Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91bd6e535a655553fcc688dfd66c2f6d767f0d294b1d5ac0fca9094949e9ac27
+oid sha256:bf0982be125e82f8e3e025b7d907e472dd770e1e3f5ad83ef4473e5365a253d6
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ab50054578b1f98b38a80e31fe5d3ca80cec2025126bcda9fac6150738c26ea
+oid sha256:04d1f012787ee2817941955f70abf4e3718aecc27b4f67763b972f97cb4a43b1
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d91819a4896d624752e6b6b60b7ae61348a5eacfbc001dd4c36a43c13bfb13d
+oid sha256:bb9a3ea44ec53a22070bc6551b352712629b97dc15f980273371583386c8e0ce
 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": 0.040029354860230834,
+  "epoch": 0.05337247314697445,
   "eval_steps": 7,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -620,6 +620,213 @@
       "learning_rate": 3.5721239031346066e-05,
       "loss": 1.1504,
       "step": 75
+    },
+    {
+      "epoch": 0.04056307959170058,
+      "grad_norm": 0.29981729388237,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.9346,
+      "step": 76
+    },
+    {
+      "epoch": 0.041096804323170325,
+      "grad_norm": 0.32428425550460815,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 1.1467,
+      "step": 77
+    },
+    {
+      "epoch": 0.041096804323170325,
+      "eval_loss": 1.2112306356430054,
+      "eval_runtime": 132.0592,
+      "eval_samples_per_second": 11.949,
+      "eval_steps_per_second": 5.975,
+      "step": 77
+    },
+    {
+      "epoch": 0.04163052905464007,
+      "grad_norm": 0.31357115507125854,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 1.1449,
+      "step": 78
+    },
+    {
+      "epoch": 0.042164253786109815,
+      "grad_norm": 0.28956103324890137,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.9929,
+      "step": 79
+    },
+    {
+      "epoch": 0.04269797851757956,
+      "grad_norm": 0.3215799927711487,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.95,
+      "step": 80
+    },
+    {
+      "epoch": 0.043231703249049305,
+      "grad_norm": 0.32306861877441406,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 1.3405,
+      "step": 81
+    },
+    {
+      "epoch": 0.04376542798051905,
+      "grad_norm": 0.34628739953041077,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 1.3823,
+      "step": 82
+    },
+    {
+      "epoch": 0.04429915271198879,
+      "grad_norm": 0.41880619525909424,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 1.2145,
+      "step": 83
+    },
+    {
+      "epoch": 0.044832877443458534,
+      "grad_norm": 0.34489524364471436,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 1.2043,
+      "step": 84
+    },
+    {
+      "epoch": 0.044832877443458534,
+      "eval_loss": 1.209867000579834,
+      "eval_runtime": 131.1054,
+      "eval_samples_per_second": 12.036,
+      "eval_steps_per_second": 6.018,
+      "step": 84
+    },
+    {
+      "epoch": 0.04536660217492828,
+      "grad_norm": 0.3454246520996094,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.4326,
+      "step": 85
+    },
+    {
+      "epoch": 0.045900326906398024,
+      "grad_norm": 0.34903326630592346,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 1.2395,
+      "step": 86
+    },
+    {
+      "epoch": 0.04643405163786777,
+      "grad_norm": 0.36401617527008057,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 1.1309,
+      "step": 87
+    },
+    {
+      "epoch": 0.046967776369337515,
+      "grad_norm": 0.3476174473762512,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 1.1396,
+      "step": 88
+    },
+    {
+      "epoch": 0.04750150110080726,
+      "grad_norm": 0.3433617353439331,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 1.3106,
+      "step": 89
+    },
+    {
+      "epoch": 0.048035225832277005,
+      "grad_norm": 0.3952890932559967,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.3647,
+      "step": 90
+    },
+    {
+      "epoch": 0.04856895056374675,
+      "grad_norm": 0.3324783444404602,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.3629,
+      "step": 91
+    },
+    {
+      "epoch": 0.04856895056374675,
+      "eval_loss": 1.209067463874817,
+      "eval_runtime": 131.1887,
+      "eval_samples_per_second": 12.028,
+      "eval_steps_per_second": 6.014,
+      "step": 91
+    },
+    {
+      "epoch": 0.049102675295216495,
+      "grad_norm": 0.3305179476737976,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 0.9684,
+      "step": 92
+    },
+    {
+      "epoch": 0.049636400026686234,
+      "grad_norm": 0.3130112290382385,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 1.4122,
+      "step": 93
+    },
+    {
+      "epoch": 0.05017012475815598,
+      "grad_norm": 0.4082207977771759,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 1.0472,
+      "step": 94
+    },
+    {
+      "epoch": 0.050703849489625724,
+      "grad_norm": 0.37707728147506714,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 1.3998,
+      "step": 95
+    },
+    {
+      "epoch": 0.05123757422109547,
+      "grad_norm": 0.3092212677001953,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 1.3452,
+      "step": 96
+    },
+    {
+      "epoch": 0.051771298952565215,
+      "grad_norm": 0.31625714898109436,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 1.3001,
+      "step": 97
+    },
+    {
+      "epoch": 0.05230502368403496,
+      "grad_norm": 0.39429420232772827,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 1.2862,
+      "step": 98
+    },
+    {
+      "epoch": 0.05230502368403496,
+      "eval_loss": 1.2093968391418457,
+      "eval_runtime": 131.0498,
+      "eval_samples_per_second": 12.041,
+      "eval_steps_per_second": 6.021,
+      "step": 98
+    },
+    {
+      "epoch": 0.052838748415504705,
+      "grad_norm": 0.3808484375476837,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 1.3516,
+      "step": 99
+    },
+    {
+      "epoch": 0.05337247314697445,
+      "grad_norm": 0.33221495151519775,
+      "learning_rate": 0.0,
+      "loss": 0.9949,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -634,12 +841,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6047170899738624.0,
+  "total_flos": 8056777010577408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null