Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3967a97ecf48f5306f1971cdcc4d264928b795b5c566f91076f83a963799082e
+oid sha256:8cc46af9fb9e5b0fc254a3faaeb87776f7c0ac981a6864af527fc9c9a231d8ff
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4cc91c3ab3e08caf9f532777b29917289de22229d8b4409be896e8e677e7227
+oid sha256:feddd1c78cbb48bc26a58875c5cf0b38d430aa2acfdc786268e603e1bd38a01e
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005051608986035215,
+  "epoch": 0.0064764217769682254,
   "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": 64.143,
       "eval_steps_per_second": 32.074,
       "step": 39
+    },
+    {
+      "epoch": 0.00518113742157458,
+      "grad_norm": 0.6653187274932861,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2066,
+      "step": 40
+    },
+    {
+      "epoch": 0.005310665857113945,
+      "grad_norm": 0.8174309134483337,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.249,
+      "step": 41
+    },
+    {
+      "epoch": 0.005440194292653309,
+      "grad_norm": 0.7076389789581299,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2075,
+      "step": 42
+    },
+    {
+      "epoch": 0.005569722728192674,
+      "grad_norm": 0.7139219045639038,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.281,
+      "step": 43
+    },
+    {
+      "epoch": 0.005699251163732038,
+      "grad_norm": 0.7278518080711365,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.4184,
+      "step": 44
+    },
+    {
+      "epoch": 0.0058287795992714025,
+      "grad_norm": 0.6572630405426025,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3265,
+      "step": 45
+    },
+    {
+      "epoch": 0.005958308034810767,
+      "grad_norm": 0.8583543300628662,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.3386,
+      "step": 46
+    },
+    {
+      "epoch": 0.006087836470350131,
+      "grad_norm": 0.6952458024024963,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.2859,
+      "step": 47
+    },
+    {
+      "epoch": 0.006217364905889496,
+      "grad_norm": 0.8060092926025391,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.3897,
+      "step": 48
+    },
+    {
+      "epoch": 0.00634689334142886,
+      "grad_norm": 0.8087725043296814,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.2154,
+      "step": 49
+    },
+    {
+      "epoch": 0.0064764217769682254,
+      "grad_norm": 0.8078595399856567,
+      "learning_rate": 0.0,
+      "loss": 0.2911,
+      "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": 1.0114468513579008e+16,
+  "total_flos": 1.28149940994048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null