Training in progress, step 27600, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1262135480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d88057cfed823ea5d6af511d7d549bd0a28fca10b9c1df2d15ec85aa5ad4c72b
|
3 |
size 1262135480
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2490815798
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2b8dd0c49acf269a4fd5ec6489dcf34bc83db6b3298bf03e0ca7ab26fc4e757
|
3 |
size 2490815798
|
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 sha256:3a8de78e722e39a242378f9e619abe10dce82fb669f6420bd3866281f0426c23
|
3 |
+
size 14180
|
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:bc179071d4d6b0c2935c28332a13543209647944abee9bab5ae5846d265bb9bb
|
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": 18.
|
5 |
"eval_steps": 400,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -1095,6 +1095,22 @@
|
|
1095 |
"eval_steps_per_second": 0.838,
|
1096 |
"eval_wer": 0.04644892928670467,
|
1097 |
"step": 27200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1098 |
}
|
1099 |
],
|
1100 |
"logging_steps": 400,
|
@@ -1102,7 +1118,7 @@
|
|
1102 |
"num_input_tokens_seen": 0,
|
1103 |
"num_train_epochs": 30,
|
1104 |
"save_steps": 400,
|
1105 |
-
"total_flos": 8.
|
1106 |
"train_batch_size": 8,
|
1107 |
"trial_name": null,
|
1108 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 18.724559023066487,
|
5 |
"eval_steps": 400,
|
6 |
+
"global_step": 27600,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
1095 |
"eval_steps_per_second": 0.838,
|
1096 |
"eval_wer": 0.04644892928670467,
|
1097 |
"step": 27200
|
1098 |
+
},
|
1099 |
+
{
|
1100 |
+
"epoch": 18.72,
|
1101 |
+
"grad_norm": 0.9943646192550659,
|
1102 |
+
"learning_rate": 0.00011404391582799633,
|
1103 |
+
"loss": 0.052,
|
1104 |
+
"step": 27600
|
1105 |
+
},
|
1106 |
+
{
|
1107 |
+
"epoch": 18.72,
|
1108 |
+
"eval_loss": 0.02736526168882847,
|
1109 |
+
"eval_runtime": 209.8515,
|
1110 |
+
"eval_samples_per_second": 6.667,
|
1111 |
+
"eval_steps_per_second": 0.834,
|
1112 |
+
"eval_wer": 0.04375288861500539,
|
1113 |
+
"step": 27600
|
1114 |
}
|
1115 |
],
|
1116 |
"logging_steps": 400,
|
|
|
1118 |
"num_input_tokens_seen": 0,
|
1119 |
"num_train_epochs": 30,
|
1120 |
"save_steps": 400,
|
1121 |
+
"total_flos": 8.417104754761507e+19,
|
1122 |
"train_batch_size": 8,
|
1123 |
"trial_name": null,
|
1124 |
"trial_params": null
|