Training in progress, step 154000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e33340944bdfba019639a505fb829fbf58de481dcbd6bfa34260585e39bc82
+oid sha256:e6bcc61c9f454b7a64e29716235e1908b8ccfcc57499ab5454255b1bfbcadea7
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea0c2ad8c2577dec58bcf798facca9b484958ae7510c46df4fbc524b7011e74a
+oid sha256:4002d60f1e4a15c1f11ee63cc36aa183850a72f44f466a3caa743e3506211571
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bb1d6d2c94dbd4fc1bf9d5756f17ab78e6ccfa57b4112f0c257527e9ee1e447
+oid sha256:4084d1a8f5942c88851794ec5108b468d411ca529332c3f218a8ddcc004c0a0e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a693861125ab0b2f85599d0c1f06c209c17c8fe0c9515e61fbc5e32f352f900
+oid sha256:74dd121f56ba98a31c6c3f650af9c804c1ddf5d4b98b55654ba270708d2e7766
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.360858406101622,
+  "epoch": 3.3828244644228795,
   "eval_steps": 500,
-  "global_step": 153000,
+  "global_step": 154000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27242,11 +27242,189 @@
       "eval_steps_per_second": 15.473,
       "num_input_tokens_seen": 87019603744,
       "step": 153000
+    },
+    {
+      "epoch": 3.3619567090176847,
+      "grad_norm": 0.09880559146404266,
+      "learning_rate": 0.0001,
+      "loss": 2.3507,
+      "num_input_tokens_seen": 87072028928,
+      "step": 153050
+    },
+    {
+      "epoch": 3.3630550119337475,
+      "grad_norm": 0.09557171911001205,
+      "learning_rate": 0.0001,
+      "loss": 2.3501,
+      "num_input_tokens_seen": 87124457728,
+      "step": 153100
+    },
+    {
+      "epoch": 3.3641533148498106,
+      "grad_norm": 0.09662795066833496,
+      "learning_rate": 0.0001,
+      "loss": 2.3499,
+      "num_input_tokens_seen": 87176886528,
+      "step": 153150
+    },
+    {
+      "epoch": 3.3652516177658733,
+      "grad_norm": 0.09444860368967056,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 87229314144,
+      "step": 153200
+    },
+    {
+      "epoch": 3.3663499206819365,
+      "grad_norm": 0.09235711395740509,
+      "learning_rate": 0.0001,
+      "loss": 2.3414,
+      "num_input_tokens_seen": 87281742944,
+      "step": 153250
+    },
+    {
+      "epoch": 3.3674482235979992,
+      "grad_norm": 0.09402730315923691,
+      "learning_rate": 0.0001,
+      "loss": 2.3476,
+      "num_input_tokens_seen": 87334170144,
+      "step": 153300
+    },
+    {
+      "epoch": 3.368546526514062,
+      "grad_norm": 0.09448970854282379,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 87386598944,
+      "step": 153350
+    },
+    {
+      "epoch": 3.369644829430125,
+      "grad_norm": 0.09693534672260284,
+      "learning_rate": 0.0001,
+      "loss": 2.3438,
+      "num_input_tokens_seen": 87439027744,
+      "step": 153400
+    },
+    {
+      "epoch": 3.370743132346188,
+      "grad_norm": 0.09623382240533829,
+      "learning_rate": 0.0001,
+      "loss": 2.3441,
+      "num_input_tokens_seen": 87491455136,
+      "step": 153450
+    },
+    {
+      "epoch": 3.3718414352622506,
+      "grad_norm": 0.09151625633239746,
+      "learning_rate": 0.0001,
+      "loss": 2.3437,
+      "num_input_tokens_seen": 87543883936,
+      "step": 153500
+    },
+    {
+      "epoch": 3.3718414352622506,
+      "eval_loss": 2.2598507404327393,
+      "eval_runtime": 80.5747,
+      "eval_samples_per_second": 62.054,
+      "eval_steps_per_second": 15.514,
+      "num_input_tokens_seen": 87543883936,
+      "step": 153500
+    },
+    {
+      "epoch": 3.3729397381783137,
+      "grad_norm": 0.09348684549331665,
+      "learning_rate": 0.0001,
+      "loss": 2.352,
+      "num_input_tokens_seen": 87596312736,
+      "step": 153550
+    },
+    {
+      "epoch": 3.3740380410943764,
+      "grad_norm": 0.08888132125139236,
+      "learning_rate": 0.0001,
+      "loss": 2.3439,
+      "num_input_tokens_seen": 87648741536,
+      "step": 153600
+    },
+    {
+      "epoch": 3.375136344010439,
+      "grad_norm": 0.09428702294826508,
+      "learning_rate": 0.0001,
+      "loss": 2.3515,
+      "num_input_tokens_seen": 87701167552,
+      "step": 153650
+    },
+    {
+      "epoch": 3.3762346469265023,
+      "grad_norm": 0.0958220586180687,
+      "learning_rate": 0.0001,
+      "loss": 2.3509,
+      "num_input_tokens_seen": 87753593472,
+      "step": 153700
+    },
+    {
+      "epoch": 3.377332949842565,
+      "grad_norm": 0.0915323942899704,
+      "learning_rate": 0.0001,
+      "loss": 2.3424,
+      "num_input_tokens_seen": 87806022112,
+      "step": 153750
+    },
+    {
+      "epoch": 3.378431252758628,
+      "grad_norm": 0.09283678978681564,
+      "learning_rate": 0.0001,
+      "loss": 2.3523,
+      "num_input_tokens_seen": 87858450912,
+      "step": 153800
+    },
+    {
+      "epoch": 3.379529555674691,
+      "grad_norm": 0.09269370883703232,
+      "learning_rate": 0.0001,
+      "loss": 2.348,
+      "num_input_tokens_seen": 87910879712,
+      "step": 153850
+    },
+    {
+      "epoch": 3.3806278585907537,
+      "grad_norm": 0.09313447028398514,
+      "learning_rate": 0.0001,
+      "loss": 2.3479,
+      "num_input_tokens_seen": 87963308512,
+      "step": 153900
+    },
+    {
+      "epoch": 3.381726161506817,
+      "grad_norm": 0.09186484664678574,
+      "learning_rate": 0.0001,
+      "loss": 2.3438,
+      "num_input_tokens_seen": 88015735712,
+      "step": 153950
+    },
+    {
+      "epoch": 3.3828244644228795,
+      "grad_norm": 0.09128747135400772,
+      "learning_rate": 0.0001,
+      "loss": 2.3461,
+      "num_input_tokens_seen": 88068164512,
+      "step": 154000
+    },
+    {
+      "epoch": 3.3828244644228795,
+      "eval_loss": 2.259556293487549,
+      "eval_runtime": 80.7318,
+      "eval_samples_per_second": 61.933,
+      "eval_steps_per_second": 15.483,
+      "num_input_tokens_seen": 88068164512,
+      "step": 154000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 87019603744,
+  "num_input_tokens_seen": 88068164512,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -27261,7 +27439,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5400882625115718e+20,
+  "total_flos": 1.5586458755303306e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null