Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb9f11c9003f340461725dc7297d65fa37d8ed44ad6b899737e39bf1fe1965f
+oid sha256:1558f8f3b6709991de1156ad221dbbdf7d5dabb7b46140e13a96eb876244959b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41854af2f98026ea351810b8e4850d6ddfa1b61b1aba2e2050031eb7d3b0ad61
+oid sha256:4f6f77f1f851d0fba6444ff5726c2d296d9123b06ec2004b96ddc764744b3e56
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c56f0790a78b5bf94a6d9091aff732ba7c09085fac6332b7af37dc01180ca7a
+oid sha256:ae36bb717637705ccf36930f0382ae2311690921b7fbd2ef59134021fd9f41e2
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a542f1c496712442c243c68480fcd35a6a054b97de0a18b9c830f9d460f75751
+oid sha256:e5191e34bf07b9a26ff951371bb530de8d3883e6c662e9fa885f57708280595c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bbfeeb4a67287e0876b286a9d02dcf5e852924fb2a1014ffe07c800afbdc2cc0
+oid sha256:d881daf90b0f348c921458b2aee19988c682c2bb93b1091bc3f03cebb85755e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17923e9de734c7100d522900edd1d31dd02ff43451edcdc4f2a469d2d3deb973
+oid sha256:12d446410c4bd04deaf0ebbcdf51a6d30f535f26352b8913d11627a7626a157a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.058360081704114386,
+  "epoch": 0.11672016340822877,
   "eval_steps": 500,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -182,6 +182,181 @@
       "learning_rate": 0.00010654031292301432,
       "loss": 0.7009,
       "step": 25
+    },
+    {
+      "epoch": 0.06069448497227896,
+      "grad_norm": 0.2985963523387909,
+      "learning_rate": 0.0001,
+      "loss": 0.714,
+      "step": 26
+    },
+    {
+      "epoch": 0.06302888824044353,
+      "grad_norm": 0.2679181694984436,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.6831,
+      "step": 27
+    },
+    {
+      "epoch": 0.06536329150860812,
+      "grad_norm": 0.254097044467926,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.9036,
+      "step": 28
+    },
+    {
+      "epoch": 0.06769769477677269,
+      "grad_norm": 0.25508198142051697,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.7911,
+      "step": 29
+    },
+    {
+      "epoch": 0.07003209804493726,
+      "grad_norm": 0.25058841705322266,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.7423,
+      "step": 30
+    },
+    {
+      "epoch": 0.07236650131310184,
+      "grad_norm": 0.25600212812423706,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.8124,
+      "step": 31
+    },
+    {
+      "epoch": 0.07470090458126641,
+      "grad_norm": 0.24672138690948486,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.7959,
+      "step": 32
+    },
+    {
+      "epoch": 0.077035307849431,
+      "grad_norm": 0.23841053247451782,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.7236,
+      "step": 33
+    },
+    {
+      "epoch": 0.07936971111759557,
+      "grad_norm": 0.2680072486400604,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.7722,
+      "step": 34
+    },
+    {
+      "epoch": 0.08170411438576014,
+      "grad_norm": 0.2535754144191742,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.7169,
+      "step": 35
+    },
+    {
+      "epoch": 0.08403851765392471,
+      "grad_norm": 0.31870993971824646,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.7683,
+      "step": 36
+    },
+    {
+      "epoch": 0.08637292092208929,
+      "grad_norm": 0.2390068918466568,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.9436,
+      "step": 37
+    },
+    {
+      "epoch": 0.08870732419025387,
+      "grad_norm": 0.24789878726005554,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.8016,
+      "step": 38
+    },
+    {
+      "epoch": 0.09104172745841844,
+      "grad_norm": 0.2508408725261688,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.7239,
+      "step": 39
+    },
+    {
+      "epoch": 0.09337613072658302,
+      "grad_norm": 0.2461533099412918,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.6868,
+      "step": 40
+    },
+    {
+      "epoch": 0.09571053399474759,
+      "grad_norm": 0.23145893216133118,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.7022,
+      "step": 41
+    },
+    {
+      "epoch": 0.09804493726291216,
+      "grad_norm": 0.27093321084976196,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.7102,
+      "step": 42
+    },
+    {
+      "epoch": 0.10037934053107675,
+      "grad_norm": 0.2575005292892456,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.8102,
+      "step": 43
+    },
+    {
+      "epoch": 0.10271374379924132,
+      "grad_norm": 0.2539258599281311,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.7719,
+      "step": 44
+    },
+    {
+      "epoch": 0.1050481470674059,
+      "grad_norm": 0.2590281069278717,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.7796,
+      "step": 45
+    },
+    {
+      "epoch": 0.10738255033557047,
+      "grad_norm": 0.2578396201133728,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.8162,
+      "step": 46
+    },
+    {
+      "epoch": 0.10971695360373504,
+      "grad_norm": 0.23866446316242218,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.7376,
+      "step": 47
+    },
+    {
+      "epoch": 0.11205135687189963,
+      "grad_norm": 0.23026113212108612,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.7812,
+      "step": 48
+    },
+    {
+      "epoch": 0.1143857601400642,
+      "grad_norm": 0.27130571007728577,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.7669,
+      "step": 49
+    },
+    {
+      "epoch": 0.11672016340822877,
+      "grad_norm": 0.2607179284095764,
+      "learning_rate": 0.0,
+      "loss": 0.7356,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -196,12 +371,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.4893387187277005e+17,
+  "total_flos": 2.9842415890622054e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null