Training in progress, step 200, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "/root/.cache/huggingface/hub/Clip-Roco_Version2_v3",
+  "architectures": [
+    "CLIPModel"
+  ],
+  "initializer_factor": 1.0,
+  "logit_scale_init_value": 2.6592,
+  "model_type": "clip",
+  "projection_dim": 512,
+  "text_config": {
+    "_name_or_path": "/kaggle/working/TextModel",
+    "architectures": [
+      "RobertaModel"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bos_token_id": 0,
+    "classifier_dropout": null,
+    "eos_token_id": 2,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "intermediate_size": 3072,
+    "max_position_embeddings": 1026,
+    "model_type": "clip_text_model",
+    "num_attention_heads": 12,
+    "position_embedding_type": "absolute",
+    "torch_dtype": "float32",
+    "type_vocab_size": 1,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "vision_config": {
+    "_name_or_path": "openai/clip-vit-large-patch14-336",
+    "dropout": 0.0,
+    "hidden_size": 1024,
+    "image_size": 336,
+    "intermediate_size": 4096,
+    "model_type": "clip_vision_model",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 24,
+    "patch_size": 14,
+    "projection_dim": 768
+  }
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:773cc262203d85ff6a2aa1fe9d91ecbbd524df3111b609cfc0935c4e59b24565
+size 1715561468

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae12e6c56f5a6640f5fda3cba4d27b953155ea4f3e97c984241b83a108384c3
+size 3431474364

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c033ff12cf13058072b46d832a06e98b057ada5d719bc000bc42a97c8844d524
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56ee02d3e4af10e6f4525fc562a33e9b176b044744f41f0d5ad35732728b4e0f
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.020014009806864807,
+  "eval_steps": 1000,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.020014009806864807,
+      "grad_norm": 0.029514456167817116,
+      "learning_rate": 4.999998120874287e-05,
+      "loss": 1.1058,
+      "step": 200
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 499650,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2867209025126400.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5f77ee2eb256c41436412ee409e9ee9618ee717832327e403d23411e2cb2d9b
+size 5176