Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75557017071a7b3ff7b9580c147ef7b9df1e16089651df4962d9bcbcd41e748b
+oid sha256:170c0d19ee4e6d137a831aa44c9ca68ca4910f427efbf8adffe38eb35cd82c34
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641794e88e031fe62733cc33906fe5ba1c803b7c4be87850d48688ef75570441
+oid sha256:3c1e5c52fa04f594553092bb955537186da0cfd9ba1a575139560689b7865aa3
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
+oid sha256:2641fe94f6f5285a893d26b6a83b6bc1718c94cdba5b09f9fe77818d5a69d3a2
 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": 0.07146260123868509,
+  "epoch": 0.09528346831824679,
   "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": 2.1034,
       "step": 75
+    },
+    {
+      "epoch": 0.07241543592186755,
+      "grad_norm": 1.2492951154708862,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.2339,
+      "step": 76
+    },
+    {
+      "epoch": 0.07336827060505002,
+      "grad_norm": 1.2088156938552856,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.2098,
+      "step": 77
+    },
+    {
+      "epoch": 0.07432110528823249,
+      "grad_norm": 1.1127347946166992,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.9861,
+      "step": 78
+    },
+    {
+      "epoch": 0.07527393997141496,
+      "grad_norm": 1.0793708562850952,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.9812,
+      "step": 79
+    },
+    {
+      "epoch": 0.07622677465459743,
+      "grad_norm": 1.1515878438949585,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0356,
+      "step": 80
+    },
+    {
+      "epoch": 0.0771796093377799,
+      "grad_norm": 1.2502024173736572,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.1648,
+      "step": 81
+    },
+    {
+      "epoch": 0.0771796093377799,
+      "eval_loss": 2.2468369007110596,
+      "eval_runtime": 195.3237,
+      "eval_samples_per_second": 4.526,
+      "eval_steps_per_second": 0.568,
+      "step": 81
+    },
+    {
+      "epoch": 0.07813244402096237,
+      "grad_norm": 1.0776357650756836,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2496,
+      "step": 82
+    },
+    {
+      "epoch": 0.07908527870414483,
+      "grad_norm": 0.9755646586418152,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.0841,
+      "step": 83
+    },
+    {
+      "epoch": 0.0800381133873273,
+      "grad_norm": 0.9808889031410217,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.3795,
+      "step": 84
+    },
+    {
+      "epoch": 0.08099094807050977,
+      "grad_norm": 0.9751318693161011,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3177,
+      "step": 85
+    },
+    {
+      "epoch": 0.08194378275369224,
+      "grad_norm": 1.2370442152023315,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.4818,
+      "step": 86
+    },
+    {
+      "epoch": 0.08289661743687471,
+      "grad_norm": 1.041976809501648,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.1223,
+      "step": 87
+    },
+    {
+      "epoch": 0.08384945212005716,
+      "grad_norm": 1.0111206769943237,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.0988,
+      "step": 88
+    },
+    {
+      "epoch": 0.08480228680323963,
+      "grad_norm": 1.0791726112365723,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.2097,
+      "step": 89
+    },
+    {
+      "epoch": 0.0857551214864221,
+      "grad_norm": 0.8062794208526611,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8917,
+      "step": 90
+    },
+    {
+      "epoch": 0.0857551214864221,
+      "eval_loss": 2.2454254627227783,
+      "eval_runtime": 195.2505,
+      "eval_samples_per_second": 4.528,
+      "eval_steps_per_second": 0.569,
+      "step": 90
+    },
+    {
+      "epoch": 0.08670795616960457,
+      "grad_norm": 1.086729884147644,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.3498,
+      "step": 91
+    },
+    {
+      "epoch": 0.08766079085278704,
+      "grad_norm": 3.8277571201324463,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1474,
+      "step": 92
+    },
+    {
+      "epoch": 0.0886136255359695,
+      "grad_norm": 1.1703578233718872,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.2442,
+      "step": 93
+    },
+    {
+      "epoch": 0.08956646021915197,
+      "grad_norm": 0.9999949336051941,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.2552,
+      "step": 94
+    },
+    {
+      "epoch": 0.09051929490233444,
+      "grad_norm": 1.0868746042251587,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.914,
+      "step": 95
+    },
+    {
+      "epoch": 0.09147212958551691,
+      "grad_norm": 1.091508150100708,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.0883,
+      "step": 96
+    },
+    {
+      "epoch": 0.09242496426869938,
+      "grad_norm": 1.046575903892517,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.4059,
+      "step": 97
+    },
+    {
+      "epoch": 0.09337779895188185,
+      "grad_norm": 1.3036117553710938,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.2796,
+      "step": 98
+    },
+    {
+      "epoch": 0.09433063363506432,
+      "grad_norm": 1.0407637357711792,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.309,
+      "step": 99
+    },
+    {
+      "epoch": 0.09433063363506432,
+      "eval_loss": 2.244947671890259,
+      "eval_runtime": 195.3553,
+      "eval_samples_per_second": 4.525,
+      "eval_steps_per_second": 0.568,
+      "step": 99
+    },
+    {
+      "epoch": 0.09528346831824679,
+      "grad_norm": 1.2726835012435913,
+      "learning_rate": 0.0,
+      "loss": 2.3422,
+      "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": 1.112830925340672e+17,
+  "total_flos": 1.483774567120896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null