Training in progress, step 43600, 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 sha256:6b709baef67fd1c70a4136cfde38477fb5a6e9c3240080d0b85506f3def62d8a
|
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 sha256:6ebcabeac1dd27f3a1a58e33c36b54755e9bd9f84e6da954e2b3b4fd9ac082ac
|
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:ec3839fe4830117e92509497bfa377895fc133a13ad1ca94900d3c03f445d3d1
|
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:d5fd9cc74931c14959da906b0f206817b94b75f65dd8dbaa5210a66f6b6816aa
|
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:af49fc0e7d967b4565d316088b696d2da18440fc4e85cafa2dc525a2bc61c22e
|
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": 18.
|
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,
|
@@ -6951,6 +6951,38 @@
|
|
6951 |
"eval_samples_per_second": 24.9,
|
6952 |
"eval_steps_per_second": 3.113,
|
6953 |
"step": 43400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
6954 |
}
|
6955 |
],
|
6956 |
"logging_steps": 100,
|
@@ -6958,7 +6990,7 @@
|
|
6958 |
"num_input_tokens_seen": 0,
|
6959 |
"num_train_epochs": 30,
|
6960 |
"save_steps": 100,
|
6961 |
-
"total_flos": 4.
|
6962 |
"train_batch_size": 8,
|
6963 |
"trial_name": null,
|
6964 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 18.354030730372553,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 43600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
6951 |
"eval_samples_per_second": 24.9,
|
6952 |
"eval_steps_per_second": 3.113,
|
6953 |
"step": 43400
|
6954 |
+
},
|
6955 |
+
{
|
6956 |
+
"epoch": 18.31,
|
6957 |
+
"grad_norm": 1.9974658489227295,
|
6958 |
+
"learning_rate": 1.9626148409893995e-05,
|
6959 |
+
"loss": 0.5745,
|
6960 |
+
"step": 43500
|
6961 |
+
},
|
6962 |
+
{
|
6963 |
+
"epoch": 18.31,
|
6964 |
+
"eval_cer": 0.35752903679949943,
|
6965 |
+
"eval_loss": 3.192854404449463,
|
6966 |
+
"eval_runtime": 397.0976,
|
6967 |
+
"eval_samples_per_second": 23.868,
|
6968 |
+
"eval_steps_per_second": 2.984,
|
6969 |
+
"step": 43500
|
6970 |
+
},
|
6971 |
+
{
|
6972 |
+
"epoch": 18.35,
|
6973 |
+
"grad_norm": 1.8913908004760742,
|
6974 |
+
"learning_rate": 1.9555477031802123e-05,
|
6975 |
+
"loss": 0.5569,
|
6976 |
+
"step": 43600
|
6977 |
+
},
|
6978 |
+
{
|
6979 |
+
"epoch": 18.35,
|
6980 |
+
"eval_cer": 0.35657092018301983,
|
6981 |
+
"eval_loss": 3.314192771911621,
|
6982 |
+
"eval_runtime": 382.2019,
|
6983 |
+
"eval_samples_per_second": 24.798,
|
6984 |
+
"eval_steps_per_second": 3.1,
|
6985 |
+
"step": 43600
|
6986 |
}
|
6987 |
],
|
6988 |
"logging_steps": 100,
|
|
|
6990 |
"num_input_tokens_seen": 0,
|
6991 |
"num_train_epochs": 30,
|
6992 |
"save_steps": 100,
|
6993 |
+
"total_flos": 4.777677491506297e+20,
|
6994 |
"train_batch_size": 8,
|
6995 |
"trial_name": null,
|
6996 |
"trial_params": null
|