Training in progress, epoch 0
Browse files- all_results.json +13 -0
- eval_results.json +8 -0
- model.safetensors +1 -1
- runs/Dec03_16-03-14_279d23e2c555/events.out.tfevents.1733242874.279d23e2c555.8837.1 +3 -0
- runs/Dec03_16-39-17_279d23e2c555/events.out.tfevents.1733243967.279d23e2c555.8837.2 +3 -0
- train_results.json +8 -0
- trainer_state.json +701 -0
- training_args.bin +1 -1
all_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26086956521739,
|
| 3 |
+
"eval_accuracy": 0.7391304347826086,
|
| 4 |
+
"eval_loss": 0.7807860374450684,
|
| 5 |
+
"eval_runtime": 0.8852,
|
| 6 |
+
"eval_samples_per_second": 51.968,
|
| 7 |
+
"eval_steps_per_second": 3.389,
|
| 8 |
+
"total_flos": 8.989085534729011e+17,
|
| 9 |
+
"train_loss": 0.6443484219637784,
|
| 10 |
+
"train_runtime": 903.3964,
|
| 11 |
+
"train_samples_per_second": 31.968,
|
| 12 |
+
"train_steps_per_second": 0.487
|
| 13 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26086956521739,
|
| 3 |
+
"eval_accuracy": 0.7391304347826086,
|
| 4 |
+
"eval_loss": 0.7807860374450684,
|
| 5 |
+
"eval_runtime": 0.8852,
|
| 6 |
+
"eval_samples_per_second": 51.968,
|
| 7 |
+
"eval_steps_per_second": 3.389
|
| 8 |
+
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 110356296
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a98a63ff4092b6aa5b0aa67da73f2990564bdc60ce0f01cd3253139468da1782
|
| 3 |
size 110356296
|
runs/Dec03_16-03-14_279d23e2c555/events.out.tfevents.1733242874.279d23e2c555.8837.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db2eea2312e8a12f37836e96797585144bec98efb983be637988a30269309016
|
| 3 |
+
size 411
|
runs/Dec03_16-39-17_279d23e2c555/events.out.tfevents.1733243967.279d23e2c555.8837.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:264ca2469e8ff79e2ed8cac9d3231f753ef21404dea3df73faab87d0fcac5bdf
|
| 3 |
+
size 6192
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 38.26086956521739,
|
| 3 |
+
"total_flos": 8.989085534729011e+17,
|
| 4 |
+
"train_loss": 0.6443484219637784,
|
| 5 |
+
"train_runtime": 903.3964,
|
| 6 |
+
"train_samples_per_second": 31.968,
|
| 7 |
+
"train_steps_per_second": 0.487
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,701 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.7391304347826086,
|
| 3 |
+
"best_model_checkpoint": "swinv2-tiny-patch4-window8-256-DMAE-da-colab2/checkpoint-299",
|
| 4 |
+
"epoch": 38.26086956521739,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 440,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.8695652173913043,
|
| 13 |
+
"grad_norm": 22.453941345214844,
|
| 14 |
+
"learning_rate": 1.465909090909091e-05,
|
| 15 |
+
"loss": 1.3473,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.9565217391304348,
|
| 20 |
+
"eval_accuracy": 0.5217391304347826,
|
| 21 |
+
"eval_loss": 1.379814863204956,
|
| 22 |
+
"eval_runtime": 0.7803,
|
| 23 |
+
"eval_samples_per_second": 58.95,
|
| 24 |
+
"eval_steps_per_second": 3.845,
|
| 25 |
+
"step": 11
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 1.7391304347826086,
|
| 29 |
+
"grad_norm": 20.24134635925293,
|
| 30 |
+
"learning_rate": 1.4318181818181818e-05,
|
| 31 |
+
"loss": 1.2638,
|
| 32 |
+
"step": 20
