Model save

last-checkpoint/config.json

@@ -1,28 +0,0 @@
-{
-  "_name_or_path": "/home/pcjf/CESGA/works/lmodels/models/tiny",
-  "architectures": [
-    "RobertaForMaskedLM"
-  ],
-  "attention_probs_dropout_prob": 0.1,
-  "bos_token_id": 0,
-  "classifier_dropout": null,
-  "eos_token_id": 2,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 6,
-  "pad_token_id": 1,
-  "position_embedding_type": "absolute",
-  "torch_dtype": "float32",
-  "transformers_version": "4.25.1",
-  "type_vocab_size": 1,
-  "use_cache": true,
-  "vocab_size": 31002
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:b02d30dbb1390014003809a5ade58a1972fa2143041cc4f6d2e32c656290b47e
-size 538943941

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0c7bd2b3fc4c75870baf39c97dd0a294d6537e6ed402cade193d9ca453a2b3ce
-size 269468281

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7ccc59651e44275f9521ab69d703635efaa8d9ba49d678eac525ffc2eaf55996
-size 14575

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:367928c873a79d90abcb66db0f8b320eea7346dc9bc779b4e7963dfc82cf2ada
-size 557

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:e576c1af05d044d7dfe73b333bc091a6eb71e1a62324659c9b82c58e9887a777
-size 627

last-checkpoint/trainer_state.json

@@ -1,170 +0,0 @@
-{
-  "best_metric": 2.2180914878845215,
-  "best_model_checkpoint": "/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-5500",
-  "epoch": 4.968273681833578,
-  "global_step": 5500,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.45,
-      "learning_rate": 9.096657633242999e-05,
-      "loss": 2.6679,
-      "step": 500
-    },
-    {
-      "epoch": 0.45,
-      "eval_loss": 2.550431489944458,
-      "eval_runtime": 33.087,
-      "eval_samples_per_second": 347.327,
-      "eval_steps_per_second": 43.431,
-      "step": 500
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 8.193315266485999e-05,
-      "loss": 2.6019,
-      "step": 1000
-    },
-    {
-      "epoch": 0.9,
-      "eval_loss": 2.475651741027832,
-      "eval_runtime": 32.0278,
-      "eval_samples_per_second": 358.813,
-      "eval_steps_per_second": 44.867,
-      "step": 1000
-    },
-    {
-      "epoch": 1.35,
-      "learning_rate": 7.289972899728998e-05,
-      "loss": 2.5247,
-      "step": 1500
-    },
-    {
-      "epoch": 1.35,
-      "eval_loss": 2.4407145977020264,
-      "eval_runtime": 32.3311,
-      "eval_samples_per_second": 355.447,
-      "eval_steps_per_second": 44.446,
-      "step": 1500
-    },
-    {
-      "epoch": 1.81,
-      "learning_rate": 6.386630532971996e-05,
-      "loss": 2.4669,
-      "step": 2000
-    },
-    {
-      "epoch": 1.81,
-      "eval_loss": 2.389404773712158,
-      "eval_runtime": 32.7481,
-      "eval_samples_per_second": 350.921,
-      "eval_steps_per_second": 43.88,
-      "step": 2000
-    },
-    {
-      "epoch": 2.26,
-      "learning_rate": 5.483288166214996e-05,
-      "loss": 2.4136,
-      "step": 2500
-    },
-    {
-      "epoch": 2.26,
-      "eval_loss": 2.3637166023254395,
-      "eval_runtime": 32.183,
-      "eval_samples_per_second": 357.083,
-      "eval_steps_per_second": 44.651,
-      "step": 2500
-    },
-    {
-      "epoch": 2.71,
-      "learning_rate": 4.579945799457995e-05,
-      "loss": 2.3683,
-      "step": 3000
-    },
-    {
-      "epoch": 2.71,
-      "eval_loss": 2.3127212524414062,
-      "eval_runtime": 33.1444,
-      "eval_samples_per_second": 346.725,
-      "eval_steps_per_second": 43.356,
-      "step": 3000
-    },
-    {
-      "epoch": 3.16,
-      "learning_rate": 3.6766034327009944e-05,
-      "loss": 2.3371,
-      "step": 3500
-    },
-    {
-      "epoch": 3.16,
-      "eval_loss": 2.294386625289917,
-      "eval_runtime": 32.528,
-      "eval_samples_per_second": 353.296,
-      "eval_steps_per_second": 44.177,
-      "step": 3500
-    },
-    {
-      "epoch": 3.61,
-      "learning_rate": 2.7732610659439927e-05,
-      "loss": 2.3041,
-      "step": 4000
-    },
-    {
-      "epoch": 3.61,
-      "eval_loss": 2.26143741607666,
-      "eval_runtime": 32.4261,
-      "eval_samples_per_second": 354.406,
-      "eval_steps_per_second": 44.316,
-      "step": 4000
-    },
-    {
-      "epoch": 4.07,
-      "learning_rate": 1.869918699186992e-05,
-      "loss": 2.2757,
-      "step": 4500
-    },
-    {
-      "epoch": 4.07,
-      "eval_loss": 2.2403604984283447,
-      "eval_runtime": 32.4416,
-      "eval_samples_per_second": 354.236,
-      "eval_steps_per_second": 44.295,
-      "step": 4500
-    },
-    {
-      "epoch": 4.52,
-      "learning_rate": 9.66576332429991e-06,
-      "loss": 2.2508,
-      "step": 5000
-    },
-    {
-      "epoch": 4.52,
-      "eval_loss": 2.2336952686309814,
-      "eval_runtime": 32.5285,
-      "eval_samples_per_second": 353.29,
-      "eval_steps_per_second": 44.177,
-      "step": 5000
-    },
-    {
-      "epoch": 4.97,
-      "learning_rate": 6.323396567299007e-07,
-      "loss": 2.2363,
-      "step": 5500
-    },
-    {
-      "epoch": 4.97,
-      "eval_loss": 2.2180914878845215,
-      "eval_runtime": 32.458,
-      "eval_samples_per_second": 354.058,
-      "eval_steps_per_second": 44.273,
-      "step": 5500
-    }
-  ],
-  "max_steps": 5535,
-  "num_train_epochs": 5,
-  "total_flos": 8.726670833749062e+16,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:687f2fe53f71dbd495a1980f0ba26bc3f950baedfff342880439c0c7042fd562
-size 3515

