Training in progress, step 500, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a19f761e30bf830087770b48019218736fd5b299fc345ac2a9e749fe3a0c0f30
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0ace67a63ab5e8241fbb758d52c5ad501256cdd48ca70fd3daad6abc6c98c0c2
|
3 |
size 18902665
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:902bb6277fa9332254dbb09d997080ddfd5d2413b689c8efea4dbf0ed8526ba1
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 2.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -63,13 +63,27 @@
|
|
63 |
"eval_samples_per_second": 30.492,
|
64 |
"eval_steps_per_second": 3.815,
|
65 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 100,
|
69 |
"max_steps": 4116,
|
70 |
"num_train_epochs": 3,
|
71 |
"save_steps": 100,
|
72 |
-
"total_flos": 1.
|
73 |
"trial_name": null,
|
74 |
"trial_params": null
|
75 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.4730148315429688,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-500",
|
4 |
+
"epoch": 0.36429872495446264,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
63 |
"eval_samples_per_second": 30.492,
|
64 |
"eval_steps_per_second": 3.815,
|
65 |
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.36,
|
69 |
+
"learning_rate": 0.0002,
|
70 |
+
"loss": 2.4703,
|
71 |
+
"step": 500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.36,
|
75 |
+
"eval_loss": 2.4730148315429688,
|
76 |
+
"eval_runtime": 205.8153,
|
77 |
+
"eval_samples_per_second": 30.484,
|
78 |
+
"eval_steps_per_second": 3.814,
|
79 |
+
"step": 500
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 100,
|
83 |
"max_steps": 4116,
|
84 |
"num_train_epochs": 3,
|
85 |
"save_steps": 100,
|
86 |
+
"total_flos": 1.469294009229312e+16,
|
87 |
"trial_name": null,
|
88 |
"trial_params": null
|
89 |
}
|