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 2.0,
|
| 36 |
+
"eval_accuracy": 0.45652173913043476,
|
| 37 |
+
"eval_loss": 1.2928154468536377,
|
| 38 |
+
"eval_runtime": 0.7744,
|
| 39 |
+
"eval_samples_per_second": 59.399,
|
| 40 |
+
"eval_steps_per_second": 3.874,
|
| 41 |
+
"step": 23
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 2.608695652173913,
|
| 45 |
+
"grad_norm": 26.064878463745117,
|
| 46 |
+
"learning_rate": 1.3977272727272727e-05,
|
| 47 |
+
"loss": 1.1776,
|
| 48 |
+
"step": 30
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 2.9565217391304346,
|
| 52 |
+
"eval_accuracy": 0.5,
|
| 53 |
+
"eval_loss": 1.2134073972702026,
|
| 54 |
+
"eval_runtime": 1.0372,
|
| 55 |
+
"eval_samples_per_second": 44.351,
|
| 56 |
+
"eval_steps_per_second": 2.892,
|
| 57 |
+
"step": 34
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.4782608695652173,
|
| 61 |
+
"grad_norm": 32.85703659057617,
|
| 62 |
+
"learning_rate": 1.3636363636363637e-05,
|
| 63 |
+
"loss": 1.1146,
|
| 64 |
+
"step": 40
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 4.0,
|
| 68 |
+
"eval_accuracy": 0.5869565217391305,
|
| 69 |
+
"eval_loss": 1.1366691589355469,
|
| 70 |
+
"eval_runtime": 0.7945,
|
| 71 |
+
"eval_samples_per_second": 57.896,
|
| 72 |
+
"eval_steps_per_second": 3.776,
|
| 73 |
+
"step": 46
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 4.3478260869565215,
|
| 77 |
+
"grad_norm": 40.311309814453125,
|
| 78 |
+
"learning_rate": 1.3295454545454546e-05,
|
| 79 |
+
"loss": 1.0618,
|
| 80 |
+
"step": 50
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 4.956521739130435,
|
| 84 |
+
"eval_accuracy": 0.6304347826086957,
|
| 85 |
+
"eval_loss": 1.0770869255065918,
|
| 86 |
+
"eval_runtime": 0.7919,
|
| 87 |
+
"eval_samples_per_second": 58.089,
|
| 88 |
+
"eval_steps_per_second": 3.788,
|
| 89 |
+
"step": 57
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 5.217391304347826,
|
| 93 |
+
"grad_norm": 38.01955795288086,
|
| 94 |
+
"learning_rate": 1.2954545454545455e-05,
|
| 95 |
+
"loss": 0.9909,
|
| 96 |
+
"step": 60
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 6.0,
|
| 100 |
+
"eval_accuracy": 0.5652173913043478,
|
| 101 |
+
"eval_loss": 1.0039759874343872,
|
| 102 |
+
"eval_runtime": 0.7765,
|
| 103 |
+
"eval_samples_per_second": 59.237,
|
| 104 |
+
"eval_steps_per_second": 3.863,
|
| 105 |
+
"step": 69
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 6.086956521739131,
|
| 109 |
+
"grad_norm": 33.40464401245117,
|
| 110 |
+
"learning_rate": 1.2613636363636365e-05,
|
| 111 |
+
"loss": 0.9572,
|
| 112 |
+
"step": 70
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 6.956521739130435,
|
| 116 |
+
"grad_norm": 48.93820571899414,
|
| 117 |
+
"learning_rate": 1.2272727272727274e-05,
|
| 118 |
+
"loss": 0.8904,
|
| 119 |
+
"step": 80
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 6.956521739130435,
|
| 123 |
+
"eval_accuracy": 0.5869565217391305,
|
| 124 |
+
"eval_loss": 0.9693464040756226,
|
| 125 |
+
"eval_runtime": 0.9998,
|
| 126 |
+
"eval_samples_per_second": 46.009,
|
| 127 |
+
"eval_steps_per_second": 3.001,
|
| 128 |
+
"step": 80
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 7.826086956521739,
