update slot resume pointers for step 150

slots/0/checkpoint-106/config.json

@@ -1,24 +0,0 @@
-{
-  "architectures": [
-    "MinixForCausalLM"
-  ],
-  "attention_dropout": 0.0,
-  "dtype": "float32",
-  "hidden_dropout": 0.0,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "max_position_embeddings": 128,
-  "model_type": "minix",
-  "neftune_alpha": 0.0,
-  "num_attention_heads": 12,
-  "num_hidden_layers": 1,
-  "num_key_value_heads": 3,
-  "qk_norm": true,
-  "rezero_init": 1.0,
-  "rms_norm_eps": 1e-06,
-  "rope_theta": 10000.0,
-  "transformers_version": "5.0.0",
-  "use_cache": false,
-  "vocab_size": 32000
-}

slots/0/checkpoint-106/trainer_state.json

@@ -1,76 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.006879197080884107,
-  "eval_steps": 500,
-  "global_step": 106,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 6.489808566871798e-05,
-      "grad_norm": 109.46859741210938,
-      "learning_rate": 5e-05,
-      "loss": 421.4660949707031,
-      "step": 1
-    },
-    {
-      "epoch": 0.0012979617133743598,
-      "grad_norm": 88.54906463623047,
-      "learning_rate": 4.999996998926224e-05,
-      "loss": 390.39101048519734,
-      "step": 20
-    },
-    {
-      "epoch": 0.0025959234267487197,
-      "grad_norm": 60.599815368652344,
-      "learning_rate": 4.999987355594792e-05,
-      "loss": 341.1005126953125,
-      "step": 40
-    },
-    {
-      "epoch": 0.003893885140123079,
-      "grad_norm": 42.03083419799805,
-      "learning_rate": 4.999971061718136e-05,
-      "loss": 318.29091796875,
-      "step": 60
-    },
-    {
-      "epoch": 0.005191846853497439,
-      "grad_norm": 34.96514129638672,
-      "learning_rate": 4.999948117339598e-05,
-      "loss": 305.076220703125,
-      "step": 80
-    },
-    {
-      "epoch": 0.006489808566871798,
-      "grad_norm": 37.357093811035156,
-      "learning_rate": 4.9999185225202174e-05,
-      "loss": 298.5962890625,
-      "step": 100
-    }
-  ],
-  "logging_steps": 20,
-  "max_steps": 38523,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
-  "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": 109817500078080.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

slots/0/latest.json

@@ -1 +1 @@
-{"worker_id": "slot:0", "checkpoint": "slots/0/checkpoint-106", "step": 106, "updated_at": 1776692646}
+{"worker_id": "slot:0", "checkpoint": "slots/0/checkpoint-150", "step": 150, "updated_at": 1776694310}