Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d4d4c98b4e8263be4a0998c2529ed6bfb3f7662532713e87bbd738b7288cc48
+oid sha256:047625ce0482857cd706667a8e58683e86d85f280d360366fa2110b61c553f3e
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae6f2b6cc1e4d89c8f6647f918f6183471b07132211250bd8d62b2b3444ee20b
+oid sha256:baa3c12fe12b7fc8b304e63b679f8f27df44eaf555a0100c49ea317a5572a40f
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83cf2fec0ca7ec51294631dd6aba678fcbda8c7622905919b355275294701a3f
+oid sha256:45d965a8183a13148716d4b122cea945c60bc9f5ac1bb607480c425d22ce2ec2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb167787cdd9594eed637547cf4a56f4a4d8ea359757a120c76bb5d91190782
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08542141230068337,
+  "epoch": 0.11389521640091116,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 152.601,
       "eval_steps_per_second": 76.3,
       "step": 75
+    },
+    {
+      "epoch": 0.08656036446469248,
+      "grad_norm": 1.660568356513977,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 7.2212,
+      "step": 76
+    },
+    {
+      "epoch": 0.08769931662870159,
+      "grad_norm": 1.246217966079712,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 7.2083,
+      "step": 77
+    },
+    {
+      "epoch": 0.0888382687927107,
+      "grad_norm": 3.0959270000457764,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 6.4632,
+      "step": 78
+    },
+    {
+      "epoch": 0.08997722095671981,
+      "grad_norm": 0.9086253643035889,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 7.066,
+      "step": 79
+    },
+    {
+      "epoch": 0.09111617312072894,
+      "grad_norm": 1.0901901721954346,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 7.1939,
+      "step": 80
+    },
+    {
+      "epoch": 0.09225512528473805,
+      "grad_norm": 1.085433006286621,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 6.8371,
+      "step": 81
+    },
+    {
+      "epoch": 0.09339407744874716,
+      "grad_norm": 1.2457612752914429,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 6.5737,
+      "step": 82
+    },
+    {
+      "epoch": 0.09453302961275627,
+      "grad_norm": 1.0281388759613037,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 7.1273,
+      "step": 83
+    },
+    {
+      "epoch": 0.09567198177676538,
+      "grad_norm": 1.773342490196228,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 6.4927,
+      "step": 84
+    },
+    {
+      "epoch": 0.09681093394077449,
+      "grad_norm": 1.254052996635437,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 6.6559,
+      "step": 85
+    },
+    {
+      "epoch": 0.0979498861047836,
+      "grad_norm": 1.370526909828186,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 7.3592,
+      "step": 86
+    },
+    {
+      "epoch": 0.09908883826879271,
+      "grad_norm": 1.2687151432037354,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 7.379,
+      "step": 87
+    },
+    {
+      "epoch": 0.10022779043280182,
+      "grad_norm": 1.558264136314392,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 7.3007,
+      "step": 88
+    },
+    {
+      "epoch": 0.10136674259681093,
+      "grad_norm": 0.8217010498046875,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 6.8845,
+      "step": 89
+    },
+    {
+      "epoch": 0.10250569476082004,
+      "grad_norm": 0.9289836883544922,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 7.1951,
+      "step": 90
+    },
+    {
+      "epoch": 0.10364464692482915,
+      "grad_norm": 1.013576626777649,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 6.769,
+      "step": 91
+    },
+    {
+      "epoch": 0.10478359908883828,
+      "grad_norm": 1.2535510063171387,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 6.6248,
+      "step": 92
+    },
+    {
+      "epoch": 0.10592255125284739,
+      "grad_norm": 1.0415903329849243,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 6.6624,
+      "step": 93
+    },
+    {
+      "epoch": 0.1070615034168565,
+      "grad_norm": 0.985383927822113,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 7.1897,
+      "step": 94
+    },
+    {
+      "epoch": 0.1082004555808656,
+      "grad_norm": 1.099430799484253,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 6.5314,
+      "step": 95
+    },
+    {
+      "epoch": 0.10933940774487472,
+      "grad_norm": 1.0735303163528442,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 6.9514,
+      "step": 96
+    },
+    {
+      "epoch": 0.11047835990888383,
+      "grad_norm": 1.0837327241897583,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 6.6242,
+      "step": 97
+    },
+    {
+      "epoch": 0.11161731207289294,
+      "grad_norm": 1.2384315729141235,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 7.505,
+      "step": 98
+    },
+    {
+      "epoch": 0.11275626423690205,
+      "grad_norm": 0.9852325320243835,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 7.0612,
+      "step": 99
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "grad_norm": 0.9873253107070923,
+      "learning_rate": 0.0,
+      "loss": 6.9599,
+      "step": 100
+    },
+    {
+      "epoch": 0.11389521640091116,
+      "eval_loss": 6.888667106628418,
+      "eval_runtime": 2.3944,
+      "eval_samples_per_second": 154.527,
+      "eval_steps_per_second": 77.264,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -578,12 +761,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8358714408960.0,
+  "total_flos": 11276069634048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null