Training in progress, step 250, 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 871457448
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6d72b45850f9bd46a63574674167cc4d248695ea91e7788e884ca837f4409b44
|
3 |
size 871457448
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 443280340
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e734ec999a8df5dbd5c6b3272ede6090669c2d7f00071f3ce7da6d92fff1d69
|
3 |
size 443280340
|
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:dcbfbbb56bd428005f0198327670f2da0570d492d6d43ed1a4647359cdd6d9b6
|
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:df71cb7a0aa557c51d3dc5b89ccfbe7992b19f21537a7247272d18106bf692c1
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.3310236930847168,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 50,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -75,6 +75,21 @@
|
|
75 |
"eval_samples_per_second": 8.454,
|
76 |
"eval_steps_per_second": 0.265,
|
77 |
"step": 200
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
}
|
79 |
],
|
80 |
"logging_steps": 50,
|
@@ -89,7 +104,7 @@
|
|
89 |
"early_stopping_threshold": 0.0
|
90 |
},
|
91 |
"attributes": {
|
92 |
-
"early_stopping_patience_counter":
|
93 |
}
|
94 |
},
|
95 |
"TrainerControl": {
|
@@ -98,12 +113,12 @@
|
|
98 |
"should_evaluate": false,
|
99 |
"should_log": false,
|
100 |
"should_save": true,
|
101 |
-
"should_training_stop":
|
102 |
},
|
103 |
"attributes": {}
|
104 |
}
|
105 |
},
|
106 |
-
"total_flos":
|
107 |
"train_batch_size": 4,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.3310236930847168,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-100",
|
4 |
+
"epoch": 0.013505118439888717,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 250,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
75 |
"eval_samples_per_second": 8.454,
|
76 |
"eval_steps_per_second": 0.265,
|
77 |
"step": 200
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.013505118439888717,
|
81 |
+
"grad_norm": 1.0352643728256226,
|
82 |
+
"learning_rate": 0.000201,
|
83 |
+
"loss": 1.3059,
|
84 |
+
"step": 250
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.013505118439888717,
|
88 |
+
"eval_loss": 1.3383946418762207,
|
89 |
+
"eval_runtime": 1848.8241,
|
90 |
+
"eval_samples_per_second": 8.432,
|
91 |
+
"eval_steps_per_second": 0.264,
|
92 |
+
"step": 250
|
93 |
}
|
94 |
],
|
95 |
"logging_steps": 50,
|
|
|
104 |
"early_stopping_threshold": 0.0
|
105 |
},
|
106 |
"attributes": {
|
107 |
+
"early_stopping_patience_counter": 3
|
108 |
}
|
109 |
},
|
110 |
"TrainerControl": {
|
|
|
113 |
"should_evaluate": false,
|
114 |
"should_log": false,
|
115 |
"should_save": true,
|
116 |
+
"should_training_stop": true
|
117 |
},
|
118 |
"attributes": {}
|
119 |
}
|
120 |
},
|
121 |
+
"total_flos": 2.15902737924096e+17,
|
122 |
"train_batch_size": 4,
|
123 |
"trial_name": null,
|
124 |
"trial_params": null
|