Pushed the IDEFICS2 fine-tuned model.

checkpoint-25/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31d96b70c9a934c487d586616624ebe4e496d1cf08e9f856712046ae9c23d890
+oid sha256:d18d31d2ab07850fc5106340e20eae20454e9eba33cbd5edad2a67f2611e7cba
 size 93378688

checkpoint-25/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6e52f560a2502a6c307967c86d7aafc307a7d8869089cca56e0ad5844bbf10
+oid sha256:29bf9fb840fa70a92bd578a839db045c72e8295b4a8902093016b8a283ae6808
 size 47425352

checkpoint-25/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614fcea8e73d817edc55868e83a17dea664dce6af99624cd6b07cf229ea0cb30
-size 14244
+oid sha256:72e70d63777ae67fd851081989e78bfd79a7d57689d0b1082faa1e5830f19194
+size 14180

checkpoint-25/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6222650a495ea54e976d1599e55e1eec1dfa515e390e5f653027100568b23eb1
+oid sha256:630fe59a784956405be1a950d9ce52e5bf6a2f1c12f3a8bd4f3869766a5850cd
 size 1064

checkpoint-25/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.1,
   "eval_steps": 10,
   "global_step": 25,
   "is_hyper_param_search": false,
@@ -9,54 +9,54 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.08,
+      "epoch": 0.02,
       "grad_norm": Infinity,
-      "learning_rate": 0.00018400000000000003,
-      "loss": 4.5662,
+      "learning_rate": 0.00017600000000000002,
+      "loss": 2.6469,
       "step": 5
     },
     {
-      "epoch": 0.16,
-      "grad_norm": 21.689138412475586,
-      "learning_rate": 0.000144,
-      "loss": 1.5225,
+      "epoch": 0.04,
+      "grad_norm": 19.0399169921875,
+      "learning_rate": 0.00013600000000000003,
+      "loss": 1.2235,
       "step": 10
     },
     {
-      "epoch": 0.16,
-      "eval_loss": 1.1455421447753906,
-      "eval_runtime": 307.8066,
-      "eval_samples_per_second": 0.65,
-      "eval_steps_per_second": 0.325,
+      "epoch": 0.04,
+      "eval_loss": 1.2343159914016724,
+      "eval_runtime": 538.9051,
+      "eval_samples_per_second": 1.856,
+      "eval_steps_per_second": 1.856,
       "step": 10
     },
     {
-      "epoch": 0.24,
-      "grad_norm": 33.072635650634766,
-      "learning_rate": 0.00010400000000000001,
-      "loss": 1.0761,
+      "epoch": 0.06,
+      "grad_norm": 11.566468238830566,
+      "learning_rate": 9.6e-05,
+      "loss": 1.3862,
       "step": 15
     },
     {
-      "epoch": 0.32,
-      "grad_norm": 17.61521339416504,
-      "learning_rate": 6.400000000000001e-05,
-      "loss": 1.0442,
+      "epoch": 0.08,
+      "grad_norm": 12.342832565307617,
+      "learning_rate": 5.6000000000000006e-05,
+      "loss": 1.1541,
       "step": 20
     },
     {
-      "epoch": 0.32,
-      "eval_loss": 1.078382134437561,
-      "eval_runtime": 307.6568,
-      "eval_samples_per_second": 0.65,
-      "eval_steps_per_second": 0.325,
+      "epoch": 0.08,
+      "eval_loss": 1.179603934288025,
+      "eval_runtime": 540.1428,
+      "eval_samples_per_second": 1.851,
+      "eval_steps_per_second": 1.851,
       "step": 20
     },
     {
-      "epoch": 0.4,
-      "grad_norm": 9.085550308227539,
-      "learning_rate": 2.4e-05,
-      "loss": 0.9102,
+      "epoch": 0.1,
+      "grad_norm": 28.799449920654297,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 1.2611,
       "step": 25
     }
   ],
@@ -77,8 +77,8 @@
       "attributes": {}
     }
   },
-  "total_flos": 1864510458066432.0,
-  "train_batch_size": 2,
+  "total_flos": 568385230334592.0,
+  "train_batch_size": 1,
   "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:b6e46dcfc153cff4330c2978ba9f33a5fa568af92b143d92ea9c00cd30120da6
+oid sha256:bab3bbe7e71b3116bde27f637c54636924026eec9c15eb4352457999d2af31df
 size 5112