Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da12c466f84c24dff56fbf8dc79868fbc3b3b449ce897493c09f29392c708add
+oid sha256:fa958ec9e1d821be8d46b88154f4988a404ca7bfe77d36532c16e224d0426d6f
 size 2269195160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:926b3a840ac04e94a9c2f845e240d3f199a8eebeb2b05d975ed1ce65114c13fe
+oid sha256:1bab4deade7f128d6df0aa163363f6be4b378e8534f24a3f4f7bb108a8bd2936
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7aa7bd6e7162b5cef71bb965bb9ca48a011a5eed5848e6b7c207b50a0c6a7f
+oid sha256:47ff6785a77b980071a1673d72897467a8d47d077d883249f712b506ffc9caab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4dd76e4cfbed647f5393d42b2fd1c0eead588dbf173cae704b7e26883a38f902
+oid sha256:badf8dd7fd843c03f3dfa379f5a62cbdac918ff18b84343f94ed7c04cd128a3f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.380952380952381,
+  "epoch": 3.0,
   "eval_steps": 6,
-  "global_step": 50,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -429,6 +429,113 @@
       "learning_rate": 1.4124637147783432e-05,
       "loss": 0.0001,
       "step": 50
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 0.0027039337437599897,
+      "learning_rate": 1.2124437891918993e-05,
+      "loss": 0.0001,
+      "step": 51
+    },
+    {
+      "epoch": 2.4761904761904763,
+      "grad_norm": 0.002979928394779563,
+      "learning_rate": 1.0257277929332332e-05,
+      "loss": 0.0001,
+      "step": 52
+    },
+    {
+      "epoch": 2.5238095238095237,
+      "grad_norm": 0.002763009862974286,
+      "learning_rate": 8.529715727489912e-06,
+      "loss": 0.0001,
+      "step": 53
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": 0.0026082261465489864,
+      "learning_rate": 6.947819411632223e-06,
+      "loss": 0.0001,
+      "step": 54
+    },
+    {
+      "epoch": 2.571428571428571,
+      "eval_loss": 0.00020980079716537148,
+      "eval_runtime": 2.2421,
+      "eval_samples_per_second": 8.028,
+      "eval_steps_per_second": 1.338,
+      "step": 54
+    },
+    {
+      "epoch": 2.619047619047619,
+      "grad_norm": 0.0024540037848055363,
+      "learning_rate": 5.51714545026264e-06,
+      "loss": 0.0001,
+      "step": 55
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.002579254098236561,
+      "learning_rate": 4.242719137849077e-06,
+      "loss": 0.0001,
+      "step": 56
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 0.0024759070947766304,
+      "learning_rate": 3.1290169432939553e-06,
+      "loss": 0.0001,
+      "step": 57
+    },
+    {
+      "epoch": 2.761904761904762,
+      "grad_norm": 0.002558476058766246,
+      "learning_rate": 2.179950786173879e-06,
+      "loss": 0.0001,
+      "step": 58
+    },
+    {
+      "epoch": 2.8095238095238093,
+      "grad_norm": 0.0033246162347495556,
+      "learning_rate": 1.3988542959794627e-06,
+      "loss": 0.0001,
+      "step": 59
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 0.002528395503759384,
+      "learning_rate": 7.884711026201585e-07,
+      "loss": 0.0001,
+      "step": 60
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 0.0002239210152765736,
+      "eval_runtime": 2.2503,
+      "eval_samples_per_second": 7.999,
+      "eval_steps_per_second": 1.333,
+      "step": 60
+    },
+    {
+      "epoch": 2.9047619047619047,
+      "grad_norm": 0.00311569613404572,
+      "learning_rate": 3.5094519932415417e-07,
+      "loss": 0.0001,
+      "step": 61
+    },
+    {
+      "epoch": 2.9523809523809526,
+      "grad_norm": 0.0025822578463703394,
+      "learning_rate": 8.781341178393244e-08,
+      "loss": 0.0001,
+      "step": 62
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.02102760784327984,
+      "learning_rate": 0.0,
+      "loss": 0.0002,
+      "step": 63
     }
   ],
   "logging_steps": 1,
@@ -443,12 +550,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.228759811417702e+16,
+  "total_flos": 5.304496956427469e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null