Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6cc0f3618df51e34558eea4e9764bf4ebfafd1dc0e4bfb9c2169deabe1f686
+oid sha256:19300d8c70ea02995c0c2cdaffbee3467827e70b916d2906f3c6729c774f531c
 size 134264397

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6c70ece44b17f0f5535d293ed5702493c45a22e5bd4b0cabf2d1051768d8748
+oid sha256:4b71a7eadddc38545a5bf0c26f2f825713f439fd01d84d4d6a53ad84420f286a
 size 268514437

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7758c13a7c7ff5a480045f73d2351906a68dc6fedb3251c796634153f77608a7
+oid sha256:4ac5d7eec6c351df2da183b4761a909ee821de3b86d81f2bc121c1dbf0ea69c1
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a03bd55ec967989abd72e176bb55c4192fe56bafe1ccfdaea2dc4dd09d252069
+oid sha256:aaf30ebf0bcd9ed5383b022bb911f7c2039ea918b316aeff6dd531cc9d7be661
 size 627

trainer_state.json

@@ -1,319 +1,211 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04406985071338071,
+  "epoch": 0.9941747572815534,
   "eval_steps": 500,
-  "global_step": 100,
+  "global_step": 64,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.0,
+      "epoch": 0.03,
       "learning_rate": 2e-05,
-      "loss": 1.7824,
+      "loss": 2.2297,
       "step": 2
     },
     {
-      "epoch": 0.0,
+      "epoch": 0.06,
       "learning_rate": 2e-05,
-      "loss": 1.6267,
+      "loss": 2.4339,
       "step": 4
     },
     {
-      "epoch": 0.0,
+      "epoch": 0.09,
       "learning_rate": 2e-05,
-      "loss": 1.4166,
+      "loss": 2.3035,
       "step": 6
     },
     {
-      "epoch": 0.0,
+      "epoch": 0.12,
       "learning_rate": 2e-05,
-      "loss": 1.6107,
+      "loss": 2.4969,
       "step": 8
     },
     {
-      "epoch": 0.0,
+      "epoch": 0.16,
       "learning_rate": 2e-05,
-      "loss": 1.787,
+      "loss": 2.5102,
       "step": 10
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.19,
       "learning_rate": 2e-05,
-      "loss": 1.6919,
+      "loss": 2.6153,
       "step": 12
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.22,
       "learning_rate": 2e-05,
-      "loss": 1.7957,
+      "loss": 2.5576,
       "step": 14
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.25,
       "learning_rate": 2e-05,
-      "loss": 1.889,
+      "loss": 2.7665,
       "step": 16
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.28,
       "learning_rate": 2e-05,
-      "loss": 1.5632,
+      "loss": 2.2178,
       "step": 18
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.31,
       "learning_rate": 2e-05,
-      "loss": 1.8422,
+      "loss": 2.2634,
       "step": 20
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.34,
       "learning_rate": 2e-05,
-      "loss": 1.7788,
+      "loss": 2.2644,
       "step": 22
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.37,
       "learning_rate": 2e-05,
-      "loss": 1.6549,
+      "loss": 2.52,
       "step": 24
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.4,
       "learning_rate": 2e-05,
-      "loss": 1.6339,
+      "loss": 2.5197,
       "step": 26
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.43,
       "learning_rate": 2e-05,
-      "loss": 1.4763,
+      "loss": 2.6477,
       "step": 28
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.47,
       "learning_rate": 2e-05,
-      "loss": 1.7348,
+      "loss": 2.5486,
       "step": 30
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.5,
       "learning_rate": 2e-05,
-      "loss": 1.5029,
+      "loss": 2.8709,
       "step": 32
     },
     {
-      "epoch": 0.01,
+      "epoch": 0.53,
       "learning_rate": 2e-05,
-      "loss": 1.6833,
+      "loss": 2.1863,
       "step": 34
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.56,
       "learning_rate": 2e-05,
-      "loss": 1.8533,
+      "loss": 2.4213,
       "step": 36
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.59,
       "learning_rate": 2e-05,
-      "loss": 1.5965,
+      "loss": 2.4462,
       "step": 38
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.62,
       "learning_rate": 2e-05,
-      "loss": 1.9984,
+      "loss": 2.4843,
       "step": 40
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.65,
       "learning_rate": 2e-05,
-      "loss": 2.24,
+      "loss": 2.5647,
       "step": 42
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.68,
       "learning_rate": 2e-05,
-      "loss": 2.4573,
+      "loss": 2.4689,
       "step": 44
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.71,
       "learning_rate": 2e-05,
-      "loss": 2.5037,
+      "loss": 2.4771,
       "step": 46
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.75,
       "learning_rate": 2e-05,
-      "loss": 2.3726,
+      "loss": 2.5889,
       "step": 48
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.78,
       "learning_rate": 2e-05,
-      "loss": 2.4345,
+      "loss": 2.2531,
       "step": 50
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.81,
       "learning_rate": 2e-05,
-      "loss": 1.8871,
+      "loss": 2.343,
       "step": 52
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.84,
       "learning_rate": 2e-05,
-      "loss": 1.7946,
+      "loss": 2.4095,
       "step": 54
     },
     {
-      "epoch": 0.02,
+      "epoch": 0.87,
       "learning_rate": 2e-05,
-      "loss": 1.4413,
+      "loss": 2.3737,
       "step": 56
     },
     {
-      "epoch": 0.03,
+      "epoch": 0.9,
       "learning_rate": 2e-05,
-      "loss": 1.5714,
+      "loss": 2.4751,
       "step": 58
     },
     {
-      "epoch": 0.03,
+      "epoch": 0.93,
       "learning_rate": 2e-05,
-      "loss": 1.6009,
+      "loss": 2.4349,
       "step": 60
     },
     {
-      "epoch": 0.03,
+      "epoch": 0.96,
       "learning_rate": 2e-05,
-      "loss": 1.5555,
+      "loss": 2.5477,
       "step": 62
     },
     {
-      "epoch": 0.03,
+      "epoch": 0.99,
       "learning_rate": 2e-05,
-      "loss": 1.5997,
+      "loss": 2.4022,
       "step": 64
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.7674,
-      "step": 66
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.5811,
-      "step": 68
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.546,
-      "step": 70
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.4433,
-      "step": 72
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.3861,
-      "step": 74
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.4049,
-      "step": 76
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 2e-05,
-      "loss": 1.4049,
-      "step": 78
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.4278,
-      "step": 80
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.3433,
-      "step": 82
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.4638,
-      "step": 84
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.6087,
-      "step": 86
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.6304,
-      "step": 88
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.6342,
-      "step": 90
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 1.8168,
-      "step": 92
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 2.1358,
-      "step": 94
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 2.1509,
-      "step": 96
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 2.1125,
-      "step": 98
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 2e-05,
-      "loss": 2.124,
-      "step": 100
     }
   ],
   "logging_steps": 2,
-  "max_steps": 6807,
+  "max_steps": 192,
   "num_train_epochs": 3,
-  "save_steps": 50,
-  "total_flos": 1989313022754816.0,
+  "save_steps": 64,
+  "total_flos": 1760434460049408.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def49e1ad1653ca9622eb4821d5fbdae15157a97ad5c8bed4fdd5675c9dd3360
+oid sha256:988a436173b01c17ed327e498d27da688b14df386aca98b672acc224467a1ac7
 size 4027