Training in progress, step 108, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a9749ffef3c830174bf40404cc485fd4c5663eea6479de77c33a29ef1deb34
+oid sha256:c094006aff2544c518cad78661fa2d417641d73d218ae414283344824b1062ab
 size 536992880

last-checkpoint/global_step108/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:993f47f680b9c7f6c4b4911b8a984dc9f216a9258a0d0dfdf9ba5fdf99d7a9a8
+size 474418016

last-checkpoint/global_step108/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2317c4a1a8b5e45e3d00f5de8aad40af1bd4e404f24a766bcbbbce7598206a2e
+size 474418016

last-checkpoint/global_step108/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff2d4c6ef7d103246066c2d03f1c4a652233b498c769fa6d433898efb7dd732
+size 474418016

last-checkpoint/global_step108/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee011b1c3b3976e689095614cfa291679912347413aaea2362e43751e3dfc375
+size 474418016

last-checkpoint/global_step108/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c17f05463192f4886edc573fd4c4e4f6cb6202e4deaa036fdab7eb4cff6e586
+size 497569222

last-checkpoint/global_step108/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fd88fdb5135c44e803a5da8c2d4e0d208c71102a545e4728399dd8950b42c0f
+size 497569222

last-checkpoint/global_step108/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4373a57b2c2cf30deab569dc4584821bc97574328a1e515b5e032ead0f92c1d
+size 497569222

last-checkpoint/global_step108/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd8662b9062b826b371c261d71462248c98a4810485455b150211d5755dbbace
+size 497569222

last-checkpoint/latest

@@ -1 +1 @@
-global_step81
+global_step108

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc34b9b7583664e073536f09b431c2900517f2eae037be0f350bebadc76f3a7a
+oid sha256:1d4a604acb40801033a18ef26f6d4904ccae9e17235a30689cbdd297cbf635ba
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:670ee22b03cb2f6e494846f535e536868078808871c8e82661cead03e336da23
+oid sha256:85ba958b693b3be1b1488820ef712ba2c6d3640a856dcd2409bea15cae78d6d8
 size 14960

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce6f51e01ab770161e01a525ecba8e0e6f6221b9b8dacc64707f0f41b381007a
+oid sha256:9d77af35e19f2f989f3468f3f525e24fb127360a01895d63c49b57c6fbe31341
 size 14960

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d55b1f769d6bd103cedb3990998f0b34e4e1d63c6ffd0c2ac3a5f8c4526e3b06
+oid sha256:24628b38b313ad9b720f780a5da8d10d2b58d9282e312631fe7ef1740e6d74fb
 size 14960

