Training in progress, step 2500
Browse files- model.safetensors +1 -1
- run-10/checkpoint-1000/model.safetensors +1 -1
- run-10/checkpoint-1000/optimizer.pt +1 -1
- run-10/checkpoint-1000/trainer_state.json +20 -20
- run-10/checkpoint-1000/training_args.bin +1 -1
- run-10/checkpoint-1500/model.safetensors +1 -1
- run-10/checkpoint-1500/optimizer.pt +1 -1
- run-10/checkpoint-1500/trainer_state.json +26 -26
- run-10/checkpoint-1500/training_args.bin +1 -1
- run-10/checkpoint-2000/model.safetensors +1 -1
- run-10/checkpoint-2000/optimizer.pt +1 -1
- run-10/checkpoint-2000/trainer_state.json +36 -36
- run-10/checkpoint-2000/training_args.bin +1 -1
- run-10/checkpoint-2500/model.safetensors +1 -1
- run-10/checkpoint-2500/optimizer.pt +1 -1
- run-10/checkpoint-2500/trainer_state.json +42 -42
- run-10/checkpoint-2500/training_args.bin +1 -1
- runs/Jan25_17-40-54_c146da53f02f/events.out.tfevents.1706209036.c146da53f02f.3236.11 +2 -2
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268290900
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eac1cce5e5410e57d71489c02c27b3b2af6e3aa248217249170091e83a0f6878
|
| 3 |
size 268290900
|
run-10/checkpoint-1000/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268290900
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5488b1fd75bc225f0465e85708beee9d03dca3da18beab40db0b6de9131562a
|
| 3 |
size 268290900
|
run-10/checkpoint-1000/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 536643898
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c617ec75c21f636b743e5354494e46c9458f994d4761b7f3e23fc2931d61a5c8
|
| 3 |
size 536643898
|
run-10/checkpoint-1000/trainer_state.json
CHANGED
|
@@ -10,41 +10,41 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_runtime": 5.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_loss": 0.
|
| 30 |
-
"eval_runtime": 5.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 11.
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 0.
|
| 39 |
-
"eval_runtime": 5.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second":
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
-
"loss": 0.
|
| 48 |
"step": 1000
|
| 49 |
}
|
| 50 |
],
|
|
@@ -52,11 +52,11 @@
|
|
| 52 |
"max_steps": 3180,
|
| 53 |
"num_train_epochs": 10,
|
| 54 |
"save_steps": 500,
|
| 55 |
-
"total_flos":
|
| 56 |
"trial_name": null,
|
| 57 |
"trial_params": {
|
| 58 |
-
"alpha": 0.
|
| 59 |
"num_train_epochs": 10,
|
| 60 |
-
"temperature":
|
| 61 |
}
|
| 62 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6035483870967742,
|
| 14 |
+
"eval_loss": 0.2065293788909912,
|
| 15 |
+
"eval_runtime": 5.4973,
|
| 16 |
+
"eval_samples_per_second": 563.918,
|
| 17 |
+
"eval_steps_per_second": 11.824,
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
+
"loss": 0.3298,
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.8422580645161291,
|
| 29 |
+
"eval_loss": 0.09804486483335495,
|
| 30 |
+
"eval_runtime": 5.6345,
|
| 31 |
+
"eval_samples_per_second": 550.179,
|
| 32 |
+
"eval_steps_per_second": 11.536,
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.8964516129032258,
|
| 38 |
+
"eval_loss": 0.06418585777282715,
|
| 39 |
+
"eval_runtime": 5.5011,
|
| 40 |
+
"eval_samples_per_second": 563.528,
|
| 41 |
+
"eval_steps_per_second": 11.816,
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
+
"loss": 0.113,
|
| 48 |
"step": 1000
|
| 49 |
}
|
| 50 |
],
|
|
|
|
| 52 |
"max_steps": 3180,
|
| 53 |
"num_train_epochs": 10,
|
| 54 |
"save_steps": 500,
|
| 55 |
+
"total_flos": 259653090321324.0,
|
| 56 |
"trial_name": null,
|
| 57 |
"trial_params": {
|
| 58 |
+
"alpha": 0.10298372805208489,
|
| 59 |
"num_train_epochs": 10,
|
| 60 |
+
"temperature": 9
|
| 61 |
}
|
| 62 |
}
|
run-10/checkpoint-1000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4877bbd4bf8c3b4c2d0a169a9c195b85ebd557cc55dabfa43eadab9c9abe3fd
|
| 3 |
size 4664
|
run-10/checkpoint-1500/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268290900
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d046f7f0f9f1d524adf8bb4905dc8a86f7aaf45fe0e66d01efad26ccd78eb218
|
| 3 |
size 268290900
|
run-10/checkpoint-1500/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 536643898
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89353e37fe4fbc594afa43fd3e441c6e8c6ad935dc6a149d555cef603eaded63
|
| 3 |
size 536643898
|
run-10/checkpoint-1500/trainer_state.json
CHANGED
|
@@ -10,56 +10,56 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_runtime": 5.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_loss": 0.
|
| 30 |
-
"eval_runtime": 5.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 11.
