Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98c116497c639a9de5648dd967f9bdbfcd53cae459720765d1a99f66144d1b8a
+oid sha256:8de17e2a9b04a92b3378972ff75ebd696d1e628e357e0e19d6f00dac3692ac7c
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb09ce014015dcc958877e3661b4c964e712b40864475f62eca254bc96b5b97
+oid sha256:a420ae88699a030515e4b080447dd18ae6ac23c7c3a7dfef13e2399100a662d7
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46c784a60f4659800f3c4472f150d377d77a69d88547c6e5e024a7e54b3ef12b
+oid sha256:1ae59499d6fa89d93656a32994352236f76ecdb3c0d5d7d01bbf5e497aa8ee6c
 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": 0.00995787054768288,
+  "epoch": 0.012766500702157539,
   "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": 460.028,
       "eval_steps_per_second": 230.154,
       "step": 39
+    },
+    {
+      "epoch": 0.01021320056172603,
+      "grad_norm": 0.557560384273529,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 44.3699,
+      "step": 40
+    },
+    {
+      "epoch": 0.010468530575769183,
+      "grad_norm": 0.5665256381034851,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 44.332,
+      "step": 41
+    },
+    {
+      "epoch": 0.010723860589812333,
+      "grad_norm": 0.6492829322814941,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 44.3921,
+      "step": 42
+    },
+    {
+      "epoch": 0.010979190603855483,
+      "grad_norm": 0.6311169862747192,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 44.3605,
+      "step": 43
+    },
+    {
+      "epoch": 0.011234520617898635,
+      "grad_norm": 0.6976051330566406,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 44.3361,
+      "step": 44
+    },
+    {
+      "epoch": 0.011489850631941785,
+      "grad_norm": 0.6850491166114807,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 44.298,
+      "step": 45
+    },
+    {
+      "epoch": 0.011745180645984935,
+      "grad_norm": 0.6100870370864868,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 44.4147,
+      "step": 46
+    },
+    {
+      "epoch": 0.012000510660028087,
+      "grad_norm": 0.6181326508522034,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 44.3837,
+      "step": 47
+    },
+    {
+      "epoch": 0.012255840674071237,
+      "grad_norm": 0.7168639302253723,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 44.3703,
+      "step": 48
+    },
+    {
+      "epoch": 0.012511170688114389,
+      "grad_norm": 0.7842406630516052,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 44.3164,
+      "step": 49
+    },
+    {
+      "epoch": 0.012766500702157539,
+      "grad_norm": 0.5945537686347961,
+      "learning_rate": 0.0,
+      "loss": 44.3395,
+      "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": 29137305600.0,
+  "total_flos": 37355520000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null