Francesco0101
commited on
Commit
•
ad353a6
1
Parent(s):
c93dfa4
Training in progress, step 6000, 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 498615900
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb61f4a482e6ffcf6d7b5f16f9bcd3ca9590a5954036318506e89a67e62fb396
|
3 |
size 498615900
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 997351674
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff95c1975c47fefd9ccd0fef1a23b06211a1da604ecd300c56deebc9ed6b57ad
|
3 |
size 997351674
|
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 sha256:9c1b7080d07b1169a02459851d423f5e1ffc70f5f33eacf6a46972b5250a9c5b
|
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 sha256:87a047fc70d34ba9e25294567dfd8e018dbff83f6d11a990d60dd7e409be4fbb
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
4 |
-
"epoch": 0.
|
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,
|
@@ -102,6 +102,25 @@
|
|
102 |
"eval_samples_per_second": 48.123,
|
103 |
"eval_steps_per_second": 6.015,
|
104 |
"step": 5000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1000,
|
@@ -121,7 +140,7 @@
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos": 1.
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7624731472235634,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-6000",
|
4 |
+
"epoch": 0.9395552771688067,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 6000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 48.123,
|
103 |
"eval_steps_per_second": 6.015,
|
104 |
"step": 5000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.9395552771688067,
|
108 |
+
"grad_norm": 16.726686477661133,
|
109 |
+
"learning_rate": 9.131944444444445e-06,
|
110 |
+
"loss": 0.4505,
|
111 |
+
"step": 6000
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.9395552771688067,
|
115 |
+
"eval_accuracy": 0.7670454545454546,
|
116 |
+
"eval_f1": 0.7624731472235634,
|
117 |
+
"eval_loss": 0.7416993379592896,
|
118 |
+
"eval_precision": 0.7669396954578515,
|
119 |
+
"eval_recall": 0.7670454545454546,
|
120 |
+
"eval_runtime": 47.5056,
|
121 |
+
"eval_samples_per_second": 48.163,
|
122 |
+
"eval_steps_per_second": 6.02,
|
123 |
+
"step": 6000
|
124 |
}
|
125 |
],
|
126 |
"logging_steps": 1000,
|
|
|
140 |
"attributes": {}
|
141 |
}
|
142 |
},
|
143 |
+
"total_flos": 1.2293550995184144e+16,
|
144 |
"train_batch_size": 8,
|
145 |
"trial_name": null,
|
146 |
"trial_params": null
|