Training in progress, epoch 7

logs/events.out.tfevents.1700288259.bdba95a6283e.570.11

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13080b2bc029286d2445d44e40209bd74a4446db1d5e656cd11dd3d052854be0
-size 5289
+oid sha256:5da599601b9a23c833d76222944176834b39287f6e485e06bacfa8c87aba1655
+size 7689

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a54cbdb80addbd38d285377fb5792193e6843866ee52476e902a3d3c00de43
+oid sha256:9ca5517aacd518be8803fdec5db7c7fca1723d07794aafc9772fb2ddcbe8e560
 size 17549312

run-8/checkpoint-2635/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ccca60740af47c426880b8da799eb6dc814af9743d51d20f0be74a2ca3c1b79
+size 17549312

run-8/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f21b19310e72c23b514307eb3ed2cb0605cce6a4fa6d549a35095264a0eb984
+size 35123898

run-8/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f498ecc7f86f66da16efa58519f2ba6628266b779089c9aa7803bfb118cc80d
+size 14308

run-8/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a724874a58c4add1c8c41a968c98ac20d512d837228c6e5076bae2f2644b41f4
+size 1064

run-8/checkpoint-2635/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-2635/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-2635/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8314220183486238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-8/checkpoint-2635",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.80156442664673e-05,
+      "loss": 0.4508,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 0.4456700384616852,
+      "eval_runtime": 2.7558,
+      "eval_samples_per_second": 316.418,
+      "eval_steps_per_second": 2.54,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.701368873315889e-05,
+      "loss": 0.2896,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.4712570309638977,
+      "eval_runtime": 2.6794,
+      "eval_samples_per_second": 325.448,
+      "eval_steps_per_second": 2.613,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 6.601173319985047e-05,
+      "loss": 0.235,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.4967746436595917,
+      "eval_runtime": 2.7343,
+      "eval_samples_per_second": 318.91,
+      "eval_steps_per_second": 2.56,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.5009777666542064e-05,
+      "loss": 0.2,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.530954897403717,
+      "eval_runtime": 2.7009,
+      "eval_samples_per_second": 322.856,
+      "eval_steps_per_second": 2.592,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.400782213323365e-05,
+      "loss": 0.1785,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.5582391023635864,
+      "eval_runtime": 2.7385,
+      "eval_samples_per_second": 318.422,
+      "eval_steps_per_second": 2.556,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 40418309418180.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9820122287000461,
+    "learning_rate": 9.901759979977571e-05,
+    "num_train_epochs": 9,
+    "temperature": 4
+  }
+}

run-8/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4fa254855b2f13d9734efd78d8354bb32f29e0d8de8a8e774484c999477177
+size 4664

run-8/checkpoint-3689/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-8/checkpoint-3689/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca5517aacd518be8803fdec5db7c7fca1723d07794aafc9772fb2ddcbe8e560
+size 17549312

run-8/checkpoint-3689/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97ce4eab6d20fbcf60a3b9261671a4efdd859d7226d6f061978627d3e6e00b0d
+size 35123898

run-8/checkpoint-3689/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc3fb950ff90ad17095c2eb92ec4723d9e41fbed95117d4e06ee07178005482
+size 14308

run-8/checkpoint-3689/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a990343979f237aee45fe91e3d526287918db3a38b05a03e79939a266e9fecb
+size 1064

run-8/checkpoint-3689/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-3689/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-8/checkpoint-3689/trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_metric": 0.8314220183486238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled_original/run-8/checkpoint-2635",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 3689,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 8.80156442664673e-05,
+      "loss": 0.4508,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8130733944954128,
+      "eval_loss": 0.4456700384616852,
+      "eval_runtime": 2.7558,
+      "eval_samples_per_second": 316.418,
+      "eval_steps_per_second": 2.54,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 7.701368873315889e-05,
+      "loss": 0.2896,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8188073394495413,
+      "eval_loss": 0.4712570309638977,
+      "eval_runtime": 2.6794,
+      "eval_samples_per_second": 325.448,
+      "eval_steps_per_second": 2.613,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 6.601173319985047e-05,
+      "loss": 0.235,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8245412844036697,
+      "eval_loss": 0.4967746436595917,
+      "eval_runtime": 2.7343,
+      "eval_samples_per_second": 318.91,
+      "eval_steps_per_second": 2.56,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 5.5009777666542064e-05,
+      "loss": 0.2,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.530954897403717,
+      "eval_runtime": 2.7009,
+      "eval_samples_per_second": 322.856,
+      "eval_steps_per_second": 2.592,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.400782213323365e-05,
+      "loss": 0.1785,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.5582391023635864,
+      "eval_runtime": 2.7385,
+      "eval_samples_per_second": 318.422,
+      "eval_steps_per_second": 2.556,
+      "step": 2635
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 3.3005866599925236e-05,
+      "loss": 0.164,
+      "step": 3162
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.823394495412844,
+      "eval_loss": 0.6088590025901794,
+      "eval_runtime": 2.6798,
+      "eval_samples_per_second": 325.399,
+      "eval_steps_per_second": 2.612,
+      "step": 3162
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 2.2003911066616825e-05,
+      "loss": 0.1528,
+      "step": 3689
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.6382232308387756,
+      "eval_runtime": 2.7756,
+      "eval_samples_per_second": 314.167,
+      "eval_steps_per_second": 2.522,
+      "step": 3689
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4743,
+  "num_train_epochs": 9,
+  "save_steps": 500,
+  "total_flos": 56612034005400.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.9820122287000461,
+    "learning_rate": 9.901759979977571e-05,
+    "num_train_epochs": 9,
+    "temperature": 4
+  }
+}

run-8/checkpoint-3689/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f4fa254855b2f13d9734efd78d8354bb32f29e0d8de8a8e774484c999477177
+size 4664