Upload folder using huggingface_hub

checkpoint-10/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./math_book",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-10/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.3"
+}

checkpoint-10/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc4f3e8d356ede8ddfa6f845f7fedbf97742e58a7649f56f60a98063d4745a89
+size 995641861

checkpoint-10/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c335e6984bd50e8ea18c94230c137305a44415b5999220e41a0bb64231864e
+size 497807197

checkpoint-10/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62328148c8e4c0ce2bb0650f6c47af0c53d9f3345dec0c8e4e46294c02b4f424
+size 14575

checkpoint-10/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0dbc54c2481c4ea53212b7d37539c1f37bd31b035ecca9d298f9ed7383571b40
+size 627

checkpoint-10/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": 1.6543781757354736,
+  "best_model_checkpoint": "./math_english_to_latex/checkpoint-10",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5e-05,
+      "loss": 4.017,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.3664,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6543781757354736,
+      "eval_runtime": 0.0554,
+      "eval_samples_per_second": 180.399,
+      "eval_steps_per_second": 18.04,
+      "step": 10
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 694056960000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-10/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
+size 4027

checkpoint-20/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./math_book",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-20/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.3"
+}

checkpoint-20/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1b7667f4b02de4be732f087c72e0b013cf844de2b11f677650711381c2deb5
+size 995641861

checkpoint-20/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bcc43425abb1dea14dd8311262f4c9b53cdfd4bc4644a96742e23c0213e8bba
+size 497807197

checkpoint-20/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:057c645c56f68344ed12cf18ea084316d300ef23ef187596b39adcec82bbd233
+size 14575

checkpoint-20/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:218685351f80f0f57d14c858d13411acae1cf38e48ed96475c40a18dd6651ff9
+size 627

checkpoint-20/trainer_state.json

@@ -0,0 +1,59 @@
+{
+  "best_metric": 0.9639002084732056,
+  "best_model_checkpoint": "./math_english_to_latex/checkpoint-20",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5e-05,
+      "loss": 4.017,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.3664,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6543781757354736,
+      "eval_runtime": 0.0554,
+      "eval_samples_per_second": 180.399,
+      "eval_steps_per_second": 18.04,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.5e-05,
+      "loss": 1.5286,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 1.1415,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9639002084732056,
+      "eval_runtime": 0.0432,
+      "eval_samples_per_second": 231.663,
+      "eval_steps_per_second": 23.166,
+      "step": 20
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 1412610048000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-20/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
+size 4027

checkpoint-30/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./math_book",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-30/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.3"
+}

checkpoint-30/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e68e06dc6b13221fcecfabefc480e582e077d12787eb3924b4b868a29c1c9a51
+size 995641861

checkpoint-30/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614ddbf13abcd71e5f5d73eab2c13f9495ce3ae76f5421fd0ad0e3601d35ee27
+size 497807197

checkpoint-30/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17aecbce0613ea0c67554a9c2289b172a9e286beca6035c8c06f4bfef55b9b70
+size 14575

checkpoint-30/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8948c2ceacdd0aa40c8e2cda98255fcdabc97f46c055f4ac17431041ab0b3492
+size 627

checkpoint-30/trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": 0.9328243136405945,
+  "best_model_checkpoint": "./math_english_to_latex/checkpoint-30",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5e-05,
+      "loss": 4.017,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.3664,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6543781757354736,
+      "eval_runtime": 0.0554,
+      "eval_samples_per_second": 180.399,
+      "eval_steps_per_second": 18.04,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.5e-05,
+      "loss": 1.5286,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 1.1415,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9639002084732056,
+      "eval_runtime": 0.0432,
+      "eval_samples_per_second": 231.663,
+      "eval_steps_per_second": 23.166,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0088,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.8763,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9328243136405945,
+      "eval_runtime": 0.0558,
+      "eval_samples_per_second": 179.081,
+      "eval_steps_per_second": 17.908,
+      "step": 30
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2104625664000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-30/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
+size 4027

checkpoint-40/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./math_book",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-40/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.3"
+}

checkpoint-40/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3453d46a769b00834686d59fb20cb1c28d3a6e2b3ad5672ad85359cf7895f8
+size 995641861

