Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46e3107b7c9b182096fbd1214e7f5eece27769d3420207085b028f388f0c3b28
+oid sha256:5349724371b049ac1934968dd7d2a7b9b3f7590d881875a4774d573a74ebf5d8
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b3043a57e704f0fe21731491216e70acd929948f79da46ee4012e4909ad6c7
+oid sha256:e71cd56355bc7471447b39796600abe7a547c8922c0358f9584d90f4f652fb10
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad2498e4585ae9e458b77e85412d56632afa93e3bb7944a5e84c45e07fd5c143
+oid sha256:dd79358f4238a053a170fe56c84672c10b332de6446eaa65c56cc21b61f73ff5
 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": 0.013813426650704485,
+  "epoch": 0.018417902200939314,
   "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": 1.4534,
       "step": 75
+    },
+    {
+      "epoch": 0.013997605672713877,
+      "grad_norm": 0.5669639706611633,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.3964,
+      "step": 76
+    },
+    {
+      "epoch": 0.014181784694723271,
+      "grad_norm": 0.525967538356781,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.4936,
+      "step": 77
+    },
+    {
+      "epoch": 0.014365963716732663,
+      "grad_norm": 0.4990406632423401,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.4064,
+      "step": 78
+    },
+    {
+      "epoch": 0.014550142738742057,
+      "grad_norm": 0.5157889127731323,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.4292,
+      "step": 79
+    },
+    {
+      "epoch": 0.01473432176075145,
+      "grad_norm": 0.5075008869171143,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.4307,
+      "step": 80
+    },
+    {
+      "epoch": 0.014918500782760843,
+      "grad_norm": 0.520317554473877,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.3444,
+      "step": 81
+    },
+    {
+      "epoch": 0.014918500782760843,
+      "eval_loss": 0.7018651366233826,
+      "eval_runtime": 1374.6373,
+      "eval_samples_per_second": 3.327,
+      "eval_steps_per_second": 0.416,
+      "step": 81
+    },
+    {
+      "epoch": 0.015102679804770237,
+      "grad_norm": 0.49962204694747925,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4096,
+      "step": 82
+    },
+    {
+      "epoch": 0.01528685882677963,
+      "grad_norm": 0.4933731257915497,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.4033,
+      "step": 83
+    },
+    {
+      "epoch": 0.015471037848789023,
+      "grad_norm": 0.49985840916633606,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.4229,
+      "step": 84
+    },
+    {
+      "epoch": 0.015655216870798416,
+      "grad_norm": 0.5326341986656189,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3568,
+      "step": 85
+    },
+    {
+      "epoch": 0.01583939589280781,
+      "grad_norm": 0.4729391634464264,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.3532,
+      "step": 86
+    },
+    {
+      "epoch": 0.016023574914817203,
+      "grad_norm": 0.5575768947601318,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.3965,
+      "step": 87
+    },
+    {
+      "epoch": 0.016207753936826594,
+      "grad_norm": 0.5217925906181335,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.3991,
+      "step": 88
+    },
+    {
+      "epoch": 0.016391932958835988,
+      "grad_norm": 0.5065118074417114,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.315,
+      "step": 89
+    },
+    {
+      "epoch": 0.01657611198084538,
+      "grad_norm": 0.48693209886550903,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.415,
+      "step": 90
+    },
+    {
+      "epoch": 0.01657611198084538,
+      "eval_loss": 0.7002039551734924,
+      "eval_runtime": 1374.6772,
+      "eval_samples_per_second": 3.327,
+      "eval_steps_per_second": 0.416,
+      "step": 90
+    },
+    {
+      "epoch": 0.016760291002854776,
+      "grad_norm": 0.5162665843963623,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.2998,
+      "step": 91
+    },
+    {
+      "epoch": 0.01694447002486417,
+      "grad_norm": 0.5575674176216125,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4777,
+      "step": 92
+    },
+    {
+      "epoch": 0.01712864904687356,
+      "grad_norm": 0.5292540192604065,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.3472,
+      "step": 93
+    },
+    {
+      "epoch": 0.017312828068882954,
+      "grad_norm": 0.5513125658035278,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.4452,
+      "step": 94
+    },
+    {
+      "epoch": 0.017497007090892348,
+      "grad_norm": 0.572922945022583,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4552,
+      "step": 95
+    },
+    {
+      "epoch": 0.01768118611290174,
+      "grad_norm": 0.5762553811073303,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.5259,
+      "step": 96
+    },
+    {
+      "epoch": 0.017865365134911132,
+      "grad_norm": 0.5325009226799011,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.3222,
+      "step": 97
+    },
+    {
+      "epoch": 0.018049544156920526,
+      "grad_norm": 0.5096551775932312,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.3978,
+      "step": 98
+    },
+    {
+      "epoch": 0.01823372317892992,
+      "grad_norm": 0.5625472068786621,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.355,
+      "step": 99
+    },
+    {
+      "epoch": 0.01823372317892992,
+      "eval_loss": 0.6998289227485657,
+      "eval_runtime": 1376.3591,
+      "eval_samples_per_second": 3.323,
+      "eval_steps_per_second": 0.416,
+      "step": 99
+    },
+    {
+      "epoch": 0.018417902200939314,
+      "grad_norm": 0.5077269673347473,
+      "learning_rate": 0.0,
+      "loss": 1.3856,
+      "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": 1.821815643045888e+17,
+  "total_flos": 2.437551243657216e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null