Training in progress, step 10, 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 sha256:46824cbb33d41feb984b47d79ab48617a092bf6e4876342b666ffd09f1f7809f
|
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 sha256:74e30d3405912663d6f63031e1c218aeb74d9f4e3f44a815cf07c817af377a38
|
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:be12eb81f8b5abab0215725b5211cac3fee2a892944bd06332e4465ced24e47b
|
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:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
|
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": 0.
|
5 |
"eval_steps": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -86,6 +86,21 @@
|
|
86 |
"learning_rate": 9e-05,
|
87 |
"loss": 1.3709,
|
88 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
89 |
}
|
90 |
],
|
91 |
"logging_steps": 1,
|
@@ -100,12 +115,12 @@
|
|
100 |
"should_evaluate": false,
|
101 |
"should_log": false,
|
102 |
"should_save": true,
|
103 |
-
"should_training_stop":
|
104 |
},
|
105 |
"attributes": {}
|
106 |
}
|
107 |
},
|
108 |
-
"total_flos":
|
109 |
"train_batch_size": 1,
|
110 |
"trial_name": null,
|
111 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004253056884635832,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 10,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
86 |
"learning_rate": 9e-05,
|
87 |
"loss": 1.3709,
|
88 |
"step": 9
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.004253056884635832,
|
92 |
+
"grad_norm": 0.8031099438667297,
|
93 |
+
"learning_rate": 0.0001,
|
94 |
+
"loss": 1.6038,
|
95 |
+
"step": 10
|
96 |
+
},
|
97 |
+
{
|
98 |
+
"epoch": 0.004253056884635832,
|
99 |
+
"eval_loss": 1.4016755819320679,
|
100 |
+
"eval_runtime": 381.7384,
|
101 |
+
"eval_samples_per_second": 2.593,
|
102 |
+
"eval_steps_per_second": 2.593,
|
103 |
+
"step": 10
|
104 |
}
|
105 |
],
|
106 |
"logging_steps": 1,
|
|
|
115 |
"should_evaluate": false,
|
116 |
"should_log": false,
|
117 |
"should_save": true,
|
118 |
+
"should_training_stop": true
|
119 |
},
|
120 |
"attributes": {}
|
121 |
}
|
122 |
},
|
123 |
+
"total_flos": 3699128496291840.0,
|
124 |
"train_batch_size": 1,
|
125 |
"trial_name": null,
|
126 |
"trial_params": null
|