Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53c4f154a40cd37ea266c1eb4d1bb93ef2914ee4b2f1b010658cbac1c69004c
+oid sha256:9ab981b8ec02673f636ffa7695fb4012d68c93daefde654c67e0527bc57ebdb0
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e04f772bad80b24cb8aa0203aa9b17a50050c059db2d6d9caa52b2bf5eb17e0
+oid sha256:d8409a494b3c0a2f7b196354833bfad6229ac6fbd5fdd3bde88e1eaf206439d1
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de4e50a6bbcf5bd9016d3fc9208330d6cf9fe6bdff9489249b7d4bfb6b1689f2
+oid sha256:814969120bf2c2d75e2132cd5402d69473d4eb31843a9c8344ec2b24f799dd9a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0045430797537650775,
+  "epoch": 0.006814619630647616,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 30.289,
       "eval_steps_per_second": 15.144,
       "step": 50
+    },
+    {
+      "epoch": 0.004633941348840379,
+      "grad_norm": 46.32371520996094,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.8385,
+      "step": 51
+    },
+    {
+      "epoch": 0.00472480294391568,
+      "grad_norm": 50.98200607299805,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 5.1699,
+      "step": 52
+    },
+    {
+      "epoch": 0.004815664538990982,
+      "grad_norm": 50.70225143432617,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 5.2527,
+      "step": 53
+    },
+    {
+      "epoch": 0.004906526134066284,
+      "grad_norm": 47.06248474121094,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.5287,
+      "step": 54
+    },
+    {
+      "epoch": 0.0049973877291415855,
+      "grad_norm": 43.91443634033203,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 4.1084,
+      "step": 55
+    },
+    {
+      "epoch": 0.005088249324216886,
+      "grad_norm": 43.865379333496094,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 4.248,
+      "step": 56
+    },
+    {
+      "epoch": 0.005179110919292188,
+      "grad_norm": 31.40968132019043,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.0994,
+      "step": 57
+    },
+    {
+      "epoch": 0.00526997251436749,
+      "grad_norm": 34.816925048828125,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 3.3691,
+      "step": 58
+    },
+    {
+      "epoch": 0.005360834109442791,
+      "grad_norm": 29.733379364013672,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.6941,
+      "step": 59
+    },
+    {
+      "epoch": 0.005451695704518093,
+      "grad_norm": 24.68531036376953,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9541,
+      "step": 60
+    },
+    {
+      "epoch": 0.005542557299593394,
+      "grad_norm": 23.424503326416016,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.9792,
+      "step": 61
+    },
+    {
+      "epoch": 0.005633418894668696,
+      "grad_norm": 32.10466766357422,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 2.261,
+      "step": 62
+    },
+    {
+      "epoch": 0.005724280489743997,
+      "grad_norm": 27.93880844116211,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3343,
+      "step": 63
+    },
+    {
+      "epoch": 0.005815142084819299,
+      "grad_norm": 23.051822662353516,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 1.5509,
+      "step": 64
+    },
+    {
+      "epoch": 0.005906003679894601,
+      "grad_norm": 25.748632431030273,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.6823,
+      "step": 65
+    },
+    {
+      "epoch": 0.005996865274969902,
+      "grad_norm": 27.34827423095703,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5725,
+      "step": 66
+    },
+    {
+      "epoch": 0.006087726870045203,
+      "grad_norm": 22.656187057495117,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.0763,
+      "step": 67
+    },
+    {
+      "epoch": 0.006178588465120505,
+      "grad_norm": 19.859046936035156,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.081,
+      "step": 68
+    },
+    {
+      "epoch": 0.006269450060195807,
+      "grad_norm": 20.085308074951172,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2761,
+      "step": 69
+    },
+    {
+      "epoch": 0.006360311655271109,
+      "grad_norm": 17.73591423034668,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.9149,
+      "step": 70
+    },
+    {
+      "epoch": 0.0064511732503464096,
+      "grad_norm": 21.190202713012695,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.4188,
+      "step": 71
+    },
+    {
+      "epoch": 0.006542034845421711,
+      "grad_norm": 20.775806427001953,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0984,
+      "step": 72
+    },
+    {
+      "epoch": 0.006632896440497013,
+      "grad_norm": 19.472455978393555,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.8902,
+      "step": 73
+    },
+    {
+      "epoch": 0.006723758035572315,
+      "grad_norm": 20.528032302856445,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.855,
+      "step": 74
+    },
+    {
+      "epoch": 0.006814619630647616,
+      "grad_norm": 18.677600860595703,
+      "learning_rate": 0.0,
+      "loss": 0.8934,
+      "step": 75
+    },
+    {
+      "epoch": 0.006814619630647616,
+      "eval_loss": 0.611670970916748,
+      "eval_runtime": 306.2641,
+      "eval_samples_per_second": 30.261,
+      "eval_steps_per_second": 15.131,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9788035851878400.0,
+  "total_flos": 1.46820537778176e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null