Training in progress, step 1000
Browse files- adapter_model.safetensors +1 -1
- trainer_log.jsonl +6 -0
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40036488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e014467c51c26cb45184dad0599e3f916baa434fbd3fc40abf18126d9a30dc49
|
3 |
size 40036488
|
trainer_log.jsonl
CHANGED
@@ -112,3 +112,9 @@
|
|
112 |
{"current_steps": 940, "total_steps": 1500, "loss": 0.8294, "accuracy": 0.949999988079071, "learning_rate": 1.5312110338697427e-06, "epoch": 0.6813445682703633, "percentage": 62.67, "elapsed_time": "2:09:46", "remaining_time": "1:17:18", "throughput": "0.00", "total_tokens": 0}
|
113 |
{"current_steps": 950, "total_steps": 1500, "loss": 0.9113, "accuracy": 0.949999988079071, "learning_rate": 1.4831583923105e-06, "epoch": 0.6885929147413247, "percentage": 63.33, "elapsed_time": "2:11:01", "remaining_time": "1:15:51", "throughput": "0.00", "total_tokens": 0}
|
114 |
{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.1089157834649086, "epoch": 0.6885929147413247, "percentage": 63.33, "elapsed_time": "2:11:31", "remaining_time": "1:16:08", "throughput": "0.00", "total_tokens": 0}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
112 |
{"current_steps": 940, "total_steps": 1500, "loss": 0.8294, "accuracy": 0.949999988079071, "learning_rate": 1.5312110338697427e-06, "epoch": 0.6813445682703633, "percentage": 62.67, "elapsed_time": "2:09:46", "remaining_time": "1:17:18", "throughput": "0.00", "total_tokens": 0}
|
113 |
{"current_steps": 950, "total_steps": 1500, "loss": 0.9113, "accuracy": 0.949999988079071, "learning_rate": 1.4831583923105e-06, "epoch": 0.6885929147413247, "percentage": 63.33, "elapsed_time": "2:11:01", "remaining_time": "1:15:51", "throughput": "0.00", "total_tokens": 0}
|
114 |
{"current_steps": 950, "total_steps": 1500, "eval_loss": 0.1089157834649086, "epoch": 0.6885929147413247, "percentage": 63.33, "elapsed_time": "2:11:31", "remaining_time": "1:16:08", "throughput": "0.00", "total_tokens": 0}
|
115 |
+
{"current_steps": 960, "total_steps": 1500, "loss": 0.8595, "accuracy": 0.9750000238418579, "learning_rate": 1.4355517710873184e-06, "epoch": 0.695841261212286, "percentage": 64.0, "elapsed_time": "2:12:55", "remaining_time": "1:14:46", "throughput": "0.00", "total_tokens": 0}
|
116 |
+
{"current_steps": 970, "total_steps": 1500, "loss": 0.9415, "accuracy": 0.987500011920929, "learning_rate": 1.388412052037682e-06, "epoch": 0.7030896076832472, "percentage": 64.67, "elapsed_time": "2:14:07", "remaining_time": "1:13:16", "throughput": "0.00", "total_tokens": 0}
|
117 |
+
{"current_steps": 980, "total_steps": 1500, "loss": 0.8961, "accuracy": 0.9624999761581421, "learning_rate": 1.3417599122003464e-06, "epoch": 0.7103379541542085, "percentage": 65.33, "elapsed_time": "2:15:18", "remaining_time": "1:11:47", "throughput": "0.00", "total_tokens": 0}
|
118 |
+
{"current_steps": 990, "total_steps": 1500, "loss": 0.7882, "accuracy": 1.0, "learning_rate": 1.2956158147457116e-06, "epoch": 0.7175863006251699, "percentage": 66.0, "elapsed_time": "2:16:37", "remaining_time": "1:10:22", "throughput": "0.00", "total_tokens": 0}
|
119 |
+
{"current_steps": 1000, "total_steps": 1500, "loss": 1.135, "accuracy": 0.949999988079071, "learning_rate": 1.2500000000000007e-06, "epoch": 0.7248346470961312, "percentage": 66.67, "elapsed_time": "2:17:55", "remaining_time": "1:08:57", "throughput": "0.00", "total_tokens": 0}
|
120 |
+
{"current_steps": 1000, "total_steps": 1500, "eval_loss": 0.1021483913064003, "epoch": 0.7248346470961312, "percentage": 66.67, "elapsed_time": "2:18:25", "remaining_time": "1:09:12", "throughput": "0.00", "total_tokens": 0}
|