Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40494549b4406533c299da8e3ab999981b74e5a0bd30c23b2f04d314fe13e73b
+oid sha256:809e9092db4f1c09facb0f1ce78d4c853033d8c1b4363fc7236b78a3f358df85
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f6d0ca3794e9368c336148eabf7afb8822908d6bc23f9eba14aea311c4ce121
+oid sha256:275b86251977b823f76ef5e0c70dfa6a4d052bfd87304c3fab997eaddf54f14c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dc7e1a295df9114854a507bc86161f7e5b05bc4a28d6ca3047f1dd8fbca7a6e
+oid sha256:5f2a0634ca0c9be90c791e750b9fb44ba83e922443eb5fe12dc48617ed81a35b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de473c64a67af75120ec0d8a1c740afb01d291e49d2f33af7e7c4ee244fb7a79
+oid sha256:732485ee871d159c7c8b1a73f7979c2f28994a3ab26ac04e6faaf6ea7863522f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8acbfea744d5ea54c135b6a4eef1e1d01ebb338447cb93af37c7c135a7d57b76
+oid sha256:6233d4c170e82496735f38a91af1c058d63c603258ad68b658ac5782bdeb7495
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e29fb16948f9473df9b05bc121381462a35ca15693f4bb3a074782ba0dafd8f
+oid sha256:2f74599e26624afabeffe36119572c465f99b8dab038fd9f2db35a3f3f617692
 size 15024

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": 0.22573363431151242,
+  "epoch": 0.33860045146726864,
   "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": 890.713,
       "eval_steps_per_second": 112.084,
       "step": 50
+    },
+    {
+      "epoch": 0.23024830699774265,
+      "grad_norm": 0.3788678050041199,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3373,
+      "step": 51
+    },
+    {
+      "epoch": 0.23476297968397292,
+      "grad_norm": 0.5251423120498657,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 10.3287,
+      "step": 52
+    },
+    {
+      "epoch": 0.23927765237020315,
+      "grad_norm": 0.47069135308265686,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 10.3243,
+      "step": 53
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 0.5533862113952637,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3245,
+      "step": 54
+    },
+    {
+      "epoch": 0.24830699774266365,
+      "grad_norm": 0.49693864583969116,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 10.3315,
+      "step": 55
+    },
+    {
+      "epoch": 0.2528216704288939,
+      "grad_norm": 0.4767528176307678,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 10.3282,
+      "step": 56
+    },
+    {
+      "epoch": 0.25733634311512416,
+      "grad_norm": 0.5245794057846069,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3109,
+      "step": 57
+    },
+    {
+      "epoch": 0.2618510158013544,
+      "grad_norm": 0.528092622756958,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 10.3253,
+      "step": 58
+    },
+    {
+      "epoch": 0.26636568848758463,
+      "grad_norm": 0.48516395688056946,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 10.3179,
+      "step": 59
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 0.5142610669136047,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3337,
+      "step": 60
+    },
+    {
+      "epoch": 0.27539503386004516,
+      "grad_norm": 0.46665993332862854,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 10.3302,
+      "step": 61
+    },
+    {
+      "epoch": 0.2799097065462754,
+      "grad_norm": 0.4745612144470215,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 10.3278,
+      "step": 62
+    },
+    {
+      "epoch": 0.28442437923250563,
+      "grad_norm": 0.47112610936164856,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3299,
+      "step": 63
+    },
+    {
+      "epoch": 0.28893905191873587,
+      "grad_norm": 0.4482511281967163,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 10.3211,
+      "step": 64
+    },
+    {
+      "epoch": 0.29345372460496616,
+      "grad_norm": 0.41518616676330566,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 10.3289,
+      "step": 65
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 0.5024863481521606,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3281,
+      "step": 66
+    },
+    {
+      "epoch": 0.30248306997742663,
+      "grad_norm": 0.48448967933654785,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 10.3213,
+      "step": 67
+    },
+    {
+      "epoch": 0.30699774266365687,
+      "grad_norm": 0.5250627994537354,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 10.3258,
+      "step": 68
+    },
+    {
+      "epoch": 0.3115124153498871,
+      "grad_norm": 0.5482112765312195,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3122,
+      "step": 69
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 0.5217831134796143,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 10.3159,
+      "step": 70
+    },
+    {
+      "epoch": 0.32054176072234764,
+      "grad_norm": 0.4971349537372589,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 10.3243,
+      "step": 71
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 0.5446459054946899,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3197,
+      "step": 72
+    },
+    {
+      "epoch": 0.3295711060948081,
+      "grad_norm": 0.4364243149757385,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 10.3398,
+      "step": 73
+    },
+    {
+      "epoch": 0.3340857787810384,
+      "grad_norm": 0.38337594270706177,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 10.3286,
+      "step": 74
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "grad_norm": 0.5091402530670166,
+      "learning_rate": 0.0,
+      "loss": 10.3228,
+      "step": 75
+    },
+    {
+      "epoch": 0.33860045146726864,
+      "eval_loss": 10.315568923950195,
+      "eval_runtime": 0.831,
+      "eval_samples_per_second": 898.891,
+      "eval_steps_per_second": 113.114,
+      "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": 21384029798400.0,
+  "total_flos": 32076044697600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null