Training in progress, step 33000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2cef3edc11233bd02d8a0fce925583abfb5c9dd14aa68691d119c85f02da0c2c
+oid sha256:e09d13e4122e8385a0b0d20fd5c3e0ad48906dae0b62b89359b90d5025d71342
 size 301235464

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802c539bacfaec7683d6ba2f0a942347dfcc3e86cdff0695306776a8172eb9e5
+oid sha256:b5a1cf3d4f7ef91e1710cd1ff627ffe86cbcad4b359e09cfc0653ed1c67113f3
 size 602335994

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bee3fafd3f39d206bc71937649788266030036a262f517651404c02bc2d21bc8
+oid sha256:e9d470001272ba85c23801cee9a0e9047fab9ee4730b52f1c2aa2f87689e581d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b45d7a8e84e284c770af40e442ab0efb2fec2b035c2481cdfd246cdf35d0dd1
+oid sha256:281c918d3dcf25df4f5a9bbf64a4fd88f0fa5c69087d3374f9f2ce6266f988a9
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15264080518024734,
+  "epoch": 0.15741083034213005,
   "eval_steps": 500,
-  "global_step": 32000,
+  "global_step": 33000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5704,11 +5704,189 @@
       "eval_steps_per_second": 24.503,
       "num_input_tokens_seen": 8388608000,
       "step": 32000
+    },
+    {
+      "epoch": 0.15287930643834147,
+      "grad_norm": 0.180119588971138,
+      "learning_rate": 0.001,
+      "loss": 2.6558,
+      "num_input_tokens_seen": 8401715200,
+      "step": 32050
+    },
+    {
+      "epoch": 0.1531178076964356,
+      "grad_norm": 0.1952589452266693,
+      "learning_rate": 0.001,
+      "loss": 2.6465,
+      "num_input_tokens_seen": 8414822400,
+      "step": 32100
+    },
+    {
+      "epoch": 0.15335630895452973,
+      "grad_norm": 0.1845589131116867,
+      "learning_rate": 0.001,
+      "loss": 2.6297,
+      "num_input_tokens_seen": 8427929600,
+      "step": 32150
+    },
+    {
+      "epoch": 0.15359481021262386,
+      "grad_norm": 0.20116594433784485,
+      "learning_rate": 0.001,
+      "loss": 2.6422,
+      "num_input_tokens_seen": 8441036800,
+      "step": 32200
+    },
+    {
+      "epoch": 0.15383331147071802,
+      "grad_norm": 0.1932612508535385,
+      "learning_rate": 0.001,
+      "loss": 2.6494,
+      "num_input_tokens_seen": 8454144000,
+      "step": 32250
+    },
+    {
+      "epoch": 0.15407181272881215,
+      "grad_norm": 0.17934490740299225,
+      "learning_rate": 0.001,
+      "loss": 2.6474,
+      "num_input_tokens_seen": 8467251200,
+      "step": 32300
+    },
+    {
+      "epoch": 0.15431031398690628,
+      "grad_norm": 0.19273313879966736,
+      "learning_rate": 0.001,
+      "loss": 2.6447,
+      "num_input_tokens_seen": 8480358400,
+      "step": 32350
+    },
+    {
+      "epoch": 0.15454881524500041,
+      "grad_norm": 0.1921055018901825,
+      "learning_rate": 0.001,
+      "loss": 2.665,
+      "num_input_tokens_seen": 8493465600,
+      "step": 32400
+    },
+    {
+      "epoch": 0.15478731650309455,
+      "grad_norm": 0.37117844820022583,
+      "learning_rate": 0.001,
+      "loss": 2.6351,
+      "num_input_tokens_seen": 8506572800,
+      "step": 32450
+    },
+    {
+      "epoch": 0.15502581776118868,
+      "grad_norm": 0.1884016990661621,
+      "learning_rate": 0.001,
+      "loss": 2.6436,
+      "num_input_tokens_seen": 8519680000,
+      "step": 32500
+    },
+    {
+      "epoch": 0.15502581776118868,
+      "eval_loss": 2.5313448905944824,
+      "eval_runtime": 50.7051,
+      "eval_samples_per_second": 98.609,
+      "eval_steps_per_second": 24.652,
+      "num_input_tokens_seen": 8519680000,
+      "step": 32500
+    },
+    {
+      "epoch": 0.15526431901928284,
+      "grad_norm": 0.22205407917499542,
+      "learning_rate": 0.001,
+      "loss": 2.6464,
+      "num_input_tokens_seen": 8532787200,
+      "step": 32550
+    },
+    {
+      "epoch": 0.15550282027737697,
+      "grad_norm": 0.18515361845493317,
+      "learning_rate": 0.001,
+      "loss": 2.642,
+      "num_input_tokens_seen": 8545894400,
+      "step": 32600
+    },
+    {
+      "epoch": 0.1557413215354711,
+      "grad_norm": 0.18903231620788574,
+      "learning_rate": 0.001,
+      "loss": 2.6446,
+      "num_input_tokens_seen": 8559001600,
+      "step": 32650
+    },
+    {
+      "epoch": 0.15597982279356523,
+      "grad_norm": 0.1857556253671646,
+      "learning_rate": 0.001,
+      "loss": 2.6561,
+      "num_input_tokens_seen": 8572108800,
+      "step": 32700
+    },
+    {
+      "epoch": 0.15621832405165936,
+      "grad_norm": 0.45706707239151,
+      "learning_rate": 0.001,
+      "loss": 2.6487,
+      "num_input_tokens_seen": 8585216000,
+      "step": 32750
+    },
+    {
+      "epoch": 0.15645682530975352,
+      "grad_norm": 0.20191136002540588,
+      "learning_rate": 0.001,
+      "loss": 2.6593,
+      "num_input_tokens_seen": 8598323200,
+      "step": 32800
+    },
+    {
+      "epoch": 0.15669532656784765,
+      "grad_norm": 0.21191105246543884,
+      "learning_rate": 0.001,
+      "loss": 2.659,
+      "num_input_tokens_seen": 8611430400,
+      "step": 32850
+    },
+    {
+      "epoch": 0.15693382782594179,
+      "grad_norm": 0.20596672594547272,
+      "learning_rate": 0.001,
+      "loss": 2.6354,
+      "num_input_tokens_seen": 8624537600,
+      "step": 32900
+    },
+    {
+      "epoch": 0.15717232908403592,
+      "grad_norm": 0.2952199876308441,
+      "learning_rate": 0.001,
+      "loss": 2.6501,
+      "num_input_tokens_seen": 8637644800,
+      "step": 32950
+    },
+    {
+      "epoch": 0.15741083034213005,
+      "grad_norm": 0.2217044234275818,
+      "learning_rate": 0.001,
+      "loss": 2.6495,
+      "num_input_tokens_seen": 8650752000,
+      "step": 33000
+    },
+    {
+      "epoch": 0.15741083034213005,
+      "eval_loss": 2.5319430828094482,
+      "eval_runtime": 50.8413,
+      "eval_samples_per_second": 98.345,
+      "eval_steps_per_second": 24.586,
+      "num_input_tokens_seen": 8650752000,
+      "step": 33000
     }
   ],
   "logging_steps": 50,
   "max_steps": 70000,
-  "num_input_tokens_seen": 8388608000,
+  "num_input_tokens_seen": 8650752000,
   "num_train_epochs": 1,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -5723,7 +5901,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.24403451281408e+18,
+  "total_flos": 2.31416059133952e+18,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null