System: Prune old checkpoint folder checkpoint-200 to save space

checkpoint-200/config.json

@@ -1,19 +0,0 @@
-{
-  "architectures": [
-    "FastPlus40mForCausalLM"
-  ],
-  "dtype": "float32",
-  "hidden_size": 512,
-  "initializer_range": 0.02,
-  "intermediate_size": 1536,
-  "kd_alpha": 0.4,
-  "kd_temperature": 2.5,
-  "max_position_embeddings": 512,
-  "model_type": "fastplus_40m",
-  "num_attention_heads": 8,
-  "num_hidden_layers": 11,
-  "tie_word_embeddings": true,
-  "transformers_version": "5.12.0",
-  "use_cache": false,
-  "vocab_size": 8160
-}

checkpoint-200/generation_config.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "output_attentions": false,
-  "output_hidden_states": false,
-  "transformers_version": "5.12.0"
-}

checkpoint-200/tokenizer_config.json

@@ -1,13 +0,0 @@
-{
-  "backend": "tokenizers",
-  "bos_token": "<s>",
-  "eos_token": "</s>",
-  "extra_special_tokens": [
-    "<|user|>",
-    "<|assistant|>"
-  ],
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "<pad>",
-  "tokenizer_class": "TokenizersBackend",
-  "unk_token": "<unk>"
-}

checkpoint-200/trainer_state.json

@@ -1,194 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.10371762875571257,
-  "eval_steps": 500,
-  "global_step": 200,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.005185881437785629,
-      "grad_norm": 266.6409606933594,
-      "learning_rate": 2.5499999999999996e-05,
-      "loss": 144.2415283203125,
-      "original_ce_loss": 9.0144,
-      "step": 10
-    },
-    {
-      "epoch": 0.010371762875571258,
-      "grad_norm": 272.673095703125,
-      "learning_rate": 6.8e-05,
-      "loss": 143.50185546875,
-      "original_ce_loss": 8.9682,
-      "step": 20
-    },
-    {
-      "epoch": 0.015557644313356886,
-      "grad_norm": 437.08270263671875,
-      "learning_rate": 0.00010625,
-      "loss": 140.732373046875,
-      "original_ce_loss": 8.7951,
-      "step": 30
-    },
-    {
-      "epoch": 0.020743525751142515,
-      "grad_norm": 268.7778625488281,
-      "learning_rate": 0.00014450000000000002,
-      "loss": 128.16519775390626,
-      "original_ce_loss": 8.0096,
-      "step": 40
-    },
-    {
-      "epoch": 0.025929407188928142,
-      "grad_norm": 38.690486907958984,
-      "learning_rate": 0.000187,
-      "loss": 117.56219482421875,
-      "original_ce_loss": 7.347,
-      "step": 50
-    },
-    {
-      "epoch": 0.031115288626713773,
-      "grad_norm": 31.22739028930664,
-      "learning_rate": 0.0002295,
-      "loss": 111.48564453125,
-      "original_ce_loss": 6.9672,
-      "step": 60
-    },
-    {
-      "epoch": 0.0363011700644994,
-      "grad_norm": 17.76206398010254,
-      "learning_rate": 0.000272,
-      "loss": 104.34268798828126,
-      "original_ce_loss": 6.5207,
-      "step": 70
-    },
-    {
-      "epoch": 0.04148705150228503,
-      "grad_norm": 101.92194366455078,
-      "learning_rate": 0.0003145,
-      "loss": 100.91859130859375,
-      "original_ce_loss": 6.3067,
-      "step": 80
-    },
-    {
-      "epoch": 0.04667293294007066,
-      "grad_norm": 28.36432647705078,
-      "learning_rate": 0.00035699999999999995,
-      "loss": 100.308935546875,
-      "original_ce_loss": 6.2686,
-      "step": 90
-    },
-    {
-      "epoch": 0.051858814377856284,
-      "grad_norm": 17.224742889404297,
-      "learning_rate": 0.00039949999999999995,
-      "loss": 100.14071655273438,
-      "original_ce_loss": 6.2581,
-      "step": 100
-    },
-    {
-      "epoch": 0.057044695815641915,
-      "grad_norm": 52.153076171875,
-      "learning_rate": 0.0004249971787418828,
-      "loss": 99.686962890625,
-      "original_ce_loss": 6.2298,
-      "step": 110
-    },
-    {
-      "epoch": 0.062230577253427545,
-      "grad_norm": 16.022294998168945,
-      "learning_rate": 0.00042494702512599277,
-      "loss": 99.31576538085938,
-      "original_ce_loss": 6.2066,
-      "step": 120
-    },
-    {
-      "epoch": 0.06741645869121317,
-      "grad_norm": 20.817411422729492,
-      "learning_rate": 0.00042483419391697364,
-      "loss": 97.84152221679688,
-      "original_ce_loss": 6.1144,
-      "step": 130
-    },
-    {
-      "epoch": 0.0726023401289988,
-      "grad_norm": 13.969531059265137,
-      "learning_rate": 0.00042465871840307033,
-      "loss": 97.0799072265625,
-      "original_ce_loss": 6.0668,
-      "step": 140
-    },
-    {
-      "epoch": 0.07778822156678443,
-      "grad_norm": 12.968173027038574,
-      "learning_rate": 0.00042442065035428465,
-      "loss": 95.65609741210938,
-      "original_ce_loss": 5.9779,
-      "step": 150
-    },
-    {
-      "epoch": 0.08297410300457006,
-      "grad_norm": 16.16962242126465,
-      "learning_rate": 0.00042412006000710166,
-      "loss": 94.4610107421875,
-      "original_ce_loss": 5.9032,
-      "step": 160
-    },
-    {
-      "epoch": 0.08815998444235569,
-      "grad_norm": 15.63354206085205,
-      "learning_rate": 0.0004237570360437679,
-      "loss": 93.08035888671876,
-      "original_ce_loss": 5.8169,
-      "step": 170
-    },
-    {
-      "epoch": 0.09334586588014132,
-      "grad_norm": 19.45943260192871,
-      "learning_rate": 0.00042333168556612805,
-      "loss": 91.3424560546875,
-      "original_ce_loss": 5.7083,
-      "step": 180
-    },
-    {
-      "epoch": 0.09853174731792694,
-      "grad_norm": 12.314143180847168,
-      "learning_rate": 0.0004228441340640267,
-      "loss": 89.93196411132813,
-      "original_ce_loss": 5.6201,
-      "step": 190
-    },
-    {
-      "epoch": 0.10371762875571257,
-      "grad_norm": 10.550477981567383,
-      "learning_rate": 0.00042229452537828567,
-      "loss": 87.97509765625,
-      "original_ce_loss": 5.4978,
-      "step": 200
-    }
-  ],
-  "logging_steps": 10,
-  "max_steps": 1929,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 200,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": true,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 2128405097422848.0,
-  "train_batch_size": 16,
-  "trial_name": null,
-  "trial_params": null
-}