update slot resume pointers for step 129

slots/0/checkpoint-162/config.json

@@ -1,24 +0,0 @@
-{
-  "architectures": [
-    "TwinyForCausalLM"
-  ],
-  "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": "twiny",
-  "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-162/trainer_state.json

@@ -1,97 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.004239566936088528,
-  "eval_steps": 500,
-  "global_step": 162,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 2.617016627215141e-05,
-      "grad_norm": 122.33340454101562,
-      "learning_rate": 5e-05,
-      "loss": 419.9996032714844,
-      "step": 1
-    },
-    {
-      "epoch": 0.0005234033254430282,
-      "grad_norm": 90.82411193847656,
-      "learning_rate": 4.999999511980259e-05,
-      "loss": 428.18197471217104,
-      "step": 20
-    },
-    {
-      "epoch": 0.0010468066508860564,
-      "grad_norm": 59.52641296386719,
-      "learning_rate": 4.999997943828395e-05,
-      "loss": 366.3947265625,
-      "step": 40
-    },
-    {
-      "epoch": 0.0015702099763290846,
-      "grad_norm": 41.61277389526367,
-      "learning_rate": 4.999995294193233e-05,
-      "loss": 325.6545166015625,
-      "step": 60
-    },
-    {
-      "epoch": 0.0020936133017721128,
-      "grad_norm": 46.67556381225586,
-      "learning_rate": 4.999991563075919e-05,
-      "loss": 310.3648193359375,
-      "step": 80
-    },
-    {
-      "epoch": 0.002617016627215141,
-      "grad_norm": 47.65824890136719,
-      "learning_rate": 4.999986750478065e-05,
-      "loss": 303.4944580078125,
-      "step": 100
-    },
-    {
-      "epoch": 0.003140419952658169,
-      "grad_norm": 62.748130798339844,
-      "learning_rate": 4.999980856401755e-05,
-      "loss": 322.3900146484375,
-      "step": 120
-    },
-    {
-      "epoch": 0.0036638232781011975,
-      "grad_norm": 47.879722595214844,
-      "learning_rate": 4.9999738808495387e-05,
-      "loss": 319.0849853515625,
-      "step": 140
-    },
-    {
-      "epoch": 0.0041872266035442255,
-      "grad_norm": 53.122230529785156,
-      "learning_rate": 4.999965823824433e-05,
-      "loss": 282.9225341796875,
-      "step": 160
-    }
-  ],
-  "logging_steps": 20,
-  "max_steps": 95530,
-  "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": 167834292572160.0,
-  "train_batch_size": 1,
-  "trial_name": null,
-  "trial_params": null
-}

slots/0/latest.json

@@ -1 +1 @@
-{"worker_id": "slot:0", "checkpoint": "slots/0/checkpoint-162", "step": 162, "updated_at": 1776327571}
+{"worker_id": "slot:0", "checkpoint": "slots/0/checkpoint-129", "step": 129, "updated_at": 1776329050}