log.txt

@@ -2916,3 +2916,17 @@ Deleting older checkpoint [/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint
 
                                                   Saving model checkpoint to /home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-5500
 Configuration saved in /home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-5500/config.json
 Model weights saved in /home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-5500/pytorch_model.bin
+Deleting older checkpoint [/home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-3000] due to args.save_total_limit
+
 99%|█████████▉| 5501/5535 [3:23:57<24:39, 43.53s/it]
 99%|█████████▉| 5502/5535 [3:23:58<17:02, 30.98s/it]
 99%|█████████▉| 5503/5535 [3:24:01<11:54, 22.34s/it]
 99%|█████████▉| 5504/5535 [3:24:02<08:19, 16.10s/it]
 99%|█████████▉| 5505/5535 [3:24:04<05:54, 11.82s/it]
 99%|█████████▉| 5506/5535 [3:24:06<04:14,  8.79s/it]
 99%|█████████▉| 5507/5535 [3:24:08<03:07,  6.70s/it]
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+Loading best model from /home/pcjf/CESGA/works/lmodels/models/tiny/checkpoint-5500 (score: 2.2180914878845215).
+
                                                     
+Saving model checkpoint to /home/pcjf/CESGA/works/lmodels/models/tiny
+Configuration saved in /home/pcjf/CESGA/works/lmodels/models/tiny/config.json
+Model weights saved in /home/pcjf/CESGA/works/lmodels/models/tiny/pytorch_model.bin
+Saving model checkpoint to /home/pcjf/CESGA/works/lmodels/models/tiny
+Configuration saved in /home/pcjf/CESGA/works/lmodels/models/tiny/config.json
+Model weights saved in /home/pcjf/CESGA/works/lmodels/models/tiny/pytorch_model.bin

runs/Jan16_09-20-43_turing/events.out.tfevents.1673857249.turing.343391.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd5a5c60e2b5269ffe970bc6f4215dfdd6880246819c0c78403571c5d64d5e9b
-size 8620
+oid sha256:afe6a154248e750b5630727b98592e9310c3101e1f3f3a647c5769bc3ff0b095
+size 8974