Add files using upload-large-folder tool

dedup/110e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d65ed930a7109bfa169be3cc33863769a7e8a63689e38807bb3a086d233629c1
+size 995642298

dedup/20e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:927c3c77d1de823aa9b77ae7001d0ab38b9c6867ee7b81230a7be8dfe9741b3e
+size 995642298

dedup/20e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c167fe75aba930830023ceedb0d2ba686bc6b5ccb4d855de597b625145143743
+size 995642298

dedup/20e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5692e222f0463a2593f429e0d2cf72484bcb66bff53710cf85dad4c2e31d32ec
+size 995642298

dedup/30e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaeffcac5cd8defa800dc937502af5951a4558d59d2ca042d871c7fb003fb1cc
+size 995642298

dedup/30e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a73dd627d6249cd2f7a27829d9e323aaa8785e1c8b024a2611ff54ff7724271e
+size 995642298

dedup/30e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:077f9d95c04afe8fc16cdcc008fb78e1d02d12e1ad17e43d3fda8955adebfcdf
+size 497774208

dedup/30e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f6a7eaffef6f3e926e763920925573f3343a97ffeaf74a3f25cbee8fe49645
+size 995642298

dedup/30e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/40e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab9f8a455e2b0601298e3e56586718020942a33992bbff1852ae8c0ecd89e68b
+size 497774208

dedup/40e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c91d205b26150d2aa1d54dea86e520828902f959e2f7b16939c1cbfb8849f09
+size 995642298

dedup/40e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a25c92a4e05989bc7e3476b7976ee0a54b9aee3e765f5f06e9b476a5436de1a8
+size 14244

dedup/40e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16279b3343ecb86d7b8753f8f78d91d4239add7871a4f782ad6b5d0e5ca914ea
+size 1064

dedup/40e1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/40e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b124b145299fe8eaae3473ed90d3abce9916e77772bdd22f01611d22257ce89b
+size 497774208

dedup/40e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc6cac41200cab5d61169bccdb8dbf98a3a84f6302acd44d57119e0d3f1f895f
+size 995642298

dedup/40e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807856c679d5d66dcec09da4bd968668501f8daf4810b024fb807eb18965059f
+size 14244

dedup/40e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd92c180bf9b20c88d63bf56aebb1f46b6197ff6f587917d1c83f5412d187cd7
+size 1064

dedup/40e2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/40e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e699b44ba5c438bfd5afa51dcce95d4491edc838d907bcb475c957a7675ccd2b
+size 497774208

dedup/40e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5215b5a278066036a8cf93b2a0aa211c186895549c35f3e734d0c3f7be3ccbb7
+size 995642298

dedup/40e3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a45de993ff4ec6e8c925af20bda39bc7c1dcd2fe5b0a97ed046036d20aec143b
+size 14244

dedup/40e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d5fb0e8f76a735327139fdd52c3c8e1162258d247e3b4a4316eba0a30ac4877
+size 1064

dedup/40e3/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/50e1/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

dedup/50e1/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

dedup/50e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3700629197e59c638fc67125d3829d8d10a2b23af7ebf376f1ae0c3c2dfea8a2
+size 497774208

dedup/50e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e32337384e215d2d1b4caf9ecafd109fb8b78c6473e1dfe652270d2f093e52b
+size 14244

dedup/50e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eec75afe034fbecd1316d811879b3fb7c9c026c439dfd70ae7c6ee7ba3d36e8
+size 1064

dedup/50e1/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

dedup/50e1/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

dedup/50e1/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4997635188396658,
+  "eval_steps": 500,
+  "global_step": 6340,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03941352672237112,
+      "grad_norm": 9.434146881103516,
+      "learning_rate": 1.9840000000000003e-05,
+      "loss": 3.5972,
+      "step": 500
+    },
+    {
+      "epoch": 0.07882705344474224,
+      "grad_norm": 8.484919548034668,
+      "learning_rate": 1.973587517972203e-05,
+      "loss": 3.0731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11824058016711335,
+      "grad_norm": 8.578750610351562,
+      "learning_rate": 1.9469620320570853e-05,
+      "loss": 2.9624,
+      "step": 1500
+    },
+    {
+      "epoch": 0.15765410688948447,
+      "grad_norm": 6.2477827072143555,
+      "learning_rate": 1.920336546141967e-05,
+      "loss": 2.8351,
+      "step": 2000
+    },
+    {
+      "epoch": 0.19706763361185559,
+      "grad_norm": 6.6669602394104,
+      "learning_rate": 1.8937110602268492e-05,
+      "loss": 2.817,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2364811603342267,
+      "grad_norm": 4.857083797454834,
+      "learning_rate": 1.8670855743117314e-05,
+      "loss": 2.7781,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2758946870565978,
+      "grad_norm": 5.961228847503662,
+      "learning_rate": 1.8404600883966135e-05,
+      "loss": 2.7681,
+      "step": 3500
+    },
+    {
+      "epoch": 0.31530821377896895,
+      "grad_norm": 3.896094560623169,
+      "learning_rate": 1.8138346024814953e-05,
+      "loss": 2.6833,
+      "step": 4000
+    },
+    {
+      "epoch": 0.35472174050134003,
+      "grad_norm": 4.19826078414917,
+      "learning_rate": 1.7872091165663774e-05,
+      "loss": 2.7317,
+      "step": 4500
+    },
+    {
+      "epoch": 0.39413526722371117,
+      "grad_norm": 4.363683223724365,
+      "learning_rate": 1.7605836306512596e-05,
+      "loss": 2.6456,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4335487939460823,
+      "grad_norm": 4.608914852142334,
+      "learning_rate": 1.7339581447361414e-05,
+      "loss": 2.6575,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4729623206684534,
+      "grad_norm": 5.031886577606201,
+      "learning_rate": 1.707332658821024e-05,
+      "loss": 2.6423,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 38058,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1268,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1656591482880000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

