Francesco0101
commited on
Commit
•
e240d9a
1
Parent(s):
bd7d2a7
Training in progress, epoch 4, checkpoint
Browse files
last-checkpoint/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Francesco0101/FRABERT-distilbert-base-uncased",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
"DistilBertForSequenceClassification"
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:377015a2f2d0a1d535fd0614cb6e75174ab1a81ff78e3fadd2e4923bce2c9638
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:502a84f2960672887c9f9567e71498adf67f718978d01edd09c4a50418162bd8
|
3 |
size 535733434
|
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 sha256:1e6f92a8b13bcc897bf3bb961d25b22aa9f5e3b3c3e1dda5ed2738319d087e7d
|
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 sha256:3ee86abee0989df8e1c5461d5ecfc6d42b43c8879a30063d7c1ee114f0c589f6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.6361710372570955,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-250",
|
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,
|
@@ -64,12 +64,31 @@
|
|
64 |
"eval_samples_per_second": 79.297,
|
65 |
"eval_steps_per_second": 9.912,
|
66 |
"step": 375
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
67 |
}
|
68 |
],
|
69 |
"logging_steps": 500,
|
70 |
-
"max_steps":
|
71 |
"num_input_tokens_seen": 0,
|
72 |
-
"num_train_epochs":
|
73 |
"save_steps": 500,
|
74 |
"stateful_callbacks": {
|
75 |
"TrainerControl": {
|
@@ -78,12 +97,12 @@
|
|
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": 16,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.6361710372570955,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-250",
|
4 |
+
"epoch": 4.0,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
64 |
"eval_samples_per_second": 79.297,
|
65 |
"eval_steps_per_second": 9.912,
|
66 |
"step": 375
|
67 |
+
},
|
68 |
+
{
|
69 |
+
"epoch": 4.0,
|
70 |
+
"grad_norm": 27.72207260131836,
|
71 |
+
"learning_rate": 0.0001,
|
72 |
+
"loss": 0.2795,
|
73 |
+
"step": 500
|
74 |
+
},
|
75 |
+
{
|
76 |
+
"epoch": 4.0,
|
77 |
+
"eval_accuracy": 0.611451048951049,
|
78 |
+
"eval_f1": 0.5839059582567918,
|
79 |
+
"eval_loss": 1.4940129518508911,
|
80 |
+
"eval_precision": 0.6264845385709801,
|
81 |
+
"eval_recall": 0.611451048951049,
|
82 |
+
"eval_runtime": 26.4977,
|
83 |
+
"eval_samples_per_second": 86.347,
|
84 |
+
"eval_steps_per_second": 10.793,
|
85 |
+
"step": 500
|
86 |
}
|
87 |
],
|
88 |
"logging_steps": 500,
|
89 |
+
"max_steps": 750,
|
90 |
"num_input_tokens_seen": 0,
|
91 |
+
"num_train_epochs": 6,
|
92 |
"save_steps": 500,
|
93 |
"stateful_callbacks": {
|
94 |
"TrainerControl": {
|
|
|
97 |
"should_evaluate": false,
|
98 |
"should_log": false,
|
99 |
"should_save": true,
|
100 |
+
"should_training_stop": false
|
101 |
},
|
102 |
"attributes": {}
|
103 |
}
|
104 |
},
|
105 |
+
"total_flos": 815516966304000.0,
|
106 |
"train_batch_size": 16,
|
107 |
"trial_name": null,
|
108 |
"trial_params": null
|
last-checkpoint/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc57af78e6fe472d6ff8fcdc48d3f980e6db66111852185ec17fc1a8cd98a77e
|
3 |
size 5176
|