Training in progress, step 500, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "facebook/esm2_t12_35M_UR50D",
+  "architectures": [
+    "EsmForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.01,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.01,
+  "hidden_size": 480,
+  "initializer_range": 0.02,
+  "intermediate_size": 1920,
+  "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": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.1",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517b7a2aaaea838cb419a14f1b515d8b5cf1ed9fde5bf86d6fb0c135a3fcfda0
+size 136000488

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ee99e2558f0635b821e5f0474f85cc00393edabfccf6bb4110621fc826ded64
+size 268176506

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee83cb0b382b6f7013b8e905a6b67eda9661bf7137607a26a8510616916ff33d
+size 14512

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cf5a1d1bb94d2ab14807987fb6e7f78b0a603abb98dc702e91c99346c1c8745
+size 14512

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0943229aeeb46312acb472f3efe5d902161c82efbe50119969078cb1567edce6
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.12421588721197441,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.958592132505176e-05,
+      "loss": 1.3838,
+      "step": 500
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.3269665241241455,
+      "eval_runtime": 63.2116,
+      "eval_samples_per_second": 255.634,
+      "eval_steps_per_second": 15.978,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 120750,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 500,
+  "total_flos": 5001938240274432.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5da2bb0b25e23c2716dc60237e84cea2973b9882dcc6ff60ec43fea4464a78
+size 4728