Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41122c3fd21b4c35f04e1b7a6ddbd55fb82b0e9f50576057a6191af37eca1ac8
+oid sha256:a2b2f11e0a035a90d366cc284edbfc56efbd4031ac02d7ef35061deb19bd75bb
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4455f759fa779b263462083aba60470f84105854abfb3485295b1f5ee87b2475
+oid sha256:9ca430a349e91eced1d018e0d0a4dacde393b35ea37b92598fa659b8d550c95c
 size 320194002

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:357e665ce75e8bf8deea826f754ac04a04f92d8e6b4a1c149eeff724c007093f
+oid sha256:5b853fd1d9f5d75364b20828ce21880c72c97d592c95e3274909b656519a1492
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2261114c9e269b253527a43714382f1a95e47b6f1bcd18ab482f6898081d146c
+oid sha256:f2dd16ebb38cfc1da107d1d9f255f1d85d6b5fbd458e9b111892adfa1b90c18a
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8e3e202811ec0dc39504e476ab2f4b3d5ca6fd60ec9a4cff413f1af2808d927
+oid sha256:41ad80b23a311f9aae5f7a5bd63acdad31c7421d9322b7c98c4151ee5dc06171
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1c734911df612fe11d551b399755740e67bb3c6ac5d05ce0142c8c618a27e45
+oid sha256:d88797a8ce73e7b65b13b9ca9d4963a1fa51b8cfc309c7419d9c267f359a7aec
 size 14960

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": 0.09752925877763328,
+  "epoch": 0.13003901170351106,
   "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": 2.2782,
       "step": 75
+    },
+    {
+      "epoch": 0.0988296488946684,
+      "grad_norm": 0.4999937415122986,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.2945,
+      "step": 76
+    },
+    {
+      "epoch": 0.10013003901170352,
+      "grad_norm": 0.8299407958984375,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.5351,
+      "step": 77
+    },
+    {
+      "epoch": 0.10143042912873862,
+      "grad_norm": 0.6675406694412231,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.1659,
+      "step": 78
+    },
+    {
+      "epoch": 0.10273081924577374,
+      "grad_norm": 0.6427927613258362,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.2989,
+      "step": 79
+    },
+    {
+      "epoch": 0.10403120936280884,
+      "grad_norm": 0.5846431851387024,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.0654,
+      "step": 80
+    },
+    {
+      "epoch": 0.10533159947984395,
+      "grad_norm": 0.6613094210624695,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.2346,
+      "step": 81
+    },
+    {
+      "epoch": 0.10533159947984395,
+      "eval_loss": 1.1542775630950928,
+      "eval_runtime": 23.6923,
+      "eval_samples_per_second": 109.36,
+      "eval_steps_per_second": 3.419,
+      "step": 81
+    },
+    {
+      "epoch": 0.10663198959687907,
+      "grad_norm": 0.7165136933326721,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2092,
+      "step": 82
+    },
+    {
+      "epoch": 0.10793237971391417,
+      "grad_norm": 0.7384254336357117,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.393,
+      "step": 83
+    },
+    {
+      "epoch": 0.10923276983094929,
+      "grad_norm": 0.695436418056488,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.2724,
+      "step": 84
+    },
+    {
+      "epoch": 0.11053315994798439,
+      "grad_norm": 0.707597553730011,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2678,
+      "step": 85
+    },
+    {
+      "epoch": 0.11183355006501951,
+      "grad_norm": 0.5971311926841736,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.1536,
+      "step": 86
+    },
+    {
+      "epoch": 0.11313394018205461,
+      "grad_norm": 0.7096117734909058,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.2853,
+      "step": 87
+    },
+    {
+      "epoch": 0.11443433029908973,
+      "grad_norm": 0.5408521890640259,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.3251,
+      "step": 88
+    },
+    {
+      "epoch": 0.11573472041612484,
+      "grad_norm": 0.838297426700592,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.5606,
+      "step": 89
+    },
+    {
+      "epoch": 0.11703511053315994,
+      "grad_norm": 0.6239537596702576,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.4324,
+      "step": 90
+    },
+    {
+      "epoch": 0.11703511053315994,
+      "eval_loss": 1.1533452272415161,
+      "eval_runtime": 23.6885,
+      "eval_samples_per_second": 109.378,
+      "eval_steps_per_second": 3.419,
+      "step": 90
+    },
+    {
+      "epoch": 0.11833550065019506,
+      "grad_norm": 0.8293536901473999,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.2212,
+      "step": 91
+    },
+    {
+      "epoch": 0.11963589076723016,
+      "grad_norm": 0.7094742655754089,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.3645,
+      "step": 92
+    },
+    {
+      "epoch": 0.12093628088426528,
+      "grad_norm": 0.6064361929893494,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.1792,
+      "step": 93
+    },
+    {
+      "epoch": 0.1222366710013004,
+      "grad_norm": 1.047988772392273,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.2758,
+      "step": 94
+    },
+    {
+      "epoch": 0.1235370611183355,
+      "grad_norm": 0.8015021085739136,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.3835,
+      "step": 95
+    },
+    {
+      "epoch": 0.12483745123537061,
+      "grad_norm": 0.6742265224456787,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.168,
+      "step": 96
+    },
+    {
+      "epoch": 0.12613784135240572,
+      "grad_norm": 0.8117397427558899,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.1964,
+      "step": 97
+    },
+    {
+      "epoch": 0.12743823146944083,
+      "grad_norm": 0.5542296767234802,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1377,
+      "step": 98
+    },
+    {
+      "epoch": 0.12873862158647595,
+      "grad_norm": 0.7904403209686279,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.2664,
+      "step": 99
+    },
+    {
+      "epoch": 0.12873862158647595,
+      "eval_loss": 1.1530934572219849,
+      "eval_runtime": 23.6744,
+      "eval_samples_per_second": 109.443,
+      "eval_steps_per_second": 3.421,
+      "step": 99
+    },
+    {
+      "epoch": 0.13003901170351106,
+      "grad_norm": 0.6629341840744019,
+      "learning_rate": 0.0,
+      "loss": 2.2386,
+      "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": 1.960393933062144e+17,
+  "total_flos": 2.613858577416192e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null