Training in progress, step 55, 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 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16bdba0deffaaa5942841eb8ee0438b0babcdd83bd9a0e3f6b8c7a3a6013cb05
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 162933396
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4e6d5f4659c4eda23faec23c3ba5e134fc8b2886d50f3b68687ad12bb88c238d
|
3 |
size 162933396
|
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:d0bd80ce846da37de479d9cfede6fa542b5bcefa089007d7fda5147685d0c796
|
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 sha256:8b16062161cca6c6d42c840fa02f9c59f431931479788fa87a822481c8e65827
|
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": 14,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -67,6 +67,13 @@
|
|
67 |
"eval_samples_per_second": 28.168,
|
68 |
"eval_steps_per_second": 14.108,
|
69 |
"step": 42
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 10,
|
@@ -81,12 +88,12 @@
|
|
81 |
"should_evaluate": false,
|
82 |
"should_log": false,
|
83 |
"should_save": true,
|
84 |
-
"should_training_stop":
|
85 |
},
|
86 |
"attributes": {}
|
87 |
}
|
88 |
},
|
89 |
-
"total_flos":
|
90 |
"train_batch_size": 2,
|
91 |
"trial_name": null,
|
92 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.02022058823529412,
|
5 |
"eval_steps": 14,
|
6 |
+
"global_step": 55,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
67 |
"eval_samples_per_second": 28.168,
|
68 |
"eval_steps_per_second": 14.108,
|
69 |
"step": 42
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.01838235294117647,
|
73 |
+
"grad_norm": 0.9920440316200256,
|
74 |
+
"learning_rate": 0.0002,
|
75 |
+
"loss": 4.367,
|
76 |
+
"step": 50
|
77 |
}
|
78 |
],
|
79 |
"logging_steps": 10,
|
|
|
88 |
"should_evaluate": false,
|
89 |
"should_log": false,
|
90 |
"should_save": true,
|
91 |
+
"should_training_stop": true
|
92 |
},
|
93 |
"attributes": {}
|
94 |
}
|
95 |
},
|
96 |
+
"total_flos": 4642848934723584.0,
|
97 |
"train_batch_size": 2,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|