Training in progress, step 38000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce938a644f0cf4d10d231b631256c1bcbd8d98d79787b20ca3ed148b88756be
+oid sha256:a94fdb7295accdf7201fc02029e5ae45ac44dcd9ef16798d70e0f488636e1f9c
 size 517931840

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64656c8de22e45c2941d2ea854ec0d370243cfeea2920fb181966f363dd14777
+oid sha256:d665c90e6bb04abc526448689a0e7c0f687d8ae7453c9e6c300bb8f38a3b48a2
 size 1035661434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0451e520bbe84b70e4cd2907956e95cd6d56464539f21e68e26c043e5cf63b1e
+oid sha256:067fc834db8daa6bcb7d646c19fb2debac62a3ca3a0f0e8b29d38f87eb5e83ea
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90815e584013ee668de6d5b656c515902fbacbb32f54a71d2d1d29e05110019f
+oid sha256:7b9f11080dc8caed5e3c50cfbb46586ae36896ccfee6afab64bede4080bf44b1
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8127435999873696,
+  "epoch": 0.8347096432302714,
   "eval_steps": 500,
-  "global_step": 37000,
+  "global_step": 38000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6594,11 +6594,189 @@
       "eval_steps_per_second": 18.779,
       "num_input_tokens_seen": 38797308160,
       "step": 37000
+    },
+    {
+      "epoch": 0.8138419021495146,
+      "grad_norm": 0.1504666954278946,
+      "learning_rate": 0.001,
+      "loss": 2.6625,
+      "num_input_tokens_seen": 38849736960,
+      "step": 37050
+    },
+    {
+      "epoch": 0.8149402043116597,
+      "grad_norm": 0.15831789374351501,
+      "learning_rate": 0.001,
+      "loss": 2.6566,
+      "num_input_tokens_seen": 38902165760,
+      "step": 37100
+    },
+    {
+      "epoch": 0.8160385064738048,
+      "grad_norm": 0.1391575187444687,
+      "learning_rate": 0.001,
+      "loss": 2.6609,
+      "num_input_tokens_seen": 38954594560,
+      "step": 37150
+    },
+    {
+      "epoch": 0.81713680863595,
+      "grad_norm": 0.22168035805225372,
+      "learning_rate": 0.001,
+      "loss": 2.6768,
+      "num_input_tokens_seen": 39007023360,
+      "step": 37200
+    },
+    {
+      "epoch": 0.818235110798095,
+      "grad_norm": 0.1874976009130478,
+      "learning_rate": 0.001,
+      "loss": 2.679,
+      "num_input_tokens_seen": 39059452160,
+      "step": 37250
+    },
+    {
+      "epoch": 0.8193334129602401,
+      "grad_norm": 0.1796240657567978,
+      "learning_rate": 0.001,
+      "loss": 2.6644,
+      "num_input_tokens_seen": 39111880960,
+      "step": 37300
+    },
+    {
+      "epoch": 0.8204317151223852,
+      "grad_norm": 0.3271934986114502,
+      "learning_rate": 0.001,
+      "loss": 2.6695,
+      "num_input_tokens_seen": 39164309760,
+      "step": 37350
+    },
+    {
+      "epoch": 0.8215300172845302,
+      "grad_norm": 0.13447704911231995,
+      "learning_rate": 0.001,
+      "loss": 2.6656,
+      "num_input_tokens_seen": 39216738560,
+      "step": 37400
+    },
+    {
+      "epoch": 0.8226283194466754,
+      "grad_norm": 0.1367628127336502,
+      "learning_rate": 0.001,
+      "loss": 2.6505,
+      "num_input_tokens_seen": 39269167360,
+      "step": 37450
+    },
+    {
+      "epoch": 0.8237266216088205,
+      "grad_norm": 0.1498686671257019,
+      "learning_rate": 0.001,
+      "loss": 2.6594,
+      "num_input_tokens_seen": 39321596160,
+      "step": 37500
+    },
+    {
+      "epoch": 0.8237266216088205,
+      "eval_loss": 2.5516529083251953,
+      "eval_runtime": 66.8213,
+      "eval_samples_per_second": 74.826,
+      "eval_steps_per_second": 18.707,
+      "num_input_tokens_seen": 39321596160,
+      "step": 37500
+    },
+    {
+      "epoch": 0.8248249237709656,
+      "grad_norm": 0.14790424704551697,
+      "learning_rate": 0.001,
+      "loss": 2.6519,
+      "num_input_tokens_seen": 39374024960,
+      "step": 37550
+    },
+    {
+      "epoch": 0.8259232259331106,
+      "grad_norm": 0.15297918021678925,
+      "learning_rate": 0.001,
+      "loss": 2.6533,
+      "num_input_tokens_seen": 39426453760,
+      "step": 37600
+    },
+    {
+      "epoch": 0.8270215280952558,
+      "grad_norm": 0.15760953724384308,
+      "learning_rate": 0.001,
+      "loss": 2.6584,
+      "num_input_tokens_seen": 39478882560,
+      "step": 37650
+    },
+    {
+      "epoch": 0.8281198302574009,
+      "grad_norm": 0.1545770913362503,
+      "learning_rate": 0.001,
+      "loss": 2.6453,
+      "num_input_tokens_seen": 39531311360,
+      "step": 37700
+    },
+    {
+      "epoch": 0.8292181324195459,
+      "grad_norm": 0.17809870839118958,
+      "learning_rate": 0.001,
+      "loss": 2.6547,
+      "num_input_tokens_seen": 39583740160,
+      "step": 37750
+    },
+    {
+      "epoch": 0.830316434581691,
+      "grad_norm": 0.2712576687335968,
+      "learning_rate": 0.001,
+      "loss": 2.6489,
+      "num_input_tokens_seen": 39636168960,
+      "step": 37800
+    },
+    {
+      "epoch": 0.8314147367438361,
+      "grad_norm": 0.1525331437587738,
+      "learning_rate": 0.001,
+      "loss": 2.6558,
+      "num_input_tokens_seen": 39688597760,
+      "step": 37850
+    },
+    {
+      "epoch": 0.8325130389059812,
+      "grad_norm": 0.1624525785446167,
+      "learning_rate": 0.001,
+      "loss": 2.6465,
+      "num_input_tokens_seen": 39741026560,
+      "step": 37900
+    },
+    {
+      "epoch": 0.8336113410681263,
+      "grad_norm": 0.14974552392959595,
+      "learning_rate": 0.001,
+      "loss": 2.6595,
+      "num_input_tokens_seen": 39793455360,
+      "step": 37950
+    },
+    {
+      "epoch": 0.8347096432302714,
+      "grad_norm": 0.15206202864646912,
+      "learning_rate": 0.001,
+      "loss": 2.6525,
+      "num_input_tokens_seen": 39845884160,
+      "step": 38000
+    },
+    {
+      "epoch": 0.8347096432302714,
+      "eval_loss": 2.549203395843506,
+      "eval_runtime": 66.3732,
+      "eval_samples_per_second": 75.332,
+      "eval_steps_per_second": 18.833,
+      "num_input_tokens_seen": 39845884160,
+      "step": 38000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 38797308160,
+  "num_input_tokens_seen": 39845884160,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -6613,7 +6791,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2095351303794196e+19,
+  "total_flos": 2.2692523019759124e+19,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null