Training in progress, step 2000, 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 sha256:0364f611be4de63f5e78aa758b5642a06dea62d2e92e9f9e3f619696f180cff0
|
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 sha256:25260468747256a00a53b16bb99bcdfb50c0007985c3c80b58e5f046545ddf3c
|
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 sha256:05b47a00d7b191e91cb3ddcae9c0ce5aa6a05fcbaa5d45f0ed1adcfa0ae198d3
|
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 sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
|
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,
|
@@ -124,13 +124,26 @@
|
|
124 |
"eval_samples_per_second": 2.749,
|
125 |
"eval_steps_per_second": 0.176,
|
126 |
"step": 1800
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
127 |
}
|
128 |
],
|
129 |
"logging_steps": 200,
|
130 |
"max_steps": 2232,
|
131 |
"num_train_epochs": 6,
|
132 |
"save_steps": 200,
|
133 |
-
"total_flos":
|
134 |
"trial_name": null,
|
135 |
"trial_params": null
|
136 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 5.376344086021505,
|
5 |
"eval_steps": 200,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
124 |
"eval_samples_per_second": 2.749,
|
125 |
"eval_steps_per_second": 0.176,
|
126 |
"step": 1800
|
127 |
+
},
|
128 |
+
{
|
129 |
+
"epoch": 5.38,
|
130 |
+
"learning_rate": 0.0002,
|
131 |
+
"loss": 0.0255,
|
132 |
+
"step": 2000
|
133 |
+
},
|
134 |
+
{
|
135 |
+
"epoch": 5.38,
|
136 |
+
"eval_runtime": 113.7853,
|
137 |
+
"eval_samples_per_second": 2.751,
|
138 |
+
"eval_steps_per_second": 0.176,
|
139 |
+
"step": 2000
|
140 |
}
|
141 |
],
|
142 |
"logging_steps": 200,
|
143 |
"max_steps": 2232,
|
144 |
"num_train_epochs": 6,
|
145 |
"save_steps": 200,
|
146 |
+
"total_flos": 9.52710909889536e+17,
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
149 |
}
|