dimasik1987
commited on
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 100697728
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb84c52d156d9bbc01f039a5bb32cc0e0b7201e943227e5f19a28cb9ec4ba630
|
3 |
size 100697728
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 201541754
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:deeb1397fc34f28836221ba2979078f2070a96006187a69ff32935fded85f5c4
|
3 |
size 201541754
|
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:c8d6c6954105413e254c1dc776a27dd427206924cc5f1ee48db29b4f18851c42
|
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 sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
|
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": 8,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -73,6 +73,42 @@
|
|
73 |
"learning_rate": 0.00013090169943749476,
|
74 |
"loss": 0.0003,
|
75 |
"step": 18
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
76 |
}
|
77 |
],
|
78 |
"logging_steps": 3,
|
@@ -87,12 +123,12 @@
|
|
87 |
"should_evaluate": false,
|
88 |
"should_log": false,
|
89 |
"should_save": true,
|
90 |
-
"should_training_stop":
|
91 |
},
|
92 |
"attributes": {}
|
93 |
}
|
94 |
},
|
95 |
-
"total_flos":
|
96 |
"train_batch_size": 2,
|
97 |
"trial_name": null,
|
98 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.718562874251497,
|
5 |
"eval_steps": 8,
|
6 |
+
"global_step": 30,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
73 |
"learning_rate": 0.00013090169943749476,
|
74 |
"loss": 0.0003,
|
75 |
"step": 18
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.5029940119760479,
|
79 |
+
"grad_norm": 0.006351693067699671,
|
80 |
+
"learning_rate": 8.435655349597689e-05,
|
81 |
+
"loss": 0.0002,
|
82 |
+
"step": 21
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 0.5748502994011976,
|
86 |
+
"grad_norm": 0.009272687137126923,
|
87 |
+
"learning_rate": 4.12214747707527e-05,
|
88 |
+
"loss": 0.0001,
|
89 |
+
"step": 24
|
90 |
+
},
|
91 |
+
{
|
92 |
+
"epoch": 0.5748502994011976,
|
93 |
+
"eval_loss": 3.0196802981663495e-05,
|
94 |
+
"eval_runtime": 1.9296,
|
95 |
+
"eval_samples_per_second": 9.329,
|
96 |
+
"eval_steps_per_second": 4.664,
|
97 |
+
"step": 24
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.6467065868263473,
|
101 |
+
"grad_norm": 0.023558655753731728,
|
102 |
+
"learning_rate": 1.0899347581163221e-05,
|
103 |
+
"loss": 0.0002,
|
104 |
+
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.718562874251497,
|
108 |
+
"grad_norm": 0.005601735319942236,
|
109 |
+
"learning_rate": 0.0,
|
110 |
+
"loss": 0.0001,
|
111 |
+
"step": 30
|
112 |
}
|
113 |
],
|
114 |
"logging_steps": 3,
|
|
|
123 |
"should_evaluate": false,
|
124 |
"should_log": false,
|
125 |
"should_save": true,
|
126 |
+
"should_training_stop": true
|
127 |
},
|
128 |
"attributes": {}
|
129 |
}
|
130 |
},
|
131 |
+
"total_flos": 5526274525102080.0,
|
132 |
"train_batch_size": 2,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|