Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6fd718b067586335897533aa7bd63ca23c94afc13ab6ac2268c18dd371e6b5
+oid sha256:d04ba4736b02a97a50388c844a3233defabb0409d7293fd25744eaf151c508f4
 size 78480072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ba6a99843396a30b988d09d1abebaed7e4105a82ed9ee4456afef511e15db0
+oid sha256:bbb67728cbb1e678c0e10e628bafdaf68c17d80c8411cf06c5fbd99821eb6ab0
 size 157104826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fd0733e9e1a88cb65e81059f246d24ee821b3191409395fdefdac17bae0a34
+oid sha256:194336d94558158d86c1d68238757bba95a14a414f0709d2086e6a135601e667
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012774655084312723,
+  "epoch": 0.025549310168625446,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,221 @@
       "eval_samples_per_second": 8.141,
       "eval_steps_per_second": 1.018,
       "step": 25
+    },
+    {
+      "epoch": 0.013285641287685232,
+      "grad_norm": 0.9014043211936951,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.0381,
+      "step": 26
+    },
+    {
+      "epoch": 0.013796627491057742,
+      "grad_norm": 1.5231494903564453,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 2.9764,
+      "step": 27
+    },
+    {
+      "epoch": 0.01430761369443025,
+      "grad_norm": 1.1799890995025635,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.8968,
+      "step": 28
+    },
+    {
+      "epoch": 0.01481859989780276,
+      "grad_norm": 1.0172849893569946,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 3.1402,
+      "step": 29
+    },
+    {
+      "epoch": 0.015329586101175269,
+      "grad_norm": 1.0696003437042236,
+      "learning_rate": 5e-05,
+      "loss": 3.0205,
+      "step": 30
+    },
+    {
+      "epoch": 0.015329586101175269,
+      "eval_loss": 2.9533283710479736,
+      "eval_runtime": 202.1751,
+      "eval_samples_per_second": 8.151,
+      "eval_steps_per_second": 1.019,
+      "step": 30
+    },
+    {
+      "epoch": 0.015840572304547777,
+      "grad_norm": 1.2514764070510864,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 3.0253,
+      "step": 31
+    },
+    {
+      "epoch": 0.016351558507920288,
+      "grad_norm": 1.0577430725097656,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 2.8868,
+      "step": 32
+    },
+    {
+      "epoch": 0.016862544711292796,
+      "grad_norm": 0.7655683159828186,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 2.9324,
+      "step": 33
+    },
+    {
+      "epoch": 0.017373530914665303,
+      "grad_norm": 0.890068769454956,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.9819,
+      "step": 34
+    },
+    {
+      "epoch": 0.01788451711803781,
+      "grad_norm": 1.170661449432373,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.9615,
+      "step": 35
+    },
+    {
+      "epoch": 0.01788451711803781,
+      "eval_loss": 2.9383625984191895,
+      "eval_runtime": 202.5804,
+      "eval_samples_per_second": 8.135,
+      "eval_steps_per_second": 1.017,
+      "step": 35
+    },
+    {
+      "epoch": 0.018395503321410323,
+      "grad_norm": 1.6589326858520508,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 3.0094,
+      "step": 36
+    },
+    {
+      "epoch": 0.01890648952478283,
+      "grad_norm": 1.0054802894592285,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 2.9128,
+      "step": 37
+    },
+    {
+      "epoch": 0.019417475728155338,
+      "grad_norm": 0.7873812317848206,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.9113,
+      "step": 38
+    },
+    {
+      "epoch": 0.01992846193152785,
+      "grad_norm": 0.8072642683982849,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 2.8723,
+      "step": 39
+    },
+    {
+      "epoch": 0.020439448134900357,
+      "grad_norm": 0.9139198660850525,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.9985,
+      "step": 40
+    },
+    {
+      "epoch": 0.020439448134900357,
+      "eval_loss": 2.9303066730499268,
+      "eval_runtime": 202.429,
+      "eval_samples_per_second": 8.141,
+      "eval_steps_per_second": 1.018,
+      "step": 40
+    },
+    {
+      "epoch": 0.020950434338272865,
+      "grad_norm": 0.8664709329605103,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 2.9143,
+      "step": 41
+    },
+    {
+      "epoch": 0.021461420541645376,
+      "grad_norm": 0.8760465383529663,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.9773,
+      "step": 42
+    },
+    {
+      "epoch": 0.021972406745017884,
+      "grad_norm": 0.9105547666549683,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 2.9997,
+      "step": 43
+    },
+    {
+      "epoch": 0.022483392948390392,
+      "grad_norm": 0.8562077283859253,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 2.9649,
+      "step": 44
+    },
+    {
+      "epoch": 0.022994379151762903,
+      "grad_norm": 0.9147664308547974,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8364,
+      "step": 45
+    },
+    {
+      "epoch": 0.022994379151762903,
+      "eval_loss": 2.927216053009033,
+      "eval_runtime": 202.2748,
+      "eval_samples_per_second": 8.147,
+      "eval_steps_per_second": 1.018,
+      "step": 45
+    },
+    {
+      "epoch": 0.02350536535513541,
+      "grad_norm": 0.9426882863044739,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.9337,
+      "step": 46
+    },
+    {
+      "epoch": 0.02401635155850792,
+      "grad_norm": 0.8832350969314575,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.9682,
+      "step": 47
+    },
+    {
+      "epoch": 0.02452733776188043,
+      "grad_norm": 1.0299304723739624,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 2.886,
+      "step": 48
+    },
+    {
+      "epoch": 0.025038323965252938,
+      "grad_norm": 0.8099086880683899,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 2.9609,
+      "step": 49
+    },
+    {
+      "epoch": 0.025549310168625446,
+      "grad_norm": 1.2001909017562866,
+      "learning_rate": 0.0,
+      "loss": 2.9463,
+      "step": 50
+    },
+    {
+      "epoch": 0.025549310168625446,
+      "eval_loss": 2.9264729022979736,
+      "eval_runtime": 202.2198,
+      "eval_samples_per_second": 8.15,
+      "eval_steps_per_second": 1.019,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -244,12 +459,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7279937555791872.0,
+  "total_flos": 1.4363120042508288e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null