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 0.
|
| 39 |
-
"eval_runtime": 5.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second":
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
-
"loss": 0.
|
| 48 |
"step": 1000
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
-
"eval_accuracy": 0.
|
| 53 |
-
"eval_loss": 0.
|
| 54 |
-
"eval_runtime": 5.
|
| 55 |
-
"eval_samples_per_second":
|
| 56 |
-
"eval_steps_per_second":
|
| 57 |
"step": 1272
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.72,
|
| 61 |
"learning_rate": 1.0566037735849058e-05,
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 1500
|
| 64 |
}
|
| 65 |
],
|
|
@@ -67,11 +67,11 @@
|
|
| 67 |
"max_steps": 3180,
|
| 68 |
"num_train_epochs": 10,
|
| 69 |
"save_steps": 500,
|
| 70 |
-
"total_flos":
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": {
|
| 73 |
-
"alpha": 0.
|
| 74 |
"num_train_epochs": 10,
|
| 75 |
-
"temperature":
|
| 76 |
}
|
| 77 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6035483870967742,
|
| 14 |
+
"eval_loss": 0.2065293788909912,
|
| 15 |
+
"eval_runtime": 5.4973,
|
| 16 |
+
"eval_samples_per_second": 563.918,
|
| 17 |
+
"eval_steps_per_second": 11.824,
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
+
"loss": 0.3298,
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.8422580645161291,
|
| 29 |
+
"eval_loss": 0.09804486483335495,
|
| 30 |
+
"eval_runtime": 5.6345,
|
| 31 |
+
"eval_samples_per_second": 550.179,
|
| 32 |
+
"eval_steps_per_second": 11.536,
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.8964516129032258,
|
| 38 |
+
"eval_loss": 0.06418585777282715,
|
| 39 |
+
"eval_runtime": 5.5011,
|
| 40 |
+
"eval_samples_per_second": 563.528,
|
| 41 |
+
"eval_steps_per_second": 11.816,
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
+
"loss": 0.113,
|
| 48 |
"step": 1000
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.9045161290322581,
|
| 53 |
+
"eval_loss": 0.04777143895626068,
|
| 54 |
+
"eval_runtime": 5.6659,
|
| 55 |
+
"eval_samples_per_second": 547.133,
|
| 56 |
+
"eval_steps_per_second": 11.472,
|
| 57 |
"step": 1272
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.72,
|
| 61 |
"learning_rate": 1.0566037735849058e-05,
|
| 62 |
+
"loss": 0.0703,
|
| 63 |
"step": 1500
|
| 64 |
}
|
| 65 |
],
|
|
|
|
| 67 |
"max_steps": 3180,
|
| 68 |
"num_train_epochs": 10,
|
| 69 |
"save_steps": 500,
|
| 70 |
+
"total_flos": 389479376069112.0,
|
| 71 |
"trial_name": null,
|
| 72 |
"trial_params": {
|
| 73 |
+
"alpha": 0.10298372805208489,
|
| 74 |
"num_train_epochs": 10,
|
| 75 |
+
"temperature": 9
|
| 76 |
}
|
| 77 |
}
|
run-10/checkpoint-1500/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4877bbd4bf8c3b4c2d0a169a9c195b85ebd557cc55dabfa43eadab9c9abe3fd
|
| 3 |
size 4664
|
run-10/checkpoint-2000/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268290900
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44ddd496d9bff9e72be53b8931dae02308ef56156956545f8ff8644c5b1a740f
|
| 3 |
size 268290900
|
run-10/checkpoint-2000/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 536643898
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98e239fb88bbadd95b3ff46d1d2f73a66c219259e916926dc745b45ffbb9ef9b
|
| 3 |
size 536643898
|
run-10/checkpoint-2000/trainer_state.json
CHANGED
|
@@ -10,80 +10,80 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_runtime": 5.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_loss": 0.
|
| 30 |
-
"eval_runtime": 5.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 11.
