Pushed the IDEFICS2 fine-tuned model.

checkpoint-25/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b966f7d4ed03a7cc5f0d9f12d11c6a36291778d9bbbf782adafd78784a19840
+oid sha256:211756393169a47923b018f9f1a4c1ff9fbedf416c232c273405a6535035e520
 size 93378688

checkpoint-25/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acbe89ccd613a30390efd87c851995b5d2229722780b43fab32b11d369a27e7d
+oid sha256:b442cfd495fcaa5f9aa918d20aa7676a7668d382bc9867031a88d6c6e08e7d26
 size 48071944

checkpoint-25/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614fcea8e73d817edc55868e83a17dea664dce6af99624cd6b07cf229ea0cb30
+oid sha256:17389751b3edcf49720757d9d28af25dc2449922678632e2f6f5f61dd49356cb
 size 14244

checkpoint-25/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e38cb40a67374f1832bcdea2ecae7e9ba187f61562de69b9f4a08e86aa1a8369
+oid sha256:6222650a495ea54e976d1599e55e1eec1dfa515e390e5f653027100568b23eb1
 size 1064

checkpoint-25/trainer_state.json

@@ -10,53 +10,53 @@
   "log_history": [
     {
       "epoch": 0.08,
-      "grad_norm": 40.98280334472656,
-      "learning_rate": 0.000168,
-      "loss": 5.6666,
+      "grad_norm": 250.87176513671875,
+      "learning_rate": 0.00018400000000000003,
+      "loss": 7.6096,
       "step": 5
     },
     {
       "epoch": 0.16,
-      "grad_norm": 9.209188461303711,
-      "learning_rate": 0.00012800000000000002,
-      "loss": 0.6902,
+      "grad_norm": 31.689001083374023,
+      "learning_rate": 0.000144,
+      "loss": 2.8395,
       "step": 10
     },
     {
       "epoch": 0.16,
-      "eval_loss": 0.462746798992157,
-      "eval_runtime": 346.7059,
-      "eval_samples_per_second": 0.577,
-      "eval_steps_per_second": 0.288,
+      "eval_loss": 1.5643075704574585,
+      "eval_runtime": 335.0339,
+      "eval_samples_per_second": 0.597,
+      "eval_steps_per_second": 0.298,
       "step": 10
     },
     {
       "epoch": 0.24,
-      "grad_norm": 5.505237102508545,
-      "learning_rate": 8.800000000000001e-05,
-      "loss": 0.4216,
+      "grad_norm": 6.646055221557617,
+      "learning_rate": 0.00010400000000000001,
+      "loss": 0.9643,
       "step": 15
     },
     {
       "epoch": 0.32,
-      "grad_norm": 6.111878871917725,
-      "learning_rate": 4.8e-05,
-      "loss": 0.3347,
+      "grad_norm": 4.9765520095825195,
+      "learning_rate": 6.400000000000001e-05,
+      "loss": 0.3674,
       "step": 20
     },
     {
       "epoch": 0.32,
-      "eval_loss": 0.34206879138946533,
-      "eval_runtime": 345.9828,
-      "eval_samples_per_second": 0.578,
-      "eval_steps_per_second": 0.289,
+      "eval_loss": 0.36727723479270935,
+      "eval_runtime": 334.6508,
+      "eval_samples_per_second": 0.598,
+      "eval_steps_per_second": 0.299,
       "step": 20
     },
     {
       "epoch": 0.4,
-      "grad_norm": 3.1234376430511475,
-      "learning_rate": 8.000000000000001e-06,
-      "loss": 0.2831,
+      "grad_norm": 3.7046844959259033,
+      "learning_rate": 2.4e-05,
+      "loss": 0.2732,
       "step": 25
     }
   ],
@@ -77,7 +77,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1864510458066432.0,
+  "total_flos": 1976516367999360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

checkpoint-25/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1d6473005f07867644da79cc6c4e621e7921819ba6d9ec1fa889bd7c906a9f8
+oid sha256:6befa3566f15769a7c667b3c47ab9f99e4cfced81d36604ee1e11af15a613d72
 size 5240