Training in progress, step 30, checkpoint

checkpoint-30/config.json

@@ -0,0 +1,198 @@
+{
+  "architectures": [
+    "Gemma4ForConditionalGeneration"
+  ],
+  "audio_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_chunk_size": 12,
+    "attention_context_left": 13,
+    "attention_context_right": 0,
+    "attention_invalid_logits_value": -1000000000.0,
+    "attention_logit_cap": 50.0,
+    "chunk_size_feed_forward": 0,
+    "conv_kernel_size": 5,
+    "dtype": "bfloat16",
+    "gradient_clipping": 10000000000.0,
+    "hidden_act": "silu",
+    "hidden_size": 1024,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "model_type": "gemma4_audio",
+    "num_attention_heads": 8,
+    "num_hidden_layers": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_proj_dims": 1536,
+    "problem_type": null,
+    "residual_weight": 0.5,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "subsampling_conv_channels": [
+      128,
+      32
+    ],
+    "use_clipped_linears": true
+  },
+  "audio_token_id": 258881,
+  "boa_token_id": 256000,
+  "boi_token_id": 255999,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eoa_token_id": 258883,
+  "eoa_token_index": 258883,
+  "eoi_token_id": 258882,
+  "eos_token_id": 1,
+  "image_token_id": 258880,
+  "initializer_range": 0.02,
+  "model_type": "gemma4",
+  "pad_token_id": 0,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attention_k_eq_v": false,
+    "bos_token_id": 2,
+    "dtype": "bfloat16",
+    "enable_moe_block": false,
+    "eos_token_id": 1,
+    "expert_intermediate_size": null,
+    "final_logit_softcapping": 30.0,
+    "global_head_dim": 512,
+    "head_dim": 256,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 2560,
+    "hidden_size_per_layer_input": 256,
+    "initializer_range": 0.02,
+    "intermediate_size": 10240,
+    "layer_types": [
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "sliding_attention",
+      "full_attention"
+    ],
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_text",
+    "moe_intermediate_size": null,
+    "num_attention_heads": 8,
+    "num_experts": null,
+    "num_global_key_value_heads": null,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 2,
+    "num_kv_shared_layers": 18,
+    "pad_token_id": 0,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "full_attention": {
+        "partial_rotary_factor": 0.25,
+        "rope_theta": 1000000.0,
+        "rope_type": "proportional"
+      },
+      "sliding_attention": {
+        "rope_theta": 10000.0,
+        "rope_type": "default"
+      }
+    },
+    "sliding_window": 512,
+    "tie_word_embeddings": true,
+    "top_k_experts": null,
+    "use_bidirectional_attention": null,
+    "use_cache": true,
+    "use_double_wide_mlp": false,
+    "vocab_size": 262144,
+    "vocab_size_per_layer_input": 262144
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": false,
+  "video_token_id": 258884,
+  "vision_config": {
+    "_name_or_path": "",
+    "architectures": null,
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "chunk_size_feed_forward": 0,
+    "default_output_length": 280,
+    "dtype": "bfloat16",
+    "global_head_dim": 64,
+    "head_dim": 64,
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "max_position_embeddings": 131072,
+    "model_type": "gemma4_vision",
+    "num_attention_heads": 12,
+    "num_hidden_layers": 16,
+    "num_key_value_heads": 12,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "patch_size": 16,
+    "pooling_kernel_size": 3,
+    "position_embedding_size": 10240,
+    "problem_type": null,
+    "return_dict": true,
+    "rms_norm_eps": 1e-06,
+    "rope_parameters": {
+      "rope_theta": 100.0,
+      "rope_type": "default"
+    },
+    "standardize": false,
+    "use_clipped_linears": true
+  },
+  "vision_soft_tokens_per_image": 280
+}

checkpoint-30/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 2,
+  "do_sample": true,
+  "eos_token_id": [
+    1,
+    1
+  ],
+  "pad_token_id": 0,
+  "temperature": 1.0,
+  "top_k": 64,
+  "top_p": 0.95,
+  "transformers_version": "5.7.0"
+}

checkpoint-30/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7530ce03c31041753706d5a18f58f1c38a2644a6984b48efc2c33b5ec2c7427e
+size 15882477500