|
| 132 |
+
"grad_norm": 42.79694366455078,
|
| 133 |
+
"learning_rate": 1.1931818181818181e-05,
|
| 134 |
+
"loss": 0.8249,
|
| 135 |
+
"step": 90
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 8.0,
|
| 139 |
+
"eval_accuracy": 0.5869565217391305,
|
| 140 |
+
"eval_loss": 0.8764547109603882,
|
| 141 |
+
"eval_runtime": 0.769,
|
| 142 |
+
"eval_samples_per_second": 59.819,
|
| 143 |
+
"eval_steps_per_second": 3.901,
|
| 144 |
+
"step": 92
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 8.695652173913043,
|
| 148 |
+
"grad_norm": 38.31732177734375,
|
| 149 |
+
"learning_rate": 1.159090909090909e-05,
|
| 150 |
+
"loss": 0.8034,
|
| 151 |
+
"step": 100
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 8.956521739130435,
|
| 155 |
+
"eval_accuracy": 0.5869565217391305,
|
| 156 |
+
"eval_loss": 0.9217849969863892,
|
| 157 |
+
"eval_runtime": 0.7697,
|
| 158 |
+
"eval_samples_per_second": 59.763,
|
| 159 |
+
"eval_steps_per_second": 3.898,
|
| 160 |
+
"step": 103
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 9.565217391304348,
|
| 164 |
+
"grad_norm": 81.84188842773438,
|
| 165 |
+
"learning_rate": 1.125e-05,
|
| 166 |
+
"loss": 0.7333,
|
| 167 |
+
"step": 110
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 10.0,
|
| 171 |
+
"eval_accuracy": 0.5869565217391305,
|
| 172 |
+
"eval_loss": 0.8731521964073181,
|
| 173 |
+
"eval_runtime": 0.7894,
|
| 174 |
+
"eval_samples_per_second": 58.269,
|
| 175 |
+
"eval_steps_per_second": 3.8,
|
| 176 |
+
"step": 115
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 10.434782608695652,
|
| 180 |
+
"grad_norm": 45.762794494628906,
|
| 181 |
+
"learning_rate": 1.0909090909090909e-05,
|
| 182 |
+
"loss": 0.6958,
|
| 183 |
+
"step": 120
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 10.956521739130435,
|
| 187 |
+
"eval_accuracy": 0.6304347826086957,
|
| 188 |
+
"eval_loss": 0.8632770776748657,
|
| 189 |
+
"eval_runtime": 1.0248,
|
| 190 |
+
"eval_samples_per_second": 44.885,
|
| 191 |
+
"eval_steps_per_second": 2.927,
|
| 192 |
+
"step": 126
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 11.304347826086957,
|
| 196 |
+
"grad_norm": 58.06085205078125,
|
| 197 |
+
"learning_rate": 1.0568181818181819e-05,
|
| 198 |
+
"loss": 0.6995,
|
| 199 |
+
"step": 130
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 12.0,
|
| 203 |
+
"eval_accuracy": 0.5434782608695652,
|
| 204 |
+
"eval_loss": 0.953408420085907,
|
| 205 |
+
"eval_runtime": 0.7813,
|
| 206 |
+
"eval_samples_per_second": 58.875,
|
| 207 |
+
"eval_steps_per_second": 3.84,
|
| 208 |
+
"step": 138
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 12.173913043478262,
|
| 212 |
+
"grad_norm": 51.27088928222656,
|
| 213 |
+
"learning_rate": 1.0227272727272727e-05,
|
| 214 |
+
"loss": 0.6955,
|
| 215 |
+
"step": 140
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 12.956521739130435,
|
| 219 |
+
"eval_accuracy": 0.6304347826086957,
|
| 220 |
+
"eval_loss": 0.8286184072494507,
|
| 221 |
+
"eval_runtime": 0.7847,
|
| 222 |
+
"eval_samples_per_second": 58.625,
|
| 223 |
+
"eval_steps_per_second": 3.823,
|
| 224 |
+
"step": 149
