Training in progress, step 1000, 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 19669752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:85adec37d0b8e80f571f5278ccab2b951f799e19227a742c3d7dd4beaea179de
|
3 |
size 19669752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 39356997
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e88b9298af46626afc01c55c243dd89291d822fe80a14e4c497608a096c0788
|
3 |
size 39356997
|
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 sha256:17812da58821a9378ebc24a70d2a909be55cf6346ab49b39cc73bc804822d6bd
|
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 sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
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,
|
@@ -133,6 +133,20 @@
|
|
133 |
"eval_samples_per_second": 2.453,
|
134 |
"eval_steps_per_second": 0.308,
|
135 |
"step": 900
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
136 |
}
|
137 |
],
|
138 |
"logging_steps": 100,
|
@@ -140,7 +154,7 @@
|
|
140 |
"num_input_tokens_seen": 0,
|
141 |
"num_train_epochs": 5,
|
142 |
"save_steps": 100,
|
143 |
-
"total_flos": 2.
|
144 |
"trial_name": null,
|
145 |
"trial_params": null
|
146 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9895688891410828,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-1000",
|
4 |
+
"epoch": 1.3333333333333333,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 1000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
133 |
"eval_samples_per_second": 2.453,
|
134 |
"eval_steps_per_second": 0.308,
|
135 |
"step": 900
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 1.33,
|
139 |
+
"learning_rate": 0.0002,
|
140 |
+
"loss": 0.8133,
|
141 |
+
"step": 1000
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 1.33,
|
145 |
+
"eval_loss": 0.9895688891410828,
|
146 |
+
"eval_runtime": 782.3169,
|
147 |
+
"eval_samples_per_second": 2.467,
|
148 |
+
"eval_steps_per_second": 0.309,
|
149 |
+
"step": 1000
|
150 |
}
|
151 |
],
|
152 |
"logging_steps": 100,
|
|
|
154 |
"num_input_tokens_seen": 0,
|
155 |
"num_train_epochs": 5,
|
156 |
"save_steps": 100,
|
157 |
+
"total_flos": 2.5910459214483456e+17,
|
158 |
"trial_name": null,
|
159 |
"trial_params": null
|
160 |
}
|