Training in progress, epoch 1
Browse files
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4877660776
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:868fe5fa9fe0eae9eb90012bea6ad6f41c35afdee2e812fcb068f4107c7dc956
|
| 3 |
size 4877660776
|
model-00002-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4932751008
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c116d13c6628f4c3ea37cd0411c41b354a93f1da413019a56cbfe092c24da04e
|
| 3 |
size 4932751008
|
model-00003-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4330865200
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ff7fcc2e25ab4eed7a9ad988927c9e2eb4b50613ddc89fe0bf968a7c03c019b
|
| 3 |
size 4330865200
|
model-00004-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1089994880
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac7af2a95ab8cfcaac78d5eb2c6baf1d175a2f1e4ae303555797f42130d9d1a9
|
| 3 |
size 1089994880
|
trainer_log.jsonl
CHANGED
|
@@ -31,3 +31,34 @@
|
|
| 31 |
{"current_steps": 31, "total_steps": 93, "loss": 0.9318, "lr": 8.501920674356755e-06, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:28:36", "remaining_time": "0:57:13"}
|
| 32 |
{"current_steps": 32, "total_steps": 93, "loss": 1.7235, "lr": 8.364362621864595e-06, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "0:30:30", "remaining_time": "0:58:09"}
|
| 33 |
{"current_steps": 33, "total_steps": 93, "loss": 0.8678, "lr": 8.221985152324385e-06, "epoch": 1.056, "percentage": 35.48, "elapsed_time": "0:31:18", "remaining_time": "0:56:55"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 31 |
{"current_steps": 31, "total_steps": 93, "loss": 0.9318, "lr": 8.501920674356755e-06, "epoch": 0.992, "percentage": 33.33, "elapsed_time": "0:28:36", "remaining_time": "0:57:13"}
|
| 32 |
{"current_steps": 32, "total_steps": 93, "loss": 1.7235, "lr": 8.364362621864595e-06, "epoch": 1.024, "percentage": 34.41, "elapsed_time": "0:30:30", "remaining_time": "0:58:09"}
|
| 33 |
{"current_steps": 33, "total_steps": 93, "loss": 0.8678, "lr": 8.221985152324385e-06, "epoch": 1.056, "percentage": 35.48, "elapsed_time": "0:31:18", "remaining_time": "0:56:55"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 93, "loss": 0.8889, "lr": 8.07499222008977e-06, "epoch": 1.088, "percentage": 36.56, "elapsed_time": "0:32:10", "remaining_time": "0:55:49"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 93, "loss": 0.9157, "lr": 7.923594391120237e-06, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:33:02", "remaining_time": "0:54:44"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 93, "loss": 0.9081, "lr": 7.768008541347423e-06, "epoch": 1.152, "percentage": 38.71, "elapsed_time": "0:33:54", "remaining_time": "0:53:41"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 93, "loss": 0.8875, "lr": 7.608457546002423e-06, "epoch": 1.184, "percentage": 39.78, "elapsed_time": "0:34:48", "remaining_time": "0:52:40"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 93, "loss": 0.8787, "lr": 7.445169960349167e-06, "epoch": 1.216, "percentage": 40.86, "elapsed_time": "0:35:40", "remaining_time": "0:51:37"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 93, "loss": 0.9457, "lr": 7.278379692281209e-06, "epoch": 1.248, "percentage": 41.94, "elapsed_time": "0:36:31", "remaining_time": "0:50:34"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 93, "loss": 0.8881, "lr": 7.10832566725092e-06, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:37:28", "remaining_time": "0:49:39"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 93, "loss": 0.8929, "lr": 6.9352514860110876e-06, "epoch": 1.312, "percentage": 44.09, "elapsed_time": "0:38:19", "remaining_time": "0:48:36"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 93, "loss": 0.7808, "lr": 6.759405075659165e-06, "epoch": 1.3439999999999999, "percentage": 45.16, "elapsed_time": "0:38:57", "remaining_time": "0:47:18"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 93, "loss": 0.8973, "lr": 6.58103833448412e-06, "epoch": 1.376, "percentage": 46.24, "elapsed_time": "0:39:52", "remaining_time": "0:46:21"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 