Training in progress, step 17700, 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 sha256:2b1498b08a6639bedf117caea6b35ac96fa9b8ee131f6ffaccbc2e8e9177c796
|
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 sha256:384bd802bf21cb1a27b836850e4820fe91126c62756261b9a247d59b2fa7efa8
|
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 sha256:619651e240468638db04ed81e283eda35fc105eb098b17746a777d41118f1405
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:94f5a1b4d910cdecfc94d665d7ca48c0140621b4304151906605cb242fb93fef
|
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:e3b87bb384b796d63345d139b5280a7bcb6e545e4f041e3f5f37032761b459b4
|
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": 7.
|
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,
|
@@ -2807,6 +2807,38 @@
|
|
2807 |
"eval_samples_per_second": 26.271,
|
2808 |
"eval_steps_per_second": 3.285,
|
2809 |
"step": 17500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2810 |
}
|
2811 |
],
|
2812 |
"logging_steps": 100,
|
@@ -2814,7 +2846,7 @@
|
|
2814 |
"num_input_tokens_seen": 0,
|
2815 |
"num_train_epochs": 30,
|
2816 |
"save_steps": 100,
|
2817 |
-
"total_flos": 1.
|
2818 |
"train_batch_size": 8,
|
2819 |
"trial_name": null,
|
2820 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 7.451062934119133,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 17700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
2807 |
"eval_samples_per_second": 26.271,
|
2808 |
"eval_steps_per_second": 3.285,
|
2809 |
"step": 17500
|
2810 |
+
},
|
2811 |
+
{
|
2812 |
+
"epoch": 7.41,
|
2813 |
+
"grad_norm": 1.692319393157959,
|
2814 |
+
"learning_rate": 3.7923674911660775e-05,
|
2815 |
+
"loss": 1.4731,
|
2816 |
+
"step": 17600
|
2817 |
+
},
|
2818 |
+
{
|
2819 |
+
"epoch": 7.41,
|
2820 |
+
"eval_cer": 0.4658597630127879,
|
2821 |
+
"eval_loss": 1.808614730834961,
|
2822 |
+
"eval_runtime": 377.9004,
|
2823 |
+
"eval_samples_per_second": 25.081,
|
2824 |
+
"eval_steps_per_second": 3.136,
|
2825 |
+
"step": 17600
|
2826 |
+
},
|
2827 |
+
{
|
2828 |
+
"epoch": 7.45,
|
2829 |
+
"grad_norm": 2.243326187133789,
|
2830 |
+
"learning_rate": 3.78530035335689e-05,
|
2831 |
+
"loss": 1.3005,
|
2832 |
+
"step": 17700
|
2833 |
+
},
|
2834 |
+
{
|
2835 |
+
"epoch": 7.45,
|
2836 |
+
"eval_cer": 0.45969066520667945,
|
2837 |
+
"eval_loss": 1.8014905452728271,
|
2838 |
+
"eval_runtime": 369.7047,
|
2839 |
+
"eval_samples_per_second": 25.637,
|
2840 |
+
"eval_steps_per_second": 3.205,
|
2841 |
+
"step": 17700
|
2842 |
}
|
2843 |
],
|
2844 |
"logging_steps": 100,
|
|
|
2846 |
"num_input_tokens_seen": 0,
|
2847 |
"num_train_epochs": 30,
|
2848 |
"save_steps": 100,
|
2849 |
+
"total_flos": 1.9400692292566293e+20,
|
2850 |
"train_batch_size": 8,
|
2851 |
"trial_name": null,
|
2852 |
"trial_params": null
|