Initial upload of custom EirGrid PatchTST model

checkpoint-1000/config.json

@@ -0,0 +1,51 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForPrediction"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "channel_attention": false,
+  "channel_consistent_masking": false,
+  "context_length": 512,
+  "d_model": 128,
+  "distribution_output": "student_t",
+  "do_mask_input": null,
+  "dropout": 0.2,
+  "dtype": "float32",
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.0,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 4,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 1,
+  "num_parallel_samples": 100,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 16,
+  "patch_stride": 1,
+  "path_dropout": 0.0,
+  "pooling_type": "mean",
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 96,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "stride": 8,
+  "transformers_version": "4.57.2",
+  "unmasked_channel_indices": null,
+  "use_cls_token": false
+}

checkpoint-1000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7783aaa156b697cdb78eabbaa2a26d0d28a950a00dd764730d39163ad101d481
+size 2706232

checkpoint-1000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c439cc54b1a36d311f8fadb5da32ac3e5db22d2a64c3c4a087093a26936c38c8
+size 4919755

checkpoint-1000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
+size 14645

checkpoint-1000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5aba71615288bb81f9b9c6331534f2597fe07aa26167e1a3fa22a9f6842cf66
+size 1465

checkpoint-1000/trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.882352941176471,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.6052117347717285,
+      "learning_rate": 0.000941764705882353,
+      "loss": 0.4992,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.9228031635284424,
+      "learning_rate": 0.0008829411764705883,
+      "loss": 0.3017,
+      "step": 200
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.9054152965545654,
+      "learning_rate": 0.0008241176470588235,
+      "loss": 0.2262,
+      "step": 300
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.4709264039993286,
+      "learning_rate": 0.0007652941176470588,
+      "loss": 0.2054,
+      "step": 400
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.9707149267196655,
+      "learning_rate": 0.0007064705882352941,
+      "loss": 0.189,
+      "step": 500
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 1.0779001712799072,
+      "learning_rate": 0.0006476470588235295,
+      "loss": 0.1946,
+      "step": 600
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.618778645992279,
+      "learning_rate": 0.0005888235294117648,
+      "loss": 0.1707,
+      "step": 700
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.7503094673156738,
+      "learning_rate": 0.0005300000000000001,
+      "loss": 0.1713,
+      "step": 800
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 0.9175742268562317,
+      "learning_rate": 0.00047117647058823533,
+      "loss": 0.1562,
+      "step": 900
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 1.0091431140899658,
+      "learning_rate": 0.0004123529411764706,
+      "loss": 0.1596,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 66137131253760.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32774ff877551baa776c41f2f9ab000017cfa88cf56832d20d86e8ff5e86bb0b
+size 5841

checkpoint-1500/config.json

@@ -0,0 +1,51 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForPrediction"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "channel_attention": false,
+  "channel_consistent_masking": false,
+  "context_length": 512,
+  "d_model": 128,
+  "distribution_output": "student_t",
+  "do_mask_input": null,
+  "dropout": 0.2,
+  "dtype": "float32",
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.0,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 4,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 1,
+  "num_parallel_samples": 100,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 16,
+  "patch_stride": 1,
+  "path_dropout": 0.0,
+  "pooling_type": "mean",
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 96,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "stride": 8,
+  "transformers_version": "4.57.2",
+  "unmasked_channel_indices": null,
+  "use_cls_token": false
+}

checkpoint-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4147fcbbd8d86e98e56356a4eb8c3333f9186b73fdae01fa4fa644becca8d093
+size 2706232

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef63cec4e1f261f1d7cb317bbd0e54d94b5db5a929aa61da6bf62e65005fd884
+size 4919755

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:363c5df1543d2c82b2f13164f35bdd0367ceb32e7fa1b2f67c19df073a08b17b
+size 14645

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fc5e55673b02706cf235bd18ab925b394c852bf28a456273fa32aa1352cec0f
+size 1465

