Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429a47ef74b8fe1528641b3dd3568e0957a75adde1d8f729569b2419e92f01b4
+oid sha256:5baf2d9d23a6ae4d841c7f6b240076a17cff9a30aa1337bd43807e5b48fd51bd
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c9ff7e76fd7718674bb87fb69adcc82a226a2f3dd2234fea1a2e3362e24eaa
+oid sha256:b2f670ec5d3256c45c640b907b6d9c5de3836dba86f58dbcef1c16c80e7d5c94
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5820296c693350b4a78d17e961b7776868327825c6555da3f47af5d5fccdd83b
+oid sha256:84ae42e8b781a4ce41f32c955d07a7079e7bcdbea407b7f2622873e5c4fb55eb
 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": 0.1037344398340249,
+  "epoch": 0.2074688796680498,
   "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": 211.022,
       "eval_steps_per_second": 27.027,
       "step": 25
+    },
+    {
+      "epoch": 0.1078838174273859,
+      "grad_norm": 454.03875732421875,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 19.4273,
+      "step": 26
+    },
+    {
+      "epoch": 0.11203319502074689,
+      "grad_norm": 303.0365905761719,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 16.5833,
+      "step": 27
+    },
+    {
+      "epoch": 0.11618257261410789,
+      "grad_norm": 367.9336242675781,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 17.764,
+      "step": 28
+    },
+    {
+      "epoch": 0.12033195020746888,
+      "grad_norm": 384.99786376953125,
+      "learning_rate": 5.392295478639225e-05,
+      "loss": 17.9249,
+      "step": 29
+    },
+    {
+      "epoch": 0.12448132780082988,
+      "grad_norm": 371.46588134765625,
+      "learning_rate": 5e-05,
+      "loss": 17.159,
+      "step": 30
+    },
+    {
+      "epoch": 0.12448132780082988,
+      "eval_loss": 9.035653114318848,
+      "eval_runtime": 0.9953,
+      "eval_samples_per_second": 203.95,
+      "eval_steps_per_second": 26.122,
+      "step": 30
+    },
+    {
+      "epoch": 0.12863070539419086,
+      "grad_norm": 358.5752868652344,
+      "learning_rate": 4.607704521360776e-05,
+      "loss": 17.0919,
+      "step": 31
+    },
+    {
+      "epoch": 0.13278008298755187,
+      "grad_norm": 370.85333251953125,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 17.5422,
+      "step": 32
+    },
+    {
+      "epoch": 0.13692946058091288,
+      "grad_norm": 346.4546813964844,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 17.4615,
+      "step": 33
+    },
+    {
+      "epoch": 0.14107883817427386,
+      "grad_norm": 365.4295959472656,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 17.6874,
+      "step": 34
+    },
+    {
+      "epoch": 0.14522821576763487,
+      "grad_norm": 308.52362060546875,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 17.1988,
+      "step": 35
+    },
+    {
+      "epoch": 0.14522821576763487,
+      "eval_loss": 9.000443458557129,
+      "eval_runtime": 0.9787,
+      "eval_samples_per_second": 207.409,
+      "eval_steps_per_second": 26.565,
+      "step": 35
+    },
+    {
+      "epoch": 0.14937759336099585,
+      "grad_norm": 384.09722900390625,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 17.3598,
+      "step": 36
+    },
+    {
+      "epoch": 0.15352697095435686,
+      "grad_norm": 401.5643310546875,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 16.8225,
+      "step": 37
+    },
+    {
+      "epoch": 0.15767634854771784,
+      "grad_norm": 367.50152587890625,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 19.3024,
+      "step": 38
+    },
+    {
+      "epoch": 0.16182572614107885,
+      "grad_norm": 454.1186218261719,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 19.1394,
+      "step": 39
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "grad_norm": 510.416015625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 17.7996,
+      "step": 40
+    },
+    {
+      "epoch": 0.16597510373443983,
+      "eval_loss": 8.98484992980957,
+      "eval_runtime": 0.9687,
+      "eval_samples_per_second": 209.557,
+      "eval_steps_per_second": 26.84,
+      "step": 40
+    },
+    {
+      "epoch": 0.17012448132780084,
+      "grad_norm": 440.44830322265625,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 19.084,
+      "step": 41
+    },
+    {
+      "epoch": 0.17427385892116182,
+      "grad_norm": 377.33685302734375,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 16.044,
+      "step": 42
+    },
+    {
+      "epoch": 0.17842323651452283,
+      "grad_norm": 399.070556640625,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 18.5397,
+      "step": 43
+    },
+    {
+      "epoch": 0.1825726141078838,
+      "grad_norm": 389.1490478515625,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 16.4042,
+      "step": 44
+    },
+    {
+      "epoch": 0.18672199170124482,
+      "grad_norm": 483.7464904785156,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 19.0675,
+      "step": 45
+    },
+    {
+      "epoch": 0.18672199170124482,
+      "eval_loss": 8.964590072631836,
+      "eval_runtime": 0.9679,
+      "eval_samples_per_second": 209.736,
+      "eval_steps_per_second": 26.863,
+      "step": 45
+    },
+    {
+      "epoch": 0.1908713692946058,
+      "grad_norm": 331.3105773925781,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 16.7486,
+      "step": 46
+    },
+    {
+      "epoch": 0.1950207468879668,
+      "grad_norm": 455.8272705078125,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 18.3657,
+      "step": 47
+    },
+    {
+      "epoch": 0.1991701244813278,
+      "grad_norm": 365.6001281738281,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 17.0653,
+      "step": 48
+    },
+    {
+      "epoch": 0.2033195020746888,
+      "grad_norm": 483.4586181640625,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 17.313,
+      "step": 49
+    },
+    {
+      "epoch": 0.2074688796680498,
+      "grad_norm": 367.5295104980469,
+      "learning_rate": 0.0,
+      "loss": 17.9008,
+      "step": 50
+    },
+    {
+      "epoch": 0.2074688796680498,
+      "eval_loss": 8.979755401611328,
+      "eval_runtime": 0.9676,
+      "eval_samples_per_second": 209.789,
+      "eval_steps_per_second": 26.869,
+      "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": 111716125900800.0,
+  "total_flos": 223432251801600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null