Upload 8 files

config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "CodeGenForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "codegen",
+  "n_ctx": 2048,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 20,
+  "n_positions": 2048,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 32,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.4",
+  "use_cache": true,
+  "vocab_size": 51200
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 50256,
+  "transformers_version": "4.55.4"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5af9e810fe00bdd169fca4fe2a4cd03eb57d28e52a759e8b1cf8b20af7f5569
+size 621314867

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21ac788626a53d4c5d331c9d5cdab447e0c773fd0e9d8d95bbd942c5fbb018c5
+size 1426902263

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db1798478f6a6f7bda5704bc8d4a8ec83ed8bd0c9d780f3378b30ba41401878
+size 14455

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f7c991de3a3c468d9acec89cabc1677735d1ba747344862f4751a9438d6c48
+size 1465

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 50.0,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.34349560737609863,
+      "learning_rate": 0.00047,
+      "loss": 1.5925,
+      "step": 10
+    },
+    {
+      "epoch": 6.8,
+      "grad_norm": 0.007123686373233795,
+      "learning_rate": 0.00043666666666666664,
+      "loss": 0.0005,
+      "step": 20
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.0007117482600733638,
+      "learning_rate": 0.00040333333333333334,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 13.4,
+      "grad_norm": 0.00027794114430435,
+      "learning_rate": 0.00037,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 16.8,
+      "grad_norm": 0.00013230700278654695,
+      "learning_rate": 0.0003366666666666667,
+      "loss": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 9.377845708513632e-05,
+      "learning_rate": 0.00030333333333333335,
+      "loss": 0.0,
+      "step": 60
+    },
+    {
+      "epoch": 23.4,
+      "grad_norm": 7.737267878837883e-05,
+      "learning_rate": 0.00027,
+      "loss": 0.0,
+      "step": 70
+    },
+    {
+      "epoch": 26.8,
+      "grad_norm": 6.79552395013161e-05,
+      "learning_rate": 0.00023666666666666668,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 30.0,
+      "grad_norm": 6.188424595165998e-05,
+      "learning_rate": 0.00020333333333333333,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 33.4,
+      "grad_norm": 5.752248034696095e-05,
+      "learning_rate": 0.00017,
+      "loss": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 36.8,
+      "grad_norm": 5.435854473034851e-05,
+      "learning_rate": 0.00013666666666666666,
+      "loss": 0.0,
+      "step": 110
+    },
+    {
+      "epoch": 40.0,
+      "grad_norm": 5.203780528972857e-05,
+      "learning_rate": 0.00010333333333333333,
+      "loss": 0.0,
+      "step": 120
+    },
+    {
+      "epoch": 43.4,
+      "grad_norm": 5.0433976866770536e-05,
+      "learning_rate": 7.000000000000001e-05,
+      "loss": 0.0,
+      "step": 130
+    },
+    {
+      "epoch": 46.8,
+      "grad_norm": 4.946757690049708e-05,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.0,
+      "step": 140
+    },
+    {
+      "epoch": 50.0,
+      "grad_norm": 4.907431866740808e-05,
+      "learning_rate": 3.3333333333333337e-06,
+      "loss": 0.0,
+      "step": 150
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 150,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 50,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 467379683328000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d11f9297b35a7a681108f1c001fb2043dd65cd6a0feb223f6b6f1a71d4ec13
+size 5777