Training in progress, step 1600, 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:b5e78b3c3161d8a4a59c39cf3a839c70c0684912d84435ca3bfd819db1caddba
|
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 sha256:2a71d4b14f386c68d6e5a22945169c5b918b3592ef5d69ad27745bd3c1a7c4b8
|
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:c8558918944e58ff478e11841feb02851541b7359c70ce8aa965e60bef436a6c
|
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:fcd2587f362188ac4728d4fa6edf8d2b0b6d72db365d49f7b847d4d79e3da09f
|
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,
|
@@ -98,13 +98,26 @@
|
|
98 |
"eval_samples_per_second": 2.754,
|
99 |
"eval_steps_per_second": 0.176,
|
100 |
"step": 1400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 200,
|
104 |
"max_steps": 2232,
|
105 |
"num_train_epochs": 6,
|
106 |
"save_steps": 200,
|
107 |
-
"total_flos":
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.301075268817204,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 1600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
98 |
"eval_samples_per_second": 2.754,
|
99 |
"eval_steps_per_second": 0.176,
|
100 |
"step": 1400
|
101 |
+
},
|
102 |
+
{
|
103 |
+
"epoch": 4.3,
|
104 |
+
"learning_rate": 0.0002,
|
105 |
+
"loss": 0.0303,
|
106 |
+
"step": 1600
|
107 |
+
},
|
108 |
+
{
|
109 |
+
"epoch": 4.3,
|
110 |
+
"eval_runtime": 113.7892,
|
111 |
+
"eval_samples_per_second": 2.751,
|
112 |
+
"eval_steps_per_second": 0.176,
|
113 |
+
"step": 1600
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 200,
|
117 |
"max_steps": 2232,
|
118 |
"num_train_epochs": 6,
|
119 |
"save_steps": 200,
|
120 |
+
"total_flos": 7.621687279116288e+17,
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|
123 |
}
|