Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3afe094312eeb4c7225b67c401543736933c8191065ba5d63e4565e46eea8f6a
+oid sha256:305e6b729688113a1845136b78a6b44148b8f8f3b023be9eba1dc6966ba552b3
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdd2313c26dd20f9478df51aeeec45dccd223711f582af76bddd0e2dfbf885be
+oid sha256:5d0ffd4dd0d4f9fbe85f2c97fdbead87494916cd3187ff5f6a6401a2aecc1f35
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3b808d66a408d8b2275d277677330b11cd9cd31bf039a5e8d6d9734d25702d
+oid sha256:364793649d2c240c9e889329bf62f9ba482938fd5dc7c4f07592f0b3309f5227
 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": 0.024115010047920854,
+  "epoch": 0.030916679548616478,
   "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": 18.574,
       "eval_steps_per_second": 9.301,
       "step": 39
+    },
+    {
+      "epoch": 0.024733343638893183,
+      "grad_norm": 2.634270668029785,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 6.2318,
+      "step": 40
+    },
+    {
+      "epoch": 0.02535167722986551,
+      "grad_norm": 3.3636908531188965,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 7.7077,
+      "step": 41
+    },
+    {
+      "epoch": 0.02597001082083784,
+      "grad_norm": 2.037014961242676,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 6.2751,
+      "step": 42
+    },
+    {
+      "epoch": 0.026588344411810173,
+      "grad_norm": 3.388461112976074,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 7.6244,
+      "step": 43
+    },
+    {
+      "epoch": 0.0272066780027825,
+      "grad_norm": 1.931207299232483,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 5.9563,
+      "step": 44
+    },
+    {
+      "epoch": 0.02782501159375483,
+      "grad_norm": 3.204418182373047,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 7.8852,
+      "step": 45
+    },
+    {
+      "epoch": 0.02844334518472716,
+      "grad_norm": 3.5687596797943115,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 6.9575,
+      "step": 46
+    },
+    {
+      "epoch": 0.02906167877569949,
+      "grad_norm": 3.0171327590942383,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 7.6163,
+      "step": 47
+    },
+    {
+      "epoch": 0.02968001236667182,
+      "grad_norm": 1.911759614944458,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 6.467,
+      "step": 48
+    },
+    {
+      "epoch": 0.03029834595764415,
+      "grad_norm": 2.2276806831359863,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 6.9883,
+      "step": 49
+    },
+    {
+      "epoch": 0.030916679548616478,
+      "grad_norm": 2.965574264526367,
+      "learning_rate": 0.0,
+      "loss": 6.6589,
+      "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": 1.26648972214272e+16,
+  "total_flos": 1.614774395731968e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null