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 0.
|
| 39 |
-
"eval_runtime": 5.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second":
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
-
"loss": 0.
|
| 48 |
"step": 1000
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
-
"eval_accuracy": 0.
|
| 53 |
-
"eval_loss": 0.
|
| 54 |
-
"eval_runtime": 5.
|
| 55 |
-
"eval_samples_per_second":
|
| 56 |
-
"eval_steps_per_second":
|
| 57 |
"step": 1272
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.72,
|
| 61 |
"learning_rate": 1.0566037735849058e-05,
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 1500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 5.0,
|
| 67 |
"eval_accuracy": 0.9151612903225806,
|
| 68 |
-
"eval_loss": 0.
|
| 69 |
-
"eval_runtime": 5.
|
| 70 |
-
"eval_samples_per_second":
|
| 71 |
-
"eval_steps_per_second": 11.
|
| 72 |
"step": 1590
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 6.0,
|
| 76 |
-
"eval_accuracy": 0.
|
| 77 |
-
"eval_loss": 0.
|
| 78 |
-
"eval_runtime": 5.
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second":
|
| 81 |
"step": 1908
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.29,
|
| 85 |
"learning_rate": 7.421383647798742e-06,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 2000
|
| 88 |
}
|
| 89 |
],
|
|
@@ -91,11 +91,11 @@
|
|
| 91 |
"max_steps": 3180,
|
| 92 |
"num_train_epochs": 10,
|
| 93 |
"save_steps": 500,
|
| 94 |
-
"total_flos":
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": {
|
| 97 |
-
"alpha": 0.
|
| 98 |
"num_train_epochs": 10,
|
| 99 |
-
"temperature":
|
| 100 |
}
|
| 101 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6035483870967742,
|
| 14 |
+
"eval_loss": 0.2065293788909912,
|
| 15 |
+
"eval_runtime": 5.4973,
|
| 16 |
+
"eval_samples_per_second": 563.918,
|
| 17 |
+
"eval_steps_per_second": 11.824,
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
+
"loss": 0.3298,
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.8422580645161291,
|
| 29 |
+
"eval_loss": 0.09804486483335495,
|
| 30 |
+
"eval_runtime": 5.6345,
|
| 31 |
+
"eval_samples_per_second": 550.179,
|
| 32 |
+
"eval_steps_per_second": 11.536,
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.8964516129032258,
|
| 38 |
+
"eval_loss": 0.06418585777282715,
|
| 39 |
+
"eval_runtime": 5.5011,
|
| 40 |
+
"eval_samples_per_second": 563.528,
|
| 41 |
+
"eval_steps_per_second": 11.816,
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
+
"loss": 0.113,
|
| 48 |
"step": 1000
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.9045161290322581,
|
| 53 |
+
"eval_loss": 0.04777143895626068,
|
| 54 |
+
"eval_runtime": 5.6659,
|
| 55 |
+
"eval_samples_per_second": 547.133,
|
| 56 |
+
"eval_steps_per_second": 11.472,
|
| 57 |
"step": 1272
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.72,
|
| 61 |
"learning_rate": 1.0566037735849058e-05,
|
| 62 |
+
"loss": 0.0703,
|
| 63 |
"step": 1500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 5.0,
|
| 67 |
"eval_accuracy": 0.9151612903225806,
|
| 68 |
+
"eval_loss": 0.03928793966770172,
|
| 69 |
+
"eval_runtime": 5.7374,
|
| 70 |
+
"eval_samples_per_second": 540.317,
|
| 71 |
+
"eval_steps_per_second": 11.329,
|
| 72 |
"step": 1590
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.9193548387096774,
|
| 77 |
+
"eval_loss": 0.034144770354032516,
|
| 78 |
+
"eval_runtime": 5.8666,
|
| 79 |
+
"eval_samples_per_second": 528.418,
|
| 80 |
+
"eval_steps_per_second": 11.08,
|
| 81 |
"step": 1908
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.29,
|
| 85 |
"learning_rate": 7.421383647798742e-06,
|
| 86 |
+
"loss": 0.0547,
|
| 87 |
"step": 2000
|
| 88 |
}
|
| 89 |
],
|
|
|
|
| 91 |
"max_steps": 3180,
|
| 92 |
"num_train_epochs": 10,
|
| 93 |
"save_steps": 500,
|
| 94 |
+
"total_flos": 519927215063004.0,
|
| 95 |
"trial_name": null,
|
| 96 |
"trial_params": {
|
| 97 |
+
"alpha": 0.10298372805208489,
|
| 98 |
"num_train_epochs": 10,
|
| 99 |
+
"temperature": 9
|
| 100 |
}
|
| 101 |
}
|
run-10/checkpoint-2000/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4877bbd4bf8c3b4c2d0a169a9c195b85ebd557cc55dabfa43eadab9c9abe3fd
|
| 3 |
size 4664
|
run-10/checkpoint-2500/model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 268290900
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eac1cce5e5410e57d71489c02c27b3b2af6e3aa248217249170091e83a0f6878
|
| 3 |
size 268290900
|
run-10/checkpoint-2500/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 536643898
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a948e2d7f8b7e0f8a1978c8146934316446d1c6d9823f7ea2c8496e3f39d3af
|
| 3 |
size 536643898
|
run-10/checkpoint-2500/trainer_state.json
CHANGED
|
@@ -10,95 +10,95 @@
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_accuracy": 0.
