Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4ae7bcd0e413129df40106ba0dc9ab23cda1bdb8e1b57f1bb4d7c61dc4e446b
+oid sha256:7d0f9ab348f049b2c39e8884e4e40ed05db19443207e234b00fc315d85157c37
 size 1421491284

run-19/checkpoint-1500/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-large",
+  "architectures": [
+    "RobertaForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

run-19/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d26f59ad7cf605249d69e6b59eda2b509a8bd84b20ae99a9ea1ef965f1de6b5
+size 1421491284

run-19/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b229cb7ffa61b11eb09c95ff9d7d4704f9525830678bba84861c73285d7fab2
+size 2843215085

run-19/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337d994df14d2464b8db4f75ed5528cb65ff69cc995770db5a502206a6a568df
+size 14244

run-19/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ad18f5ee7cf75a195fc6e3c3a1a6eee5529ea25f7c7c06c7db55b1c3c4b655
+size 1064

run-19/checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

run-19/checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

run-19/checkpoint-1500/trainer_state.json

@@ -0,0 +1,117 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.02139037433155,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7787462472915649,
+      "eval_loss": 0.460673063993454,
+      "eval_runtime": 8.9946,
+      "eval_samples_per_second": 331.643,
+      "eval_steps_per_second": 20.79,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.817968487739563,
+      "eval_loss": 0.4022049903869629,
+      "eval_runtime": 9.0054,
+      "eval_samples_per_second": 331.248,
+      "eval_steps_per_second": 20.765,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 15.16759967803955,
+      "learning_rate": 9.967927666611134e-06,
+      "loss": 0.4384,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.47557684779167175,
+      "eval_runtime": 8.8858,
+      "eval_samples_per_second": 335.706,
+      "eval_steps_per_second": 21.045,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8266845345497131,
+      "eval_loss": 0.5004067420959473,
+      "eval_runtime": 8.9322,
+      "eval_samples_per_second": 333.961,
+      "eval_steps_per_second": 20.936,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.825678825378418,
+      "eval_loss": 0.5987616777420044,
+      "eval_runtime": 8.9664,
+      "eval_samples_per_second": 332.685,
+      "eval_steps_per_second": 20.856,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 13.802921295166016,
+      "learning_rate": 6.329997861278603e-06,
+      "loss": 0.1515,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8327187299728394,
+      "eval_loss": 0.649012565612793,
+      "eval_runtime": 8.9317,
+      "eval_samples_per_second": 333.977,
+      "eval_steps_per_second": 20.937,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8300368785858154,
+      "eval_loss": 0.6699344515800476,
+      "eval_runtime": 8.9599,
+      "eval_samples_per_second": 332.928,
+      "eval_steps_per_second": 20.871,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.838082492351532,
+      "eval_loss": 0.727820098400116,
+      "eval_runtime": 9.5409,
+      "eval_samples_per_second": 312.654,
+      "eval_steps_per_second": 19.6,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 15.661439895629883,
+      "learning_rate": 2.6920680559460726e-06,
+      "loss": 0.0564,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.9128805855881372e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.3605857471943663e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-19/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b8e9b834503e65fc1550a21b9f29ac5bff4b8192e8708111f8a41a661eb532c
+size 5048