Upload 10 files

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
-tags: []
+base_model: "google/paligemma2-3b-mix-224"
+library_name: peft
 ---
 
 # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

adapter_config.json

@@ -3,9 +3,6 @@
   "auto_mapping": null,
   "base_model_name_or_path": "google/paligemma2-3b-mix-224",
   "bias": "none",
-  "corda_config": null,
-  "eva_config": null,
-  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -14,7 +11,6 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
-  "lora_bias": false,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -24,16 +20,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
-    "o_proj",
     "k_proj",
     "v_proj",
     "q_proj",
+    "o_proj",
     "gate_proj",
+    "up_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM",
-  "trainable_token_indices": null,
   "use_dora": false,
   "use_rslora": false
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4324ad05c2dff116eff9380c148fc90c1deaa8028725108d5bef69b3c2e6b9
-size 47586024
+oid sha256:a511b121be797fcb5d3d65c6f7184c8f098a2cfd888f6c370171447e6c78df6b
+size 95091968

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:faf5838bb5646bcbb176ff208a6cd531975a986bdc1051e1c97ff00f2c7beeb6
+size 177067885

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e3fdfd7a7afb530434f864281cd280c451d7d81adbb77995b9f4b59ff1211ce
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b7d5e6a79fbd3e6d4b7b6f2d6e993f71346d78d8db708acb0558adbd252a68
+size 1465

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 0.0627085492014885,
+  "best_model_checkpoint": "OpenAHA-Calvin-1p-3b/checkpoint-2000",
+  "epoch": 2.6496519721577725,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6629101756711966,
+      "grad_norm": 4.84523344039917,
+      "learning_rate": 1.733071638861629e-05,
+      "loss": 0.5578,
+      "step": 500
+    },
+    {
+      "epoch": 0.6629101756711966,
+      "eval_loss": 0.1356603056192398,
+      "eval_runtime": 31.1266,
+      "eval_samples_per_second": 13.044,
+      "eval_steps_per_second": 1.638,
+      "step": 500
+    },
+    {
+      "epoch": 1.3248259860788862,
+      "grad_norm": 7.176058769226074,
+      "learning_rate": 1.2423945044160943e-05,
+      "loss": 0.0908,
+      "step": 1000
+    },
+    {
+      "epoch": 1.3248259860788862,
+      "eval_loss": 0.08840304613113403,
+      "eval_runtime": 29.435,
+      "eval_samples_per_second": 13.793,
+      "eval_steps_per_second": 1.733,
+      "step": 1000
+    },
+    {
+      "epoch": 1.9877361617500828,
+      "grad_norm": 2.4896891117095947,
+      "learning_rate": 7.517173699705595e-06,
+      "loss": 0.0603,
+      "step": 1500
+    },
+    {
+      "epoch": 1.9877361617500828,
+      "eval_loss": 0.07601085305213928,
+      "eval_runtime": 29.6732,
+      "eval_samples_per_second": 13.682,
+      "eval_steps_per_second": 1.719,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6496519721577725,
+      "grad_norm": 5.802169322967529,
+      "learning_rate": 2.6104023552502455e-06,
+      "loss": 0.0406,
+      "step": 2000
+    },
+    {
+      "epoch": 2.6496519721577725,
+      "eval_loss": 0.0627085492014885,
+      "eval_runtime": 29.4236,
+      "eval_samples_per_second": 13.798,
+      "eval_steps_per_second": 1.733,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2265,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.832880380047903e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14d243a019bb5e8de15a30ea6dad7c03b3845286dd8a0918ffe16bc6cfd0012d
+size 5777