Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535c6acfeef113242a4a143d89c0b354cf193bc6de8f40e6d012e841c06c38e9
+oid sha256:a84d2b376de5eac83c253f95649d402b4c8a84c6633890dfc59fcce25fc929c9
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdab8e2b0aeff7cf9e881b9247c325a1d059b36723b420ca7a8d8fe8b98caf44
+oid sha256:b6d678ed16f43d7c19fc9b902f4a0a35e4f3748bc0fe8503774bcf56d0f15f92
 size 101184122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1d644a4a39d949387b662bdefaee2232811c755c916d4547d1e6e803c86cf5
+oid sha256:03234c59276a3926e42276e51b5f8ade5ed5a056f62f458d656d76b351955cf2
 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": 0.06361323155216285,
+  "epoch": 0.08481764206955046,
   "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": 0.4464,
       "step": 75
+    },
+    {
+      "epoch": 0.06446140797285835,
+      "grad_norm": 0.5965391993522644,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4651,
+      "step": 76
+    },
+    {
+      "epoch": 0.06530958439355386,
+      "grad_norm": 0.6338193416595459,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.4456,
+      "step": 77
+    },
+    {
+      "epoch": 0.06615776081424936,
+      "grad_norm": 0.3467748165130615,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.4615,
+      "step": 78
+    },
+    {
+      "epoch": 0.06700593723494487,
+      "grad_norm": 1.386129379272461,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 0.4637,
+      "step": 79
+    },
+    {
+      "epoch": 0.06785411365564037,
+      "grad_norm": 1.2354660034179688,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.4714,
+      "step": 80
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "grad_norm": 0.4873424768447876,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.4542,
+      "step": 81
+    },
+    {
+      "epoch": 0.06870229007633588,
+      "eval_loss": 0.46868446469306946,
+      "eval_runtime": 29.0217,
+      "eval_samples_per_second": 34.216,
+      "eval_steps_per_second": 4.307,
+      "step": 81
+    },
+    {
+      "epoch": 0.06955046649703138,
+      "grad_norm": 1.060185194015503,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.4299,
+      "step": 82
+    },
+    {
+      "epoch": 0.07039864291772689,
+      "grad_norm": 0.6003854274749756,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 0.4664,
+      "step": 83
+    },
+    {
+      "epoch": 0.07124681933842239,
+      "grad_norm": 0.601787805557251,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.454,
+      "step": 84
+    },
+    {
+      "epoch": 0.0720949957591179,
+      "grad_norm": 1.4092165231704712,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4443,
+      "step": 85
+    },
+    {
+      "epoch": 0.0729431721798134,
+      "grad_norm": 1.0296019315719604,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.4481,
+      "step": 86
+    },
+    {
+      "epoch": 0.0737913486005089,
+      "grad_norm": 0.7165821194648743,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.4655,
+      "step": 87
+    },
+    {
+      "epoch": 0.07463952502120441,
+      "grad_norm": 0.7949168682098389,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.4624,
+      "step": 88
+    },
+    {
+      "epoch": 0.07548770144189991,
+      "grad_norm": 1.36370849609375,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 0.4611,
+      "step": 89
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "grad_norm": 0.7988469004631042,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.4684,
+      "step": 90
+    },
+    {
+      "epoch": 0.07633587786259542,
+      "eval_loss": 0.4706438183784485,
+      "eval_runtime": 28.8299,
+      "eval_samples_per_second": 34.443,
+      "eval_steps_per_second": 4.336,
+      "step": 90
+    },
+    {
+      "epoch": 0.07718405428329092,
+      "grad_norm": 1.1426377296447754,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.4921,
+      "step": 91
+    },
+    {
+      "epoch": 0.07803223070398643,
+      "grad_norm": 1.0854405164718628,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.4708,
+      "step": 92
+    },
+    {
+      "epoch": 0.07888040712468193,
+      "grad_norm": 1.211848497390747,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 0.4789,
+      "step": 93
+    },
+    {
+      "epoch": 0.07972858354537744,
+      "grad_norm": 1.167067527770996,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4487,
+      "step": 94
+    },
+    {
+      "epoch": 0.08057675996607294,
+      "grad_norm": 1.2036820650100708,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.4864,
+      "step": 95
+    },
+    {
+      "epoch": 0.08142493638676845,
+      "grad_norm": 1.0609307289123535,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4492,
+      "step": 96
+    },
+    {
+      "epoch": 0.08227311280746395,
+      "grad_norm": 0.47746893763542175,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.4749,
+      "step": 97
+    },
+    {
+      "epoch": 0.08312128922815945,
+      "grad_norm": 2.1157803535461426,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.5022,
+      "step": 98
+    },
+    {
+      "epoch": 0.08396946564885496,
+      "grad_norm": 1.4069894552230835,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 0.4857,
+      "step": 99
+    },
+    {
+      "epoch": 0.08396946564885496,
+      "eval_loss": 0.4704572558403015,
+      "eval_runtime": 28.8321,
+      "eval_samples_per_second": 34.441,
+      "eval_steps_per_second": 4.335,
+      "step": 99
+    },
+    {
+      "epoch": 0.08481764206955046,
+      "grad_norm": 0.7878907918930054,
+      "learning_rate": 0.0,
+      "loss": 0.4399,
+      "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": 7720265790259200.0,
+  "total_flos": 1.02936877203456e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null