Synchronizing local compiler cache.

neuronxcc-2.16.345.0+69131dd3/0_REGISTRY/0.0.28.dev0/training/llama/michaelbenayoun/llama-2-tiny-4kv-heads-4layers-random/c0d059d36d413eed342f.json

@@ -0,0 +1 @@
+{"_attn_implementation_autoset": true, "architectures": ["LlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "head_dim": 4, "hidden_act": "silu", "hidden_size": 128, "initializer_range": 0.02, "intermediate_size": 128, "is_decoder": true, "max_position_embeddings": 4096, "mlp_bias": false, "model_type": "llama", "neuron": {"compiler_version": "2.16.345.0+69131dd3", "input_specs": {"attention_mask": [1, 128], "input_ids": [1, 128], "labels": [1, 128]}, "model_class": "LlamaForCausalLM", "num_neuron_cores_per_node": 2, "pipeline_parallel_size": 1, "precision": "float32", "tensor_parallel_size": 2, "training": true}, "num_attention_heads": 32, "num_hidden_layers": 4, "num_key_value_heads": 4, "pad_token_id": 0, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float32", "use_cache": true, "vocab_size": 32000}

neuronxcc-2.16.345.0+69131dd3/MODULE_16438529901037340477+3cc9a3cb/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer"]

neuronxcc-2.16.345.0+69131dd3/MODULE_16438529901037340477+3cc9a3cb/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1cc2536db5dd48d7261a090325ea30fd90e00865e6d1ae413c21adfa6bdf2d9
+size 172063

neuronxcc-2.16.345.0+69131dd3/MODULE_16879611434903391361+3cc9a3cb/compile_flags.json

@@ -0,0 +1 @@
+["--target=trn1", "--model-type=transformer"]

neuronxcc-2.16.345.0+69131dd3/MODULE_16879611434903391361+3cc9a3cb/model.hlo_module.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d926df6b0d1e6fe81fb7a4c406a3c7d648516857973887e201e76bad4c8bebb
+size 172433