checkpoint-1500/trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.823529411764707,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.6052117347717285,
+      "learning_rate": 0.000941764705882353,
+      "loss": 0.4992,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.9228031635284424,
+      "learning_rate": 0.0008829411764705883,
+      "loss": 0.3017,
+      "step": 200
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.9054152965545654,
+      "learning_rate": 0.0008241176470588235,
+      "loss": 0.2262,
+      "step": 300
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.4709264039993286,
+      "learning_rate": 0.0007652941176470588,
+      "loss": 0.2054,
+      "step": 400
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.9707149267196655,
+      "learning_rate": 0.0007064705882352941,
+      "loss": 0.189,
+      "step": 500
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 1.0779001712799072,
+      "learning_rate": 0.0006476470588235295,
+      "loss": 0.1946,
+      "step": 600
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.618778645992279,
+      "learning_rate": 0.0005888235294117648,
+      "loss": 0.1707,
+      "step": 700
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.7503094673156738,
+      "learning_rate": 0.0005300000000000001,
+      "loss": 0.1713,
+      "step": 800
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 0.9175742268562317,
+      "learning_rate": 0.00047117647058823533,
+      "loss": 0.1562,
+      "step": 900
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 1.0091431140899658,
+      "learning_rate": 0.0004123529411764706,
+      "loss": 0.1596,
+      "step": 1000
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 0.6883541941642761,
+      "learning_rate": 0.0003535294117647059,
+      "loss": 0.1435,
+      "step": 1100
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.7159141898155212,
+      "learning_rate": 0.0002947058823529412,
+      "loss": 0.1385,
+      "step": 1200
+    },
+    {
+      "epoch": 7.647058823529412,
+      "grad_norm": 0.5263181924819946,
+      "learning_rate": 0.00023588235294117648,
+      "loss": 0.1278,
+      "step": 1300
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.7766987681388855,
+      "learning_rate": 0.00017705882352941178,
+      "loss": 0.1137,
+      "step": 1400
+    },
+    {
+      "epoch": 8.823529411764707,
+      "grad_norm": 0.5680007338523865,
+      "learning_rate": 0.00011823529411764706,
+      "loss": 0.109,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 99203629449216.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32774ff877551baa776c41f2f9ab000017cfa88cf56832d20d86e8ff5e86bb0b
+size 5841

checkpoint-1700/config.json

@@ -0,0 +1,51 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForPrediction"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "channel_attention": false,
+  "channel_consistent_masking": false,
+  "context_length": 512,
+  "d_model": 128,
+  "distribution_output": "student_t",
+  "do_mask_input": null,
+  "dropout": 0.2,
+  "dtype": "float32",
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.0,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 4,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 1,
+  "num_parallel_samples": 100,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 16,
+  "patch_stride": 1,
+  "path_dropout": 0.0,
+  "pooling_type": "mean",
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 96,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "stride": 8,
+  "transformers_version": "4.57.2",
+  "unmasked_channel_indices": null,
+  "use_cls_token": false
+}

checkpoint-1700/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21dc4879ece6a29c81f0a7f8d8308fc4abebdb09a65c0a1a3bcdcb183e3f3c3d
+size 2706232

checkpoint-1700/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4276747baa7d90ecde3827ea14aaa1aa4bd718694e6e32c90ab0470464454585
+size 4919755

checkpoint-1700/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17cd930da9783ca70bad4b9cdeee6a06c0acea8f34645a333c93341f487f66a3
+size 14645

checkpoint-1700/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:831b1bc8606cc8d89268945da8ee1eae567fffaf4b2bc45f4bc9b1b5eaa02c13
+size 1465

checkpoint-1700/trainer_state.json

@@ -0,0 +1,153 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1700,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.6052117347717285,
+      "learning_rate": 0.000941764705882353,
+      "loss": 0.4992,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.9228031635284424,
+      "learning_rate": 0.0008829411764705883,
+      "loss": 0.3017,
+      "step": 200
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.9054152965545654,
+      "learning_rate": 0.0008241176470588235,
+      "loss": 0.2262,
+      "step": 300
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.4709264039993286,
+      "learning_rate": 0.0007652941176470588,
+      "loss": 0.2054,
+      "step": 400
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.9707149267196655,
+      "learning_rate": 0.0007064705882352941,
+      "loss": 0.189,
+      "step": 500
+    },
+    {
+      "epoch": 3.5294117647058822,
+      "grad_norm": 1.0779001712799072,
+      "learning_rate": 0.0006476470588235295,
+      "loss": 0.1946,
+      "step": 600
+    },
+    {
+      "epoch": 4.117647058823529,
+      "grad_norm": 0.618778645992279,
+      "learning_rate": 0.0005888235294117648,
+      "loss": 0.1707,
+      "step": 700
+    },
+    {
+      "epoch": 4.705882352941177,
+      "grad_norm": 0.7503094673156738,
+      "learning_rate": 0.0005300000000000001,
+      "loss": 0.1713,
+      "step": 800
+    },
+    {
+      "epoch": 5.294117647058823,
+      "grad_norm": 0.9175742268562317,
+      "learning_rate": 0.00047117647058823533,
+      "loss": 0.1562,
+      "step": 900
+    },
+    {
+      "epoch": 5.882352941176471,
+      "grad_norm": 1.0091431140899658,
+      "learning_rate": 0.0004123529411764706,
+      "loss": 0.1596,
+      "step": 1000
+    },
+    {
+      "epoch": 6.470588235294118,
+      "grad_norm": 0.6883541941642761,
+      "learning_rate": 0.0003535294117647059,
+      "loss": 0.1435,
+      "step": 1100
+    },
+    {
+      "epoch": 7.0588235294117645,
+      "grad_norm": 0.7159141898155212,
+      "learning_rate": 0.0002947058823529412,
+      "loss": 0.1385,
+      "step": 1200
+    },
+    {
+      "epoch": 7.647058823529412,
+      "grad_norm": 0.5263181924819946,
+      "learning_rate": 0.00023588235294117648,
+      "loss": 0.1278,
+      "step": 1300
+    },
+    {
+      "epoch": 8.235294117647058,
+      "grad_norm": 0.7766987681388855,
+      "learning_rate": 0.00017705882352941178,
+      "loss": 0.1137,
+      "step": 1400
+    },
+    {
+      "epoch": 8.823529411764707,
+      "grad_norm": 0.5680007338523865,
+      "learning_rate": 0.00011823529411764706,
+      "loss": 0.109,
+      "step": 1500
+    },
+    {
+      "epoch": 9.411764705882353,
+      "grad_norm": 0.6185672879219055,
+      "learning_rate": 5.9411764705882355e-05,
+      "loss": 0.1049,
+      "step": 1600
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.800317108631134,
+      "learning_rate": 5.88235294117647e-07,
+      "loss": 0.1046,
+      "step": 1700
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 112426920837120.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1700/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32774ff877551baa776c41f2f9ab000017cfa88cf56832d20d86e8ff5e86bb0b
+size 5841

