Training in progress, step 8, 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 22573704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51ab0d44cca828a9fb41b331a69b9f6b0e54d4c0a43a33ca1e363caf747b2b55
|
3 |
size 22573704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 11710970
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcf4bf34b3237b9ee54d16a598137b8a1dad776c723bbebbb7552d7abb0076de
|
3 |
size 11710970
|
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 sha256:5a485799ba454abd38fe3a4a519cfebf2a5c0c59a3a253af42549ee82ed73b6e
|
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 sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
|
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": 2,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -81,6 +81,28 @@
|
|
81 |
"eval_samples_per_second": 40.287,
|
82 |
"eval_steps_per_second": 20.143,
|
83 |
"step": 6
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
84 |
}
|
85 |
],
|
86 |
"logging_steps": 1,
|
@@ -95,12 +117,12 @@
|
|
95 |
"should_evaluate": false,
|
96 |
"should_log": false,
|
97 |
"should_save": true,
|
98 |
-
"should_training_stop":
|
99 |
},
|
100 |
"attributes": {}
|
101 |
}
|
102 |
},
|
103 |
-
"total_flos":
|
104 |
"train_batch_size": 2,
|
105 |
"trial_name": null,
|
106 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0020870018913454642,
|
5 |
"eval_steps": 2,
|
6 |
+
"global_step": 8,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
81 |
"eval_samples_per_second": 40.287,
|
82 |
"eval_steps_per_second": 20.143,
|
83 |
"step": 6
|
84 |
+
},
|
85 |
+
{
|
86 |
+
"epoch": 0.001826126654927281,
|
87 |
+
"grad_norm": 0.7364896535873413,
|
88 |
+
"learning_rate": 0.00014,
|
89 |
+
"loss": 3.8027,
|
90 |
+
"step": 7
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.0020870018913454642,
|
94 |
+
"grad_norm": 0.728878378868103,
|
95 |
+
"learning_rate": 0.00016,
|
96 |
+
"loss": 4.0511,
|
97 |
+
"step": 8
|
98 |
+
},
|
99 |
+
{
|
100 |
+
"epoch": 0.0020870018913454642,
|
101 |
+
"eval_loss": 3.9365174770355225,
|
102 |
+
"eval_runtime": 39.8991,
|
103 |
+
"eval_samples_per_second": 40.452,
|
104 |
+
"eval_steps_per_second": 20.226,
|
105 |
+
"step": 8
|
106 |
}
|
107 |
],
|
108 |
"logging_steps": 1,
|
|
|
117 |
"should_evaluate": false,
|
118 |
"should_log": false,
|
119 |
"should_save": true,
|
120 |
+
"should_training_stop": true
|
121 |
},
|
122 |
"attributes": {}
|
123 |
}
|
124 |
},
|
125 |
+
"total_flos": 378859186814976.0,
|
126 |
"train_batch_size": 2,
|
127 |
"trial_name": null,
|
128 |
"trial_params": null
|