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:da33b8cd502c5040bf8ee3ecf8ef3aeca2b8fdf42cd6455a3a297fbbe4abb784
+oid sha256:13e8af639e9a3b72d20354c4ad4a4e6fcf58baad6e22d9eab5a74479a8923782
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bd3dba1d55d25e70411df3032e8551e28f410a083ae5c1babf3108a666de946
+oid sha256:09a9265b72ab0d7955ba1b680e3938988684ae2022c2a8f6ec63409d067ba8a7
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6fbed7f002e0a36d46cfcf55f056cd93ce50fb21ed9f550b59e1a3e4a227136
+oid sha256:87195be8c484cd05a4b575494f191b5e3dc266eb179b1d377f3c78fe4b20121e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.011744440964610085,
+  "epoch": 0.015659254619480114,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 1.6743,
       "step": 75
+    },
+    {
+      "epoch": 0.011901033510804886,
+      "grad_norm": 0.49672675132751465,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3063,
+      "step": 76
+    },
+    {
+      "epoch": 0.012057626056999686,
+      "grad_norm": 0.5522364377975464,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.8666,
+      "step": 77
+    },
+    {
+      "epoch": 0.012214218603194488,
+      "grad_norm": 0.6612314581871033,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.9022,
+      "step": 78
+    },
+    {
+      "epoch": 0.01237081114938929,
+      "grad_norm": 0.5317505598068237,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.0386,
+      "step": 79
+    },
+    {
+      "epoch": 0.01252740369558409,
+      "grad_norm": 0.5432467460632324,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.8287,
+      "step": 80
+    },
+    {
+      "epoch": 0.012683996241778892,
+      "grad_norm": 0.4582969844341278,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.4847,
+      "step": 81
+    },
+    {
+      "epoch": 0.012683996241778892,
+      "eval_loss": 1.0726039409637451,
+      "eval_runtime": 341.6866,
+      "eval_samples_per_second": 15.74,
+      "eval_steps_per_second": 1.97,
+      "step": 81
+    },
+    {
+      "epoch": 0.012840588787973693,
+      "grad_norm": 0.49256080389022827,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.5165,
+      "step": 82
+    },
+    {
+      "epoch": 0.012997181334168493,
+      "grad_norm": 0.4961276352405548,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.1499,
+      "step": 83
+    },
+    {
+      "epoch": 0.013153773880363295,
+      "grad_norm": 0.5461624264717102,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.8055,
+      "step": 84
+    },
+    {
+      "epoch": 0.013310366426558097,
+      "grad_norm": 0.49188461899757385,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1544,
+      "step": 85
+    },
+    {
+      "epoch": 0.013466958972752897,
+      "grad_norm": 0.5389429330825806,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3448,
+      "step": 86
+    },
+    {
+      "epoch": 0.013623551518947698,
+      "grad_norm": 0.521251916885376,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.0522,
+      "step": 87
+    },
+    {
+      "epoch": 0.013780144065142498,
+      "grad_norm": 0.5706208944320679,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.4151,
+      "step": 88
+    },
+    {
+      "epoch": 0.0139367366113373,
+      "grad_norm": 0.5204151272773743,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.1975,
+      "step": 89
+    },
+    {
+      "epoch": 0.014093329157532102,
+      "grad_norm": 0.6270158886909485,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.9621,
+      "step": 90
+    },
+    {
+      "epoch": 0.014093329157532102,
+      "eval_loss": 1.0648150444030762,
+      "eval_runtime": 341.792,
+      "eval_samples_per_second": 15.735,
+      "eval_steps_per_second": 1.969,
+      "step": 90
+    },
+    {
+      "epoch": 0.014249921703726902,
+      "grad_norm": 0.6548490524291992,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9719,
+      "step": 91
+    },
+    {
+      "epoch": 0.014406514249921704,
+      "grad_norm": 0.5670599937438965,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9317,
+      "step": 92
+    },
+    {
+      "epoch": 0.014563106796116505,
+      "grad_norm": 0.4700786769390106,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.766,
+      "step": 93
+    },
+    {
+      "epoch": 0.014719699342311305,
+      "grad_norm": 0.47002893686294556,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.5283,
+      "step": 94
+    },
+    {
+      "epoch": 0.014876291888506107,
+      "grad_norm": 0.46464380621910095,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.9799,
+      "step": 95
+    },
+    {
+      "epoch": 0.015032884434700909,
+      "grad_norm": 0.5638867020606995,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1551,
+      "step": 96
+    },
+    {
+      "epoch": 0.015189476980895709,
+      "grad_norm": 0.49153435230255127,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.1155,
+      "step": 97
+    },
+    {
+      "epoch": 0.01534606952709051,
+      "grad_norm": 0.45866310596466064,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.049,
+      "step": 98
+    },
+    {
+      "epoch": 0.015502662073285312,
+      "grad_norm": 0.4746398329734802,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.6255,
+      "step": 99
+    },
+    {
+      "epoch": 0.015502662073285312,
+      "eval_loss": 1.063291311264038,
+      "eval_runtime": 341.6956,
+      "eval_samples_per_second": 15.739,
+      "eval_steps_per_second": 1.97,
+      "step": 99
+    },
+    {
+      "epoch": 0.015659254619480114,
+      "grad_norm": 0.6611264944076538,
+      "learning_rate": 0.0,
+      "loss": 1.0954,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.54405315805184e+16,
+  "total_flos": 2.05873754406912e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null