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 sha256:82c59ec2d8158df03dc91fa7bf16e8507d566511b5411f9c67de05e90ccd6e91
+size 136000488

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a884ac11bbb6fd1dc22614df6924f8dd43c3773bcea3ac35a711f03ab60f071f
+size 268170437

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a7b20bb4e542525420e5ea134af9c0d0ac407af2eb17d014634f87b7c9d9ca
+size 13553

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71f795f060986bf4341bea9d8720ae7bfda0098d9ee25a8bcebb898741611d0
+size 627

last-checkpoint/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06210408644888834,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 9.998757918271022e-05,
+      "loss": 1.4897,
+      "step": 100
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.997515836542045e-05,
+      "loss": 1.4177,
+      "step": 200
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.996273754813067e-05,
+      "loss": 1.3882,
+      "step": 300
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.99503167308409e-05,
+      "loss": 1.4079,
+      "step": 400
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 9.993789591355111e-05,
+      "loss": 1.3846,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 1.3667649030685425,
+      "eval_runtime": 632.9435,
+      "eval_samples_per_second": 25.53,
+      "eval_steps_per_second": 0.4,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 805100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "total_flos": 2500969057152000.0,
+  "train_batch_size": 64,
+  "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:b6d59a9adb744b2a139b8a100e72cc86e9fa7d2ee2e2b625692bb081e86590b4
+size 4283