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b842b024e7609e993d6c174def3f8f329d0b2e8d4f00c44396e44f9f3e3cda
+oid sha256:347e78783bdffbe59a6a30fe7d177e31fdbdc48384eb3094510fabb6fef09779
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7465437788018433,
+  "epoch": 0.9953917050691244,
   "eval_steps": 11,
-  "global_step": 81,
+  "global_step": 108,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -638,6 +638,211 @@
       "learning_rate": 2.9004497406582e-05,
       "loss": 2.1402,
       "step": 81
+    },
+    {
+      "epoch": 0.7557603686635944,
+      "grad_norm": 0.009968014397025708,
+      "learning_rate": 2.8728819646461336e-05,
+      "loss": 2.2383,
+      "step": 82
+    },
+    {
+      "epoch": 0.7649769585253456,
+      "grad_norm": 0.009620205315061477,
+      "learning_rate": 2.8461301125590613e-05,
+      "loss": 2.2639,
+      "step": 83
+    },
+    {
+      "epoch": 0.7741935483870968,
+      "grad_norm": 0.00977544354748898,
+      "learning_rate": 2.8202190698460053e-05,
+      "loss": 2.265,
+      "step": 84
+    },
+    {
+      "epoch": 0.783410138248848,
+      "grad_norm": 0.010307755448269416,
+      "learning_rate": 2.7951729398075695e-05,
+      "loss": 2.2436,
+      "step": 85
+    },
+    {
+      "epoch": 0.7926267281105991,
+      "grad_norm": 0.009422457517611288,
+      "learning_rate": 2.7710150211742585e-05,
+      "loss": 2.25,
+      "step": 86
+    },
+    {
+      "epoch": 0.8018433179723502,
+      "grad_norm": 0.009754638407058579,
+      "learning_rate": 2.7477677864332375e-05,
+      "loss": 2.2758,
+      "step": 87
+    },
+    {
+      "epoch": 0.8110599078341014,
+      "grad_norm": 0.009561231269697724,
+      "learning_rate": 2.7254528609236844e-05,
+      "loss": 2.2473,
+      "step": 88
+    },
+    {
+      "epoch": 0.8110599078341014,
+      "eval_loss": 2.2800304889678955,
+      "eval_runtime": 296.664,
+      "eval_samples_per_second": 0.674,
+      "eval_steps_per_second": 0.169,
+      "step": 88
+    },
+    {
+      "epoch": 0.8202764976958525,
+      "grad_norm": 0.01112849185110947,
+      "learning_rate": 2.7040910027201976e-05,
+      "loss": 2.3045,
+      "step": 89
+    },
+    {
+      "epoch": 0.8294930875576036,
+      "grad_norm": 0.010506389237890506,
+      "learning_rate": 2.683702083322948e-05,
+      "loss": 2.2741,
+      "step": 90
+    },
+    {
+      "epoch": 0.8387096774193549,
+      "grad_norm": 0.009768468870786754,
+      "learning_rate": 2.6643050691725647e-05,
+      "loss": 2.2703,
+      "step": 91
+    },
+    {
+      "epoch": 0.847926267281106,
+      "grad_norm": 0.010141192796013403,
+      "learning_rate": 2.6459180040069244e-05,
+      "loss": 2.2548,
+      "step": 92
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.010229279382807752,
+      "learning_rate": 2.6285579920762826e-05,
+      "loss": 2.2488,
+      "step": 93
+    },
+    {
+      "epoch": 0.8663594470046083,
+      "grad_norm": 0.010307954340086967,
+      "learning_rate": 2.6122411822323345e-05,
+      "loss": 2.275,
+      "step": 94
+    },
+    {
+      "epoch": 0.8755760368663594,
+      "grad_norm": 0.011123883009152893,
+      "learning_rate": 2.5969827529060266e-05,
+      "loss": 2.124,
+      "step": 95
+    },
+    {
+      "epoch": 0.8847926267281107,
+      "grad_norm": 0.009608681495586172,
+      "learning_rate": 2.5827968979880805e-05,
+      "loss": 2.3229,
+      "step": 96
+    },
+    {
+      "epoch": 0.8940092165898618,
+      "grad_norm": 0.009782962640744528,
+      "learning_rate": 2.5696968136253768e-05,
+      "loss": 2.2763,
+      "step": 97
+    },
+    {
+      "epoch": 0.9032258064516129,
+      "grad_norm": 0.009605554717833914,
+      "learning_rate": 2.5576946859454592e-05,
+      "loss": 2.2603,
+      "step": 98
+    },
+    {
+      "epoch": 0.9124423963133641,
+      "grad_norm": 0.009456935936538857,
+      "learning_rate": 2.5468016797206052e-05,
+      "loss": 2.1912,
+      "step": 99
+    },
+    {
+      "epoch": 0.9124423963133641,
+      "eval_loss": 2.27895188331604,
+      "eval_runtime": 291.7402,
+      "eval_samples_per_second": 0.686,
+      "eval_steps_per_second": 0.171,
+      "step": 99
+    },
+    {
+      "epoch": 0.9216589861751152,
+      "grad_norm": 0.010595387456993979,
+      "learning_rate": 2.5370279279819864e-05,
+      "loss": 2.2735,
+      "step": 100
+    },
+    {
+      "epoch": 0.9308755760368663,
+      "grad_norm": 0.010469741198338179,
+      "learning_rate": 2.528382522593594e-05,
+      "loss": 2.2018,
+      "step": 101
+    },
+    {
+      "epoch": 0.9400921658986175,
+      "grad_norm": 0.01162265413802059,
+      "learning_rate": 2.5208735057946846e-05,
+      "loss": 2.3279,
+      "step": 102
+    },
+    {
+      "epoch": 0.9493087557603687,
+      "grad_norm": 0.0109629214839692,
+      "learning_rate": 2.5145078627186302e-05,
+      "loss": 2.2708,
+      "step": 103
+    },
+    {
+      "epoch": 0.9585253456221198,
+      "grad_norm": 0.010413150712905432,
+      "learning_rate": 2.5092915148951153e-05,
+      "loss": 2.3774,
+      "step": 104
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.010610525090597078,
+      "learning_rate": 2.5052293147417382e-05,
+      "loss": 2.231,
+      "step": 105
+    },
+    {
+      "epoch": 0.9769585253456221,
+      "grad_norm": 0.010306572358828672,
+      "learning_rate": 2.5023250410501333e-05,
+      "loss": 2.4008,
+      "step": 106
+    },
+    {
+      "epoch": 0.9861751152073732,
+      "grad_norm": 0.010261194384190835,
+      "learning_rate": 2.5005813954708107e-05,
+      "loss": 2.3173,
+      "step": 107
+    },
+    {
+      "epoch": 0.9953917050691244,
+      "grad_norm": 0.010312253992880615,
+      "learning_rate": 2.5e-05,
+      "loss": 2.3206,
+      "step": 108
     }
   ],
   "logging_steps": 1,
@@ -652,12 +857,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.5219590543966208e+16,
+  "total_flos": 2.037172357247795e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null