dedup/50e1/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/50e2/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

dedup/50e2/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.46.3"
+}

dedup/50e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f794e43fd171e67a36ebcc83718e62b54b2b6656758ae28f995a4105751e7988
+size 497774208

dedup/50e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2689ab206a82db62279594f16b10bb0bdc4c8d4c61896ad408ae60856958089
+size 14244

dedup/50e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991ec17df4c4ea8f0fa0b7fd0395f896493164c82e2ee5e70955a5e9b1c4b9df
+size 1064

dedup/50e2/special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

dedup/50e2/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "return_tensors": "pt",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

dedup/50e2/trainer_state.json

@@ -0,0 +1,299 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4992905565189973,
+  "eval_steps": 500,
+  "global_step": 19020,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03941352672237112,
+      "grad_norm": 9.434146881103516,
+      "learning_rate": 1.9840000000000003e-05,
+      "loss": 3.5972,
+      "step": 500
+    },
+    {
+      "epoch": 0.07882705344474224,
+      "grad_norm": 8.484919548034668,
+      "learning_rate": 1.973587517972203e-05,
+      "loss": 3.0731,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11824058016711335,
+      "grad_norm": 8.578750610351562,
+      "learning_rate": 1.9469620320570853e-05,
+      "loss": 2.9624,
+      "step": 1500
+    },
+    {
+      "epoch": 0.15765410688948447,
+      "grad_norm": 6.2477827072143555,
+      "learning_rate": 1.920336546141967e-05,
+      "loss": 2.8351,
+      "step": 2000
+    },
+    {
+      "epoch": 0.19706763361185559,
+      "grad_norm": 6.6669602394104,
+      "learning_rate": 1.8937110602268492e-05,
+      "loss": 2.817,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2364811603342267,
+      "grad_norm": 4.857083797454834,
+      "learning_rate": 1.8670855743117314e-05,
+      "loss": 2.7781,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2758946870565978,
+      "grad_norm": 5.961228847503662,
+      "learning_rate": 1.8404600883966135e-05,
+      "loss": 2.7681,
+      "step": 3500
+    },
+    {
+      "epoch": 0.31530821377896895,
+      "grad_norm": 3.896094560623169,
+      "learning_rate": 1.8138346024814953e-05,
+      "loss": 2.6833,
+      "step": 4000
+    },
+    {
+      "epoch": 0.35472174050134003,
+      "grad_norm": 4.19826078414917,
+      "learning_rate": 1.7872091165663774e-05,
+      "loss": 2.7317,
+      "step": 4500
+    },
+    {
+      "epoch": 0.39413526722371117,
+      "grad_norm": 4.363683223724365,
+      "learning_rate": 1.7605836306512596e-05,
+      "loss": 2.6456,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4335487939460823,
+      "grad_norm": 4.608914852142334,
+      "learning_rate": 1.7339581447361414e-05,
+      "loss": 2.6575,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4729623206684534,
+      "grad_norm": 5.031886577606201,
+      "learning_rate": 1.707332658821024e-05,
+      "loss": 2.6423,
+      "step": 6000
+    },
+    {
+      "epoch": 0.5123758473908245,
+      "grad_norm": 4.503154277801514,
+      "learning_rate": 1.6807071729059057e-05,
+      "loss": 2.6062,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5517893741131956,
+      "grad_norm": 3.5765438079833984,
+      "learning_rate": 1.654134937962618e-05,
+      "loss": 2.6487,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5912029008355668,
+      "grad_norm": 3.3804619312286377,
+      "learning_rate": 1.6275094520475e-05,
+      "loss": 2.6378,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6306164275579379,
+      "grad_norm": 4.173604965209961,
+      "learning_rate": 1.600883966132382e-05,
+      "loss": 2.5821,
+      "step": 8000
+    },
+    {
+      "epoch": 0.670029954280309,
+      "grad_norm": 3.0175459384918213,
+      "learning_rate": 1.5743117311890943e-05,
+      "loss": 2.5756,
+      "step": 8500
+    },
+    {
+      "epoch": 0.7094434810026801,
+      "grad_norm": 4.371723651885986,
+      "learning_rate": 1.5476862452739764e-05,
