Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48488aa8be640fd61cfe535f77c3431a5d526046e72ff4ff26d925e924a341b5
+oid sha256:12122c0cda03955309f86362155bfcfe0d91bc26d61ebef9424e9bc1d0f53e4c
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ba2f96298e02f6c1dc2f3c07106e76323a8ccda782cbeb726696941ce43f8e
+oid sha256:d7eb756ef6774db85ffe95f38d7750cc2ce7151ed756ec5991a73b4bdd8ca845
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8cc330a79fd720d64a2e46161cee2bfc8976c23b0235a144073fb971c9bb68c
+oid sha256:05ee794078b448e63ebc124b5d91002b1daad89eeb6d4698f45f8080ac3390a3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.019306930693069307,
+  "epoch": 0.024752475247524754,
   "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": 63.654,
       "eval_steps_per_second": 31.864,
       "step": 39
+    },
+    {
+      "epoch": 0.019801980198019802,
+      "grad_norm": 0.5925613641738892,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 2.348,
+      "step": 40
+    },
+    {
+      "epoch": 0.020297029702970298,
+      "grad_norm": 0.6979615092277527,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 2.5928,
+      "step": 41
+    },
+    {
+      "epoch": 0.020792079207920793,
+      "grad_norm": 0.5888616442680359,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 2.5446,
+      "step": 42
+    },
+    {
+      "epoch": 0.02128712871287129,
+      "grad_norm": 0.5887708067893982,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 2.5574,
+      "step": 43
+    },
+    {
+      "epoch": 0.02178217821782178,
+      "grad_norm": 0.5959057211875916,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 2.3598,
+      "step": 44
+    },
+    {
+      "epoch": 0.022277227722772276,
+      "grad_norm": 0.47111913561820984,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 2.4035,
+      "step": 45
+    },
+    {
+      "epoch": 0.02277227722772277,
+      "grad_norm": 0.5968517065048218,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 2.5494,
+      "step": 46
+    },
+    {
+      "epoch": 0.023267326732673267,
+      "grad_norm": 0.7809783220291138,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 2.6556,
+      "step": 47
+    },
+    {
+      "epoch": 0.023762376237623763,
+      "grad_norm": 0.6950249075889587,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 2.508,
+      "step": 48
+    },
+    {
+      "epoch": 0.024257425742574258,
+      "grad_norm": 0.5339661240577698,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 2.4161,
+      "step": 49
+    },
+    {
+      "epoch": 0.024752475247524754,
+      "grad_norm": 0.7153289318084717,
+      "learning_rate": 0.0,
+      "loss": 2.5135,
+      "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": 1227801495601152.0,
+  "total_flos": 1624279061889024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null