Training in progress, step 2000, checkpoint
Browse files- last-checkpoint/model-00001-of-00002.safetensors +1 -1
- last-checkpoint/model-00002-of-00002.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +21 -5
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 4992706480
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c898e609fdda35987bd7786597130ae4ba100ee8ac5d1e8f7269c50c2906945e
|
3 |
size 4992706480
|
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 1180663192
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdbc6f78299a35327f6373c05ac2e17a55d61b593b7b3e08619d5d93055d35ed
|
3 |
size 1180663192
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3137197104
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:311180caf4240054a27966b3508f651f78e4ae3a5178c32b25a52159c37606bb
|
3 |
size 3137197104
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fcc12401cba9931be6060cfcc50da713c04670587ca5b721e1de93ce49f13f5
|
3 |
size 15024
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d02506f7376b66f45759751daeb25b57479f2258914b7ecad5907e52b7bcbe74
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9ba726a626db10df92d907838572b5da99270630d5c7e384fe674eedabdc84a9
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1ca629c6979f42e37da46584de0ee8b3d3c674d47a9eac426570f3e48cfb4245
|
3 |
size 15024
|
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 sha256:259805fc640bd5a4985b0004ce4bf3845eca928190e4b1ca10176742a6181381
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 58.04611904264016,
|
3 |
"best_model_checkpoint": "./models/rootflo/fauna-v0.7/checkpoint-1000",
|
4 |
-
"epoch":
|
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,
|
@@ -55,6 +55,22 @@
|
|
55 |
"eval_steps_per_second": 0.005,
|
56 |
"eval_wer": 59.10879607626941,
|
57 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
}
|
59 |
],
|
60 |
"logging_steps": 500,
|
@@ -69,7 +85,7 @@
|
|
69 |
"early_stopping_threshold": 0.5
|
70 |
},
|
71 |
"attributes": {
|
72 |
-
"early_stopping_patience_counter":
|
73 |
}
|
74 |
},
|
75 |
"TrainerControl": {
|
@@ -78,12 +94,12 @@
|
|
78 |
"should_evaluate": false,
|
79 |
"should_log": false,
|
80 |
"should_save": true,
|
81 |
-
"should_training_stop":
|
82 |
},
|
83 |
"attributes": {}
|
84 |
}
|
85 |
},
|
86 |
-
"total_flos":
|
87 |
"train_batch_size": 72,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 58.04611904264016,
|
3 |
"best_model_checkpoint": "./models/rootflo/fauna-v0.7/checkpoint-1000",
|
4 |
+
"epoch": 4.278074866310161,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 2000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
55 |
"eval_steps_per_second": 0.005,
|
56 |
"eval_wer": 59.10879607626941,
|
57 |
"step": 1500
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 4.278074866310161,
|
61 |
+
"grad_norm": 0.32307836413383484,
|
62 |
+
"learning_rate": 9.506789790182363e-07,
|
63 |
+
"loss": 0.0241,
|
64 |
+
"step": 2000
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 4.278074866310161,
|
68 |
+
"eval_loss": 0.055830925703048706,
|
69 |
+
"eval_runtime": 1280.7604,
|
70 |
+
"eval_samples_per_second": 2.03,
|
71 |
+
"eval_steps_per_second": 0.005,
|
72 |
+
"eval_wer": 60.71897040092771,
|
73 |
+
"step": 2000
|
74 |
}
|
75 |
],
|
76 |
"logging_steps": 500,
|
|
|
85 |
"early_stopping_threshold": 0.5
|
86 |
},
|
87 |
"attributes": {
|
88 |
+
"early_stopping_patience_counter": 3
|
89 |
}
|
90 |
},
|
91 |
"TrainerControl": {
|
|
|
94 |
"should_evaluate": false,
|
95 |
"should_log": false,
|
96 |
"should_save": true,
|
97 |
+
"should_training_stop": true
|
98 |
},
|
99 |
"attributes": {}
|
100 |
}
|
101 |
},
|
102 |
+
"total_flos": 2.4458931356758945e+21,
|
103 |
"train_batch_size": 72,
|
104 |
"trial_name": null,
|
105 |
"trial_params": null
|