Training in progress, step 20500, checkpoint

checkpoint-20500/config.json

@@ -0,0 +1,195 @@
+{
+  "architectures": [
+    "SrcProberForConditionalGeneration"
+  ],
+  "asm_encoder_config": {
+    "_name_or_path": "",
+    "add_cross_attention": false,
+    "architectures": [
+      "LongelmForMaskedLMWithEdgePrediction"
+    ],
+    "attention_probs_dropout_prob": 0.1,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "block_size": 8,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "classifier_dropout": null,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "ep_add_linear_projection": true,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "global_memory_size": 1,
+    "hidden_act": "gelu",
+    "hidden_dropout_prob": 0.1,
+    "hidden_size": 768,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "layer_norm_eps": 1e-12,
+    "length_penalty": 1.0,
+    "max_blocks": 200,
+    "max_length": 20,
+    "max_position_embeddings": 1805,
+    "max_relative_position_embeddings": 8,
+    "min_length": 0,
+    "model_type": "longelm",
+    "no_repeat_ngram_size": 0,
+    "node_size": 1,
+    "num_attention_heads": 12,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 12,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": 3,
+    "position_embedding_type": "mixed",
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": true,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "type_vocab_size": 2,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 50265
+  },
+  "asm_feature_select_strategy": "nodes",
+  "asm_token_index": 32016,
+  "ignore_index": -100,
+  "model_type": "rad-prober",
+  "pad_token_id": 2,
+  "projector_hidden_act": "gelu",
+  "src_lm_config": {
+    "_name_or_path": "codellama/CodeLlama-13b-hf",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 13824,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 16384,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 40,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 40,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization_config": {
+      "_load_in_4bit": false,
+      "_load_in_8bit": true,
+      "bnb_4bit_compute_dtype": "float32",
+      "bnb_4bit_quant_storage": "uint8",
+      "bnb_4bit_quant_type": "fp4",
+      "bnb_4bit_use_double_quant": false,
+      "llm_int8_enable_fp32_cpu_offload": false,
+      "llm_int8_has_fp16_weight": false,
+      "llm_int8_skip_modules": null,
+      "llm_int8_threshold": 6.0,
+      "load_in_4bit": false,
+      "load_in_8bit": true,
+      "quant_method": "bitsandbytes"
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 1000000,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "bfloat16",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32017
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3"
+}

checkpoint-20500/generation_config.json

@@ -0,0 +1,4 @@
+{
+  "_from_model_config": true,
+  "transformers_version": "4.39.3"
+}

checkpoint-20500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d881866cb21742071f3eea08b5e3fdb077d3a1fbd594fe8d34a9be02eb338aac
+size 620848256

checkpoint-20500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0479d0c0246a8d09af0a6957cdb0486de2a9df50499f5de55b3cb940327d5bcf
+size 297976223

checkpoint-20500/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0586dd9cd0bb5c9fb1c3fe1e10bab56b242728a63b6bfa386a490abc59db4e62
+size 14960

checkpoint-20500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa3ef8741eeaaffe08d22007bdf524f2d89fc19291ca3de7c79d7176aeb4a2b1
+size 14960

checkpoint-20500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ced7273262f1c7391931e05b1f9b9a80720f22e112921c7d3d9fd4def2d8e2d
+size 14960

checkpoint-20500/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c79a7f7d35df73e9264ae367d9168b7bf22966003fd40b0fb44bcbb3367a507f
+size 14960

checkpoint-20500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90ffbd408fe3ad3bce82f74084a6c26cc181931323dedef33082419014ec7cc2
+size 1064

checkpoint-20500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd6a31d2da7b4686068d511137b843e541147626d5878a410233f3ef91ae5dc6
+size 5048