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 13.043478260869565,
|
| 228 |
+
"grad_norm": 96.10741424560547,
|
| 229 |
+
"learning_rate": 9.886363636363637e-06,
|
| 230 |
+
"loss": 0.6661,
|
| 231 |
+
"step": 150
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 13.91304347826087,
|
| 235 |
+
"grad_norm": 48.46059036254883,
|
| 236 |
+
"learning_rate": 9.545454545454545e-06,
|
| 237 |
+
"loss": 0.6558,
|
| 238 |
+
"step": 160
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 14.0,
|
| 242 |
+
"eval_accuracy": 0.5869565217391305,
|
| 243 |
+
"eval_loss": 0.8844228982925415,
|
| 244 |
+
"eval_runtime": 1.0361,
|
| 245 |
+
"eval_samples_per_second": 44.396,
|
| 246 |
+
"eval_steps_per_second": 2.895,
|
| 247 |
+
"step": 161
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 14.782608695652174,
|
| 251 |
+
"grad_norm": 54.17131805419922,
|
| 252 |
+
"learning_rate": 9.204545454545455e-06,
|
| 253 |
+
"loss": 0.5951,
|
| 254 |
+
"step": 170
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 14.956521739130435,
|
| 258 |
+
"eval_accuracy": 0.6086956521739131,
|
| 259 |
+
"eval_loss": 0.9009382724761963,
|
| 260 |
+
"eval_runtime": 0.7773,
|
| 261 |
+
"eval_samples_per_second": 59.177,
|
| 262 |
+
"eval_steps_per_second": 3.859,
|
| 263 |
+
"step": 172
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 15.652173913043478,
|
| 267 |
+
"grad_norm": 65.09960174560547,
|
| 268 |
+
"learning_rate": 8.863636363636365e-06,
|
| 269 |
+
"loss": 0.5674,
|
| 270 |
+
"step": 180
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 16.0,
|
| 274 |
+
"eval_accuracy": 0.6086956521739131,
|
| 275 |
+
"eval_loss": 0.8455564379692078,
|
| 276 |
+
"eval_runtime": 0.7915,
|
| 277 |
+
"eval_samples_per_second": 58.115,
|
| 278 |
+
"eval_steps_per_second": 3.79,
|
| 279 |
+
"step": 184
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 16.52173913043478,
|
| 283 |
+
"grad_norm": 63.43704605102539,
|
| 284 |
+
"learning_rate": 8.522727272727273e-06,
|
| 285 |
+
"loss": 0.5718,
|
| 286 |
+
"step": 190
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 16.956521739130434,
|
| 290 |
+
"eval_accuracy": 0.6521739130434783,
|
| 291 |
+
"eval_loss": 0.8150178790092468,
|
| 292 |
+
"eval_runtime": 0.9714,
|
| 293 |
+
"eval_samples_per_second": 47.355,
|
| 294 |
+
"eval_steps_per_second": 3.088,
|
| 295 |
+
"step": 195
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 17.391304347826086,
|
| 299 |
+
"grad_norm": 66.53179931640625,
|
| 300 |
+
"learning_rate": 8.181818181818181e-06,
|
| 301 |
+
"loss": 0.6046,
|
| 302 |
+
"step": 200
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 18.0,
|
| 306 |
+
"eval_accuracy": 0.6086956521739131,
|
| 307 |
+
"eval_loss": 0.8729226589202881,
|
| 308 |
+
"eval_runtime": 0.7955,
|
| 309 |
+
"eval_samples_per_second": 57.826,
|
| 310 |
+
"eval_steps_per_second": 3.771,
|
| 311 |
+
"step": 207
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 18.26086956521739,
|
| 315 |
+
"grad_norm": 53.03925704956055,
|
| 316 |
+
"learning_rate": 7.840909090909091e-06,
|
| 317 |
+
"loss": 0.5532,
|
| 318 |
+
"step": 210
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 18.956521739130434,
|
| 322 |
+
