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 25271744
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05126d608f30dd02d326405040d0c248526b13ae55826b9047639f80025c83b7
|
3 |
size 25271744
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 13685516
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf215a39e3088bb4df2b46cbdbc7cb38c58cd7960f2c39cfc1edec5396fa436b
|
3 |
size 13685516
|
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:e0be20b444c694a9fb8dcec3a7b29360980c5ed66d740a18fd0bbb3974911bb5
|
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": 13,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -88,6 +88,27 @@
|
|
88 |
"eval_samples_per_second": 51.977,
|
89 |
"eval_steps_per_second": 25.989,
|
90 |
"step": 39
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
91 |
}
|
92 |
],
|
93 |
"logging_steps": 5,
|
@@ -102,12 +123,12 @@
|
|
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": 0.08771929824561403,
|
5 |
"eval_steps": 13,
|
6 |
+
"global_step": 50,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
88 |
"eval_samples_per_second": 51.977,
|
89 |
"eval_steps_per_second": 25.989,
|
90 |
"step": 39
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.07017543859649122,
|
94 |
+
"grad_norm": 1.5622270107269287,
|
95 |
+
"learning_rate": 1.4644660940672627e-05,
|
96 |
+
"loss": 1.5705,
|
97 |
+
"step": 40
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.07894736842105263,
|
101 |
+
"grad_norm": 1.5886890888214111,
|
102 |
+
"learning_rate": 3.8060233744356633e-06,
|
103 |
+
"loss": 1.5824,
|
104 |
+
"step": 45
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.08771929824561403,
|
108 |
+
"grad_norm": 1.3832000494003296,
|
109 |
+
"learning_rate": 0.0,
|
110 |
+
"loss": 1.6189,
|
111 |
+
"step": 50
|
112 |
}
|
113 |
],
|
114 |
"logging_steps": 5,
|
|
|
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": 1278959891251200.0,
|
132 |
"train_batch_size": 2,
|
133 |
"trial_name": null,
|
134 |
"trial_params": null
|