Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83269e3cfbde9090fa6028a91d869c8b8b2115aeed8d629808d49b4ec2e3d075
+oid sha256:9e5b12c08b31346eafdb2ac53d91a52fa33e4ba0560bf78c451c2d66f9abe4e4
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84ffaed945f47880c71315965c5e779876b9dfce3b467f9785a2a7c9c21fe43
+oid sha256:a21506433f5e00198927a1d587d434cd635cc4d4e63d03fac3d080b0e188aad7
 size 52046596

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0035219499bf80f14c3b5787ac1ac146c8de055bac8a418dfcfbff045301c7f4
+oid sha256:52f2bc10d113296ab4ca464f5bbfb74155ff72da2655558d6f4b4cf55625c5ff
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ca19d3b8edd633f8d3adf40710e317660e2d8852cc44439313915e692028228
+oid sha256:3600ff16e292e1b93a47cd88f5b14ebef0e4d673f53555918d404284973cd158
 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": 0.7298245614035088,
+  "epoch": 0.935672514619883,
   "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": 19.16,
       "eval_steps_per_second": 4.79,
       "step": 39
+    },
+    {
+      "epoch": 0.7485380116959064,
+      "grad_norm": 0.7017357349395752,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9648,
+      "step": 40
+    },
+    {
+      "epoch": 0.7672514619883041,
+      "grad_norm": 1.0196352005004883,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.9957,
+      "step": 41
+    },
+    {
+      "epoch": 0.7859649122807018,
+      "grad_norm": 0.8696815967559814,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0241,
+      "step": 42
+    },
+    {
+      "epoch": 0.8046783625730994,
+      "grad_norm": 0.6451800465583801,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0231,
+      "step": 43
+    },
+    {
+      "epoch": 0.8233918128654971,
+      "grad_norm": 0.6225769519805908,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0602,
+      "step": 44
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.7051582932472229,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.0722,
+      "step": 45
+    },
+    {
+      "epoch": 0.8608187134502924,
+      "grad_norm": 0.6919586658477783,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0155,
+      "step": 46
+    },
+    {
+      "epoch": 0.87953216374269,
+      "grad_norm": 0.7243795394897461,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0473,
+      "step": 47
+    },
+    {
+      "epoch": 0.8982456140350877,
+      "grad_norm": 0.6832768321037292,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9921,
+      "step": 48
+    },
+    {
+      "epoch": 0.9169590643274854,
+      "grad_norm": 0.7054731249809265,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9649,
+      "step": 49
+    },
+    {
+      "epoch": 0.935672514619883,
+      "grad_norm": 0.8198917508125305,
+      "learning_rate": 0.0,
+      "loss": 1.016,
+      "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": 4.109279678504632e+17,
+  "total_flos": 5.268307280134144e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null