Training in progress, step 8, 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 12609312
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:591457a7d85945e20c1f6355910df3cd6bbe79e0500209db4be6ed3501be5817
|
3 |
size 12609312
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6614970
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c69463b10f69c9e900e42e3a8ef6e28cce2663c7e57c0fc1f56d4c6120b45d84
|
3 |
size 6614970
|
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 sha256:9647c1d1489472b2eb35ef1640e8fbfd2b703ac05016081caaa618a2891d4551
|
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 sha256:6a3d18e607a27cfab9cec7cfaa7384cdb877a2330c4bcd4e1efcae25be9908cb
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -81,6 +81,28 @@
|
|
81 |
"eval_samples_per_second": 145.68,
|
82 |
"eval_steps_per_second": 78.443,
|
83 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 1,
|
@@ -95,12 +117,12 @@
|
|
95 |
"should_evaluate": false,
|
96 |
"should_log": false,
|
97 |
"should_save": true,
|
98 |
-
"should_training_stop":
|
99 |
},
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0756302521008403,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 8,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"eval_samples_per_second": 145.68,
|
82 |
"eval_steps_per_second": 78.443,
|
83 |
"step": 6
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.9411764705882353,
|
87 |
+
"grad_norm": 44.79998779296875,
|
88 |
+
"learning_rate": 7e-05,
|
89 |
+
"loss": 10.6719,
|
90 |
+
"step": 7
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 1.0756302521008403,
|
94 |
+
"grad_norm": 50.22980880737305,
|
95 |
+
"learning_rate": 8e-05,
|
96 |
+
"loss": 10.1758,
|
97 |
+
"step": 8
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 1.0756302521008403,
|
101 |
+
"eval_loss": 0.6066706776618958,
|
102 |
+
"eval_runtime": 0.0922,
|
103 |
+
"eval_samples_per_second": 140.947,
|
104 |
+
"eval_steps_per_second": 75.894,
|
105 |
+
"step": 8
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 1,
|
|
|
117 |
"should_evaluate": false,
|
118 |
"should_log": false,
|
119 |
"should_save": true,
|
120 |
+
"should_training_stop": true
|
121 |
},
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
+
"total_flos": 280731410497536.0,
|
126 |
"train_batch_size": 2,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|