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b3c811eb39f7cf4873cfc7ded7e3a0b3b3f885cfa292048e4271ac565d0e571
+size 29852609572

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80e64c12f0838d10ccdb70de08adeb65f476535360b1ea65dcb2c1f252abae8e
+size 1465

checkpoint-30/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12bac982b793c44b03d52a250a9f0d0b666813da566b910c24a6da0695fd11e6
+size 32170070

checkpoint-30/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "audio_token": "<|audio|>",
+  "backend": "tokenizers",
+  "boa_token": "<|audio>",
+  "boi_token": "<|image>",
+  "bos_token": "<bos>",
+  "eoa_token": "<audio|>",
+  "eoc_token": "<channel|>",
+  "eoi_token": "<image|>",
+  "eos_token": "<eos>",
+  "eot_token": "<turn|>",
+  "escape_token": "<|\"|>",
+  "etc_token": "<tool_call|>",
+  "etd_token": "<tool|>",
+  "etr_token": "<tool_response|>",
+  "extra_special_tokens": [
+    "<|video|>"
+  ],
+  "image_token": "<|image|>",
+  "is_local": false,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {
+    "audio_token": "<|audio|>",
+    "boa_token": "<|audio>",
+    "boi_token": "<|image>",
+    "eoa_token": "<audio|>",
+    "eoc_token": "<channel|>",
+    "eoi_token": "<image|>",
+    "eot_token": "<turn|>",
+    "escape_token": "<|\"|>",
+    "etc_token": "<tool_call|>",
+    "etd_token": "<tool|>",
+    "etr_token": "<tool_response|>",
+    "image_token": "<|image|>",
+    "soc_token": "<|channel>",
+    "sot_token": "<|turn>",
+    "stc_token": "<|tool_call>",
+    "std_token": "<|tool>",
+    "str_token": "<|tool_response>",
+    "think_token": "<|think|>"
+  },
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "processor_class": "Gemma4Processor",
+  "soc_token": "<|channel>",
+  "sot_token": "<|turn>",
+  "stc_token": "<|tool_call>",
+  "std_token": "<|tool>",
+  "str_token": "<|tool_response>",
+  "think_token": "<|think|>",
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-30/trainer_state.json

