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:d98d380e2ef25ebe15f834feeeceeaaa5a1259ad9e106311f8a62327fc02c996
+oid sha256:57010d679733f58494cf9df0b1d7904fa0ecb37c89183a88ccf2e3a5d5c15d80
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b8b4b5d4e61ae376da175312d3f51fa09b4833c20d2acaa0e802d9ceafbd55
+oid sha256:465b04a1b8593883d9ec9afb16d0d3a3a0efdfc22ac8bb34a852cb4c41e4b294
 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": 2.1019,
       "step": 75
+    },
+    {
+      "epoch": 0.07241543592186755,
+      "grad_norm": 1.1712687015533447,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.23,
+      "step": 76
+    },
+    {
+      "epoch": 0.07336827060505002,
+      "grad_norm": 1.1676398515701294,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.2097,
+      "step": 77
+    },
+    {
+      "epoch": 0.07432110528823249,
+      "grad_norm": 1.0858781337738037,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.9864,
+      "step": 78
+    },
+    {
+      "epoch": 0.07527393997141496,
+      "grad_norm": 1.0200934410095215,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.983,
+      "step": 79
+    },
+    {
+      "epoch": 0.07622677465459743,
+      "grad_norm": 1.2078415155410767,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0384,
+      "step": 80
+    },
+    {
+      "epoch": 0.0771796093377799,
+      "grad_norm": 1.313916563987732,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.172,
+      "step": 81
+    },
+    {
+      "epoch": 0.0771796093377799,
+      "eval_loss": 2.246673345565796,
+      "eval_runtime": 195.4363,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 0.568,
+      "step": 81
+    },
+    {
+      "epoch": 0.07813244402096237,
+      "grad_norm": 1.1175813674926758,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2528,
+      "step": 82
+    },
+    {
+      "epoch": 0.07908527870414483,
+      "grad_norm": 1.010094404220581,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.0849,
+      "step": 83
+    },
+    {
+      "epoch": 0.0800381133873273,
+      "grad_norm": 1.0223758220672607,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.3816,
+      "step": 84
+    },
+    {
+      "epoch": 0.08099094807050977,
+      "grad_norm": 1.022613286972046,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3138,
+      "step": 85
+    },
+    {
+      "epoch": 0.08194378275369224,
+      "grad_norm": 1.2156208753585815,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.4753,
+      "step": 86
+    },
+    {
+      "epoch": 0.08289661743687471,
+      "grad_norm": 1.0357915163040161,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.1229,
+      "step": 87
+    },
+    {
+      "epoch": 0.08384945212005716,
+      "grad_norm": 1.0248066186904907,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1021,
+      "step": 88
+    },
+    {
+      "epoch": 0.08480228680323963,
+      "grad_norm": 1.2692477703094482,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.204,
+      "step": 89
+    },
+    {
+      "epoch": 0.0857551214864221,
+      "grad_norm": 0.8067759275436401,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.892,
+      "step": 90
+    },
+    {
+      "epoch": 0.0857551214864221,
+      "eval_loss": 2.2446084022521973,
+      "eval_runtime": 195.6818,
+      "eval_samples_per_second": 4.518,
+      "eval_steps_per_second": 0.567,
+      "step": 90
+    },
+    {
+      "epoch": 0.08670795616960457,
+      "grad_norm": 1.087090015411377,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.3492,
+      "step": 91
+    },
+    {
+      "epoch": 0.08766079085278704,
+      "grad_norm": 4.056462287902832,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1434,
+      "step": 92
+    },
+    {
+      "epoch": 0.0886136255359695,
+      "grad_norm": 1.1611731052398682,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.2396,
+      "step": 93
+    },
+    {
+      "epoch": 0.08956646021915197,
+      "grad_norm": 0.980168342590332,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.2525,
+      "step": 94
+    },
+    {
+      "epoch": 0.09051929490233444,
+      "grad_norm": 1.268860936164856,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.9124,
+      "step": 95
+    },
+    {
+      "epoch": 0.09147212958551691,
+      "grad_norm": 1.115757942199707,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.0948,
+      "step": 96
+    },
+    {
+      "epoch": 0.09242496426869938,
+      "grad_norm": 1.067868709564209,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.403,
+      "step": 97
+    },
+    {
+      "epoch": 0.09337779895188185,
+      "grad_norm": 1.161622166633606,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.2761,
+      "step": 98
+    },
+    {
+      "epoch": 0.09433063363506432,
+      "grad_norm": 1.0254334211349487,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.3167,
+      "step": 99
+    },
+    {
+      "epoch": 0.09433063363506432,
+      "eval_loss": 2.2442753314971924,
+      "eval_runtime": 195.3934,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 0.568,
+      "step": 99
+    },
+    {
+      "epoch": 0.09528346831824679,
+      "grad_norm": 1.2676490545272827,
+      "learning_rate": 0.0,
+      "loss": 2.3509,
+      "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