Training in progress, step 1000, checkpoint

checkpoint-1000/config.json

@@ -0,0 +1,25 @@
+{
+  "annotation_transformer": false,
+  "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": "allenai/scibert_scivocab_uncased",
+  "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 sha256:4dc78b7536600829f0fc97871110daee7dda780a9f927d3a0c3cba9d34eef30c
+size 1570427506

checkpoint-1000/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02239842315101017,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002239842315101017,
+      "grad_norm": 71.10852813720703,
+      "learning_rate": 0.0001,
+      "loss": 3.5057,
+      "step": 100
+    },
+    {
+      "epoch": 0.004479684630202034,
+      "grad_norm": 57.756534576416016,
+      "learning_rate": 9.9998756572327e-05,
+      "loss": 0.8254,
+      "step": 200
+    },
+    {
+      "epoch": 0.006719526945303051,
+      "grad_norm": 44.61080551147461,
+      "learning_rate": 9.999502635115246e-05,
+      "loss": 0.6935,
+      "step": 300
+    },
+    {
+      "epoch": 0.008959369260404068,
+      "grad_norm": 50.82619094848633,
+      "learning_rate": 9.998880952200681e-05,
+      "loss": 0.5972,
+      "step": 400
+    },
+    {
+      "epoch": 0.011199211575505085,
+      "grad_norm": 44.26677703857422,
+      "learning_rate": 9.998010639409713e-05,
+      "loss": 0.5408,
+      "step": 500
+    },
+    {
+      "epoch": 0.013439053890606102,
+      "grad_norm": 42.8045654296875,
+      "learning_rate": 9.996891740029186e-05,
+      "loss": 0.5509,
+      "step": 600
+    },
+    {
+      "epoch": 0.01567889620570712,
+      "grad_norm": 30.989139556884766,
+      "learning_rate": 9.995524309709913e-05,
+      "loss": 0.4823,
+      "step": 700
+    },
+    {
+      "epoch": 0.017918738520808136,
+      "grad_norm": 34.01952362060547,
+      "learning_rate": 9.993908416463927e-05,
+      "loss": 0.5111,
+      "step": 800
+    },
+    {
+      "epoch": 0.020158580835909153,
+      "grad_norm": 34.079307556152344,
+      "learning_rate": 9.992044140661079e-05,
+      "loss": 0.4635,
+      "step": 900
+    },
+    {
+      "epoch": 0.02239842315101017,
+      "grad_norm": 26.16071128845215,
+      "learning_rate": 9.989931575025056e-05,
+      "loss": 0.4883,
+      "step": 1000
+    },
+    {
+      "epoch": 0.02239842315101017,
+      "eval_avg_non_pair_similarity": 0.0020343252948339737,
+      "eval_avg_pair_similarity": 0.008852629057131708,
+      "eval_loss": 0.5431402921676636,
+      "eval_runtime": 19.6178,
+      "eval_samples_per_second": 25.487,
+      "eval_similarity_ratio": 4.35162905343228,
+      "eval_steps_per_second": 0.816,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 44646,
+  "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 sha256:7c6bbe0930b5977d5ef83c9c6a2872aea787e9f64c3d133a00319e43c833ad34
+size 5112