Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91c4efd86d4f806c6bd015bc91268c34751c8ea13e3481b867ccdc373235cf51
+oid sha256:96b5bb601b96c54f639dae1f12925a5fbeabf94f0a4b478d684aa6c61e50131e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0cf038d141305206d5d9c29e6517433b96721e964a4d8c495f4b8b8c9fb8a31
+oid sha256:4b741099a68a3f5325825dbae4452e30bb6fa2e6833ca3e4e231ac7d07fb3932
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd0e9045183916a77f191421cff82618df77003ceaa3909e936c6fdd5d3e7edd
+oid sha256:1986b6a448dc2a78046d7f7e86b6f18c94a4b92940813ffe1227215cc7b7f048
 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": 0.022553129969640016,
+  "epoch": 0.028914269191846177,
   "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": 29.52,
       "eval_steps_per_second": 14.78,
       "step": 39
+    },
+    {
+      "epoch": 0.02313141535347694,
+      "grad_norm": 0.6595151424407959,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.6198,
+      "step": 40
+    },
+    {
+      "epoch": 0.023709700737313863,
+      "grad_norm": 0.7210184931755066,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.607,
+      "step": 41
+    },
+    {
+      "epoch": 0.02428798612115079,
+      "grad_norm": 0.7432602643966675,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.6241,
+      "step": 42
+    },
+    {
+      "epoch": 0.02486627150498771,
+      "grad_norm": 0.7371325492858887,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.639,
+      "step": 43
+    },
+    {
+      "epoch": 0.025444556888824636,
+      "grad_norm": 0.690451979637146,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.6563,
+      "step": 44
+    },
+    {
+      "epoch": 0.026022842272661557,
+      "grad_norm": 0.6509324312210083,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.5702,
+      "step": 45
+    },
+    {
+      "epoch": 0.026601127656498483,
+      "grad_norm": 0.6391157507896423,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.6043,
+      "step": 46
+    },
+    {
+      "epoch": 0.027179413040335405,
+      "grad_norm": 0.7080129384994507,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.6471,
+      "step": 47
+    },
+    {
+      "epoch": 0.02775769842417233,
+      "grad_norm": 0.6260955333709717,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.6057,
+      "step": 48
+    },
+    {
+      "epoch": 0.028335983808009252,
+      "grad_norm": 0.7455611824989319,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.649,
+      "step": 49
+    },
+    {
+      "epoch": 0.028914269191846177,
+      "grad_norm": 0.7520791292190552,
+      "learning_rate": 0.0,
+      "loss": 0.6281,
+      "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": 7536974311194624.0,
+  "total_flos": 9617734090358784.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null