tuanna08go
commited on
Training in progress, step 39, 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 6804608
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbe3220fcc5f5412981604379deab23869b19a9532fe5fcb7169b99c7b75cff1
|
3 |
size 6804608
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3633530
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b9b5d423b980203d505ca2b1e20b9b5f49cd5d55359155f7072fb14af385807
|
3 |
size 3633530
|
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 sha256:1315906b24c353ffb372fa61e423b6374fc83ec7776f1c3a47263ba225c105f0
|
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 sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
|
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,
|
@@ -45,6 +45,21 @@
|
|
45 |
"eval_samples_per_second": 169.869,
|
46 |
"eval_steps_per_second": 21.246,
|
47 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
@@ -64,7 +79,7 @@
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 8,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0296043267862226,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 39,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 169.869,
|
46 |
"eval_steps_per_second": 21.246,
|
47 |
"step": 20
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.02277255906632508,
|
51 |
+
"grad_norm": 0.3428688645362854,
|
52 |
+
"learning_rate": 3.705904774487396e-05,
|
53 |
+
"loss": 2.6651,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.02277255906632508,
|
58 |
+
"eval_loss": 2.8514456748962402,
|
59 |
+
"eval_runtime": 52.0319,
|
60 |
+
"eval_samples_per_second": 170.569,
|
61 |
+
"eval_steps_per_second": 21.333,
|
62 |
+
"step": 30
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 10,
|
|
|
79 |
"attributes": {}
|
80 |
}
|
81 |
},
|
82 |
+
"total_flos": 2959455736037376.0,
|
83 |
"train_batch_size": 8,
|
84 |
"trial_name": null,
|
85 |
"trial_params": null
|