"eval_accuracy": 0.717391304347826,
|
| 323 |
+
"eval_loss": 0.7663016319274902,
|
| 324 |
+
"eval_runtime": 0.768,
|
| 325 |
+
"eval_samples_per_second": 59.893,
|
| 326 |
+
"eval_steps_per_second": 3.906,
|
| 327 |
+
"step": 218
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 19.130434782608695,
|
| 331 |
+
"grad_norm": 42.510982513427734,
|
| 332 |
+
"learning_rate": 7.5e-06,
|
| 333 |
+
"loss": 0.5593,
|
| 334 |
+
"step": 220
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 20.0,
|
| 338 |
+
"grad_norm": 34.26123046875,
|
| 339 |
+
"learning_rate": 7.159090909090909e-06,
|
| 340 |
+
"loss": 0.5246,
|
| 341 |
+
"step": 230
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 20.0,
|
| 345 |
+
"eval_accuracy": 0.6521739130434783,
|
| 346 |
+
"eval_loss": 0.8457368016242981,
|
| 347 |
+
"eval_runtime": 0.7575,
|
| 348 |
+
"eval_samples_per_second": 60.729,
|
| 349 |
+
"eval_steps_per_second": 3.961,
|
| 350 |
+
"step": 230
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 20.869565217391305,
|
| 354 |
+
"grad_norm": 68.56008911132812,
|
| 355 |
+
"learning_rate": 6.818181818181818e-06,
|
| 356 |
+
"loss": 0.5147,
|
| 357 |
+
"step": 240
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 20.956521739130434,
|
| 361 |
+
"eval_accuracy": 0.6086956521739131,
|
| 362 |
+
"eval_loss": 0.8597407341003418,
|
| 363 |
+
"eval_runtime": 1.014,
|
| 364 |
+
"eval_samples_per_second": 45.366,
|
| 365 |
+
"eval_steps_per_second": 2.959,
|
| 366 |
+
"step": 241
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 21.73913043478261,
|
| 370 |
+
"grad_norm": 56.340675354003906,
|
| 371 |
+
"learning_rate": 6.477272727272727e-06,
|
| 372 |
+
"loss": 0.5162,
|
| 373 |
+
"step": 250
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 22.0,
|
| 377 |
+
"eval_accuracy": 0.717391304347826,
|
| 378 |
+
"eval_loss": 0.7643864750862122,
|
| 379 |
+
"eval_runtime": 0.7518,
|
| 380 |
+
"eval_samples_per_second": 61.187,
|
| 381 |
+
"eval_steps_per_second": 3.99,
|
| 382 |
+
"step": 253
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 22.608695652173914,
|
| 386 |
+
"grad_norm": 59.545936584472656,
|
| 387 |
+
"learning_rate": 6.136363636363637e-06,
|
| 388 |
+
"loss": 0.5194,
|
| 389 |
+
"step": 260
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 22.956521739130434,
|
| 393 |
+
"eval_accuracy": 0.6304347826086957,
|
| 394 |
+
"eval_loss": 0.8359962701797485,
|
| 395 |
+
"eval_runtime": 0.7609,
|
| 396 |
+
"eval_samples_per_second": 60.452,
|
| 397 |
+
"eval_steps_per_second": 3.943,
|
| 398 |
+
"step": 264
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 23.47826086956522,
|
| 402 |
+
"grad_norm": 60.10955810546875,
|
| 403 |
+
"learning_rate": 5.795454545454545e-06,
|
| 404 |
+
"loss": 0.5078,
|
| 405 |
+
"step": 270
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 24.0,
|
| 409 |
+
"eval_accuracy": 0.6739130434782609,
|
| 410 |
+
"eval_loss": 0.848309338092804,
|
| 411 |
+
"eval_runtime": 1.0035,
|
| 412 |
+
"eval_samples_per_second": 45.838,
|
| 413 |
+
"eval_steps_per_second": 2.989,
|
| 414 |
+
"step": 276
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 24.347826086956523,
|
| 418 |
+
