Training in progress, step 9, 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 sha256:36c03b40d520d2f20ca7f8fe14d233f188908f6f0e132f49120bbf902cbb3a65
|
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 168037178
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5b10d385d17816b4355bce575402b5f8e7861f8f46b30b5b87877d787b9eb49a
|
3 |
size 168037178
|
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:bc6c1736fef1dd6f59b0e0436ac03f5bf52fc685c6304e2891f3922fbeca4f35
|
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 sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
|
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": 3,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -73,6 +73,35 @@
|
|
73 |
"eval_samples_per_second": 13.023,
|
74 |
"eval_steps_per_second": 13.023,
|
75 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 1,
|
@@ -92,7 +121,7 @@
|
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 1,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.024226110363391656,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 9,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"eval_samples_per_second": 13.023,
|
74 |
"eval_steps_per_second": 13.023,
|
75 |
"step": 6
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.018842530282637954,
|
79 |
+
"grad_norm": 1.148888111114502,
|
80 |
+
"learning_rate": 0.00014,
|
81 |
+
"loss": 0.4991,
|
82 |
+
"step": 7
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.021534320323014805,
|
86 |
+
"grad_norm": 1.1360676288604736,
|
87 |
+
"learning_rate": 0.00016,
|
88 |
+
"loss": 0.446,
|
89 |
+
"step": 8
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.024226110363391656,
|
93 |
+
"grad_norm": 1.3324047327041626,
|
94 |
+
"learning_rate": 0.00018,
|
95 |
+
"loss": 0.4577,
|
96 |
+
"step": 9
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.024226110363391656,
|
100 |
+
"eval_loss": 0.40684258937835693,
|
101 |
+
"eval_runtime": 6.0984,
|
102 |
+
"eval_samples_per_second": 12.954,
|
103 |
+
"eval_steps_per_second": 12.954,
|
104 |
+
"step": 9
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
+
"total_flos": 2080759779164160.0,
|
125 |
"train_batch_size": 1,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|