Upload folder using huggingface_hub

flyte_training_config.json

@@ -1 +1 @@
-{"base_model": "togethercomputer/RedPajama-INCITE-Base-3B-v1", "data_path": "wikipedia", "data_name": "20220301.simple", "num_epochs": 5, "max_steps": -1, "learning_rate": 2e-05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "batch_size": 16, "micro_batch_size": 1, "val_set_size": 0, "group_by_length": false, "instruction_key": "instruction", "input_key": "input", "output_key": "output", "device_map": "auto", "cache_dir": null, "optim": "adamw_torch", "model_max_length": 512, "debug_mode": false, "debug_train_data_size": 1024, "wandb_project": ""}
+{"base_model": "togethercomputer/RedPajama-INCITE-Base-3B-v1", "data_path": "wikipedia", "data_name": "20220301.simple", "num_epochs": 10, "max_steps": -1, "learning_rate": 2e-05, "weight_decay": 0.02, "warmup_ratio": 0.03, "lr_scheduler_type": "cosine", "batch_size": 16, "micro_batch_size": 1, "val_set_size": 0, "group_by_length": false, "instruction_key": "instruction", "input_key": "input", "output_key": "output", "device_map": "auto", "cache_dir": null, "optim": "adamw_torch", "model_max_length": 512, "debug_mode": false, "debug_train_data_size": 1024, "wandb_project": ""}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3892be9a5a69f1bdc1a76ac3c79cf722f4608b39d7e72ba1ea4412996b3e0e
+oid sha256:eeaa01593806267e4358ec662b32448529e9521f7f15a6f131021450b6196cc2
 size 5686106713

trainer_state.json

@@ -1,25 +1,31 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3333333333333335,
-  "global_step": 5,
+  "epoch": 6.666666666666667,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 3.33,
-      "step": 5,
-      "total_flos": 2077564600320.0,
-      "train_loss": 2.06929931640625,
-      "train_runtime": 218.7837,
-      "train_samples_per_second": 4.319,
+      "epoch": 6.67,
+      "learning_rate": 2e-05,
+      "loss": 2.0319,
+      "step": 10
+    },
+    {
+      "epoch": 6.67,
+      "step": 10,
+      "total_flos": 4181427486720.0,
+      "train_loss": 2.031925582885742,
+      "train_runtime": 431.4804,
+      "train_samples_per_second": 4.38,
       "train_steps_per_second": 0.023
     }
   ],
-  "max_steps": 5,
-  "num_train_epochs": 5,
-  "total_flos": 2077564600320.0,
+  "max_steps": 10,
+  "num_train_epochs": 10,
+  "total_flos": 4181427486720.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f954b5220fecd13e835e992ca0ed4b4cbebb8a29156115f726c8b5905282a3a
+oid sha256:54edde13ce02c45f23a8f5849df5058faeed6968da673a0576bf1bf3d8463d11
 size 5563