Add files using upload-large-folder tool

dedup/50e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:812a753ba6d9825da33e75c6c05c6ad56c8556a8e2225c799e56cfa96426208a
+size 995642298

dedup/50e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a3cb39260d4490b138c2f573409c196f29953334440dd98b97c3c85bd2bad34
+size 995642298

dedup/50e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624a0d4939aca4f96eb2a41eebbb88bcebf58ac9bd87a3c98667fe4c699c3a94
+size 995642298

dedup/60e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77d3fe35f23eb5e8ce726515a892db776453fe1c6e7eb76a7e4f55cbc919d6e9
+size 497774208

dedup/60e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881d4e4daf12cb60ce10cd2144f6680c958eb1bc2bb86c1a0a93d943c3f79cf2
+size 995642298

dedup/60e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84d69762faa3dba53eb7d2afdbd292993013b315b66673790caa6dba2574a4ed
+size 497774208

dedup/60e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7929173db4c979c4d267f59efc989b2f327a320a1f7e44ffcb853e3d740dc5ea
+size 995642298

dedup/60e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cad32f325728a297a27c12242c302060f74792b36e887ca1408e25e6e7db65
+size 497774208

dedup/60e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03608d4e11223350b77c5960dec381ac5b797a01138558c8b9a5553fe2d612d9
+size 995642298

dedup/70e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94932e9328e336b5856934c5610cefed187116426a1b77638753d493f7d5ff33
+size 497774208

dedup/70e1/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc17d9250d6593a64b7fc8077ca334224116deab81cf25ba890d2b008f159a0
+size 995642298

dedup/70e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b7ed1508b3d0655f55f899b34a90c59300ced183573603635e0492a791d896
+size 14244

dedup/70e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4d574555efe2c2c8df4972b8f5d111d0cab7559abafad7cb0c9d7dfeb6c9012
+size 1064

dedup/70e1/training_args.bin

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

dedup/70e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de099f79e6d837da5c41d1150814714e1e1fe73cebe11922da6f527afb054965
+size 497774208

dedup/70e2/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02fcf78839b920feb3fb33d01c9405dc2517c0f8425eba402c2c34af56181575
+size 995642298

dedup/70e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24f281fa12b33d920c1fcc63299f6bfcd3ae876a13d6597809308c0e75f7de69
+size 14244

dedup/70e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39111cb1afec59874f0a0f63e2d6385eabd217762a945eb1d1404640d31974c1
+size 1064

dedup/70e2/training_args.bin

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

dedup/70e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f9bda9e75cecc4c699cb79a91da485d320288b6065ee0a42edf7c9919532ff
+size 497774208

dedup/70e3/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47d45dd416c82e630be2ecb6359610c3e9dfd65feb90b018273b2f27ede345fe
+size 995642298

dedup/70e3/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3062888a9e963646858817dea6139ed0fc914e83b144f69d78abb75b7a4ed1d
+size 14244

dedup/70e3/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:602bf433bfb82810befd66dc7d227e4a0bd443342af755bbd3dc89a4c84cca18
+size 1064

dedup/70e3/training_args.bin

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

dedup/80e1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb0a6e0e86f5475c6d3b9d0eb00b30058d129aace9b8b8cf41a5c3ada135a48
+size 497774208

dedup/80e1/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f0915b4cc37c59ec6560211091a4190b09ae1b0056e1e0e37a17a29d5c33e0c
+size 14244

dedup/80e1/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbda21e2f15b59f8fafd93ef9a61b289c1395e7e65a8d045c458d0a1a14fb4d0
+size 1064

dedup/80e1/special_tokens_map.json

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

dedup/80e1/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/80e1/trainer_state.json

@@ -0,0 +1,173 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7996216301434652,
+  "eval_steps": 500,
+  "global_step": 10144,
+  "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
+    }
+  ],
+  "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": 2650546372608000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

dedup/80e1/training_args.bin

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

dedup/80e2/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/80e2/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/80e2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c9044a2bab5d5db7700857cb4bef468ef0d5b0a1407d16e475084e299399f1
+size 497774208

dedup/80e2/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8023f447d7010c39574a0ebfc8e36bb700dabfb204946b70ea31230bb64a81cb
+size 14244

dedup/80e2/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02473c898dd302065466f4f1da2f41173a9502151c0b826f2457de39ad16f12d
+size 1064

dedup/80e2/special_tokens_map.json

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

dedup/80e2/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/80e2/trainer_state.json

@@ -0,0 +1,348 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7991486678227968,
+  "eval_steps": 500,
+  "global_step": 22824,
+  "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
+    },
+    {
+      "epoch": 1.5371275421724735,
+      "grad_norm": 3.229764223098755,
+      "learning_rate": 9.886575430001598e-06,
+      "loss": 2.4041,
+      "step": 19500
+    },
+    {
+      "epoch": 1.5765410688948447,
+      "grad_norm": 2.389808416366577,
+      "learning_rate": 9.620853080568721e-06,
+      "loss": 2.4336,
+      "step": 20000
+    },
+    {
+      "epoch": 1.6159545956172159,
+      "grad_norm": 3.6460657119750977,
+      "learning_rate": 9.354598221417541e-06,
+      "loss": 2.4151,
+      "step": 20500
+    },
+    {
+      "epoch": 1.655368122339587,
+      "grad_norm": 3.6286749839782715,
+      "learning_rate": 9.088343362266362e-06,
+      "loss": 2.4395,
+      "step": 21000
+    },
+    {
+      "epoch": 1.694781649061958,
+      "grad_norm": 3.662971258163452,
+      "learning_rate": 8.822088503115182e-06,
+      "loss": 2.4143,
+      "step": 21500
+    },
+    {
+      "epoch": 1.734195175784329,
+      "grad_norm": 3.5085411071777344,
+      "learning_rate": 8.555833643964004e-06,
+      "loss": 2.4443,
+      "step": 22000
+    },
+    {
+      "epoch": 1.7736087025067002,
+      "grad_norm": 2.7148663997650146,
+      "learning_rate": 8.289578784812823e-06,
+      "loss": 2.3879,
+      "step": 22500
+    }
+  ],
+  "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": 5963598692352000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

dedup/80e2/training_args.bin

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

dedup/80e3/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/80e3/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/80e3/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16c299f8afb3d6fd20c4e8482394de91d21ae3cbadd5940f59d345a89a7a91bb
+size 497774208