Training in progress, epoch 1

README.md

@@ -9,14 +9,14 @@ metrics:
 - recall
 - f1
 model-index:
-- name: model_2_stage2-seed_2025
+- name: model_2_stage2-seed_123
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-# model_2_stage2-seed_2025
+# model_2_stage2-seed_123
 
 This model is a fine-tuned version of [maud-dr/model_2_stage1](https://huggingface.co/maud-dr/model_2_stage1) on the None dataset.
 It achieves the following results on the evaluation set:
@@ -45,10 +45,10 @@ The following hyperparameters were used during training:
 - learning_rate: 0.0003
 - train_batch_size: 16
 - eval_batch_size: 16
-- seed: 42
+- seed: 123
 - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
 - lr_scheduler_type: linear
-- num_epochs: 2
+- num_epochs: 15
 - mixed_precision_training: Native AMP
 
 ### Training results
@@ -57,6 +57,19 @@ The following hyperparameters were used during training:
 |:-------------:|:-----:|:----:|:---------------:|:---------:|:------:|:---:|
 | 0.0           | 1.0   | 224  | nan             | 0.0       | 0.0    | 0.0 |
 | 0.0           | 2.0   | 448  | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 3.0   | 672  | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 4.0   | 896  | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 5.0   | 1120 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 6.0   | 1344 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 7.0   | 1568 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 8.0   | 1792 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 9.0   | 2016 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 10.0  | 2240 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 11.0  | 2464 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 12.0  | 2688 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 13.0  | 2912 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 14.0  | 3136 | nan             | 0.0       | 0.0    | 0.0 |
+| 0.0           | 15.0  | 3360 | nan             | 0.0       | 0.0    | 0.0 |
 
 
 ### Framework versions

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2fae4fc1437ec3ef15e0dff23ad9ec86d7436184a511b4afec815cbe78bcb1b
+oid sha256:1062a16fe2cbe9aff50a5c3072cbcac932ee35863abf00b3b6d4475b456c95b8
 size 894020048

runs/Jun04_16-20-37_model2-stage2-0-0/events.out.tfevents.1749054041.model2-stage2-0-0.1.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5442a3346e8376002f40f2115790cbc8da6e1d9a3beea5a2963ee812d81487e0
+size 19576

runs/Jun04_16-20-37_model2-stage2-0-0/events.out.tfevents.1749056705.model2-stage2-0-0.1.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:886ad74c6633025007a2b5c029a1ab932c7dbaa431c314b858b8664727435a2b
+size 508

runs/Jun04_17-05-05_model2-stage2-0-0/events.out.tfevents.1749056707.model2-stage2-0-0.1.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce30e06731a13632173f1d0d2b8b2ce9d919af8e0c364369326c0f4b984f9d6
+size 19628

runs/Jun04_17-05-05_model2-stage2-0-0/events.out.tfevents.1749059368.model2-stage2-0-0.1.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb22d12faa0030ed916924614e1c03ca72d23d45d9dd2a174ca94ee02e24ff1b
+size 508

runs/Jun04_17-49-28_model2-stage2-0-0/events.out.tfevents.1749059370.model2-stage2-0-0.1.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f351c7ebab4374712cb0b1bf7c0b802d22f3a4829138d328e80af7dadf6c0c4b
+size 6855

tokenizer_config.json

@@ -932,7 +932,7 @@
   "eos_token": "</s>",
   "extra_ids": 100,
   "extra_special_tokens": {},
-  "max_length": 128,
+  "max_length": 224,
   "model_max_length": 512,
   "pad_token": "<pad>",
   "sp_model_kwargs": {},

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22bf1123d4c8e9d9211d44e12fab7a5aafb2265c50d380ee1475f9a110bda0dc
+oid sha256:61ce72ac9ce48c40a13d30c7d1f448250050d69bbe3ea8f136dfd9b99dc043a5
 size 5905