Training in progress, step 1200, 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 250422888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b57af93b93b031de6e632de092d31a96e7b6a4bc72353591acdc5c6475f51e76
|
3 |
size 250422888
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 126034975
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f046e63e10418a9dac2b2d0622e3354a7d5efbbc4b83e3cf9a3c254b0725a0b9
|
3 |
size 126034975
|
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 sha256:5776b72341fe8dcc62fa355a6219987d7315883c515cce58c8413060cb570a18
|
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 sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 200,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -72,13 +72,26 @@
|
|
72 |
"eval_samples_per_second": 2.752,
|
73 |
"eval_steps_per_second": 0.176,
|
74 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 200,
|
78 |
"max_steps": 2232,
|
79 |
"num_train_epochs": 6,
|
80 |
"save_steps": 200,
|
81 |
-
"total_flos":
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 3.225806451612903,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 1200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
72 |
"eval_samples_per_second": 2.752,
|
73 |
"eval_steps_per_second": 0.176,
|
74 |
"step": 1000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 3.23,
|
78 |
+
"learning_rate": 0.0002,
|
79 |
+
"loss": 0.0396,
|
80 |
+
"step": 1200
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 3.23,
|
84 |
+
"eval_runtime": 113.7472,
|
85 |
+
"eval_samples_per_second": 2.752,
|
86 |
+
"eval_steps_per_second": 0.176,
|
87 |
+
"step": 1200
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 200,
|
91 |
"max_steps": 2232,
|
92 |
"num_train_epochs": 6,
|
93 |
"save_steps": 200,
|
94 |
+
"total_flos": 5.716265459337216e+17,
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|