Training in progress, step 155000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6bcc61c9f454b7a64e29716235e1908b8ccfcc57499ab5454255b1bfbcadea7
+oid sha256:e85428a0f815969dced7abfb0c3db479ab6e9ac0b0476ec45794af0f2488296e
 size 1410301944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4002d60f1e4a15c1f11ee63cc36aa183850a72f44f466a3caa743e3506211571
+oid sha256:4cfe591240bbf8339bc0b20dc4896e7920caa6915b0ec035cadf1d16c6737411
 size 2820185786

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4084d1a8f5942c88851794ec5108b468d411ca529332c3f218a8ddcc004c0a0e
+oid sha256:13333a98c36f942bf81dc162e3112c4a9758770e0e5d231e4e8af488e2291291
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74dd121f56ba98a31c6c3f650af9c804c1ddf5d4b98b55654ba270708d2e7766
+oid sha256:46ed0a6739f44065f2f96ef3493947a9f7597f7e2d294443183887f798d35555
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.3828244644228795,
+  "epoch": 3.404790522744137,
   "eval_steps": 500,
-  "global_step": 154000,
+  "global_step": 155000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -27420,11 +27420,189 @@
       "eval_steps_per_second": 15.483,
       "num_input_tokens_seen": 88068164512,
       "step": 154000
+    },
+    {
+      "epoch": 3.3839227673389427,
+      "grad_norm": 0.09020719677209854,
+      "learning_rate": 0.0001,
+      "loss": 2.3497,
+      "num_input_tokens_seen": 88120592672,
+      "step": 154050
+    },
+    {
+      "epoch": 3.3850210702550054,
+      "grad_norm": 0.09590700268745422,
+      "learning_rate": 0.0001,
+      "loss": 2.3511,
+      "num_input_tokens_seen": 88173020768,
+      "step": 154100
+    },
+    {
+      "epoch": 3.386119373171068,
+      "grad_norm": 0.09949789196252823,
+      "learning_rate": 0.0001,
+      "loss": 2.3442,
+      "num_input_tokens_seen": 88225449568,
+      "step": 154150
+    },
+    {
+      "epoch": 3.387217676087131,
+      "grad_norm": 0.08850202709436417,
+      "learning_rate": 0.0001,
+      "loss": 2.3491,
+      "num_input_tokens_seen": 88277876544,
+      "step": 154200
+    },
+    {
+      "epoch": 3.388315979003194,
+      "grad_norm": 0.09314405918121338,
+      "learning_rate": 0.0001,
+      "loss": 2.3502,
+      "num_input_tokens_seen": 88330304416,
+      "step": 154250
+    },
+    {
+      "epoch": 3.3894142819192568,
+      "grad_norm": 0.09926445782184601,
+      "learning_rate": 0.0001,
+      "loss": 2.345,
+      "num_input_tokens_seen": 88382733216,
+      "step": 154300
+    },
+    {
+      "epoch": 3.39051258483532,
+      "grad_norm": 0.09468773007392883,
+      "learning_rate": 0.0001,
+      "loss": 2.3429,
+      "num_input_tokens_seen": 88435156832,
+      "step": 154350
+    },
+    {
+      "epoch": 3.3916108877513826,
+      "grad_norm": 0.09661844372749329,
+      "learning_rate": 0.0001,
+      "loss": 2.3465,
+      "num_input_tokens_seen": 88487585632,
+      "step": 154400
+    },
+    {
+      "epoch": 3.3927091906674454,
+      "grad_norm": 0.09253469109535217,
+      "learning_rate": 0.0001,
+      "loss": 2.3455,
+      "num_input_tokens_seen": 88540012544,
+      "step": 154450
+    },
+    {
+      "epoch": 3.3938074935835085,
+      "grad_norm": 0.08921549469232559,
+      "learning_rate": 0.0001,
+      "loss": 2.3491,
+      "num_input_tokens_seen": 88592441344,
+      "step": 154500
+    },
+    {
+      "epoch": 3.3938074935835085,
+      "eval_loss": 2.259216785430908,
+      "eval_runtime": 80.6571,
+      "eval_samples_per_second": 61.991,
+      "eval_steps_per_second": 15.498,
+      "num_input_tokens_seen": 88592441344,
+      "step": 154500
+    },
+    {
+      "epoch": 3.3949057964995712,
+      "grad_norm": 0.09509548544883728,
+      "learning_rate": 0.0001,
+      "loss": 2.3423,
+      "num_input_tokens_seen": 88644870144,
+      "step": 154550
+    },
+    {
+      "epoch": 3.3960040994156344,
+      "grad_norm": 0.0929824560880661,
+      "learning_rate": 0.0001,
+      "loss": 2.3429,
+      "num_input_tokens_seen": 88697298944,
+      "step": 154600
+    },
+    {
+      "epoch": 3.397102402331697,
+      "grad_norm": 0.09483112394809723,
+      "learning_rate": 0.0001,
+      "loss": 2.3451,
+      "num_input_tokens_seen": 88749721920,
+      "step": 154650
+    },
+    {
+      "epoch": 3.39820070524776,
+      "grad_norm": 0.09392872452735901,
+      "learning_rate": 0.0001,
+      "loss": 2.3437,
+      "num_input_tokens_seen": 88802150720,
+      "step": 154700
+    },
+    {
+      "epoch": 3.399299008163823,
+      "grad_norm": 0.09336952865123749,
+      "learning_rate": 0.0001,
+      "loss": 2.3414,
+      "num_input_tokens_seen": 88854579520,
+      "step": 154750
+    },
+    {
+      "epoch": 3.4003973110798857,
+      "grad_norm": 0.0942087471485138,
+      "learning_rate": 0.0001,
+      "loss": 2.3497,
+      "num_input_tokens_seen": 88907008320,
+      "step": 154800
+    },
+    {
+      "epoch": 3.4014956139959485,
+      "grad_norm": 0.10055429488420486,
+      "learning_rate": 0.0001,
+      "loss": 2.3472,
+      "num_input_tokens_seen": 88959437120,
+      "step": 154850
+    },
+    {
+      "epoch": 3.4025939169120116,
+      "grad_norm": 0.10026364773511887,
+      "learning_rate": 0.0001,
+      "loss": 2.3524,
+      "num_input_tokens_seen": 89011865920,
+      "step": 154900
+    },
+    {
+      "epoch": 3.4036922198280744,
+      "grad_norm": 0.09667252004146576,
+      "learning_rate": 0.0001,
+      "loss": 2.3448,
+      "num_input_tokens_seen": 89064293312,
+      "step": 154950
+    },
+    {
+      "epoch": 3.404790522744137,
+      "grad_norm": 3.4680259227752686,
+      "learning_rate": 0.0001,
+      "loss": 2.3532,
+      "num_input_tokens_seen": 89116722112,
+      "step": 155000
+    },
+    {
+      "epoch": 3.404790522744137,
+      "eval_loss": 2.2594308853149414,
+      "eval_runtime": 80.9279,
+      "eval_samples_per_second": 61.783,
+      "eval_steps_per_second": 15.446,
+      "num_input_tokens_seen": 89116722112,
+      "step": 155000
     }
   ],
   "logging_steps": 50,
   "max_steps": 200000,
-  "num_input_tokens_seen": 88068164512,
+  "num_input_tokens_seen": 89116722112,
   "num_train_epochs": 5,
   "save_steps": 1000,
   "stateful_callbacks": {
@@ -27439,7 +27617,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5586458755303306e+20,
+  "total_flos": 1.5772034324812677e+20,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null