Training in progress, step 36, 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 119801528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a3c2762c571c0d472e9f96b1a6ab5ebe60c80236aa9d02e95d879fba2b696d7
|
3 |
size 119801528
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61392180
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67659d4a100d6a74f23dbd65de58b7d899481f715ac585a16dd52546d5ec933a
|
3 |
size 61392180
|
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:c598e29dba8d750f59c50100c9a2dec5ec82c42c8be10e01f2e136148ac10443
|
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:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
|
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": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -102,6 +102,35 @@
|
|
102 |
"eval_samples_per_second": 22.539,
|
103 |
"eval_steps_per_second": 2.818,
|
104 |
"step": 27
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
@@ -121,7 +150,7 @@
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos": 1.
|
125 |
"train_batch_size": 8,
|
126 |
"trial_name": null,
|
127 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.024299696253796826,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 36,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
102 |
"eval_samples_per_second": 22.539,
|
103 |
"eval_steps_per_second": 2.818,
|
104 |
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.020249746878164023,
|
108 |
+
"grad_norm": 0.591693639755249,
|
109 |
+
"learning_rate": 8.83022221559489e-05,
|
110 |
+
"loss": 1.0773,
|
111 |
+
"step": 30
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.022274721565980427,
|
115 |
+
"grad_norm": 0.5439223051071167,
|
116 |
+
"learning_rate": 8.473291852294987e-05,
|
117 |
+
"loss": 1.015,
|
118 |
+
"step": 33
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.024299696253796826,
|
122 |
+
"grad_norm": 0.7373484969139099,
|
123 |
+
"learning_rate": 8.07830737662829e-05,
|
124 |
+
"loss": 1.0284,
|
125 |
+
"step": 36
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.024299696253796826,
|
129 |
+
"eval_loss": 1.0242911577224731,
|
130 |
+
"eval_runtime": 110.7565,
|
131 |
+
"eval_samples_per_second": 22.527,
|
132 |
+
"eval_steps_per_second": 2.817,
|
133 |
+
"step": 36
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
+
"total_flos": 1.9851404340363264e+16,
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|