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 402688040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb0176b68ecbe2fce2f307fef7fdf9659ef1d8275644952af4f2a54cfd7b0613
|
3 |
size 402688040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 204773716
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bc11e80bbcdaafae4e0b2316318451a47a40a6fda2c8ecc865b7d50a4d2fc0e5
|
3 |
size 204773716
|
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 sha256:67ff416eca3171d2c9a68ad576ed879be0e6b55eb33ab3781515c26d3067effc
|
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": 14.759,
|
103 |
"eval_steps_per_second": 1.878,
|
104 |
"step": 27
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
105 |
}
|
106 |
],
|
107 |
"logging_steps": 3,
|
@@ -121,7 +150,7 @@
|
|
121 |
"attributes": {}
|
122 |
}
|
123 |
},
|
124 |
-
"total_flos": 2.
|
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": 0.3673469387755102,
|
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": 14.759,
|
103 |
"eval_steps_per_second": 1.878,
|
104 |
"step": 27
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 0.30612244897959184,
|
108 |
+
"grad_norm": 4.704708099365234,
|
109 |
+
"learning_rate": 8.83022221559489e-05,
|
110 |
+
"loss": 6.8546,
|
111 |
+
"step": 30
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.336734693877551,
|
115 |
+
"grad_norm": 4.343167304992676,
|
116 |
+
"learning_rate": 8.473291852294987e-05,
|
117 |
+
"loss": 6.9952,
|
118 |
+
"step": 33
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 0.3673469387755102,
|
122 |
+
"grad_norm": 3.5825247764587402,
|
123 |
+
"learning_rate": 8.07830737662829e-05,
|
124 |
+
"loss": 6.6506,
|
125 |
+
"step": 36
|
126 |
+
},
|
127 |
+
{
|
128 |
+
"epoch": 0.3673469387755102,
|
129 |
+
"eval_loss": 1.6432121992111206,
|
130 |
+
"eval_runtime": 11.181,
|
131 |
+
"eval_samples_per_second": 14.757,
|
132 |
+
"eval_steps_per_second": 1.878,
|
133 |
+
"step": 36
|
134 |
}
|
135 |
],
|
136 |
"logging_steps": 3,
|
|
|
150 |
"attributes": {}
|
151 |
}
|
152 |
},
|
153 |
+
"total_flos": 2.706048037158912e+16,
|
154 |
"train_batch_size": 8,
|
155 |
"trial_name": null,
|
156 |
"trial_params": null
|