@@ -0,0 +1,244 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.31456072086831866,
+  "eval_steps": 1,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010485357362277289,
+      "grad_norm": 498.0,
+      "learning_rate": 0.0,
+      "loss": 1.6033425331115723,
+      "step": 1
+    },
+    {
+      "epoch": 0.020970714724554577,
+      "grad_norm": 139.0,
+      "learning_rate": 4e-08,
+      "loss": 1.5843058824539185,
+      "step": 2
+    },
+    {
+      "epoch": 0.03145607208683186,
+      "grad_norm": 158.0,
+      "learning_rate": 8e-08,
+      "loss": 1.624650239944458,
+      "step": 3
+    },
+    {
+      "epoch": 0.041941429449109155,
+      "grad_norm": 201.0,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 1.5930713415145874,
+      "step": 4
+    },
+    {
+      "epoch": 0.05242678681138644,
+      "grad_norm": 1392.0,
+      "learning_rate": 1.6e-07,
+      "loss": 1.6284583806991577,
+      "step": 5
+    },
+    {
+      "epoch": 0.06291214417366373,
+      "grad_norm": 644.0,
+      "learning_rate": 2.0000000000000002e-07,
+      "loss": 1.5755040645599365,
+      "step": 6
+    },
+    {
+      "epoch": 0.07339750153594102,
+      "grad_norm": 358.0,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 1.5862637758255005,
+      "step": 7
+    },
+    {
+      "epoch": 0.08388285889821831,
+      "grad_norm": 1012.0,
+      "learning_rate": 2.8e-07,
+      "loss": 1.6306817531585693,
+      "step": 8
+    },
+    {
+      "epoch": 0.0943682162604956,
+      "grad_norm": 187.0,
+      "learning_rate": 3.2e-07,
+      "loss": 1.5844253301620483,
+      "step": 9
+    },
+    {
+      "epoch": 0.10485357362277288,
+      "grad_norm": 342.0,
+      "learning_rate": 3.6e-07,
+      "loss": 1.5895334482192993,
+      "step": 10
+    },
+    {
+      "epoch": 0.11533893098505017,
+      "grad_norm": 816.0,
+      "learning_rate": 4.0000000000000003e-07,
+      "loss": 1.5861637592315674,
+      "step": 11
+    },
+    {
+      "epoch": 0.12582428834732745,
+      "grad_norm": 260.0,
+      "learning_rate": 4.4e-07,
+      "loss": 1.57806396484375,
+      "step": 12
+    },
+    {
+      "epoch": 0.13630964570960474,
+      "grad_norm": 326.0,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 1.5836868286132812,
+      "step": 13
+    },
+    {
+      "epoch": 0.14679500307188204,
+      "grad_norm": 668.0,
+      "learning_rate": 5.2e-07,
+      "loss": 1.5597259998321533,
+      "step": 14
+    },
+    {
+      "epoch": 0.15728036043415933,
+      "grad_norm": 256.0,
+      "learning_rate": 5.6e-07,
+      "loss": 1.5852601528167725,
+      "step": 15
+    },
+    {
+      "epoch": 0.16776571779643662,
+      "grad_norm": 205.0,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 1.5899027585983276,
+      "step": 16
+    },
+    {
+      "epoch": 0.1782510751587139,
+      "grad_norm": 188.0,
+      "learning_rate": 6.4e-07,
+      "loss": 1.5692049264907837,
+      "step": 17
+    },
+    {
+      "epoch": 0.1887364325209912,
+      "grad_norm": 426.0,
+      "learning_rate": 6.800000000000001e-07,
+      "loss": 1.55263090133667,
+      "step": 18
+    },
+    {
+      "epoch": 0.1992217898832685,
+      "grad_norm": 245.0,
+      "learning_rate": 7.2e-07,
+      "loss": 1.5602704286575317,
+      "step": 19
+    },
+    {
+      "epoch": 0.20970714724554576,
+      "grad_norm": 158.0,
+      "learning_rate": 7.6e-07,
+      "loss": 1.5857173204421997,
+      "step": 20
+    },
+    {
+      "epoch": 0.22019250460782305,
+      "grad_norm": 90.0,
+      "learning_rate": 8.000000000000001e-07,
+      "loss": 1.5650298595428467,
+      "step": 21
+    },
+    {
+      "epoch": 0.23067786197010035,
+      "grad_norm": 148.0,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 1.548302173614502,
+      "step": 22
+    },
+    {
+      "epoch": 0.24116321933237764,
+      "grad_norm": 187.0,
+      "learning_rate": 8.8e-07,
+      "loss": 1.5342053174972534,
+      "step": 23
+    },
+    {
+      "epoch": 0.2516485766946549,
+      "grad_norm": 282.0,
+      "learning_rate": 9.200000000000001e-07,
+      "loss": 1.5395140647888184,
+      "step": 24
+    },
+    {
+      "epoch": 0.2621339340569322,
+      "grad_norm": 212.0,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 1.5411065816879272,
+      "step": 25
+    },
+    {
+      "epoch": 0.2726192914192095,
+      "grad_norm": 1640.0,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.520958423614502,
+      "step": 26
+    },
+    {
+      "epoch": 0.2831046487814868,
+      "grad_norm": 161.0,
+      "learning_rate": 1.04e-06,
+      "loss": 1.516421914100647,
+      "step": 27
+    },
+    {
+      "epoch": 0.29359000614376407,
+      "grad_norm": 175.0,
+      "learning_rate": 1.08e-06,
+      "loss": 1.492469310760498,
+      "step": 28
+    },
+    {
+      "epoch": 0.30407536350604136,
+      "grad_norm": 115.0,
+      "learning_rate": 1.12e-06,
+      "loss": 1.5238401889801025,
+      "step": 29
+    },
+    {
+      "epoch": 0.31456072086831866,
+      "grad_norm": 96.5,
+      "learning_rate": 1.1600000000000001e-06,
+      "loss": 1.4782272577285767,
+      "step": 30
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 96,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 5,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6803622975596134e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:874ac4b635f5e0e0130ccc11de5bfc6cee2eac14aa65567d5f9737b0b5cc556a
+size 5265