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 80013120
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8537c37fd2e2d5e1c5584989502163e4ad318e21c3879095c886d6342b0bed9b
|
3 |
size 80013120
|
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 sha256:0bfccabe4bc2de0a286904047a4c7ae879beb4f3401ad3e7c4fa83f6f0d93885
|
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 sha256:06fc0cfe095850993cdc3f27a66d7ebe34df200989cac63a9753ccea421a02a2
|
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": 10,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -88,6 +88,43 @@
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 1.5325,
|
90 |
"step": 35
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
@@ -102,12 +139,12 @@
|
|
102 |
"should_evaluate": false,
|
103 |
"should_log": false,
|
104 |
"should_save": true,
|
105 |
-
"should_training_stop":
|
106 |
},
|
107 |
"attributes": {}
|
108 |
}
|
109 |
},
|
110 |
-
"total_flos":
|
111 |
"train_batch_size": 2,
|
112 |
"trial_name": null,
|
113 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.08688097306689835,
|
5 |
"eval_steps": 10,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
88 |
"learning_rate": 3.086582838174551e-05,
|
89 |
"loss": 1.5325,
|
90 |
"step": 35
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.06950477845351868,
|
94 |
+
"grad_norm": 0.6465645432472229,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 1.5266,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.06950477845351868,
|
101 |
+
"eval_loss": 1.5528888702392578,
|
102 |
+
"eval_runtime": 16.9993,
|
103 |
+
"eval_samples_per_second": 14.295,
|
104 |
+
"eval_steps_per_second": 7.177,
|
105 |
+
"step": 40
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.07819287576020852,
|
109 |
+
"grad_norm": 0.5526885390281677,
|
110 |
+
"learning_rate": 3.8060233744356633e-06,
|
111 |
+
"loss": 1.5525,
|
112 |
+
"step": 45
|
113 |
+
},
|
114 |
+
{
|
115 |
+
"epoch": 0.08688097306689835,
|
116 |
+
"grad_norm": 0.5791680812835693,
|
117 |
+
"learning_rate": 0.0,
|
118 |
+
"loss": 1.5404,
|
119 |
+
"step": 50
|
120 |
+
},
|
121 |
+
{
|
122 |
+
"epoch": 0.08688097306689835,
|
123 |
+
"eval_loss": 1.5478538274765015,
|
124 |
+
"eval_runtime": 16.5528,
|
125 |
+
"eval_samples_per_second": 14.68,
|
126 |
+
"eval_steps_per_second": 7.37,
|
127 |
+
"step": 50
|
128 |
}
|
129 |
],
|
130 |
"logging_steps": 5,
|
|
|
139 |
"should_evaluate": false,
|
140 |
"should_log": false,
|
141 |
"should_save": true,
|
142 |
+
"should_training_stop": true
|
143 |
},
|
144 |
"attributes": {}
|
145 |
}
|
146 |
},
|
147 |
+
"total_flos": 9598568528609280.0,
|
148 |
"train_batch_size": 2,
|
149 |
"trial_name": null,
|
150 |
"trial_params": null
|