Upload 8 files

config.json

@@ -1,39 +1,39 @@
-{
-  "_name_or_path": "cuba6112/orion",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPT2LMHeadModel"
-  ],
-  "attn_pdrop": 0.1,
-  "bos_token_id": 50256,
-  "embd_pdrop": 0.1,
-  "eos_token_id": 50256,
-  "initializer_range": 0.02,
-  "layer_norm_epsilon": 1e-05,
-  "model_type": "gpt2",
-  "n_ctx": 1024,
-  "n_embd": 768,
-  "n_head": 12,
-  "n_inner": null,
-  "n_layer": 12,
-  "n_positions": 1024,
-  "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,
-  "task_specific_params": {
-    "text-generation": {
-      "do_sample": true,
-      "max_length": 50
-    }
-  },
-  "torch_dtype": "float32",
-  "transformers_version": "4.41.2",
-  "use_cache": true,
-  "vocab_size": 50257
-}
+{
+  "_name_or_path": "cuba6112/orion",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "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,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.3",
+  "use_cache": false,
+  "vocab_size": 50257
+}

generation_config.json

@@ -1,6 +1,6 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 50256,
-  "eos_token_id": 50256,
-  "transformers_version": "4.41.2"
-}
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.42.3"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cf3dd926baddf275f3dee77a0ade1195e86a7048d07a82a5c810ac2eb21b57e
+oid sha256:6f1b4b49904bd699ce93e72f5b945fb13676567e97edd23aa44f2192d37a9128
 size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee568c18000b7f7e4d68a3b949530c06f3f87b5ad9e13ab866fcd923d5498a51
+size 995641861

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4889454ecb083d29ee0f0aef373df0a03de5640b2e6e0c3f3cec90171b704454
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0ec98e2a6c718c9639ab63b74b63911306853723b3ecc13f83d842f99d6f23
+size 627

trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": 8.097002084978036e-05,
+  "best_model_checkpoint": "./orion-finetuned-squad\\checkpoint-500",
+  "epoch": 1.6,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 13.155216217041016,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 7.6002,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 9.965179443359375,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 6.7941,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.015015125274658,
+      "learning_rate": 3e-06,
+      "loss": 5.5048,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.8797528743743896,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 4.688,
+      "step": 200
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 2.3939545154571533,
+      "learning_rate": 5e-06,
+      "loss": 4.2605,
+      "step": 250
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 1.693825364112854,
+      "learning_rate": 6e-06,
+      "loss": 4.0418,
+      "step": 300
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 1.439347267150879,
+      "learning_rate": 7e-06,
+      "loss": 3.9253,
+      "step": 350
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.3246393203735352,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.8597,
+      "step": 400
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 1.3454995155334473,
+      "learning_rate": 9e-06,
+      "loss": 3.813,
+      "step": 450
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 1.3214969635009766,
+      "learning_rate": 1e-05,
+      "loss": 3.774,
+      "step": 500
+    },
+    {
+      "epoch": 1.6,
+      "eval_accuracy": 8.097002084978036e-05,
+      "eval_loss": 3.5968761444091797,
+      "eval_perplexity": 28132.972634939182,
+      "eval_runtime": 4090.3007,
+      "eval_samples_per_second": 0.098,
+      "eval_steps_per_second": 0.098,
+      "step": 500
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 936,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1045168128000000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:563bdb3ca14c85894d15e5f828e1a663ca673eee2aa2e1700daed3a3dcb4e694
-size 5112
+oid sha256:6aaf4b8795de1182633f1339fcbb834c703fa75f0e49c23ac67d8e1e719bbe6b
+size 4603