Upload 10 files

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "esm2_t33_650M_UR50D",
+  "architectures": [
+    "EsmForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 5120,
+  "is_folding_model": false,
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 33,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c041a3728a9d155667d5b6d5b45d09a2f60c5f37fe54323393dd1af966f3d1f
+size 2609498088

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aef653fd544db72d7644d4c30e34ed73dad32c3cd65b6bad8700767996b8ab6b
+size 5208796146

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d30a5019c46f6a0a26e117eb0ea3ba4f44aa65ffff07bd5dceb7b0523466ff5
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f8e7df58a699bf9bf218a2744612343802b99cce412fc8c64899bf08d47280
+size 1064

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<cls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<cls>",
+  "eos_token": "<eos>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "EsmTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1435383,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9999979099654935,
+      "grad_norm": 0.4689459204673767,
+      "learning_rate": 3.333336816724178e-05,
+      "loss": 0.429,
+      "step": 478460
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.35967788100242615,
+      "eval_runtime": 475.8634,
+      "eval_samples_per_second": 105.072,
+      "eval_steps_per_second": 6.567,
+      "step": 478461
+    },
+    {
+      "epoch": 1.999995819930987,
+      "grad_norm": 0.761919379234314,
+      "learning_rate": 1.666673633448355e-05,
+      "loss": 0.3379,
+      "step": 956920
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.32030364871025085,
+      "eval_runtime": 473.1594,
+      "eval_samples_per_second": 105.673,
+      "eval_steps_per_second": 6.605,
+      "step": 956922
+    },
+    {
+      "epoch": 2.9999937298964805,
+      "grad_norm": 0.48390546441078186,
+      "learning_rate": 1.0450172532348509e-10,
+      "loss": 0.3053,
+      "step": 1435380
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2977253198623657,
+      "eval_runtime": 471.5778,
+      "eval_samples_per_second": 106.027,
+      "eval_steps_per_second": 6.627,
+      "step": 1435383
+    }
+  ],
+  "logging_steps": 478460,
+  "max_steps": 1435383,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 1.5249976131388174e+19,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b8f599e3c38da4d02f33185b84f88947b66199e0a6b53f3a579887ae9255001
+size 4920

vocab.txt

@@ -0,0 +1,33 @@
+<cls>
+<pad>
+<eos>
+<unk>
+L
+A
+G
+V
+S
+E
+R
+T
+I
+D
+P
+K
+Q
+N
+F
+Y
+M
+H
+W
+C
+X
+B
+U
+Z
+O
+.
+-
+<null_1>
+<mask>