Training in progress, step 50, 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 125040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:762d99ff7c507130ec23054b5cc9ba4a511e4c78d77ad9d2e79aaf30a15b66b0
|
3 |
size 125040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 162868
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:031f102c81ee38b8f81643ede81cbfee79e06d047ac4c2bedd7bec7c96c1bbe6
|
3 |
size 162868
|
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 sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
|
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:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -45,6 +45,35 @@
|
|
45 |
"eval_samples_per_second": 309.106,
|
46 |
"eval_steps_per_second": 154.827,
|
47 |
"step": 26
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
@@ -59,12 +88,12 @@
|
|
59 |
"should_evaluate": false,
|
60 |
"should_log": false,
|
61 |
"should_save": true,
|
62 |
-
"should_training_stop":
|
63 |
},
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 2,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.037292560134253215,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 309.106,
|
46 |
"eval_steps_per_second": 154.827,
|
47 |
"step": 26
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.02237553608055193,
|
51 |
+
"grad_norm": 1.2946125268936157,
|
52 |
+
"learning_rate": 5e-05,
|
53 |
+
"loss": 44.3946,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.02908819690471751,
|
58 |
+
"eval_loss": 11.084484100341797,
|
59 |
+
"eval_runtime": 1.8157,
|
60 |
+
"eval_samples_per_second": 311.172,
|
61 |
+
"eval_steps_per_second": 155.861,
|
62 |
+
"step": 39
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"epoch": 0.029834048107402575,
|
66 |
+
"grad_norm": 1.4587301015853882,
|
67 |
+
"learning_rate": 1.4644660940672627e-05,
|
68 |
+
"loss": 44.3598,
|
69 |
+
"step": 40
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.037292560134253215,
|
73 |
+
"grad_norm": 1.4952447414398193,
|
74 |
+
"learning_rate": 0.0,
|
75 |
+
"loss": 44.3477,
|
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": 954835402752.0,
|
97 |
"train_batch_size": 2,
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|