Training in progress, step 30, 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 604317736
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe1107b5e1c5799533472846b4a28f41bdeb556eb064473154289f8f040de5f8
|
3 |
size 604317736
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 41119636
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bae10f6b72caa67a65fc0fafce85c6490f05bc32ba8106dc3246c2bc93f25fc7
|
3 |
size 41119636
|
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:b282f04de260040fb20ce8f68d3f23a0f5f33e104a69b7ece5f30022e97e831e
|
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:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
|
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": 6,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -75,6 +75,28 @@
|
|
75 |
"eval_samples_per_second": 13.117,
|
76 |
"eval_steps_per_second": 7.063,
|
77 |
"step": 24
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
}
|
79 |
],
|
80 |
"logging_steps": 5,
|
@@ -89,12 +111,12 @@
|
|
89 |
"should_evaluate": false,
|
90 |
"should_log": false,
|
91 |
"should_save": true,
|
92 |
-
"should_training_stop":
|
93 |
},
|
94 |
"attributes": {}
|
95 |
}
|
96 |
},
|
97 |
-
"total_flos":
|
98 |
"train_batch_size": 2,
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0168067226890756,
|
5 |
"eval_steps": 6,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
75 |
"eval_samples_per_second": 13.117,
|
76 |
"eval_steps_per_second": 7.063,
|
77 |
"step": 24
|
78 |
+
},
|
79 |
+
{
|
80 |
+
"epoch": 0.8403361344537815,
|
81 |
+
"grad_norm": 0.008725620806217194,
|
82 |
+
"learning_rate": 1.4644660940672627e-05,
|
83 |
+
"loss": 0.0006,
|
84 |
+
"step": 25
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 1.0168067226890756,
|
88 |
+
"grad_norm": 0.014241045340895653,
|
89 |
+
"learning_rate": 0.0,
|
90 |
+
"loss": 0.0005,
|
91 |
+
"step": 30
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 1.0168067226890756,
|
95 |
+
"eval_loss": 0.0004074503667652607,
|
96 |
+
"eval_runtime": 0.9569,
|
97 |
+
"eval_samples_per_second": 13.585,
|
98 |
+
"eval_steps_per_second": 7.315,
|
99 |
+
"step": 30
|
100 |
}
|
101 |
],
|
102 |
"logging_steps": 5,
|
|
|
111 |
"should_evaluate": false,
|
112 |
"should_log": false,
|
113 |
"should_save": true,
|
114 |
+
"should_training_stop": true
|
115 |
},
|
116 |
"attributes": {}
|
117 |
}
|
118 |
},
|
119 |
+
"total_flos": 4886202427637760.0,
|
120 |
"train_batch_size": 2,
|
121 |
"trial_name": null,
|
122 |
"trial_params": null
|