Training in progress, step 120, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 83945296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:883e04ba6493b0210abcdc03ad3c241d372cd53bcdc0dd6f7326767d296a46ff
|
3 |
size 83945296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:157fd7d66e53d2118bc8660679cf1549401109ae5936c1a1cde4af6f64da944e
|
3 |
size 43122580
|
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 sha256:20a506f623132050456b627574cb73c39814e4dbfb60fd7247de788ec41d96ab
|
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:cfbf37e06b1028e14300a03c20e82d87771c1c433a5c2645c3ab0f5750099a9b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.3662590980529785,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 20,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -62,6 +62,14 @@
|
|
62 |
"eval_samples_per_second": 35.732,
|
63 |
"eval_steps_per_second": 1.122,
|
64 |
"step": 100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
}
|
66 |
],
|
67 |
"logging_steps": 100,
|
@@ -76,7 +84,7 @@
|
|
76 |
"early_stopping_threshold": 0.0
|
77 |
},
|
78 |
"attributes": {
|
79 |
-
"early_stopping_patience_counter":
|
80 |
}
|
81 |
},
|
82 |
"TrainerControl": {
|
@@ -85,12 +93,12 @@
|
|
85 |
"should_evaluate": false,
|
86 |
"should_log": false,
|
87 |
"should_save": true,
|
88 |
-
"should_training_stop":
|
89 |
},
|
90 |
"attributes": {}
|
91 |
}
|
92 |
},
|
93 |
-
"total_flos":
|
94 |
"train_batch_size": 4,
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.3662590980529785,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.010303967027305513,
|
5 |
"eval_steps": 20,
|
6 |
+
"global_step": 120,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
62 |
"eval_samples_per_second": 35.732,
|
63 |
"eval_steps_per_second": 1.122,
|
64 |
"step": 100
|
65 |
+
},
|
66 |
+
{
|
67 |
+
"epoch": 0.010303967027305513,
|
68 |
+
"eval_loss": 0.3811986744403839,
|
69 |
+
"eval_runtime": 137.1238,
|
70 |
+
"eval_samples_per_second": 35.763,
|
71 |
+
"eval_steps_per_second": 1.123,
|
72 |
+
"step": 120
|
73 |
}
|
74 |
],
|
75 |
"logging_steps": 100,
|
|
|
84 |
"early_stopping_threshold": 0.0
|
85 |
},
|
86 |
"attributes": {
|
87 |
+
"early_stopping_patience_counter": 1
|
88 |
}
|
89 |
},
|
90 |
"TrainerControl": {
|
|
|
93 |
"should_evaluate": false,
|
94 |
"should_log": false,
|
95 |
"should_save": true,
|
96 |
+
"should_training_stop": true
|
97 |
},
|
98 |
"attributes": {}
|
99 |
}
|
100 |
},
|
101 |
+
"total_flos": 2.1733105345757184e+16,
|
102 |
"train_batch_size": 4,
|
103 |
"trial_name": null,
|
104 |
"trial_params": null
|