Training in progress, step 350, 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 335604696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8479e96980dfe84bd67a52f617ea8ea83c29af8221c12ca40c9a794d529df52f
|
| 3 |
size 335604696
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 170920532
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83334d49a28bae3229c9e1c601348ed0a17ce397e392fcde2188878e194722d2
|
| 3 |
size 170920532
|
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 sha256:7b8102c4fa5704c0cf29aa353c5d198a149efa45b3b748cc0a18c699c2efe093
|
| 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 sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
|
| 3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
{
|
| 2 |
-
"best_metric": 2.
|
| 3 |
-
"best_model_checkpoint": "miner_id_24/checkpoint-
|
| 4 |
-
"epoch": 0.
|
| 5 |
"eval_steps": 50,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
@@ -112,6 +112,21 @@
|
|
| 112 |
"eval_samples_per_second": 8.953,
|
| 113 |
"eval_steps_per_second": 4.479,
|
| 114 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 115 |
}
|
| 116 |
],
|
| 117 |
"logging_steps": 40,
|
|
@@ -140,7 +155,7 @@
|
|
| 140 |
"attributes": {}
|
| 141 |
}
|
| 142 |
},
|
| 143 |
-
"total_flos": 2.
|
| 144 |
"train_batch_size": 2,
|
| 145 |
"trial_name": null,
|
| 146 |
"trial_params": null
|
|
|
|
| 1 |
{
|
| 2 |
+
"best_metric": 2.524484872817993,
|
| 3 |
+
"best_model_checkpoint": "miner_id_24/checkpoint-350",
|
| 4 |
+
"epoch": 0.15929002161793152,
|
| 5 |
"eval_steps": 50,
|
| 6 |
+
"global_step": 350,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 112 |
"eval_samples_per_second": 8.953,
|
| 113 |
"eval_steps_per_second": 4.479,
|
| 114 |
"step": 300
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.14563659119353736,
|
| 118 |
+
"grad_norm": 0.6200185418128967,
|
| 119 |
+
"learning_rate": 1.4644660940672627e-05,
|
| 120 |
+
"loss": 2.5298,
|
| 121 |
+
"step": 320
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.15929002161793152,
|
| 125 |
+
"eval_loss": 2.524484872817993,
|
| 126 |
+
"eval_runtime": 206.8563,
|
| 127 |
+
"eval_samples_per_second": 8.948,
|
| 128 |
+
"eval_steps_per_second": 4.477,
|
| 129 |
+
"step": 350
|
| 130 |
}
|
| 131 |
],
|
| 132 |
"logging_steps": 40,
|
|
|
|
| 155 |
"attributes": {}
|
| 156 |
}
|
| 157 |
},
|
| 158 |
+
"total_flos": 2.4571719268171776e+17,
|
| 159 |
"train_batch_size": 2,
|
| 160 |
"trial_name": null,
|
| 161 |
"trial_params": null
|