Training in progress, step 85, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86ee6e154e49069091d893455757e17295ee85019f64a663e52903b19cfc1cf
+oid sha256:c93154ec6a8dec35705ce9d1c2f4a5c55f118f8418e41f2d63409d33becad085
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e1a75388d3fb482b018a16ca66ce2bf8d2b482576fc3daf3f841c59f4c236cb
+oid sha256:7f4de1512f949d496d512471d0c604d3dad5cd6125348a1d0f27f1b0c5a351ea
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051417fc01d33b78aa641f032182ab64da1fcc15fe5a876899f334dcea2dc357
+oid sha256:fdd3ea04947084511a30ef65c56c4e673088b8f8e3ac5e88f4ddcd31448dda70
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f4e77fd2a3bb3f08929494d77da2f57f8781f91a45852bcf8f71a5777dd088c
+oid sha256:b383ad1d61ff4e9bbd86bd276c043e414782d2bb7de68ada3e289a786eb79681
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.23038644785600848,
+  "epoch": 0.2879830598200106,
   "eval_steps": 50,
-  "global_step": 68,
+  "global_step": 85,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -499,6 +499,125 @@
       "learning_rate": 0.00012518479547691435,
       "loss": 10.3485,
       "step": 68
+    },
+    {
+      "epoch": 0.23377448385389094,
+      "grad_norm": 0.028004931285977364,
+      "learning_rate": 0.00012420442717428804,
+      "loss": 10.3488,
+      "step": 69
+    },
+    {
+      "epoch": 0.23716251985177342,
+      "grad_norm": 0.030328616499900818,
+      "learning_rate": 0.00012320907072649044,
+      "loss": 10.3479,
+      "step": 70
+    },
+    {
+      "epoch": 0.2405505558496559,
+      "grad_norm": 0.027720727026462555,
+      "learning_rate": 0.0001221990293287378,
+      "loss": 10.3477,
+      "step": 71
+    },
+    {
+      "epoch": 0.24393859184753838,
+      "grad_norm": 0.02903708443045616,
+      "learning_rate": 0.00012117461064942435,
+      "loss": 10.3479,
+      "step": 72
+    },
+    {
+      "epoch": 0.24732662784542087,
+      "grad_norm": 0.026270205155014992,
+      "learning_rate": 0.00012013612673640363,
+      "loss": 10.3473,
+      "step": 73
+    },
+    {
+      "epoch": 0.2507146638433033,
+      "grad_norm": 0.022023234516382217,
+      "learning_rate": 0.00011908389392193547,
+      "loss": 10.3462,
+      "step": 74
+    },
+    {
+      "epoch": 0.25410269984118583,
+      "grad_norm": 0.018086234107613564,
+      "learning_rate": 0.00011801823272632844,
+      "loss": 10.3471,
+      "step": 75
+    },
+    {
+      "epoch": 0.2574907358390683,
+      "grad_norm": 0.017115121707320213,
+      "learning_rate": 0.00011693946776030599,
+      "loss": 10.3481,
+      "step": 76
+    },
+    {
+      "epoch": 0.26087877183695074,
+      "grad_norm": 0.022446399554610252,
+      "learning_rate": 0.00011584792762612703,
+      "loss": 10.3469,
+      "step": 77
+    },
+    {
+      "epoch": 0.26426680783483325,
+      "grad_norm": 0.023726455867290497,
+      "learning_rate": 0.00011474394481749035,
+      "loss": 10.3475,
+      "step": 78
+    },
+    {
+      "epoch": 0.2676548438327157,
+      "grad_norm": 0.02203121967613697,
+      "learning_rate": 0.00011362785561825406,
+      "loss": 10.3484,
+      "step": 79
+    },
+    {
+      "epoch": 0.2710428798305982,
+      "grad_norm": 0.016930948942899704,
+      "learning_rate": 0.0001125,
+      "loss": 10.3476,
+      "step": 80
+    },
+    {
+      "epoch": 0.27443091582848067,
+      "grad_norm": 0.017117898911237717,
+      "learning_rate": 0.00011136072151847529,
+      "loss": 10.3474,
+      "step": 81
+    },
+    {
+      "epoch": 0.2778189518263632,
+      "grad_norm": 0.02053241617977619,
+      "learning_rate": 0.00011021036720894179,
+      "loss": 10.3467,
+      "step": 82
+    },
+    {
+      "epoch": 0.28120698782424564,
+      "grad_norm": 0.022768596187233925,
+      "learning_rate": 0.00010904928748046599,
+      "loss": 10.3479,
+      "step": 83
+    },
+    {
+      "epoch": 0.2845950238221281,
+      "grad_norm": 0.016698352992534637,
+      "learning_rate": 0.0001078778360091808,
+      "loss": 10.3468,
+      "step": 84
+    },
+    {
+      "epoch": 0.2879830598200106,
+      "grad_norm": 0.020199725404381752,
+      "learning_rate": 0.00010669636963055245,
+      "loss": 10.3473,
+      "step": 85
     }
   ],
   "logging_steps": 1,
@@ -518,7 +637,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 29122375581696.0,
+  "total_flos": 36406310731776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null