tuanna08go
commited on
Training in progress, step 50, 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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2fa21f0ad322c7b0de970bbefca3a6a7c24f4e89343050b6515128cefbd76149
|
3 |
size 80013120
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daa68b5c8f338d475294c1c6935fc032279f00e285fe5ab7eaaaeff9d862499e
|
3 |
size 41119636
|
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 sha256:2d22da228c10047b6aca8bff047d8811b8f2fe710a24bb2653ba24727ffbd82f
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -60,6 +60,36 @@
|
|
60 |
"eval_samples_per_second": 19.649,
|
61 |
"eval_steps_per_second": 2.471,
|
62 |
"step": 30
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
@@ -74,12 +104,12 @@
|
|
74 |
"should_evaluate": false,
|
75 |
"should_log": false,
|
76 |
"should_save": true,
|
77 |
-
"should_training_stop":
|
78 |
},
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
-
"total_flos": 1.
|
83 |
"train_batch_size": 8,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.39980009995002497,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 19.649,
|
61 |
"eval_steps_per_second": 2.471,
|
62 |
"step": 30
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.31984007996002,
|
66 |
+
"grad_norm": 0.9687657952308655,
|
67 |
+
"learning_rate": 1.0332332985438248e-05,
|
68 |
+
"loss": 0.0748,
|
69 |
+
"step": 40
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.31984007996002,
|
73 |
+
"eval_loss": 0.047222234308719635,
|
74 |
+
"eval_runtime": 42.7922,
|
75 |
+
"eval_samples_per_second": 19.7,
|
76 |
+
"eval_steps_per_second": 2.477,
|
77 |
+
"step": 40
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.39980009995002497,
|
81 |
+
"grad_norm": 0.9597257971763611,
|
82 |
+
"learning_rate": 0.0,
|
83 |
+
"loss": 0.0422,
|
84 |
+
"step": 50
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.39980009995002497,
|
88 |
+
"eval_loss": 0.04197036102414131,
|
89 |
+
"eval_runtime": 42.9309,
|
90 |
+
"eval_samples_per_second": 19.636,
|
91 |
+
"eval_steps_per_second": 2.469,
|
92 |
+
"step": 50
|
93 |
}
|
94 |
],
|
95 |
"logging_steps": 10,
|
|
|
104 |
"should_evaluate": false,
|
105 |
"should_log": false,
|
106 |
"should_save": true,
|
107 |
+
"should_training_stop": true
|
108 |
},
|
109 |
"attributes": {}
|
110 |
}
|
111 |
},
|
112 |
+
"total_flos": 1.3599921684873216e+17,
|
113 |
"train_batch_size": 8,
|
114 |
"trial_name": null,
|
115 |
"trial_params": null
|