Training in progress, step 700, 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 9444296
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d3e1f8b0cec562fb4467971ece65fe9b94eb3ea2eab8bb408b42cc3a0990f80
|
3 |
size 9444296
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 18902665
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3af11427625f8329b704add0a16af887bc5b36ef53e0207553c8fcc14b088a3
|
3 |
size 18902665
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b6053380893400c5dade000ca2c1b057384a8b90a1c04643c48140a2351ddf03
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -91,6 +91,20 @@
|
|
91 |
"eval_samples_per_second": 27.675,
|
92 |
"eval_steps_per_second": 3.469,
|
93 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
}
|
95 |
],
|
96 |
"logging_steps": 100,
|
@@ -98,7 +112,7 @@
|
|
98 |
"num_input_tokens_seen": 0,
|
99 |
"num_train_epochs": 3,
|
100 |
"save_steps": 100,
|
101 |
-
"total_flos":
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|
104 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.9750773906707764,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-700",
|
4 |
+
"epoch": 0.9943181818181818,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
91 |
"eval_samples_per_second": 27.675,
|
92 |
"eval_steps_per_second": 3.469,
|
93 |
"step": 600
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.99,
|
97 |
+
"learning_rate": 0.0002,
|
98 |
+
"loss": 2.133,
|
99 |
+
"step": 700
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.99,
|
103 |
+
"eval_loss": 1.9750773906707764,
|
104 |
+
"eval_runtime": 53.9551,
|
105 |
+
"eval_samples_per_second": 27.653,
|
106 |
+
"eval_steps_per_second": 3.466,
|
107 |
+
"step": 700
|
108 |
}
|
109 |
],
|
110 |
"logging_steps": 100,
|
|
|
112 |
"num_input_tokens_seen": 0,
|
113 |
"num_train_epochs": 3,
|
114 |
"save_steps": 100,
|
115 |
+
"total_flos": 2.129173542494208e+16,
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|