"grad_norm": 55.76680374145508,
|
| 419 |
+
"learning_rate": 5.4545454545454545e-06,
|
| 420 |
+
"loss": 0.5,
|
| 421 |
+
"step": 280
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"epoch": 24.956521739130434,
|
| 425 |
+
"eval_accuracy": 0.6304347826086957,
|
| 426 |
+
"eval_loss": 0.8623191714286804,
|
| 427 |
+
"eval_runtime": 0.7687,
|
| 428 |
+
"eval_samples_per_second": 59.839,
|
| 429 |
+
"eval_steps_per_second": 3.903,
|
| 430 |
+
"step": 287
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 25.217391304347824,
|
| 434 |
+
"grad_norm": 58.6871452331543,
|
| 435 |
+
"learning_rate": 5.1136363636363635e-06,
|
| 436 |
+
"loss": 0.4946,
|
| 437 |
+
"step": 290
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 26.0,
|
| 441 |
+
"eval_accuracy": 0.7391304347826086,
|
| 442 |
+
"eval_loss": 0.7807860374450684,
|
| 443 |
+
"eval_runtime": 0.7717,
|
| 444 |
+
"eval_samples_per_second": 59.61,
|
| 445 |
+
"eval_steps_per_second": 3.888,
|
| 446 |
+
"step": 299
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 26.08695652173913,
|
| 450 |
+
"grad_norm": 68.36862182617188,
|
| 451 |
+
"learning_rate": 4.7727272727272725e-06,
|
| 452 |
+
"loss": 0.5023,
|
| 453 |
+
"step": 300
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 26.956521739130434,
|
| 457 |
+
"grad_norm": 48.596290588378906,
|
| 458 |
+
"learning_rate": 4.4318181818181824e-06,
|
| 459 |
+
"loss": 0.4659,
|
| 460 |
+
"step": 310
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 26.956521739130434,
|
| 464 |
+
"eval_accuracy": 0.6739130434782609,
|
| 465 |
+
"eval_loss": 0.8033761382102966,
|
| 466 |
+
"eval_runtime": 0.7637,
|
| 467 |
+
"eval_samples_per_second": 60.235,
|
| 468 |
+
"eval_steps_per_second": 3.928,
|
| 469 |
+
"step": 310
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 27.82608695652174,
|
| 473 |
+
"grad_norm": 51.9083251953125,
|
| 474 |
+
"learning_rate": 4.090909090909091e-06,
|
| 475 |
+
"loss": 0.4588,
|
| 476 |
+
"step": 320
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 28.0,
|
| 480 |
+
"eval_accuracy": 0.6739130434782609,
|
| 481 |
+
"eval_loss": 0.7967244982719421,
|
| 482 |
+
"eval_runtime": 1.0275,
|
| 483 |
+
"eval_samples_per_second": 44.769,
|
| 484 |
+
"eval_steps_per_second": 2.92,
|
| 485 |
+
"step": 322
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 28.695652173913043,
|
| 489 |
+
"grad_norm": 53.64326858520508,
|
| 490 |
+
"learning_rate": 3.75e-06,
|
| 491 |
+
"loss": 0.52,
|
| 492 |
+
"step": 330
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 28.956521739130434,
|
| 496 |
+
"eval_accuracy": 0.6521739130434783,
|
| 497 |
+
"eval_loss": 0.8431867361068726,
|
| 498 |
+
"eval_runtime": 0.7615,
|
| 499 |
+
"eval_samples_per_second": 60.404,
|
| 500 |
+
"eval_steps_per_second": 3.939,
|
| 501 |
+
"step": 333
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 29.565217391304348,
|
| 505 |
+
"grad_norm": 53.978824615478516,
|
| 506 |
+
"learning_rate": 3.409090909090909e-06,
|
| 507 |
+
"loss": 0.4111,
|
| 508 |
+
"step": 340
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 30.0,
|
| 512 |
+
"eval_accuracy": 0.6739130434782609,
|
| 513 |
+
"eval_loss": 0.829429566860199,
