Training in progress, step 350, 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 226532664
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4945bc45a931e3a9068880456bee710150e01dab8f210a49958ab0ed862b813
|
3 |
size 226532664
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 115354964
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f3c57d7dc7cef39f097fade4d0b59bd6ae2c69f72dd64c90d59903a2334952d
|
3 |
size 115354964
|
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 sha256:2b052e5df4f86b10c33b2b2118c73a42b5ed720a3341bfff72a68c70091410ef
|
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 sha256:9d122eb52a09fd811e3690e63326c47d9c149dc6af282e256398b51305ba12bd
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.05342056602239609,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
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,
|
@@ -105,6 +105,21 @@
|
|
105 |
"eval_samples_per_second": 59.984,
|
106 |
"eval_steps_per_second": 1.916,
|
107 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 50,
|
@@ -119,7 +134,7 @@
|
|
119 |
"early_stopping_threshold": 0.0
|
120 |
},
|
121 |
"attributes": {
|
122 |
-
"early_stopping_patience_counter":
|
123 |
}
|
124 |
},
|
125 |
"TrainerControl": {
|
@@ -128,12 +143,12 @@
|
|
128 |
"should_evaluate": false,
|
129 |
"should_log": false,
|
130 |
"should_save": true,
|
131 |
-
"should_training_stop":
|
132 |
},
|
133 |
"attributes": {}
|
134 |
}
|
135 |
},
|
136 |
-
"total_flos":
|
137 |
"train_batch_size": 16,
|
138 |
"trial_name": null,
|
139 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.05342056602239609,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-200",
|
4 |
+
"epoch": 0.9655172413793104,
|
5 |
"eval_steps": 50,
|
6 |
+
"global_step": 350,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
105 |
"eval_samples_per_second": 59.984,
|
106 |
"eval_steps_per_second": 1.916,
|
107 |
"step": 300
|
108 |
+
},
|
109 |
+
{
|
110 |
+
"epoch": 0.9655172413793104,
|
111 |
+
"grad_norm": 1.2447991371154785,
|
112 |
+
"learning_rate": 0.000201,
|
113 |
+
"loss": 0.0479,
|
114 |
+
"step": 350
|
115 |
+
},
|
116 |
+
{
|
117 |
+
"epoch": 0.9655172413793104,
|
118 |
+
"eval_loss": 0.0536101870238781,
|
119 |
+
"eval_runtime": 19.9502,
|
120 |
+
"eval_samples_per_second": 61.202,
|
121 |
+
"eval_steps_per_second": 1.955,
|
122 |
+
"step": 350
|
123 |
}
|
124 |
],
|
125 |
"logging_steps": 50,
|
|
|
134 |
"early_stopping_threshold": 0.0
|
135 |
},
|
136 |
"attributes": {
|
137 |
+
"early_stopping_patience_counter": 3
|
138 |
}
|
139 |
},
|
140 |
"TrainerControl": {
|
|
|
143 |
"should_evaluate": false,
|
144 |
"should_log": false,
|
145 |
"should_save": true,
|
146 |
+
"should_training_stop": true
|
147 |
},
|
148 |
"attributes": {}
|
149 |
}
|
150 |
},
|
151 |
+
"total_flos": 1.08829656219648e+17,
|
152 |
"train_batch_size": 16,
|
153 |
"trial_name": null,
|
154 |
"trial_params": null
|