End of training

last-checkpoint/config.json

@@ -1,54 +0,0 @@
-{
-  "_name_or_path": "EleutherAI/gpt-neo-125M",
-  "activation_function": "gelu_new",
-  "architectures": [
-    "GPTNeoForCausalLM"
-  ],
-  "attention_dropout": 0,
-  "attention_layers": [
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local",
-    "global",
-    "local"
-  ],
-  "attention_types": [
-    [
-      [
-        "global",
-        "local"
-      ],
-      6
-    ]
-  ],
-  "bos_token_id": 50256,
-  "embed_dropout": 0,
-  "eos_token_id": 50256,
-  "gradient_checkpointing": false,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": null,
-  "layer_norm_epsilon": 1e-05,
-  "max_position_embeddings": 2048,
-  "model_type": "gpt_neo",
-  "num_heads": 12,
-  "num_layers": 12,
-  "resid_dropout": 0,
-  "summary_activation": null,
-  "summary_first_dropout": 0.1,
-  "summary_proj_to_labels": true,
-  "summary_type": "cls_index",
-  "summary_use_proj": true,
-  "torch_dtype": "float32",
-  "transformers_version": "4.22.2",
-  "use_cache": true,
-  "vocab_size": 50257,
-  "window_size": 256
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:316aa9628e5df110704448178f52ca291bf33412db0a8c43a32ba3fcc767272a
-size 1001681601

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2ce969201a5530585c7cc2add3f6cd10ed5111cf369b38f7b864f201e3f7adac
-size 551185105

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:84838ccd45951bbe1e5f964cffc9f60572ee4f5e111f59de86b1a56f3d7a6bd8
-size 14503

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:76a745544100357029ff333b51546a03f40831009ab368d3991b4bf0b60ed69c
-size 559

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f1e2d8d0c9cbd38f26c8c49786d7fe0ec44bf98d82863f0308efe6f4d75d9785
-size 623

last-checkpoint/trainer_state.json

@@ -1,22 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.006782603977318972,
-  "global_step": 500,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.01,
-      "learning_rate": 4.9104720564297346e-05,
-      "loss": 0.2225,
-      "step": 500
-    }
-  ],
-  "max_steps": 221154,
-  "num_train_epochs": 3,
-  "total_flos": 522414194688000.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:2f2a12baa40a1005edc658f4a0ccce80b0f6ecaf6163a7adf3b407bb690d71bf
-size 3503

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce969201a5530585c7cc2add3f6cd10ed5111cf369b38f7b864f201e3f7adac
+oid sha256:5d5cb3b36763060ba9aad79ca85644fea4e0883d7cef6ca7dc401cf20cbd78f9
 size 551185105

runs/Oct04_18-06-35_5a47983d32da/events.out.tfevents.1664906817.5a47983d32da.68.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9993ed3697103058940f6388de28dfe4fa183898e7660ba424b459112b1a7c4f
-size 16829
+oid sha256:c4040b2dc66fdfb01c77cd5761ce791793cc48cae2bca93e40159c3a90afd22f
+size 19184