Training in progress, step 62000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dc1817a301fc24319ca1c05c92090e28d0ab00a3a5d43949da4772ff52fcf2b
+oid sha256:0c05cde8285dd52085342b46430f4e5412103d775ef2ecb3ff92fe973f05563a
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c0576570955fbd0c77602fddc48b3da384f1445f3f7054045594138138a2617
+oid sha256:13bd3612e3785a0d69245374e9d503a45ff63d121c602ad8a1a69ce58b21ee6f
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8ee7735caca4437694ef1fa1c7821cadab81eb5dba9c8318224d8baee7f9384
+oid sha256:b604bf86b8b70beb6e4043604c61f8577f1fbe75a9d1e20249b5622ec5aa2654
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88c7ed774bb0bea4c8451805c5254d2a8728348d14f02b8481173830b417e9b0
+oid sha256:3b86dd42ce2bfa419ab9d950fa2e032bc9074c23516cf132dad718a38dfd9a2d
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.29097153487484645,
+  "epoch": 0.2957415600367292,
   "eval_steps": 500,
-  "global_step": 61000,
+  "global_step": 62000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10866,11 +10866,189 @@
       "eval_steps_per_second": 23.343,
       "num_input_tokens_seen": 15990779456,
       "step": 61000
+    },
+    {
+      "epoch": 0.2912100361329406,
+      "grad_norm": 0.19767510890960693,
+      "learning_rate": 0.0007118738970516943,
+      "loss": 2.5963,
+      "num_input_tokens_seen": 16003886656,
+      "step": 61050
+    },
+    {
+      "epoch": 0.2914485373910347,
+      "grad_norm": 0.21463529765605927,
+      "learning_rate": 0.0007067792524832604,
+      "loss": 2.5825,
+      "num_input_tokens_seen": 16016993856,
+      "step": 61100
+    },
+    {
+      "epoch": 0.29168703864912887,
+      "grad_norm": 0.2011532485485077,
+      "learning_rate": 0.0007016585772004026,
+      "loss": 2.5783,
+      "num_input_tokens_seen": 16030101056,
+      "step": 61150
+    },
+    {
+      "epoch": 0.29192553990722303,
+      "grad_norm": 0.19351401925086975,
+      "learning_rate": 0.0006965125158269618,
+      "loss": 2.5619,
+      "num_input_tokens_seen": 16043208256,
+      "step": 61200
+    },
+    {
+      "epoch": 0.29216404116531713,
+      "grad_norm": 0.1988568902015686,
+      "learning_rate": 0.000691341716182545,
+      "loss": 2.6007,
+      "num_input_tokens_seen": 16056315456,
+      "step": 61250
+    },
+    {
+      "epoch": 0.2924025424234113,
+      "grad_norm": 0.20459413528442383,
+      "learning_rate": 0.0006861468292009726,
+      "loss": 2.5762,
+      "num_input_tokens_seen": 16069422656,
+      "step": 61300
+    },
+    {
+      "epoch": 0.2926410436815054,
+      "grad_norm": 0.1914205551147461,
+      "learning_rate": 0.0006809285088483361,
+      "loss": 2.5734,
+      "num_input_tokens_seen": 16082529856,
+      "step": 61350
+    },
+    {
+      "epoch": 0.29287954493959956,
+      "grad_norm": 0.194325253367424,
+      "learning_rate": 0.0006756874120406714,
+      "loss": 2.5874,
+      "num_input_tokens_seen": 16095637056,
+      "step": 61400
+    },
+    {
+      "epoch": 0.2931180461976937,
+      "grad_norm": 0.20854853093624115,
+      "learning_rate": 0.0006704241985612625,
+      "loss": 2.5865,
+      "num_input_tokens_seen": 16108744256,
+      "step": 61450
+    },
+    {
+      "epoch": 0.2933565474557878,
+      "grad_norm": 0.190395787358284,
+      "learning_rate": 0.0006651395309775837,
+      "loss": 2.5716,
+      "num_input_tokens_seen": 16121851456,
+      "step": 61500
+    },
+    {
+      "epoch": 0.2933565474557878,
+      "eval_loss": 2.4551966190338135,
+      "eval_runtime": 53.3343,
+      "eval_samples_per_second": 93.748,
+      "eval_steps_per_second": 23.437,
+      "num_input_tokens_seen": 16121851456,
+      "step": 61500
+    },
+    {
+      "epoch": 0.293595048713882,
+      "grad_norm": 0.20652073621749878,
+      "learning_rate": 0.0006598340745578908,
+      "loss": 2.5765,
+      "num_input_tokens_seen": 16134958656,
+      "step": 61550
+    },
+    {
+      "epoch": 0.2938335499719761,
+      "grad_norm": 0.20701836049556732,
+      "learning_rate": 0.0006545084971874737,
+      "loss": 2.5653,
+      "num_input_tokens_seen": 16148065856,
+      "step": 61600
+    },
+    {
+      "epoch": 0.29407205123007024,
+      "grad_norm": 0.1792392134666443,
+      "learning_rate": 0.000649163469284578,
+      "loss": 2.577,
+      "num_input_tokens_seen": 16161173056,
+      "step": 61650
+    },
+    {
+      "epoch": 0.2943105524881644,
+      "grad_norm": 0.21742790937423706,
+      "learning_rate": 0.0006437996637160086,
+      "loss": 2.574,
+      "num_input_tokens_seen": 16174280256,
+      "step": 61700
+    },
+    {
+      "epoch": 0.2945490537462585,
+      "grad_norm": 0.20747682452201843,
+      "learning_rate": 0.0006384177557124247,
+      "loss": 2.564,
+      "num_input_tokens_seen": 16187387456,
+      "step": 61750
+    },
+    {
+      "epoch": 0.29478755500435266,
+      "grad_norm": 0.19990311563014984,
+      "learning_rate": 0.0006330184227833376,
+      "loss": 2.5866,
+      "num_input_tokens_seen": 16200494656,
+      "step": 61800
+    },
+    {
+      "epoch": 0.29502605626244677,
+      "grad_norm": 0.20410317182540894,
+      "learning_rate": 0.0006276023446318213,
+      "loss": 2.5559,
+      "num_input_tokens_seen": 16213601856,
+      "step": 61850
+    },
+    {
+      "epoch": 0.2952645575205409,
+      "grad_norm": 0.19365034997463226,
+      "learning_rate": 0.000622170203068947,
+      "loss": 2.5705,
+      "num_input_tokens_seen": 16226709056,
+      "step": 61900
+    },
+    {
+      "epoch": 0.29550305877863503,
+      "grad_norm": 0.2115161269903183,
+      "learning_rate": 0.0006167226819279528,
+      "loss": 2.5621,
+      "num_input_tokens_seen": 16239816256,
+      "step": 61950
+    },
+    {
+      "epoch": 0.2957415600367292,
+      "grad_norm": 0.22992485761642456,
+      "learning_rate": 0.0006112604669781572,
+      "loss": 2.5587,
+      "num_input_tokens_seen": 16252923456,
+      "step": 62000
+    },
+    {
+      "epoch": 0.2957415600367292,
+      "eval_loss": 2.452096462249756,
+      "eval_runtime": 53.6354,
+      "eval_samples_per_second": 93.222,
+      "eval_steps_per_second": 23.306,
+      "num_input_tokens_seen": 16252923456,
+      "step": 62000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 15990779456,
+  "num_input_tokens_seen": 16252923456,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -10885,7 +11063,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.2776895744874906e+18,
+  "total_flos": 4.3478156530129306e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null