm": 1.4680047035217285,
|
79 |
+
"learning_rate": 0.00016,
|
80 |
+
"loss": 2.3005,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.005565002318750966,
|
85 |
+
"grad_norm": 2.1011433601379395,
|
86 |
+
"learning_rate": 0.00018,
|
87 |
+
"loss": 2.7788,
|
88 |
+
"step": 9
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.005565002318750966,
|
92 |
+
"eval_loss": 2.6470463275909424,
|
93 |
+
"eval_runtime": 32.9286,
|
94 |
+
"eval_samples_per_second": 20.681,
|
95 |
+
"eval_steps_per_second": 10.356,
|
96 |
+
"step": 9
|
97 |
}
|
98 |
],
|
99 |
"logging_steps": 1,
|
|
|
113 |
"attributes": {}
|
114 |
}
|
115 |
},
|
116 |
+
"total_flos": 82360301518848.0,
|
117 |
"train_batch_size": 2,
|
118 |
"trial_name": null,
|
119 |
"trial_params": null
|