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 17640136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a6b90437c93c4a5fb0097221dac61f0ce892ec66da496a9dd9d207aa3b17f934
|
3 |
size 17640136
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9568884
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8595762ce8faee1d64414b7c803d133a12b464eeaf463ecd555bd16f13dda537
|
3 |
size 9568884
|
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:f25fd11b6c56f79f3f87a7138e96ebdc8fa6ba4ac58a0040c86d5934744edf26
|
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,
|
@@ -65,6 +65,35 @@
|
|
65 |
"eval_samples_per_second": 13.82,
|
66 |
"eval_steps_per_second": 6.91,
|
67 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
68 |
}
|
69 |
],
|
70 |
"logging_steps": 1,
|
@@ -84,7 +113,7 @@
|
|
84 |
"attributes": {}
|
85 |
}
|
86 |
},
|
87 |
-
"total_flos":
|
88 |
"train_batch_size": 2,
|
89 |
"trial_name": null,
|
90 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.010657193605683837,
|
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,
|
|
|
65 |
"eval_samples_per_second": 13.82,
|
66 |
"eval_steps_per_second": 6.91,
|
67 |
"step": 6
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.008288928359976317,
|
71 |
+
"grad_norm": 0.8722746968269348,
|
72 |
+
"learning_rate": 0.00014,
|
73 |
+
"loss": 1.8956,
|
74 |
+
"step": 7
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.009473060982830076,
|
78 |
+
"grad_norm": 0.738004207611084,
|
79 |
+
"learning_rate": 0.00016,
|
80 |
+
"loss": 1.8152,
|
81 |
+
"step": 8
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.010657193605683837,
|
85 |
+
"grad_norm": 0.803749144077301,
|
86 |
+
"learning_rate": 0.00018,
|
87 |
+
"loss": 1.7991,
|
88 |
+
"step": 9
|
89 |
+
},
|
90 |
+
{
|
91 |
+
"epoch": 0.010657193605683837,
|
92 |
+
"eval_loss": 1.57768714427948,
|
93 |
+
"eval_runtime": 25.2018,
|
94 |
+
"eval_samples_per_second": 14.126,
|
95 |
+
"eval_steps_per_second": 7.063,
|
96 |
+
"step": 9
|
97 |
}
|
98 |
],
|
99 |
"logging_steps": 1,
|
|
|
113 |
"attributes": {}
|
114 |
}
|
115 |
},
|
116 |
+
"total_flos": 120201521135616.0,
|
117 |
"train_batch_size": 2,
|
118 |
"trial_name": null,
|
119 |
"trial_params": null
|