avsolatorio
commited on
Commit
•
5843f5e
1
Parent(s):
4685aa0
Training in progress, step 5000, 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 567860028
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:63eb21b9e1cf0bf907284263d4a9338422b7e189e5c909d860a7e71d14a4c2ae
|
3 |
size 567860028
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1135783354
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21a4128037147f3652b538c047a600b904144cfd95ce967abe8a3e0c26a0b50c
|
3 |
size 1135783354
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de88be6318b528394c4873328ca35b0d7d30d60396593a873b67c289e2c805b1
|
3 |
size 14244
|
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 sha256:3c593d69b250076041f56e5e5b5b7926da7e9d2966997964c90a264036cb10f5
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-
|
4 |
-
"epoch":
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -111,6 +111,32 @@
|
|
111 |
"eval_samples_per_second": 568.374,
|
112 |
"eval_steps_per_second": 2.243,
|
113 |
"step": 4000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 500,
|
@@ -139,7 +165,7 @@
|
|
139 |
"attributes": {}
|
140 |
}
|
141 |
},
|
142 |
-
"total_flos":
|
143 |
"train_batch_size": 4,
|
144 |
"trial_name": null,
|
145 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.04508376494050026,
|
3 |
+
"best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-5000",
|
4 |
+
"epoch": 2.465483234714004,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 5000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
111 |
"eval_samples_per_second": 568.374,
|
112 |
"eval_steps_per_second": 2.243,
|
113 |
"step": 4000
|
114 |
+
},
|
115 |
+
{
|
116 |
+
"epoch": 2.2189349112426036,
|
117 |
+
"grad_norm": 0.3222791850566864,
|
118 |
+
"learning_rate": 1.9556213017751483e-05,
|
119 |
+
"loss": 0.0476,
|
120 |
+
"step": 4500
|
121 |
+
},
|
122 |
+
{
|
123 |
+
"epoch": 2.465483234714004,
|
124 |
+
"grad_norm": 0.3560543656349182,
|
125 |
+
"learning_rate": 1.95069033530572e-05,
|
126 |
+
"loss": 0.0466,
|
127 |
+
"step": 5000
|
128 |
+
},
|
129 |
+
{
|
130 |
+
"epoch": 2.465483234714004,
|
131 |
+
"eval_accuracy": 0.9856697421942543,
|
132 |
+
"eval_f1": 0.48531432934588953,
|
133 |
+
"eval_loss": 0.04508376494050026,
|
134 |
+
"eval_precision": 0.7322580645161291,
|
135 |
+
"eval_recall": 0.3629234868671488,
|
136 |
+
"eval_runtime": 14.2501,
|
137 |
+
"eval_samples_per_second": 569.119,
|
138 |
+
"eval_steps_per_second": 2.246,
|
139 |
+
"step": 5000
|
140 |
}
|
141 |
],
|
142 |
"logging_steps": 500,
|
|
|
165 |
"attributes": {}
|
166 |
}
|
167 |
},
|
168 |
+
"total_flos": 112902580652976.0,
|
169 |
"train_batch_size": 4,
|
170 |
"trial_name": null,
|
171 |
"trial_params": null
|