Upload folder using huggingface_hub

README.md

@@ -1,6 +1,6 @@
 ---
 library_name: peft
-base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+base_model: h2oai/h2o-danube-1.8b-base
 ---
 
 # Model Card for Model ID

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T",
+  "base_model_name_or_path": "h2oai/h2o-danube-1.8b-base",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e443a4b77690ae8ea98866ecd80948a9ac967af43ca6c41b123d7813f98f1a1b
-size 201892112
+oid sha256:a25dc5f18c13ba001c3dd4833b38998495bca32e4fc2b3862189b49977d9d0a4
+size 276869160

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c23aa512c4ca59dbb6e55d07e4ed63dff8046ed1c4c66a8da6dd475a75706df
-size 403891130
+oid sha256:d794d064d32b160d37fa1fc880603b241704ea283e6b24f7548164dcddcb28ef
+size 553854714

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8ab280b54fa9a51b7dff88a6e54c1c3adf0020d8bcd2afab4f9808dd880e6a7
+oid sha256:dd38096c5f4eb91f3c792eb437a4956dc2c0d979024cbb20afe0a69ea7d2a253
 size 14244

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ccb54d0139ddf32a93ee725362dd8028f6a8c59e1e2faa2e66ab1b6583eb8b9
+oid sha256:ca1b350e5e1233e1d4e9c4bf5bb67e8477013f852f64ba2692581bc4acde2d13
 size 1064

