Training in progress, step 1000, checkpoint

checkpoint-1000/config.json

@@ -0,0 +1,25 @@
+{
+  "annotation_transformer": true,
+  "architectures": [
+    "CAMP"
+  ],
+  "diff": false,
+  "dropout": 0.05,
+  "hidden_dim": 640,
+  "input_dim": 384,
+  "intermediate_dim": 2560,
+  "kernel_size": 11,
+  "latent": false,
+  "mlm": false,
+  "mnr": false,
+  "model_type": "CAMP",
+  "nhead": 8,
+  "nlp_path": "lhallee/annotation_transformer_uniref90",
+  "num_hidden_layers": 1,
+  "out_dim": 512,
+  "plm_path": "facebook/esm2_t33_650m_UR50D",
+  "pooling": "avg",
+  "token": null,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2"
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47c782ddb5211942ef6df6de13e3c6b988433b0231587f3c8ea0412c029a303e
+size 1384137156

checkpoint-1000/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.06205013651030032,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0062050136510300325,
+      "grad_norm": 101.88961029052734,
+      "learning_rate": 0.0001,
+      "loss": 4.5088,
+      "step": 100
+    },
+    {
+      "epoch": 0.012410027302060065,
+      "grad_norm": 99.7363510131836,
+      "learning_rate": 9.999038127056248e-05,
+      "loss": 0.8644,
+      "step": 200
+    },
+    {
+      "epoch": 0.018615040953090096,
+      "grad_norm": 59.41786575317383,
+      "learning_rate": 9.996152878304816e-05,
+      "loss": 0.7189,
+      "step": 300
+    },
+    {
+      "epoch": 0.02482005460412013,
+      "grad_norm": 61.05416488647461,
+      "learning_rate": 9.991345363842789e-05,
+      "loss": 0.6253,
+      "step": 400
+    },
+    {
+      "epoch": 0.03102506825515016,
+      "grad_norm": 53.87808609008789,
+      "learning_rate": 9.9846174333574e-05,
+      "loss": 0.5863,
+      "step": 500
+    },
+    {
+      "epoch": 0.03723008190618019,
+      "grad_norm": 48.58293914794922,
+      "learning_rate": 9.975971675414371e-05,
+      "loss": 0.5555,
+      "step": 600
+    },
+    {
+      "epoch": 0.04343509555721023,
+      "grad_norm": 42.353153228759766,
+      "learning_rate": 9.965411416461959e-05,
+      "loss": 0.5566,
+      "step": 700
+    },
+    {
+      "epoch": 0.04964010920824026,
+      "grad_norm": 46.06748580932617,
+      "learning_rate": 9.952940719551112e-05,
+      "loss": 0.5425,
+      "step": 800
+    },
+    {
+      "epoch": 0.05584512285927029,
+      "grad_norm": 46.486637115478516,
+      "learning_rate": 9.938564382772205e-05,
+      "loss": 0.5004,
+      "step": 900
+    },
+    {
+      "epoch": 0.06205013651030032,
+      "grad_norm": 43.99421691894531,
+      "learning_rate": 9.922287937408994e-05,
+      "loss": 0.4722,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06205013651030032,
+      "eval_avg_non_pair_similarity": -0.00011276310920446573,
+      "eval_avg_pair_similarity": 0.0020758428336121143,
+      "eval_loss": 0.44835320115089417,
+      "eval_runtime": 52.6112,
+      "eval_samples_per_second": 9.504,
+      "eval_similarity_ratio": -18.408882552609725,
+      "eval_steps_per_second": 0.304,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 16116,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45f6f301aa93fd04cb88245f1be6b5d49fae9be8dd0abe1d8a346a6aadd21663
+size 5112