|
| 514 |
+
"eval_runtime": 0.7724,
|
| 515 |
+
"eval_samples_per_second": 59.557,
|
| 516 |
+
"eval_steps_per_second": 3.884,
|
| 517 |
+
"step": 345
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 30.434782608695652,
|
| 521 |
+
"grad_norm": 71.12972259521484,
|
| 522 |
+
"learning_rate": 3.0681818181818186e-06,
|
| 523 |
+
"loss": 0.4453,
|
| 524 |
+
"step": 350
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 30.956521739130434,
|
| 528 |
+
"eval_accuracy": 0.6956521739130435,
|
| 529 |
+
"eval_loss": 0.8066554665565491,
|
| 530 |
+
"eval_runtime": 0.7622,
|
| 531 |
+
"eval_samples_per_second": 60.354,
|
| 532 |
+
"eval_steps_per_second": 3.936,
|
| 533 |
+
"step": 356
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 31.304347826086957,
|
| 537 |
+
"grad_norm": 74.20552062988281,
|
| 538 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 539 |
+
"loss": 0.4218,
|
| 540 |
+
"step": 360
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 32.0,
|
| 544 |
+
"eval_accuracy": 0.6956521739130435,
|
| 545 |
+
"eval_loss": 0.8085731267929077,
|
| 546 |
+
"eval_runtime": 1.0497,
|
| 547 |
+
"eval_samples_per_second": 43.823,
|
| 548 |
+
"eval_steps_per_second": 2.858,
|
| 549 |
+
"step": 368
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 32.17391304347826,
|
| 553 |
+
"grad_norm": 60.71514129638672,
|
| 554 |
+
"learning_rate": 2.3863636363636363e-06,
|
| 555 |
+
"loss": 0.454,
|
| 556 |
+
"step": 370
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 32.95652173913044,
|
| 560 |
+
"eval_accuracy": 0.6739130434782609,
|
| 561 |
+
"eval_loss": 0.8196858167648315,
|
| 562 |
+
"eval_runtime": 0.7648,
|
| 563 |
+
"eval_samples_per_second": 60.144,
|
| 564 |
+
"eval_steps_per_second": 3.922,
|
| 565 |
+
"step": 379
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 33.04347826086956,
|
| 569 |
+
"grad_norm": 64.47042846679688,
|
| 570 |
+
"learning_rate": 2.0454545454545453e-06,
|
| 571 |
+
"loss": 0.4595,
|
| 572 |
+
"step": 380
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 33.91304347826087,
|
| 576 |
+
"grad_norm": 47.03898239135742,
|
| 577 |
+
"learning_rate": 1.7045454545454546e-06,
|
| 578 |
+
"loss": 0.4564,
|
| 579 |
+
"step": 390
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 34.0,
|
| 583 |
+
"eval_accuracy": 0.6739130434782609,
|
| 584 |
+
"eval_loss": 0.834749162197113,
|
| 585 |
+
"eval_runtime": 0.7832,
|
| 586 |
+
"eval_samples_per_second": 58.733,
|
| 587 |
+
"eval_steps_per_second": 3.83,
|
| 588 |
+
"step": 391
|
| 589 |
+
},
|
| 590 |
+
{
|
| 591 |
+
"epoch": 34.78260869565217,
|
| 592 |
+
"grad_norm": 60.85267639160156,
|
| 593 |
+
"learning_rate": 1.3636363636363636e-06,
|
| 594 |
+
"loss": 0.4245,
|
| 595 |
+
"step": 400
|
| 596 |
+
},
|
| 597 |
+
{
|
| 598 |
+
"epoch": 34.95652173913044,
|
| 599 |
+
"eval_accuracy": 0.6739130434782609,
|
| 600 |
+
"eval_loss": 0.8404383659362793,
|
| 601 |
+
"eval_runtime": 1.0129,
|
| 602 |
+
"eval_samples_per_second": 45.415,
|
| 603 |
+
"eval_steps_per_second": 2.962,
|
| 604 |
+
"step": 402
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 35.65217391304348,
|
| 608 |
+
"grad_norm": 63.768638610839844,
|
