Training in progress, step 11, 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 50365768
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea321bb845a04845d86d73c0a3e90e3d4b49ce8991573c6bbe5fa41d606d5a00
|
3 |
size 50365768
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25859156
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56fb95c98329161045596a2de8da6c9afd81010f6af02377f98d3e6677ffa842
|
3 |
size 25859156
|
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 sha256:378aedea43ec2599fada704f46935cae762ddfbec983a85abad82a85ce32c77a
|
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 sha256:4968f693466c40cb971e90a0117e2a9be84fd1e9f8d5d00ed1cc54675e5c78ec
|
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":
|
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,
|
@@ -102,6 +102,20 @@
|
|
102 |
"eval_samples_per_second": 19.929,
|
103 |
"eval_steps_per_second": 9.964,
|
104 |
"step": 9
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 1,
|
@@ -116,12 +130,12 @@
|
|
116 |
"should_evaluate": false,
|
117 |
"should_log": false,
|
118 |
"should_save": true,
|
119 |
-
"should_training_stop":
|
120 |
},
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos":
|
125 |
"train_batch_size": 2,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0538922155688624,
|
5 |
"eval_steps": 3,
|
6 |
+
"global_step": 11,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 19.929,
|
103 |
"eval_steps_per_second": 9.964,
|
104 |
"step": 9
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.9580838323353293,
|
108 |
+
"grad_norm": 16.325122833251953,
|
109 |
+
"learning_rate": 0.0001,
|
110 |
+
"loss": 3.4328,
|
111 |
+
"step": 10
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 1.0538922155688624,
|
115 |
+
"grad_norm": 14.050758361816406,
|
116 |
+
"learning_rate": 0.0,
|
117 |
+
"loss": 2.343,
|
118 |
+
"step": 11
|
119 |
}
|
120 |
],
|
121 |
"logging_steps": 1,
|
|
|
130 |
"should_evaluate": false,
|
131 |
"should_log": false,
|
132 |
"should_save": true,
|
133 |
+
"should_training_stop": true
|
134 |
},
|
135 |
"attributes": {}
|
136 |
}
|
137 |
},
|
138 |
+
"total_flos": 4027520444792832.0,
|
139 |
"train_batch_size": 2,
|
140 |
"trial_name": null,
|
141 |
"trial_params": null
|