checkpoint-500/config.json

@@ -0,0 +1,51 @@
+{
+  "activation_function": "gelu",
+  "architectures": [
+    "PatchTSTForPrediction"
+  ],
+  "attention_dropout": 0.0,
+  "bias": true,
+  "channel_attention": false,
+  "channel_consistent_masking": false,
+  "context_length": 512,
+  "d_model": 128,
+  "distribution_output": "student_t",
+  "do_mask_input": null,
+  "dropout": 0.2,
+  "dtype": "float32",
+  "ff_dropout": 0.0,
+  "ffn_dim": 512,
+  "head_dropout": 0.0,
+  "init_std": 0.02,
+  "loss": "mse",
+  "mask_type": "random",
+  "mask_value": 0,
+  "model_type": "patchtst",
+  "norm_eps": 1e-05,
+  "norm_type": "batchnorm",
+  "num_attention_heads": 4,
+  "num_forecast_mask_patches": [
+    2
+  ],
+  "num_hidden_layers": 3,
+  "num_input_channels": 1,
+  "num_parallel_samples": 100,
+  "num_targets": 1,
+  "output_range": null,
+  "patch_length": 16,
+  "patch_stride": 1,
+  "path_dropout": 0.0,
+  "pooling_type": "mean",
+  "positional_dropout": 0.0,
+  "positional_encoding_type": "sincos",
+  "pre_norm": true,
+  "prediction_length": 96,
+  "random_mask_ratio": 0.5,
+  "scaling": "std",
+  "share_embedding": true,
+  "share_projection": true,
+  "stride": 8,
+  "transformers_version": "4.57.2",
+  "unmasked_channel_indices": null,
+  "use_cls_token": false
+}

checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f2a4df6a37059d8e9667493de8891843cbb4f04f005ae81c9bab11957dd97e8
+size 2706232

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d2823881ef847728d49306e0178c242950001ced89b5bc58ea56983f2dde9e8
+size 4919755

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d890428ddf5f25f5d14a33c2b07b254aeced1824515a0802d8099c5d1c1f9dc
+size 1465

checkpoint-500/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9411764705882355,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5882352941176471,
+      "grad_norm": 0.6052117347717285,
+      "learning_rate": 0.000941764705882353,
+      "loss": 0.4992,
+      "step": 100
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "grad_norm": 0.9228031635284424,
+      "learning_rate": 0.0008829411764705883,
+      "loss": 0.3017,
+      "step": 200
+    },
+    {
+      "epoch": 1.7647058823529411,
+      "grad_norm": 0.9054152965545654,
+      "learning_rate": 0.0008241176470588235,
+      "loss": 0.2262,
+      "step": 300
+    },
+    {
+      "epoch": 2.3529411764705883,
+      "grad_norm": 1.4709264039993286,
+      "learning_rate": 0.0007652941176470588,
+      "loss": 0.2054,
+      "step": 400
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.9707149267196655,
+      "learning_rate": 0.0007064705882352941,
+      "loss": 0.189,
+      "step": 500
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1700,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 33070633058304.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32774ff877551baa776c41f2f9ab000017cfa88cf56832d20d86e8ff5e86bb0b
+size 5841