trainer_state.json

@@ -1,218 +1,164 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9990680335507922,
+  "epoch": 0.9846153846153847,
   "eval_steps": 500,
-  "global_step": 67,
+  "global_step": 48,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
-      "learning_rate": 1.3333333333333333e-05,
-      "loss": 2.4258,
+      "epoch": 0.04,
+      "learning_rate": 0.0,
+      "loss": 1.9733,
       "step": 2
     },
     {
-      "epoch": 0.06,
-      "learning_rate": 1.9987954562051724e-05,
-      "loss": 1.57,
+      "epoch": 0.08,
+      "learning_rate": 0.0,
+      "loss": 2.2221,
       "step": 4
     },
     {
-      "epoch": 0.09,
-      "learning_rate": 1.989176509964781e-05,
-      "loss": 1.4754,
+      "epoch": 0.12,
+      "learning_rate": 1e-05,
+      "loss": 2.3779,
       "step": 6
     },
     {
-      "epoch": 0.12,
-      "learning_rate": 1.9700312531945444e-05,
-      "loss": 1.6236,
+      "epoch": 0.16,
+      "learning_rate": 1.9976687691905394e-05,
+      "loss": 2.3971,
       "step": 8
     },
     {
-      "epoch": 0.15,
-      "learning_rate": 1.941544065183021e-05,
-      "loss": 1.4219,
+      "epoch": 0.21,
+      "learning_rate": 1.9976687691905394e-05,
+      "loss": 2.5739,
       "step": 10
     },
     {
-      "epoch": 0.18,
-      "learning_rate": 1.9039892931234434e-05,
-      "loss": 1.776,
+      "epoch": 0.25,
+      "learning_rate": 1.9976687691905394e-05,
+      "loss": 3.2187,
       "step": 12
     },
     {
-      "epoch": 0.21,
-      "learning_rate": 1.8577286100002723e-05,
-      "loss": 2.0921,
+      "epoch": 0.29,
+      "learning_rate": 1.979084087682323e-05,
+      "loss": 1.9869,
       "step": 14
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 1.803207531480645e-05,
-      "loss": 2.4632,
+      "epoch": 0.33,
+      "learning_rate": 1.9422609221188208e-05,
+      "loss": 2.2685,
       "step": 16
     },
     {
-      "epoch": 0.27,
-      "learning_rate": 1.7409511253549592e-05,
-      "loss": 1.8968,
+      "epoch": 0.37,
+      "learning_rate": 1.8878852184023754e-05,
+      "loss": 2.4541,
       "step": 18
     },
     {
-      "epoch": 0.3,
-      "learning_rate": 1.6715589548470187e-05,
-      "loss": 1.4684,
+      "epoch": 0.41,
+      "learning_rate": 1.816969893010442e-05,
+      "loss": 2.414,
       "step": 20
     },
     {
-      "epoch": 0.33,
-      "learning_rate": 1.5956993044924334e-05,
-      "loss": 1.3878,
+      "epoch": 0.45,
+      "learning_rate": 1.730835964278124e-05,
+      "loss": 2.4032,
       "step": 22
     },
     {
-      "epoch": 0.36,
-      "learning_rate": 1.5141027441932217e-05,
-      "loss": 1.4707,
+      "epoch": 0.49,
+      "learning_rate": 1.631087944326053e-05,
+      "loss": 2.9531,
       "step": 24
     },
     {
-      "epoch": 0.39,
-      "learning_rate": 1.4275550934302822e-05,
-      "loss": 1.3869,
+      "epoch": 0.53,
+      "learning_rate": 1.5195839500354337e-05,
+      "loss": 2.1097,
       "step": 26
     },
     {
-      "epoch": 0.42,
-      "learning_rate": 1.3368898533922202e-05,
-      "loss": 1.7064,
+      "epoch": 0.57,
+      "learning_rate": 1.3984010898462417e-05,
+      "loss": 2.1521,
       "step": 28
     },
     {
-      "epoch": 0.45,
-      "learning_rate": 1.242980179903264e-05,
-      "loss": 1.9753,
+      "epoch": 0.62,
+      "learning_rate": 1.2697967711570243e-05,
+      "loss": 2.278,
       "step": 30
     },
     {
-      "epoch": 0.48,
-      "learning_rate": 1.1467304744553618e-05,
-      "loss": 2.0576,
+      "epoch": 0.66,
+      "learning_rate": 1.1361666490962468e-05,
+      "loss": 2.2287,
       "step": 32
     },
     {
-      "epoch": 0.51,
-      "learning_rate": 1.0490676743274181e-05,
-      "loss": 1.923,
+      "epoch": 0.7,
+      "learning_rate": 1e-05,
+      "loss": 2.5034,
       "step": 34
     },
     {
-      "epoch": 0.54,
-      "learning_rate": 9.50932325672582e-06,
-      "loss": 1.3469,
+      "epoch": 0.74,
+      "learning_rate": 8.638333509037537e-06,
+      "loss": 3.026,
       "step": 36
     },
     {
-      "epoch": 0.57,
-      "learning_rate": 8.532695255446384e-06,
-      "loss": 1.4244,
+      "epoch": 0.78,
+      "learning_rate": 7.3020322884297565e-06,
+      "loss": 1.7926,
       "step": 38
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 7.570198200967363e-06,
-      "loss": 1.4338,
+      "epoch": 0.82,
+      "learning_rate": 6.015989101537586e-06,
+      "loss": 2.1822,
       "step": 40
     },
     {
-      "epoch": 0.63,
-      "learning_rate": 6.631101466077801e-06,
-      "loss": 1.2679,
+      "epoch": 0.86,
+      "learning_rate": 4.804160499645667e-06,
+      "loss": 2.2541,
       "step": 42
     },
     {
-      "epoch": 0.66,
-      "learning_rate": 5.724449065697182e-06,
-      "loss": 1.5914,
+      "epoch": 0.9,
+      "learning_rate": 3.689120556739475e-06,
+      "loss": 2.1944,
       "step": 44
     },
     {
-      "epoch": 0.69,
-      "learning_rate": 4.858972558067784e-06,
-      "loss": 1.8144,
+      "epoch": 0.94,
+      "learning_rate": 2.691640357218759e-06,
+      "loss": 2.4724,
       "step": 46
     },
-    {
-      "epoch": 0.72,
-      "learning_rate": 4.043006955075667e-06,
-      "loss": 2.1111,
-      "step": 48
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 3.284410451529816e-06,
-      "loss": 2.377,
-      "step": 50
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 2.5904887464504115e-06,
-      "loss": 1.3301,
-      "step": 52
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 1.967924685193552e-06,
-      "loss": 1.4278,
-      "step": 54
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 1.4227138999972801e-06,
-      "loss": 1.4215,
-      "step": 56
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 9.601070687655667e-07,
-      "loss": 1.3279,
-      "step": 58
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 5.845593481697931e-07,
-      "loss": 1.6736,
-      "step": 60
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 2.996874680545603e-07,
-      "loss": 1.7918,
-      "step": 62
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 1.0823490035218986e-07,
-      "loss": 1.9479,
-      "step": 64
-    },
     {
       "epoch": 0.98,
-      "learning_rate": 1.2045437948275952e-08,
-      "loss": 1.6699,
-      "step": 66
+      "learning_rate": 1.8303010698955803e-06,
+      "loss": 2.7384,
+      "step": 48
     }
   ],
   "logging_steps": 2,
-  "max_steps": 67,
+  "max_steps": 48,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 3851865594519552.0,
+  "total_flos": 4332935139001344.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfe66d78fbcb57ad2c7ff0a658e305d43b78796e68a48c6432c6805f2f7c823e
+oid sha256:26ad374dc3cfd70d72688444627da4b827ca8fff71960781e47a734fc51e3855
 size 4728