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:e336a19695e7c95ab4d444c76b90384ca1d7030d3a13c1af1caf49bf5a3f4266
+oid sha256:fa60dc34d5b92ccf8639758480744f7ad23addf0f6985307c6bd5563509e042a
 size 692136856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c248e74721ed477079bc3ea5c85edd96348c0e6b244ae126bd515f6ce0001ae0
+oid sha256:b055914cc0ef288d2b82e3b196099da56bfcd9d744fb056a7943ff663ed03c7a
 size 85723284

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a72025a75dfde9f6316cf7e78853946a2bfc45ed559fba6d15f16c4440f7ee5
+oid sha256:3ac9e56eb478bb7f690364dd51912aceda670c4f7d68fb18770d429dcec15f3a
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99ef6f22d42e935fbf13f0628837cd5d2513a098109335b9474dbc5e57db0c7d
+oid sha256:b99c176154c32f3c6148d434b4181fc39da3594f48ce393bb9e59b1fd24bca4d
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75c3c8ae7ddabeca3cb69703f6b35f00b9125a4c27b56ccba4ed0e4669bb5433
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.636085626911315,
+  "epoch": 0.8154943934760448,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 10.866,
       "eval_steps_per_second": 2.736,
       "step": 39
+    },
+    {
+      "epoch": 0.6523955147808359,
+      "grad_norm": 0.4775455594062805,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.7349,
+      "step": 40
+    },
+    {
+      "epoch": 0.6687054026503568,
+      "grad_norm": 0.38767868280410767,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7301,
+      "step": 41
+    },
+    {
+      "epoch": 0.6850152905198776,
+      "grad_norm": 0.41658639907836914,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.746,
+      "step": 42
+    },
+    {
+      "epoch": 0.7013251783893986,
+      "grad_norm": 0.4417034685611725,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6826,
+      "step": 43
+    },
+    {
+      "epoch": 0.7176350662589195,
+      "grad_norm": 0.4221656322479248,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7321,
+      "step": 44
+    },
+    {
+      "epoch": 0.7339449541284404,
+      "grad_norm": 0.46607765555381775,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7588,
+      "step": 45
+    },
+    {
+      "epoch": 0.7502548419979612,
+      "grad_norm": 0.4196472465991974,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7583,
+      "step": 46
+    },
+    {
+      "epoch": 0.7665647298674821,
+      "grad_norm": 0.4299370050430298,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7796,
+      "step": 47
+    },
+    {
+      "epoch": 0.7828746177370031,
+      "grad_norm": 0.4492173492908478,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7992,
+      "step": 48
+    },
+    {
+      "epoch": 0.799184505606524,
+      "grad_norm": 0.47522222995758057,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7723,
+      "step": 49
+    },
+    {
+      "epoch": 0.8154943934760448,
+      "grad_norm": 0.3986295461654663,
+      "learning_rate": 0.0,
+      "loss": 0.7772,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.77506116865491e+17,
+  "total_flos": 1.1250078421352448e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null