Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,21 @@
+{
+  "_name_or_path": "tattabio/gLM2_650M",
+  "architectures": [
+    "gLM2ForMaskedLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "configuration_glm2.gLM2Config",
+    "AutoModel": "modeling_glm2.gLM2Model",
+    "AutoModelForMaskedLM": "modeling_glm2.gLM2ForMaskedLM"
+  },
+  "depth": 33,
+  "dim": 1280,
+  "ffn_dim_multiplier": null,
+  "heads": 20,
+  "model_type": "gLM2",
+  "norm_eps": 1e-05,
+  "swiglu_multiple_of": 256,
+  "torch_dtype": "float32",
+  "transformers_version": "4.49.0",
+  "vocab_size": 37
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9710ceb6e6839dcee08d16f242c5bba9ec7262d7b88c7e640aceb3b663ff6f3
+size 2682482800

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac473dbf7326427941f23a0ac8aa3e8a370949d7710f345860b7664662ac1d2
+size 5365108834

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60b2820168c2d4ed8da5ba96b74ce6644fe96b99636f1c5591e51029cf20942e
+size 15006

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43cfdcb9d2b904f214c9579df005c8d06131d0b7a4103660e917a59d32b07f93
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 1.4935803413391113,
+  "best_model_checkpoint": "mgh6/HTH_nt_MLM/checkpoint-257",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 257,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5239282846450806,
+      "learning_rate": 9.832682291666667e-05,
+      "loss": 1.5981,
+      "step": 257
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.4935803413391113,
+      "eval_runtime": 9.2798,
+      "eval_samples_per_second": 46.553,
+      "eval_steps_per_second": 5.819,
+      "step": 257
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 15360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 60,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 10,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.693286615993549e+16,
+  "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 sha256:145c2fa7d2449400b8b78f9c3bc76f59c339909b1e11ef066d215b797c8472c8
+size 5368