Training in progress, step 200, 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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3121a28c875ee9d3bd89e59c8edb358d9121c97be10c375e82067292eab61e8f
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 341314196
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:889aac5d21661d91fef9a7e7c1b67c76df788c8a9e1cde263ad1df1973a962dc
|
3 |
size 341314196
|
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 sha256:1ee24c5ef11a2eb2e3c22812ca1566027ab574a0cd5e8f2917bec0debbde95be
|
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 sha256:6b51679d46ea2c57fcac0772d2e4bf6dbf16bbc7ace56db882f50350a3c0938b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.13016663491725922,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
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,
|
@@ -60,6 +60,21 @@
|
|
60 |
"eval_samples_per_second": 37.615,
|
61 |
"eval_steps_per_second": 1.175,
|
62 |
"step": 150
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
63 |
}
|
64 |
],
|
65 |
"logging_steps": 50,
|
@@ -74,7 +89,7 @@
|
|
74 |
"early_stopping_threshold": 0.0
|
75 |
},
|
76 |
"attributes": {
|
77 |
-
"early_stopping_patience_counter":
|
78 |
}
|
79 |
},
|
80 |
"TrainerControl": {
|
@@ -83,12 +98,12 @@
|
|
83 |
"should_evaluate": false,
|
84 |
"should_log": false,
|
85 |
"should_save": true,
|
86 |
-
"should_training_stop":
|
87 |
},
|
88 |
"attributes": {}
|
89 |
}
|
90 |
},
|
91 |
-
"total_flos": 1.
|
92 |
"train_batch_size": 8,
|
93 |
"trial_name": null,
|
94 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.13016663491725922,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-50",
|
4 |
+
"epoch": 0.07572889057175312,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 200,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
60 |
"eval_samples_per_second": 37.615,
|
61 |
"eval_steps_per_second": 1.175,
|
62 |
"step": 150
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.07572889057175312,
|
66 |
+
"grad_norm": 8.742836952209473,
|
67 |
+
"learning_rate": 0.000203,
|
68 |
+
"loss": 0.1106,
|
69 |
+
"step": 200
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.07572889057175312,
|
73 |
+
"eval_loss": 0.309421181678772,
|
74 |
+
"eval_runtime": 118.1554,
|
75 |
+
"eval_samples_per_second": 37.645,
|
76 |
+
"eval_steps_per_second": 1.176,
|
77 |
+
"step": 200
|
78 |
}
|
79 |
],
|
80 |
"logging_steps": 50,
|
|
|
89 |
"early_stopping_threshold": 0.0
|
90 |
},
|
91 |
"attributes": {
|
92 |
+
"early_stopping_patience_counter": 3
|
93 |
}
|
94 |
},
|
95 |
"TrainerControl": {
|
|
|
98 |
"should_evaluate": false,
|
99 |
"should_log": false,
|
100 |
"should_save": true,
|
101 |
+
"should_training_stop": true
|
102 |
},
|
103 |
"attributes": {}
|
104 |
}
|
105 |
},
|
106 |
+
"total_flos": 1.7159341958234112e+17,
|
107 |
"train_batch_size": 8,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|