| 609 |
+
"learning_rate": 1.0227272727272727e-06,
|
| 610 |
+
"loss": 0.4165,
|
| 611 |
+
"step": 410
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 36.0,
|
| 615 |
+
"eval_accuracy": 0.6739130434782609,
|
| 616 |
+
"eval_loss": 0.8332401514053345,
|
| 617 |
+
"eval_runtime": 0.7702,
|
| 618 |
+
"eval_samples_per_second": 59.723,
|
| 619 |
+
"eval_steps_per_second": 3.895,
|
| 620 |
+
"step": 414
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 36.52173913043478,
|
| 624 |
+
"grad_norm": 306.15679931640625,
|
| 625 |
+
"learning_rate": 6.818181818181818e-07,
|
| 626 |
+
"loss": 0.4377,
|
| 627 |
+
"step": 420
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 36.95652173913044,
|
| 631 |
+
"eval_accuracy": 0.6739130434782609,
|
| 632 |
+
"eval_loss": 0.8381772041320801,
|
| 633 |
+
"eval_runtime": 0.7433,
|
| 634 |
+
"eval_samples_per_second": 61.886,
|
| 635 |
+
"eval_steps_per_second": 4.036,
|
| 636 |
+
"step": 425
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"epoch": 37.391304347826086,
|
| 640 |
+
"grad_norm": 51.60419845581055,
|
| 641 |
+
"learning_rate": 3.409090909090909e-07,
|
| 642 |
+
"loss": 0.4387,
|
| 643 |
+
"step": 430
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 38.0,
|
| 647 |
+
"eval_accuracy": 0.6956521739130435,
|
| 648 |
+
"eval_loss": 0.8344257473945618,
|
| 649 |
+
"eval_runtime": 0.7845,
|
| 650 |
+
"eval_samples_per_second": 58.64,
|
| 651 |
+
"eval_steps_per_second": 3.824,
|
| 652 |
+
"step": 437
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 38.26086956521739,
|
| 656 |
+
"grad_norm": 57.41154861450195,
|
| 657 |
+
"learning_rate": 0.0,
|
| 658 |
+
"loss": 0.4321,
|
| 659 |
+
"step": 440
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 38.26086956521739,
|
| 663 |
+
"eval_accuracy": 0.6956521739130435,
|
| 664 |
+
"eval_loss": 0.8340795040130615,
|
| 665 |
+
"eval_runtime": 1.5565,
|
| 666 |
+
"eval_samples_per_second": 29.553,
|
| 667 |
+
"eval_steps_per_second": 1.927,
|
| 668 |
+
"step": 440
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 38.26086956521739,
|
| 672 |
+
"step": 440,
|
| 673 |
+
"total_flos": 8.989085534729011e+17,
|
| 674 |
+
"train_loss": 0.6443484219637784,
|
| 675 |
+
"train_runtime": 903.3964,
|
| 676 |
+
"train_samples_per_second": 31.968,
|
| 677 |
+
"train_steps_per_second": 0.487
|
| 678 |
+
}
|
| 679 |
+
],
|
| 680 |
+
"logging_steps": 10,
|
| 681 |
+
"max_steps": 440,
|
| 682 |
+
"num_input_tokens_seen": 0,
|
| 683 |
+
"num_train_epochs": 40,
|
| 684 |
+
"save_steps": 500,
|
| 685 |
+
"stateful_callbacks": {
|
| 686 |
+
"TrainerControl": {
|
| 687 |
+
"args": {
|
| 688 |
+
"should_epoch_stop": false,
|
| 689 |
+
"should_evaluate": false,
|
| 690 |
+
"should_log": false,
|
| 691 |
+
"should_save": true,
|
| 692 |
+
"should_training_stop": true
|
| 693 |
+
},
|
| 694 |
+
"attributes": {}
|
| 695 |
+
}
|
| 696 |
+
},
|
| 697 |
+
"total_flos": 8.989085534729011e+17,
|
| 698 |
+
"train_batch_size": 16,
|
| 699 |
+
"trial_name": null,
|
| 700 |
+
"trial_params": null
|
| 701 |
+
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18cf43f8c73413d228cd2aeef98d5c03497d248a421fe7b816fd15ab88ccbcbc
|
| 3 |
size 5368
|