Training in progress, step 600, 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:eb3a80fba2780b854dbda92a752a596df2b730b0a37cc218f01e2f4b201b936f
|
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 sha256:97cdbc9747e412d12aab838ba272f6ddcacfefa2275a9d3021af33b42d1bb666
|
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:c5e1dc5f769c4cbaa0ba676908c39cfb7cd49352afc3941d90d0685280366309
|
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 sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
|
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,
|
@@ -77,13 +77,27 @@
|
|
77 |
"eval_samples_per_second": 30.634,
|
78 |
"eval_steps_per_second": 3.833,
|
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.
|
87 |
"trial_name": null,
|
88 |
"trial_params": null
|
89 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 2.4717156887054443,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-600",
|
4 |
+
"epoch": 0.4371584699453552,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
77 |
"eval_samples_per_second": 30.634,
|
78 |
"eval_steps_per_second": 3.833,
|
79 |
"step": 500
|
80 |
+
},
|
81 |
+
{
|
82 |
+
"epoch": 0.44,
|
83 |
+
"learning_rate": 0.0002,
|
84 |
+
"loss": 2.4668,
|
85 |
+
"step": 600
|
86 |
+
},
|
87 |
+
{
|
88 |
+
"epoch": 0.44,
|
89 |
+
"eval_loss": 2.4717156887054443,
|
90 |
+
"eval_runtime": 204.8144,
|
91 |
+
"eval_samples_per_second": 30.633,
|
92 |
+
"eval_steps_per_second": 3.833,
|
93 |
+
"step": 600
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 100,
|
97 |
"max_steps": 4116,
|
98 |
"num_train_epochs": 3,
|
99 |
"save_steps": 100,
|
100 |
+
"total_flos": 1.752346796949504e+16,
|
101 |
"trial_name": null,
|
102 |
"trial_params": null
|
103 |
}
|