Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dac956b46c939cbbbc1108a2f2e9d6ad606696f956ee49ce3709465d6cb9ba8
+oid sha256:0ba07a2c443bf681fee4e7118c3fac8673c380af721e9dcd838f2be5fcbe3f8e
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f9bcc7102e8def67c4d4800cfdbbdb598f82463f927a7832f0efcc6c41ed3e
+oid sha256:b1cb06fe47fe071b2cd854851c28a15f77ba65ebef1f319abc10bafb81a85b09
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdf0878306dfabad22df73aa5835c9e34d3f3302f1c21c247c88f8c2ea4fd50f
+oid sha256:dd9dfdcd675c502babec9c71489244852c01ea23b87ae35a698ebc50c399ec90
 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": 0.08062348830959419,
+  "epoch": 0.10749798441279226,
   "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": 59.86,
       "eval_steps_per_second": 29.93,
       "step": 75
+    },
+    {
+      "epoch": 0.08169846815372211,
+      "grad_norm": 1.249240517616272,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 0.3514,
+      "step": 76
+    },
+    {
+      "epoch": 0.08277344799785004,
+      "grad_norm": 1.8722736835479736,
+      "learning_rate": 3.053416295410026e-05,
+      "loss": 0.4375,
+      "step": 77
+    },
+    {
+      "epoch": 0.08384842784197796,
+      "grad_norm": 1.9906784296035767,
+      "learning_rate": 2.8066019966134904e-05,
+      "loss": 0.4844,
+      "step": 78
+    },
+    {
+      "epoch": 0.08492340768610589,
+      "grad_norm": 2.18096661567688,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.6117,
+      "step": 79
+    },
+    {
+      "epoch": 0.08599838753023381,
+      "grad_norm": 1.6384766101837158,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.3738,
+      "step": 80
+    },
+    {
+      "epoch": 0.08707336737436173,
+      "grad_norm": 1.8226215839385986,
+      "learning_rate": 2.119892463932781e-05,
+      "loss": 0.5135,
+      "step": 81
+    },
+    {
+      "epoch": 0.08814834721848966,
+      "grad_norm": 2.0796890258789062,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5532,
+      "step": 82
+    },
+    {
+      "epoch": 0.08922332706261758,
+      "grad_norm": 1.9040170907974243,
+      "learning_rate": 1.7096242744495837e-05,
+      "loss": 0.5375,
+      "step": 83
+    },
+    {
+      "epoch": 0.09029830690674549,
+      "grad_norm": 2.2996716499328613,
+      "learning_rate": 1.5195190384357404e-05,
+      "loss": 0.6571,
+      "step": 84
+    },
+    {
+      "epoch": 0.09137328675087342,
+      "grad_norm": 1.1326524019241333,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.2645,
+      "step": 85
+    },
+    {
+      "epoch": 0.09244826659500134,
+      "grad_norm": 1.2741332054138184,
+      "learning_rate": 1.1705240714107302e-05,
+      "loss": 0.395,
+      "step": 86
+    },
+    {
+      "epoch": 0.09352324643912927,
+      "grad_norm": 2.874173879623413,
+      "learning_rate": 1.0120595370083318e-05,
+      "loss": 0.4343,
+      "step": 87
+    },
+    {
+      "epoch": 0.09459822628325719,
+      "grad_norm": 1.7088797092437744,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.3476,
+      "step": 88
+    },
+    {
+      "epoch": 0.09567320612738511,
+      "grad_norm": 1.496488094329834,
+      "learning_rate": 7.281614543321269e-06,
+      "loss": 0.401,
+      "step": 89
+    },
+    {
+      "epoch": 0.09674818597151304,
+      "grad_norm": 1.7089238166809082,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 0.4049,
+      "step": 90
+    },
+    {
+      "epoch": 0.09782316581564096,
+      "grad_norm": 1.9336659908294678,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.5173,
+      "step": 91
+    },
+    {
+      "epoch": 0.09889814565976889,
+      "grad_norm": 1.4552040100097656,
+      "learning_rate": 3.873830406168111e-06,
+      "loss": 0.4601,
+      "step": 92
+    },
+    {
+      "epoch": 0.0999731255038968,
+      "grad_norm": 1.9344124794006348,
+      "learning_rate": 2.970427372400353e-06,
+      "loss": 0.4151,
+      "step": 93
+    },
+    {
+      "epoch": 0.10104810534802472,
+      "grad_norm": 1.7460708618164062,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 0.3309,
+      "step": 94
+    },
+    {
+      "epoch": 0.10212308519215264,
+      "grad_norm": 1.8331955671310425,
+      "learning_rate": 1.5192246987791981e-06,
+      "loss": 0.3887,
+      "step": 95
+    },
+    {
+      "epoch": 0.10319806503628057,
+      "grad_norm": 1.653121829032898,
+      "learning_rate": 9.731931258429638e-07,
+      "loss": 0.3739,
+      "step": 96
+    },
+    {
+      "epoch": 0.10427304488040849,
+      "grad_norm": 1.7250211238861084,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.4968,
+      "step": 97
+    },
+    {
+      "epoch": 0.10534802472453642,
+      "grad_norm": 1.43699312210083,
+      "learning_rate": 2.4359497401758024e-07,
+      "loss": 0.4566,
+      "step": 98
+    },
+    {
+      "epoch": 0.10642300456866434,
+      "grad_norm": 1.4448294639587402,
+      "learning_rate": 6.09172980904238e-08,
+      "loss": 0.3394,
+      "step": 99
+    },
+    {
+      "epoch": 0.10749798441279226,
+      "grad_norm": 1.6877906322479248,
+      "learning_rate": 0.0,
+      "loss": 0.3672,
+      "step": 100
+    },
+    {
+      "epoch": 0.10749798441279226,
+      "eval_loss": 0.5043053030967712,
+      "eval_runtime": 7.0996,
+      "eval_samples_per_second": 55.215,
+      "eval_steps_per_second": 27.607,
+      "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": 3671083450368000.0,
+  "total_flos": 4894777933824000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null