Upload 7 files

config.json

@@ -1,23 +1,23 @@
 {
-  "model_type": "gpt2",
-  "architectures": ["GPT2LMHeadModel"],
-  "tokenizer_config": {
-    "bos_token_id": 50256,
-    "eos_token_id": 50256,
-    "n_positions": 2048
-  },
+  "_name_or_path": "ayjays132/Phillnet2",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
   "config": {
     "activation_function": "gelu_new",
+    "attn_pdrop": 0.1,
+    "embd_pdrop": 0.1,
+    "initializer_range": 0.02,
+    "layer_norm_epsilon": 1e-05,
     "n_ctx": 2048,
     "n_embd": 2048,
     "n_head": 16,
     "n_layer": 24,
     "n_positions": 2048,
     "n_special": 0,
-    "attn_pdrop": 0.1,
-    "embd_pdrop": 0.1,
-    "initializer_range": 0.02,
-    "layer_norm_epsilon": 1e-05,
     "resid_pdrop": 0.1,
     "summary_activation": null,
     "summary_first_dropout": 0.1,
@@ -25,53 +25,105 @@
     "summary_type": "cls_index",
     "summary_use_proj": true
   },
-  "task_specific_params": {
-    "conversational": {
-      "max_length": 1024,
-      "min_length": 20,
-      "length_penalty": 1.5,
-      "num_beams": 5,
-      "early_stopping": true,
-      "no_repeat_ngram_size": 3,
-      "temperature": 0.7,
-      "top_k": 50,
-      "top_p": 0.9
-    }
-  },
-  "transformers_version": "4.34.0",
-  "language": ["en"],
-  "tags": ["conversational"],
-  "metrics": ["perplexity", "accuracy"],
-  "pipeline_tag": "conversational",
-  "library_name": "transformers",
-  "datasets": ["vicgalle/alpaca-gpt4"],
-  "license": "apache-2.0",
   "custom_params": {
+    "DEFAULT_ADAPTATION_RATE": 0.05,
+    "DEFAULT_MAX_NEURONS": 242798,
+    "actual_vocab_size": 25000,
     "adaptation_rate": 0.05,
+    "complexity_metric": null,
     "desired_improvement_rate": 0.02,
     "ecosystem_dynamics": {
       "environmental_volatility": 0.1,
       "resource_pool": 1
     },
+    "embedding_dim": 2048,
+    "eval_interval": 10,
+    "gamma": 0.99,
     "growth_improvement_threshold": 0.01,
     "hidden_dim": 2048,
-    "initial_neuron_count": 5000,
+    "initial_neuron_count": 105000,
     "innovative_growth_net": {
       "adaptation_rate": 0.05,
       "initial_capacity": 250000,
       "input_size": 2048
     },
-    "input_dimension": 768,
+    "input_dimension": 2048,
+    "learning_rate": 0.001,
     "low_stability_threshold": 0.01,
-    "max_complexity": 10000,
-    "max_neurons": 250000,
-    "max_sequence_length": 1024,
+    "max_complexity": 5000000,
+    "max_neurons": 800000,
+    "max_sequence_length": 2048,
     "min_epochs_before_growth": 5,
     "model_filename": "pytorch_model.bin",
+    "num_classes": 25000,
     "num_embeddings": 25000,
+    "num_heads": 64,
+    "num_words": 25000,
     "pruning_improvement_threshold": 0.005,
+    "sequence_length": 1024,
     "some_adaptation_rate": 0.05,
+    "some_intermediate_size": 2048,
     "stability_threshold": 0.02,
-    "start_token_index": 2
-  }
+    "start_token_index": 2,
+    "update_freq": 100,
+    "vocab_size": 25000,
+    "weight_decay": 0.005
+  },
+  "datasets": [
+    "vicgalle/alpaca-gpt4"
+  ],
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "language": [
+    "en"
+  ],
+  "layer_norm_epsilon": 1e-05,
+  "library_name": "transformers",
+  "license": "apache-2.0",
+  "metrics": [
+    "perplexity",
+    "accuracy"
+  ],
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pipeline_tag": "conversational",
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "tags": [
+    "conversational"
+  ],
+  "task_specific_params": {
+    "conversational": {
+      "early_stopping": true,
+      "length_penalty": 1.5,
+      "max_length": 1024,
+      "min_length": 20,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 5,
+      "temperature": 0.7,
+      "top_k": 50,
+      "top_p": 0.9
+    }
+  },
+  "tokenizer_config": {
+    "bos_token_id": 50256,
+    "eos_token_id": 50256,
+    "n_positions": 2048
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.2",
+  "use_cache": true,
+  "vocab_size": 50257
 }

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.37.2"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f779615d12286a46511e2a045318ec6efc922e969ecdc4be9deb51882ba33ea7
+size 995642298

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4458df18d15a0c76ca43f3bdfe7dffc0fe842fd5b118301979cd74c1fa701768
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b377bcf2fb431adbbcb1481ea1975ebb709f64959b03e92ca011ea3a0e14a18
+size 1064

trainer_state.json

@@ -0,0 +1,141 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0475020475020473,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.8293748293748295e-05,
+      "loss": 4.3223,
+      "step": 500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.658749658749659e-05,
+      "loss": 4.2808,
+      "step": 1000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.4881244881244886e-05,
+      "loss": 4.2576,
+      "step": 1500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 4.317499317499318e-05,
+      "loss": 4.1952,
+      "step": 2000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.146874146874147e-05,
+      "loss": 4.133,
+      "step": 2500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 3.976248976248976e-05,
+      "loss": 4.0789,
+      "step": 3000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.8056238056238055e-05,
+      "loss": 4.0146,
+      "step": 3500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 3.6349986349986354e-05,
+      "loss": 3.9639,
+      "step": 4000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.4643734643734647e-05,
+      "loss": 3.9444,
+      "step": 4500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.293748293748294e-05,
+      "loss": 3.8477,
+      "step": 5000
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 3.123123123123123e-05,
+      "loss": 3.7137,
+      "step": 5500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.952497952497953e-05,
+      "loss": 3.6799,
+      "step": 6000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.781872781872782e-05,
+      "loss": 3.674,
+      "step": 6500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6112476112476115e-05,
+      "loss": 3.6476,
+      "step": 7000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4406224406224407e-05,
+      "loss": 3.6145,
+      "step": 7500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.2699972699972703e-05,
+      "loss": 3.5609,
+      "step": 8000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.0993720993720995e-05,
+      "loss": 3.5179,
+      "step": 8500
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.928746928746929e-05,
+      "loss": 3.5089,
+      "step": 9000
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7581217581217583e-05,
+      "loss": 3.5192,
+      "step": 9500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.5874965874965875e-05,
+      "loss": 3.39,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14652,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "total_flos": 1.0451158695936e+16,
+  "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:d538e97fb781d4d52eb5049837204dc5502fe82b56c0a46d2972d514d5318480
+size 4792