Training in progress, step 100, 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": "4.45.2",
+  "vocab_size": 37
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b14f81830b72149ea0d8c4100992492b70830c0be8b1cf197598950492d5dbd
+size 2682482800

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f55c73a5198d71456c1007c1e2b3c9a0187abff0edd38f53f302c9bc1425c1a9
+size 5365108834

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e59ba1bafb88d66ae26193100490c9a785a11de83c469025dd06b157587f9a12
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4265d5553bfb55a8aabc39f0360eb599499fd97cae117d1fd7b125b5d6a87d7a
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2338b1fc8e1dc5158561fa405d6ffdd4c3a51a1e4efc57735695a177e000c2ac
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d2a43d2cfd5f337ec43b74fcfb4a4040703c5eddc8ac6f4f043ce24274fe35f
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e82975d48b3a94464d8ca425e4fcde1c6037da4312b3dd05fa799b2e3c703a0d
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,47 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.007675232145791034,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003837616072895517,
+      "grad_norm": 4.467618942260742,
+      "learning_rate": 0.0009961621123733496,
+      "loss": 1.752,
+      "step": 50
+    },
+    {
+      "epoch": 0.007675232145791034,
+      "grad_norm": 1.9758433103561401,
+      "learning_rate": 0.0009923242247466995,
+      "loss": 1.2354,
+      "step": 100
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 13028,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.712602232001659e+17,
+  "train_batch_size": 2,
+  "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:fa210eeb1786e732e3ecfb64143949504cb9722bc191a603cef1c219287b0f6f
+size 5240