93, "loss": 0.9228, "lr": 6.4004067711245366e-06, "epoch": 1.408, "percentage": 47.31, "elapsed_time": "0:40:56", "remaining_time": "0:45:35"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 93, "loss": 0.857, "lr": 6.2177691385549595e-06, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:41:47", "remaining_time": "0:44:34"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 93, "loss": 0.843, "lr": 6.033387063424765e-06, "epoch": 1.472, "percentage": 49.46, "elapsed_time": "0:42:36", "remaining_time": "0:43:32"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 93, "loss": 1.0347, "lr": 5.8475246712804845e-06, "epoch": 1.504, "percentage": 50.54, "elapsed_time": "0:43:40", "remaining_time": "0:42:44"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 93, "loss": 0.817, "lr": 5.660448208208513e-06, "epoch": 1.536, "percentage": 51.61, "elapsed_time": "0:44:23", "remaining_time": "0:41:37"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 93, "loss": 0.8407, "lr": 5.472425659440157e-06, "epoch": 1.568, "percentage": 52.69, "elapsed_time": "0:45:17", "remaining_time": "0:40:39"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 93, "loss": 0.8921, "lr": 5.2837263654653715e-06, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:46:03", "remaining_time": "0:39:36"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 93, "loss": 0.9579, "lr": 5.094620636205096e-06, "epoch": 1.6320000000000001, "percentage": 54.84, "elapsed_time": "0:46:57", "remaining_time": "0:38:40"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 93, "loss": 0.7933, "lr": 4.905379363794907e-06, "epoch": 1.6640000000000001, "percentage": 55.91, "elapsed_time": "0:47:46", "remaining_time": "0:37:40"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 93, "loss": 0.97, "lr": 4.71627363453463e-06, "epoch": 1.696, "percentage": 56.99, "elapsed_time": "0:48:52", "remaining_time": "0:36:53"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 93, "loss": 0.8357, "lr": 4.527574340559844e-06, "epoch": 1.728, "percentage": 58.06, "elapsed_time": "0:49:51", "remaining_time": "0:36:00"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 93, "loss": 0.828, "lr": 4.33955179179149e-06, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:50:43", "remaining_time": "0:35:02"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 93, "loss": 0.8928, "lr": 4.152475328719517e-06, "epoch": 1.792, "percentage": 60.22, "elapsed_time": "0:51:36", "remaining_time": "0:34:05"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 93, "loss": 0.9052, "lr": 3.966612936575235e-06, "epoch": 1.8239999999999998, "percentage": 61.29, "elapsed_time": "0:52:29", "remaining_time": "0:33:08"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 93, "loss": 0.9586, "lr": 3.782230861445041e-06, "epoch": 1.8559999999999999, "percentage": 62.37, "elapsed_time": "0:53:28", "remaining_time": "0:32:16"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 93, "loss": 0.8434, "lr": 3.5995932288754655e-06, "epoch": 1.888, "percentage": 63.44, "elapsed_time": "0:54:28", "remaining_time": "0:31:23"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 93, "loss": 0.8777, "lr": 3.4189616655158803e-06, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:55:26", "remaining_time": "0:30:29"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 93, "loss": 0.8699, "lr": 3.240594924340835e-06, "epoch": 1.952, "percentage": 65.59, "elapsed_time": "0:56:22", "remaining_time": "0:29:34"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 93, "loss": 0.8321, "lr": 3.0647485139889145e-06, "epoch": 1.984, "percentage": 66.67, "elapsed_time": "0:57:15", "remaining_time": "0:28:37"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 93, "loss": 1.5436, "lr": 2.89167433274908e-06, "epoch": 2.016, "percentage": 67.74, "elapsed_time": "0:59:20", "remaining_time": "0:28:15"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 93, "loss": 0.8582, "lr": 2.721620307718793e-06, "epoch": 2.048, "percentage": 68.82, "elapsed_time": "1:00:15", "remaining_time": "0:27:18"}
|