philip-hightech
commited on
Training in progress, step 4, 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 100059752
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1dde91e11fa6f6d72541f6e9d9e89a08853ac7528fdd25a21bacc78f21868295
|
3 |
size 100059752
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 51244020
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd4a176d6530e04fec245ebc8101c37c84d65f22a3d106cb0362f3ea89085e32
|
3 |
size 51244020
|
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 sha256:07773440cf3b6a4fcd877501a2b20b144b9dc9e52bb1ba47b219b866e853282c
|
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 sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
|
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": 1,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -52,6 +52,21 @@
|
|
52 |
"eval_samples_per_second": 14.738,
|
53 |
"eval_steps_per_second": 7.369,
|
54 |
"step": 3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
55 |
}
|
56 |
],
|
57 |
"logging_steps": 1,
|
@@ -66,12 +81,12 @@
|
|
66 |
"should_evaluate": false,
|
67 |
"should_log": false,
|
68 |
"should_save": true,
|
69 |
-
"should_training_stop":
|
70 |
},
|
71 |
"attributes": {}
|
72 |
}
|
73 |
},
|
74 |
-
"total_flos":
|
75 |
"train_batch_size": 2,
|
76 |
"trial_name": null,
|
77 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1428571428571428,
|
5 |
"eval_steps": 1,
|
6 |
+
"global_step": 4,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
52 |
"eval_samples_per_second": 14.738,
|
53 |
"eval_steps_per_second": 7.369,
|
54 |
"step": 3
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 1.1428571428571428,
|
58 |
+
"grad_norm": 0.9278996586799622,
|
59 |
+
"learning_rate": 8e-05,
|
60 |
+
"loss": 1.7144,
|
61 |
+
"step": 4
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 1.1428571428571428,
|
65 |
+
"eval_loss": 1.0874218940734863,
|
66 |
+
"eval_runtime": 0.1369,
|
67 |
+
"eval_samples_per_second": 14.608,
|
68 |
+
"eval_steps_per_second": 7.304,
|
69 |
+
"step": 4
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 1,
|
|
|
81 |
"should_evaluate": false,
|
82 |
"should_log": false,
|
83 |
"should_save": true,
|
84 |
+
"should_training_stop": true
|
85 |
},
|
86 |
"attributes": {}
|
87 |
}
|
88 |
},
|
89 |
+
"total_flos": 1528873133015040.0,
|
90 |
"train_batch_size": 2,
|
91 |
"trial_name": null,
|
92 |
"trial_params": null
|