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_runtime": 5.
|
| 16 |
-
"eval_samples_per_second":
|
| 17 |
-
"eval_steps_per_second":
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
-
"loss": 0.
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
-
"eval_accuracy": 0.
|
| 29 |
-
"eval_loss": 0.
|
| 30 |
-
"eval_runtime": 5.
|
| 31 |
-
"eval_samples_per_second":
|
| 32 |
-
"eval_steps_per_second": 11.
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
-
"eval_accuracy": 0.
|
| 38 |
-
"eval_loss": 0.
|
| 39 |
-
"eval_runtime": 5.
|
| 40 |
-
"eval_samples_per_second":
|
| 41 |
-
"eval_steps_per_second":
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
-
"loss": 0.
|
| 48 |
"step": 1000
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
-
"eval_accuracy": 0.
|
| 53 |
-
"eval_loss": 0.
|
| 54 |
-
"eval_runtime": 5.
|
| 55 |
-
"eval_samples_per_second":
|
| 56 |
-
"eval_steps_per_second":
|
| 57 |
"step": 1272
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.72,
|
| 61 |
"learning_rate": 1.0566037735849058e-05,
|
| 62 |
-
"loss": 0.
|
| 63 |
"step": 1500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 5.0,
|
| 67 |
"eval_accuracy": 0.9151612903225806,
|
| 68 |
-
"eval_loss": 0.
|
| 69 |
-
"eval_runtime": 5.
|
| 70 |
-
"eval_samples_per_second":
|
| 71 |
-
"eval_steps_per_second": 11.
|
| 72 |
"step": 1590
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 6.0,
|
| 76 |
-
"eval_accuracy": 0.
|
| 77 |
-
"eval_loss": 0.
|
| 78 |
-
"eval_runtime": 5.
|
| 79 |
-
"eval_samples_per_second":
|
| 80 |
-
"eval_steps_per_second":
|
| 81 |
"step": 1908
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.29,
|
| 85 |
"learning_rate": 7.421383647798742e-06,
|
| 86 |
-
"loss": 0.
|
| 87 |
"step": 2000
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 7.0,
|
| 91 |
-
"eval_accuracy": 0.
|
| 92 |
-
"eval_loss": 0.
|
| 93 |
-
"eval_runtime": 5.
|
| 94 |
-
"eval_samples_per_second":
|
| 95 |
-
"eval_steps_per_second": 11.
|
| 96 |
"step": 2226
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 7.86,
|
| 100 |
"learning_rate": 4.276729559748428e-06,
|
| 101 |
-
"loss": 0.
|
| 102 |
"step": 2500
|
| 103 |
}
|
| 104 |
],
|
|
@@ -106,11 +106,11 @@
|
|
| 106 |
"max_steps": 3180,
|
| 107 |
"num_train_epochs": 10,
|
| 108 |
"save_steps": 500,
|
| 109 |
-
"total_flos":
|
| 110 |
"trial_name": null,
|
| 111 |
"trial_params": {
|
| 112 |
-
"alpha": 0.