+      "loss": 2.5365,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7488570077250513,
+      "grad_norm": 3.797525644302368,
+      "learning_rate": 1.5210607593588584e-05,
+      "loss": 2.5734,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7882705344474223,
+      "grad_norm": 2.7907519340515137,
+      "learning_rate": 1.4944352734437404e-05,
+      "loss": 2.5801,
+      "step": 10000
+    },
+    {
+      "epoch": 0.8276840611697934,
+      "grad_norm": 3.6856374740600586,
+      "learning_rate": 1.4678097875286225e-05,
+      "loss": 2.5198,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8670975878921646,
+      "grad_norm": 3.692336320877075,
+      "learning_rate": 1.4411843016135045e-05,
+      "loss": 2.5294,
+      "step": 11000
+    },
+    {
+      "epoch": 0.9065111146145357,
+      "grad_norm": 3.4679853916168213,
+      "learning_rate": 1.4145588156983866e-05,
+      "loss": 2.5818,
+      "step": 11500
+    },
+    {
+      "epoch": 0.9459246413369068,
+      "grad_norm": 3.318463087081909,
+      "learning_rate": 1.3879333297832686e-05,
+      "loss": 2.5145,
+      "step": 12000
+    },
+    {
+      "epoch": 0.985338168059278,
+      "grad_norm": 3.9721946716308594,
+      "learning_rate": 1.361361094839981e-05,
+      "loss": 2.5793,
+      "step": 12500
+    },
+    {
+      "epoch": 1.024751694781649,
+      "grad_norm": 4.008026123046875,
+      "learning_rate": 1.3347356089248631e-05,
+      "loss": 2.4809,
+      "step": 13000
+    },
+    {
+      "epoch": 1.0641652215040203,
+      "grad_norm": 2.818800926208496,
+      "learning_rate": 1.308110123009745e-05,
+      "loss": 2.4303,
+      "step": 13500
+    },
+    {
+      "epoch": 1.1035787482263912,
+      "grad_norm": 2.989525556564331,
+      "learning_rate": 1.281484637094627e-05,
+      "loss": 2.4062,
+      "step": 14000
+    },
+    {
+      "epoch": 1.1429922749487624,
+      "grad_norm": 3.570216178894043,
+      "learning_rate": 1.2548591511795092e-05,
+      "loss": 2.4559,
+      "step": 14500
+    },
+    {
+      "epoch": 1.1824058016711336,
+      "grad_norm": 3.4571452140808105,
+      "learning_rate": 1.2282336652643912e-05,
+      "loss": 2.4451,
+      "step": 15000
+    },
+    {
+      "epoch": 1.2218193283935046,
+      "grad_norm": 3.5280067920684814,
+      "learning_rate": 1.2016081793492733e-05,
+      "loss": 2.4488,
+      "step": 15500
+    },
+    {
+      "epoch": 1.2612328551158758,
+      "grad_norm": 3.444591999053955,
+      "learning_rate": 1.1749826934341553e-05,
+      "loss": 2.4949,
+      "step": 16000
+    },
+    {
+      "epoch": 1.3006463818382468,
+      "grad_norm": 3.746109962463379,
+      "learning_rate": 1.1484104584908674e-05,
+      "loss": 2.4157,
+      "step": 16500
+    },
+    {
+      "epoch": 1.340059908560618,
+      "grad_norm": 3.2765095233917236,
+      "learning_rate": 1.1217849725757498e-05,
+      "loss": 2.442,
+      "step": 17000
+    },
+    {
+      "epoch": 1.3794734352829892,
+      "grad_norm": 3.1070899963378906,
+      "learning_rate": 1.0951594866606317e-05,
+      "loss": 2.4619,
+      "step": 17500
+    },
+    {
+      "epoch": 1.4188869620053604,
+      "grad_norm": 3.6844067573547363,
+      "learning_rate": 1.0685340007455135e-05,
+      "loss": 2.4091,
+      "step": 18000
+    },
+    {
+      "epoch": 1.4583004887277313,
+      "grad_norm": 3.408829927444458,
+      "learning_rate": 1.0419085148303958e-05,
+      "loss": 2.4427,
+      "step": 18500
+    },
+    {
+      "epoch": 1.4977140154501025,
+      "grad_norm": 3.1087682247161865,
+      "learning_rate": 1.0152830289152778e-05,
+      "loss": 2.4273,
+      "step": 19000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 38058,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1268,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4969643802624000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

dedup/50e2/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9754fc64c1191d5171e19a3aeb0f1c6bd08598f16d128c415805e45786e74d7
+size 5240

dedup/50e3/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2",
+  "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": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}