Upload folder using huggingface_hub

slots/2/checkpoint-45/config.json

@@ -0,0 +1,36 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "neftune_alpha": 0.0,
+  "num_attention_heads": 15,
+  "num_hidden_layers": 34,
+  "num_key_value_heads": 5,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "qk_norm": true,
+  "rezero_init": 1.0,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 100000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false,
+  "vocab_size": 49152
+}

slots/2/checkpoint-45/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "transformers_version": "5.0.0",
+  "use_cache": false
+}

slots/2/checkpoint-45/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6de057e1c46698fa4b5fb5654cefc786ff17136fe66982099338869aa809faa4
+size 1714721544

slots/2/checkpoint-45/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4c45e462c77952e6e1e46f7188737e7c13447e689a7f87d907fd7cf01c3c66c
+size 175903435

slots/2/checkpoint-45/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

slots/2/checkpoint-45/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:086dc169253861f78404ea1102fa01a09bbbb53998b133727a258ae89c174a49
+size 1383

slots/2/checkpoint-45/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ccc75e11f2ebe6cc99d05a08befc8e0ec44beef7438c4515edb5911c51ef79b
+size 1465

slots/2/checkpoint-45/trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5272311212814645,
+  "eval_steps": 500,
+  "global_step": 45,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003905296558457408,
+      "grad_norm": 2.961405038833618,
+      "learning_rate": 5e-05,
+      "loss": 11.042926788330078,
+      "step": 1
+    },
+    {
+      "epoch": 0.07810593116914816,
+      "grad_norm": 2.913111925125122,
+      "learning_rate": 4.994503670730125e-05,
+      "loss": 10.412632992393092,
+      "step": 20
+    },
+    {
+      "epoch": 0.46864988558352405,
+      "grad_norm": 3.2307448387145996,
+      "learning_rate": 4.795731611254473e-05,
+      "loss": 8.959894816080729,
+      "step": 40
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 301,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 1000000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.35005674143744e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

slots/2/checkpoint-45/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69ada62714d958c25cca51829f8ea6cdd265294d59777b45e1eca279f136098
+size 5201