Training in progress, step 31500, checkpoint
Browse files
last-checkpoint/model-00001-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4978139416
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b873a74cd85a7444c0192282714f2d098858bb6f1a3a0918b2e959c631252ae
|
3 |
size 4978139416
|
last-checkpoint/model-00002-of-00002.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3659223436
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b9847471a8fd7c6857174d23c423cd8a42f9fdb4816150a44f8df1411bd9e1c
|
3 |
size 3659223436
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 17241500333
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b25a848c08828cafb3a66f0504b00fb96895d1acc816cd999813ceecd40249ca
|
3 |
size 17241500333
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14567
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c23ac0726bb090165d240f34770fc857f9071db19378988c8da075c49c106078
|
3 |
size 14567
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d8f86a3c26a655dfe015c220ca87fec81bde322514d5aa3c29e06276681b938
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 13.
|
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,
|
@@ -5015,6 +5015,38 @@
|
|
5015 |
"eval_samples_per_second": 25.09,
|
5016 |
"eval_steps_per_second": 3.137,
|
5017 |
"step": 31300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5018 |
}
|
5019 |
],
|
5020 |
"logging_steps": 100,
|
@@ -5022,7 +5054,7 @@
|
|
5022 |
"num_input_tokens_seen": 0,
|
5023 |
"num_train_epochs": 30,
|
5024 |
"save_steps": 100,
|
5025 |
-
"total_flos": 3.
|
5026 |
"train_batch_size": 8,
|
5027 |
"trial_name": null,
|
5028 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 13.260366238686592,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 31500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
5015 |
"eval_samples_per_second": 25.09,
|
5016 |
"eval_steps_per_second": 3.137,
|
5017 |
"step": 31300
|
5018 |
+
},
|
5019 |
+
{
|
5020 |
+
"epoch": 13.22,
|
5021 |
+
"grad_norm": 3.4888200759887695,
|
5022 |
+
"learning_rate": 2.817455830388693e-05,
|
5023 |
+
"loss": 0.9847,
|
5024 |
+
"step": 31400
|
5025 |
+
},
|
5026 |
+
{
|
5027 |
+
"epoch": 13.22,
|
5028 |
+
"eval_cer": 0.39935864846896874,
|
5029 |
+
"eval_loss": 2.095374584197998,
|
5030 |
+
"eval_runtime": 395.2097,
|
5031 |
+
"eval_samples_per_second": 23.982,
|
5032 |
+
"eval_steps_per_second": 2.998,
|
5033 |
+
"step": 31400
|
5034 |
+
},
|
5035 |
+
{
|
5036 |
+
"epoch": 13.26,
|
5037 |
+
"grad_norm": 1.688668966293335,
|
5038 |
+
"learning_rate": 2.8103886925795053e-05,
|
5039 |
+
"loss": 1.0167,
|
5040 |
+
"step": 31500
|
5041 |
+
},
|
5042 |
+
{
|
5043 |
+
"epoch": 13.26,
|
5044 |
+
"eval_cer": 0.40794747956669664,
|
5045 |
+
"eval_loss": 1.7657544612884521,
|
5046 |
+
"eval_runtime": 377.384,
|
5047 |
+
"eval_samples_per_second": 25.115,
|
5048 |
+
"eval_steps_per_second": 3.14,
|
5049 |
+
"step": 31500
|
5050 |
}
|
5051 |
],
|
5052 |
"logging_steps": 100,
|
|
|
5054 |
"num_input_tokens_seen": 0,
|
5055 |
"num_train_epochs": 30,
|
5056 |
"save_steps": 100,
|
5057 |
+
"total_flos": 3.451975086227115e+20,
|
5058 |
"train_batch_size": 8,
|
5059 |
"trial_name": null,
|
5060 |
"trial_params": null
|