checkpoint-40/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:775f950a6d635bf980bbe63af2b91b6ff92e9f7347fb7f90a8fc276e946cb0ee
+size 497807197

checkpoint-40/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95d6249fe5dbe9ed1bdc4e1e9d80fa12fbc07191f47a1e57dc947f3569fdc481
+size 14575

checkpoint-40/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65d499424d0de0fd41d728ede1e4893a9a720923ec53cfd9bdd2b1d9dc3ef04c
+size 627

checkpoint-40/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8390220403671265,
+  "best_model_checkpoint": "./math_english_to_latex/checkpoint-40",
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5e-05,
+      "loss": 4.017,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.3664,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6543781757354736,
+      "eval_runtime": 0.0554,
+      "eval_samples_per_second": 180.399,
+      "eval_steps_per_second": 18.04,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.5e-05,
+      "loss": 1.5286,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 1.1415,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9639002084732056,
+      "eval_runtime": 0.0432,
+      "eval_samples_per_second": 231.663,
+      "eval_steps_per_second": 23.166,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0088,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.8763,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9328243136405945,
+      "eval_runtime": 0.0558,
+      "eval_samples_per_second": 179.081,
+      "eval_steps_per_second": 17.908,
+      "step": 30
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7908,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 0.7064,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8390220403671265,
+      "eval_runtime": 0.0587,
+      "eval_samples_per_second": 170.325,
+      "eval_steps_per_second": 17.032,
+      "step": 40
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 2821137408000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-40/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
+size 4027

checkpoint-50/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "./math_book",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-50/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.33.3"
+}

checkpoint-50/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2589c0138c8106a780a99c8ce6a96448b92015473973706d98a0a4863ca1fb6c
+size 995641861

checkpoint-50/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a55534c9559377760090a8313f92652a5e9dfb16a1f0b54e7dcdcc6759c75e34
+size 497807197

checkpoint-50/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd6c953ef6c5d1b59c7873d17cbf35f053273ce2e932635048554e043bf5520
+size 14575

checkpoint-50/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0056b270b78cdea3e106b2ed4ba29feeb330610d33a86c55b973dc5c9fa3140
+size 627

checkpoint-50/trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": 0.8027936816215515,
+  "best_model_checkpoint": "./math_english_to_latex/checkpoint-50",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.5e-05,
+      "loss": 4.017,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4e-05,
+      "loss": 2.3664,
+      "step": 10
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6543781757354736,
+      "eval_runtime": 0.0554,
+      "eval_samples_per_second": 180.399,
+      "eval_steps_per_second": 18.04,
+      "step": 10
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.5e-05,
+      "loss": 1.5286,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3e-05,
+      "loss": 1.1415,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.9639002084732056,
+      "eval_runtime": 0.0432,
+      "eval_samples_per_second": 231.663,
+      "eval_steps_per_second": 23.166,
+      "step": 20
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0088,
+      "step": 25
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2e-05,
+      "loss": 0.8763,
+      "step": 30
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.9328243136405945,
+      "eval_runtime": 0.0558,
+      "eval_samples_per_second": 179.081,
+      "eval_steps_per_second": 17.908,
+      "step": 30
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.5e-05,
+      "loss": 0.7908,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1e-05,
+      "loss": 0.7064,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.8390220403671265,
+      "eval_runtime": 0.0587,
+      "eval_samples_per_second": 170.325,
+      "eval_steps_per_second": 17.032,
+      "step": 40
+    },
+    {
+      "epoch": 4.5,
+      "learning_rate": 5e-06,
+      "loss": 0.7189,
+      "step": 45
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0,
+      "loss": 0.6468,
+      "step": 50
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.8027936816215515,
+      "eval_runtime": 0.045,
+      "eval_samples_per_second": 222.202,
+      "eval_steps_per_second": 22.22,
+      "step": 50
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 3529483776000.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-50/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:303ce339a7f76da035116fc250a1a1200a7a835e1425bcc16f4bcc1059494c98
+size 4027

runs/Sep29_04-53-15_5b6467461428/events.out.tfevents.1695963195.5b6467461428.3940.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65ecf37153b98806ea96d1342c2f524c5b8c35d50e4c4b54d3396929d292b21d
+size 8019