|
| 113 |
"num_train_epochs": 10,
|
| 114 |
-
"temperature":
|
| 115 |
}
|
| 116 |
}
|
|
|
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_accuracy": 0.6035483870967742,
|
| 14 |
+
"eval_loss": 0.2065293788909912,
|
| 15 |
+
"eval_runtime": 5.4973,
|
| 16 |
+
"eval_samples_per_second": 563.918,
|
| 17 |
+
"eval_steps_per_second": 11.824,
|
| 18 |
"step": 318
|
| 19 |
},
|
| 20 |
{
|
| 21 |
"epoch": 1.57,
|
| 22 |
"learning_rate": 1.685534591194969e-05,
|
| 23 |
+
"loss": 0.3298,
|
| 24 |
"step": 500
|
| 25 |
},
|
| 26 |
{
|
| 27 |
"epoch": 2.0,
|
| 28 |
+
"eval_accuracy": 0.8422580645161291,
|
| 29 |
+
"eval_loss": 0.09804486483335495,
|
| 30 |
+
"eval_runtime": 5.6345,
|
| 31 |
+
"eval_samples_per_second": 550.179,
|
| 32 |
+
"eval_steps_per_second": 11.536,
|
| 33 |
"step": 636
|
| 34 |
},
|
| 35 |
{
|
| 36 |
"epoch": 3.0,
|
| 37 |
+
"eval_accuracy": 0.8964516129032258,
|
| 38 |
+
"eval_loss": 0.06418585777282715,
|
| 39 |
+
"eval_runtime": 5.5011,
|
| 40 |
+
"eval_samples_per_second": 563.528,
|
| 41 |
+
"eval_steps_per_second": 11.816,
|
| 42 |
"step": 954
|
| 43 |
},
|
| 44 |
{
|
| 45 |
"epoch": 3.14,
|
| 46 |
"learning_rate": 1.371069182389937e-05,
|
| 47 |
+
"loss": 0.113,
|
| 48 |
"step": 1000
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_accuracy": 0.9045161290322581,
|
| 53 |
+
"eval_loss": 0.04777143895626068,
|
| 54 |
+
"eval_runtime": 5.6659,
|
| 55 |
+
"eval_samples_per_second": 547.133,
|
| 56 |
+
"eval_steps_per_second": 11.472,
|
| 57 |
"step": 1272
|
| 58 |
},
|
| 59 |
{
|
| 60 |
"epoch": 4.72,
|
| 61 |
"learning_rate": 1.0566037735849058e-05,
|
| 62 |
+
"loss": 0.0703,
|
| 63 |
"step": 1500
|
| 64 |
},
|
| 65 |
{
|
| 66 |
"epoch": 5.0,
|
| 67 |
"eval_accuracy": 0.9151612903225806,
|
| 68 |
+
"eval_loss": 0.03928793966770172,
|
| 69 |
+
"eval_runtime": 5.7374,
|
| 70 |
+
"eval_samples_per_second": 540.317,
|
| 71 |
+
"eval_steps_per_second": 11.329,
|
| 72 |
"step": 1590
|
| 73 |
},
|
| 74 |
{
|
| 75 |
"epoch": 6.0,
|
| 76 |
+
"eval_accuracy": 0.9193548387096774,
|
| 77 |
+
"eval_loss": 0.034144770354032516,
|
| 78 |
+
"eval_runtime": 5.8666,
|
| 79 |
+
"eval_samples_per_second": 528.418,
|
| 80 |
+
"eval_steps_per_second": 11.08,
|
| 81 |
"step": 1908
|
| 82 |
},
|
| 83 |
{
|
| 84 |
"epoch": 6.29,
|
| 85 |
"learning_rate": 7.421383647798742e-06,
|
| 86 |
+
"loss": 0.0547,
|
| 87 |
"step": 2000
|
| 88 |
},
|
| 89 |
{
|
| 90 |
"epoch": 7.0,
|
| 91 |
+
"eval_accuracy": 0.9216129032258065,
|
| 92 |
+
"eval_loss": 0.03088981844484806,
|
| 93 |
+
"eval_runtime": 5.6168,
|
| 94 |
+
"eval_samples_per_second": 551.918,
|
| 95 |
+
"eval_steps_per_second": 11.572,
|
| 96 |
"step": 2226
|
| 97 |
},
|
| 98 |
{
|
| 99 |
"epoch": 7.86,
|
| 100 |
"learning_rate": 4.276729559748428e-06,
|
| 101 |
+
"loss": 0.0471,
|
| 102 |
"step": 2500
|
| 103 |
}
|
| 104 |
],
|
|
|
|
| 106 |
"max_steps": 3180,
|
| 107 |
"num_train_epochs": 10,
|
| 108 |
"save_steps": 500,
|
| 109 |
+
"total_flos": 649636246191744.0,
|
| 110 |
"trial_name": null,
|
| 111 |
"trial_params": {
|
| 112 |
+
"alpha": 0.10298372805208489,
|
| 113 |
"num_train_epochs": 10,
|
| 114 |
+
"temperature": 9
|
| 115 |
}
|
| 116 |
}
|
run-10/checkpoint-2500/training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4877bbd4bf8c3b4c2d0a169a9c195b85ebd557cc55dabfa43eadab9c9abe3fd
|
| 3 |
size 4664
|
runs/Jan25_17-40-54_c146da53f02f/events.out.tfevents.1706209036.c146da53f02f.3236.11
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0f3cea5f9b1c5f185363e75ce60869c1b39ff69e09529fa18dc3434494e04700
|
| 3 |
+
size 15534
|