Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:528b70aef25cb1547a0fb0e68249b8b62dceba159d3a8b3efb5dd523ead5f5b1
+oid sha256:d4bbbe7b7a78d162266932f355d6ee9b4e6510d7c795d94cf00fc8b8be5c2905
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c40d5b13524ad64dc993f097b0281cda84693625c758404c8e572635a126411
+oid sha256:0ed63354f292f2c4e30b3f6e73e0334840d9b321939e8c61d2acd98f77c3c486
 size 11710970

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea0ed9293538f53d752a83a3cda59c22b35cb0be6ab3badce493bda80f44cbc
+oid sha256:9becc56fe934ad5baadf355da32d010984487971eb75f8366fb85a2f8bc9e9af
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051edb58c1177b5e5e14c9e71436ef45ed45b57cbff0f64aeb1ef492f01d86a4
+oid sha256:0b1d31e272092386e33c556ad219d146833983425300318f6eeeb298c0b66e64
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a44c98272bd3b4f2ac204de34d3d9a19353fe7c4a9c52ed73896742ec484d67b
+oid sha256:d3a1468d1d2bf187a1b37c231abac3d3fc57280b3d435408225b7c49e30d06dd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:019f1715cee0a033ca1ce2fb562bb8a40ce585cfd132821a3c89beeca1eff7a0
+oid sha256:6ac67a7049dd5ba668f558efb19764d999a6df65139ff17a6e99881c5411332c
 size 15024

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": 0.7050847457627119,
+  "epoch": 0.903954802259887,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,36 @@
       "eval_samples_per_second": 508.472,
       "eval_steps_per_second": 16.039,
       "step": 30
+    },
+    {
+      "epoch": 0.7231638418079096,
+      "grad_norm": 0.3768801987171173,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0006,
+      "step": 40
+    },
+    {
+      "epoch": 0.7231638418079096,
+      "eval_loss": 0.968154788017273,
+      "eval_runtime": 2.9315,
+      "eval_samples_per_second": 508.273,
+      "eval_steps_per_second": 16.033,
+      "step": 40
+    },
+    {
+      "epoch": 0.903954802259887,
+      "grad_norm": 0.3605632781982422,
+      "learning_rate": 0.0,
+      "loss": 0.9658,
+      "step": 50
+    },
+    {
+      "epoch": 0.903954802259887,
+      "eval_loss": 0.957095742225647,
+      "eval_runtime": 2.9221,
+      "eval_samples_per_second": 509.911,
+      "eval_steps_per_second": 16.084,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +104,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.004016065334477e+16,
+  "total_flos": 7.69745649401856e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null