FastPlus125m Geodesic Backup checkpoint-100 at global step 100

checkpoint-100/config.json

@@ -0,0 +1,20 @@
+{
+  "architectures": [
+    "FastPlus125mForCausalLM"
+  ],
+  "dtype": "float32",
+  "hidden_size": 1024,
+  "hyperbolic_dim": 16,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "kd_alpha": 0.4,
+  "kd_temperature": 2.5,
+  "max_position_embeddings": 512,
+  "model_type": "fastplus_125m",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 16,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 32704
+}

checkpoint-100/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.13.1"
+}

checkpoint-100/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fdcaf993d41441d2c9f7920e60450f9a6038aef97f0f786c2418cbfc0573792
+size 952467608

checkpoint-100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6519c2827767a71269a8f81ff507c36ac6601d73a632a95ff0d137daa76e25ef
+size 1893222379

checkpoint-100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe123c31d10591747ed95e990d9a3bef058bc972de7c981b56054fcda3e6665e
+size 14645

checkpoint-100/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4393a84a3109995aa1202073b039b12062e3189ed89aa0b94ef0510ba843009
+size 1383

checkpoint-100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a88f02c948af9fecb2a5d641eba4b1e32158ec0aef993b2e628c8ed55396c3d0
+size 8953

checkpoint-100/tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": [
+    "<|user|>",
+    "<|assistant|>"
+  ],
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<unk>"
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.03522211949104037,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0035222119491040375,
+      "grad_norm": 48.87228775024414,
+      "learning_rate": 6.000000000000001e-07,
+      "lorentz_dist_loss": 10.4283,
+      "loss": 10.4336,
+      "step": 10
+    },
+    {
+      "epoch": 0.007044423898208075,
+      "grad_norm": 45.45050048828125,
+      "learning_rate": 1.2666666666666667e-06,
+      "lorentz_dist_loss": 10.4047,
+      "loss": 10.4101,
+      "step": 20
+    },
+    {
+      "epoch": 0.010566635847312112,
+      "grad_norm": 31.035011291503906,
+      "learning_rate": 1.9333333333333336e-06,
+      "lorentz_dist_loss": 10.3635,
+      "loss": 10.3688,
+      "step": 30
+    },
+    {
+      "epoch": 0.01408884779641615,
+      "grad_norm": 14.959467887878418,
+      "learning_rate": 2.6e-06,
+      "lorentz_dist_loss": 10.3231,
+      "loss": 10.3285,
+      "step": 40
+    },
+    {
+      "epoch": 0.017611059745520186,
+      "grad_norm": 7.208108425140381,
+      "learning_rate": 3.2666666666666666e-06,
+      "lorentz_dist_loss": 10.3009,
+      "loss": 10.3064,
+      "step": 50
+    },
+    {
+      "epoch": 0.021133271694624225,
+      "grad_norm": 5.267526149749756,
+      "learning_rate": 3.9333333333333335e-06,
+      "lorentz_dist_loss": 10.2958,
+      "loss": 10.3013,
+      "step": 60
+    },
+    {
+      "epoch": 0.02465548364372826,
+      "grad_norm": 5.801661968231201,
+      "learning_rate": 4.6e-06,
+      "lorentz_dist_loss": 10.2894,
+      "loss": 10.2948,
+      "step": 70
+    },
+    {
+      "epoch": 0.0281776955928323,
+      "grad_norm": 6.631390571594238,
+      "learning_rate": 5.266666666666667e-06,
+      "lorentz_dist_loss": 10.2795,
+      "loss": 10.2851,
+      "step": 80
+    },
+    {
+      "epoch": 0.031699907541936335,
+      "grad_norm": 4.531800746917725,
+      "learning_rate": 5.933333333333334e-06,
+      "lorentz_dist_loss": 10.2664,
+      "loss": 10.2721,
+      "step": 90
+    },
+    {
+      "epoch": 0.03522211949104037,
+      "grad_norm": 4.587399959564209,
+      "learning_rate": 6.6e-06,
+      "lorentz_dist_loss": 10.2592,
+      "loss": 10.265,
+      "step": 100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2840,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.536835291684864e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}