Training in progress, step 9240, 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 13982248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7fe8097e3bf3e1d6200427c42cdec0c2208ac0a54599f9e26cee7d2c0f344fc
|
3 |
size 13982248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 7062522
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3eaf1fbcdbde0059ee1f06c827026e1b557db2f3b07d9f7936261fe98f775bdb
|
3 |
size 7062522
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e15b7ccc90968bcd87b2edf84a9cd99b1e92aa9a9e59ab6ccd2cb1a860be1afb
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63037139d6ccc8c3ea7fa5702f09392e604fb2ed06455649be80ce23f1ff1ce0
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -3234,6 +3234,13 @@
|
|
3234 |
"learning_rate": 1.761003841513674e-05,
|
3235 |
"loss": 3.4684,
|
3236 |
"step": 9220
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3237 |
}
|
3238 |
],
|
3239 |
"logging_steps": 20,
|
@@ -3241,7 +3248,7 @@
|
|
3241 |
"num_input_tokens_seen": 0,
|
3242 |
"num_train_epochs": 2,
|
3243 |
"save_steps": 20,
|
3244 |
-
"total_flos": 2.
|
3245 |
"train_batch_size": 8,
|
3246 |
"trial_name": null,
|
3247 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.7392,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 9240,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
3234 |
"learning_rate": 1.761003841513674e-05,
|
3235 |
"loss": 3.4684,
|
3236 |
"step": 9220
|
3237 |
+
},
|
3238 |
+
{
|
3239 |
+
"epoch": 0.74,
|
3240 |
+
"grad_norm": 32.939849853515625,
|
3241 |
+
"learning_rate": 1.7562184578517207e-05,
|
3242 |
+
"loss": 3.4478,
|
3243 |
+
"step": 9240
|
3244 |
}
|
3245 |
],
|
3246 |
"logging_steps": 20,
|
|
|
3248 |
"num_input_tokens_seen": 0,
|
3249 |
"num_train_epochs": 2,
|
3250 |
"save_steps": 20,
|
3251 |
+
"total_flos": 2.184768798641357e+16,
|
3252 |
"train_batch_size": 8,
|
3253 |
"trial_name": null,
|
3254 |
"trial_params": null
|