Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97625289ed6754e4841bfde32e560e217b158f058e89b7806575405bbdc56a6e
+oid sha256:a4455e927f2295487fa69c6f6589c41b0ab03e0b4b2c440f84d46d0a84a929b7
 size 1421491284

run-11/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-11/checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4455e927f2295487fa69c6f6589c41b0ab03e0b4b2c440f84d46d0a84a929b7
+size 1421491284

run-11/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9d0804215cf79302de51fbfc42abbd3547d89b20da2c3f8a431ff55dd98fbe
+size 2843215085

run-11/checkpoint-1500/rng_state.pth

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

run-11/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bdbe322edf8fa5319411b68e5a6ddddde14c943b0570ee34284e1f1892fa966
+size 1064

run-11/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-11/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-11/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": 0.7562856078147888,
+      "eval_loss": 0.47381648421287537,
+      "eval_runtime": 8.9994,
+      "eval_samples_per_second": 331.468,
+      "eval_steps_per_second": 20.779,
+      "step": 187
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7981897592544556,
+      "eval_loss": 0.42580413818359375,
+      "eval_runtime": 9.0271,
+      "eval_samples_per_second": 330.449,
+      "eval_steps_per_second": 20.715,
+      "step": 374
+    },
+    {
+      "epoch": 2.6737967914438503,
+      "grad_norm": 11.08890151977539,
+      "learning_rate": 7.813495284053265e-06,
+      "loss": 0.4673,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.808917224407196,
+      "eval_loss": 0.4457302689552307,
+      "eval_runtime": 8.9701,
+      "eval_samples_per_second": 332.548,
+      "eval_steps_per_second": 20.847,
+      "step": 561
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8129400014877319,
+      "eval_loss": 0.4927816390991211,
+      "eval_runtime": 9.0176,
+      "eval_samples_per_second": 330.797,
+      "eval_steps_per_second": 20.737,
+      "step": 748
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.816627562046051,
+      "eval_loss": 0.5265363454818726,
+      "eval_runtime": 9.022,
+      "eval_samples_per_second": 330.637,
+      "eval_steps_per_second": 20.727,
+      "step": 935
+    },
+    {
+      "epoch": 5.347593582887701,
+      "grad_norm": 13.312323570251465,
+      "learning_rate": 4.961854669435285e-06,
+      "loss": 0.1911,
+      "step": 1000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8162923455238342,
+      "eval_loss": 0.6189388632774353,
+      "eval_runtime": 8.9828,
+      "eval_samples_per_second": 332.078,
+      "eval_steps_per_second": 20.817,
+      "step": 1122
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.8176332712173462,
+      "eval_loss": 0.6575231552124023,
+      "eval_runtime": 9.0604,
+      "eval_samples_per_second": 329.233,
+      "eval_steps_per_second": 20.639,
+      "step": 1309
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.8280254602432251,
+      "eval_loss": 0.6579554080963135,
+      "eval_runtime": 9.0264,
+      "eval_samples_per_second": 330.476,
+      "eval_steps_per_second": 20.717,
+      "step": 1496
+    },
+    {
+      "epoch": 8.02139037433155,
+      "grad_norm": 20.2036075592041,
+      "learning_rate": 2.110214054817305e-06,
+      "loss": 0.0833,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1870,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1.7020351033613064e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.0665135898671243e-05,
+    "per_device_train_batch_size": 64
+  }
+}

run-11/checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3203b2e502cf3a9547ee82ef9b5657a0dabb9a86e981d634e57d93445c61c108
+size 5048