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:a9ab19a8a8f8fa395c8a765767034493cd40b33b06b69f316a5bc79f2fb8a137
+oid sha256:6f457b42d2924311d6385e3d082277d66bf56a13ea1aed2b2c66839023d5b13b
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b3b4462eee314e4809a24235151a982dab5d604d062fa3e99d0e2c7a7446c2
+oid sha256:a77d569f3fabbf97a85eceb12a6f12b034329b77daf77c165c240e8e876d1628
 size 60837186

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fc69ab1dcca216771161e0b91f7d26d9c90fd7c25977be460383903db704a06
+oid sha256:8a1658d632652adcbe63cac75e96f1db776eefb7599c6fef183ad994d5bd66c3
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:975fb42b56b65e8821d845db3ce30cfc648ea90ad5ce64077e43a4d086f034fc
+oid sha256:4406e8ac0eff4b9d2b3ffcfdafd38a3be4e1f654b02ae8e38b4876194d266d40
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d61d85a65f01744d9a673e2b200c99e2454febba890b00c501a234f6e9909e25
+oid sha256:badf8dd7fd843c03f3dfa379f5a62cbdac918ff18b84343f94ed7c04cd128a3f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.758893280632411,
+  "epoch": 0.9960474308300395,
   "eval_steps": 16,
-  "global_step": 48,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -375,6 +375,111 @@
       "eval_samples_per_second": 13.211,
       "eval_steps_per_second": 3.334,
       "step": 48
+    },
+    {
+      "epoch": 0.7747035573122529,
+      "grad_norm": 0.8376194834709167,
+      "learning_rate": 9.8e-05,
+      "loss": 0.1525,
+      "step": 49
+    },
+    {
+      "epoch": 0.7905138339920948,
+      "grad_norm": 0.18561908602714539,
+      "learning_rate": 0.0001,
+      "loss": 0.0172,
+      "step": 50
+    },
+    {
+      "epoch": 0.8063241106719368,
+      "grad_norm": 0.31320735812187195,
+      "learning_rate": 9.85470908713026e-05,
+      "loss": 0.0038,
+      "step": 51
+    },
+    {
+      "epoch": 0.8221343873517787,
+      "grad_norm": 0.4068452715873718,
+      "learning_rate": 9.42728012826605e-05,
+      "loss": 0.0178,
+      "step": 52
+    },
+    {
+      "epoch": 0.8379446640316206,
+      "grad_norm": 0.16684125363826752,
+      "learning_rate": 8.742553740855506e-05,
+      "loss": 0.0087,
+      "step": 53
+    },
+    {
+      "epoch": 0.8537549407114624,
+      "grad_norm": 0.05175252631306648,
+      "learning_rate": 7.840323733655778e-05,
+      "loss": 0.0011,
+      "step": 54
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.018029799684882164,
+      "learning_rate": 6.773024435212678e-05,
+      "loss": 0.0006,
+      "step": 55
+    },
+    {
+      "epoch": 0.8853754940711462,
+      "grad_norm": 0.03412799909710884,
+      "learning_rate": 5.602683401276615e-05,
+      "loss": 0.0009,
+      "step": 56
+    },
+    {
+      "epoch": 0.9011857707509882,
+      "grad_norm": 0.06215568631887436,
+      "learning_rate": 4.397316598723385e-05,
+      "loss": 0.0011,
+      "step": 57
+    },
+    {
+      "epoch": 0.9169960474308301,
+      "grad_norm": 0.05936681851744652,
+      "learning_rate": 3.226975564787322e-05,
+      "loss": 0.0011,
+      "step": 58
+    },
+    {
+      "epoch": 0.932806324110672,
+      "grad_norm": 0.045637015253305435,
+      "learning_rate": 2.1596762663442218e-05,
+      "loss": 0.0011,
+      "step": 59
+    },
+    {
+      "epoch": 0.9486166007905138,
+      "grad_norm": 0.03515447676181793,
+      "learning_rate": 1.257446259144494e-05,
+      "loss": 0.001,
+      "step": 60
+    },
+    {
+      "epoch": 0.9644268774703557,
+      "grad_norm": 0.04813205078244209,
+      "learning_rate": 5.727198717339511e-06,
+      "loss": 0.0011,
+      "step": 61
+    },
+    {
+      "epoch": 0.9802371541501976,
+      "grad_norm": 0.05862165987491608,
+      "learning_rate": 1.4529091286973995e-06,
+      "loss": 0.0012,
+      "step": 62
+    },
+    {
+      "epoch": 0.9960474308300395,
+      "grad_norm": 0.07167425751686096,
+      "learning_rate": 0.0,
+      "loss": 0.0096,
+      "step": 63
     }
   ],
   "logging_steps": 1,
@@ -389,12 +494,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7214050224111616.0,
+  "total_flos": 9264114014617600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null