Training in progress, step 1100, checkpoint
Browse files
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2e6267cdf54ef8159468c1a3bed02ee80b2d475e78769c6e6e8bc54ef44bbf5
|
3 |
size 160285149
|
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 sha256:3ea8e7768d6355b0ca58baf95157a79cbb61186a0365142518a48fd468e8760a
|
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:b4bf4b575f9656653a74de8d5ce98da75ce68ed173f5d239c8569bfe6db90e7d
|
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": 1.
|
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,
|
@@ -137,13 +137,26 @@
|
|
137 |
"eval_samples_per_second": 1.905,
|
138 |
"eval_steps_per_second": 0.239,
|
139 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
140 |
}
|
141 |
],
|
142 |
"logging_steps": 100,
|
143 |
"max_steps": 2025,
|
144 |
"num_train_epochs": 3,
|
145 |
"save_steps": 100,
|
146 |
-
"total_flos": 2.
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
149 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.6296296296296298,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1100,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
137 |
"eval_samples_per_second": 1.905,
|
138 |
"eval_steps_per_second": 0.239,
|
139 |
"step": 1000
|
140 |
+
},
|
141 |
+
{
|
142 |
+
"epoch": 1.63,
|
143 |
+
"learning_rate": 0.0,
|
144 |
+
"loss": 8.3661,
|
145 |
+
"step": 1100
|
146 |
+
},
|
147 |
+
{
|
148 |
+
"epoch": 1.63,
|
149 |
+
"eval_runtime": 788.2154,
|
150 |
+
"eval_samples_per_second": 1.903,
|
151 |
+
"eval_steps_per_second": 0.239,
|
152 |
+
"step": 1100
|
153 |
}
|
154 |
],
|
155 |
"logging_steps": 100,
|
156 |
"max_steps": 2025,
|
157 |
"num_train_epochs": 3,
|
158 |
"save_steps": 100,
|
159 |
+
"total_flos": 2.29064438710272e+17,
|
160 |
"trial_name": null,
|
161 |
"trial_params": null
|
162 |
}
|