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:c158013999a0e7d4ba52ad22e28bf36f549f33c2f05866da198b3f4e70231d01
+oid sha256:38e61e772a5079658cc19d5c86162f6d47042dcfc35bd86acdbb3227fa1c4f49
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518af2edfed8f5eeaca73f2afa0ee80745cffc281c7562db218e9ea84fd00f10
+oid sha256:c8e57290ec0506e4cb0c1a39c2d8013d9b1b95d3d7993a081cac1b0b2853115f
 size 180543866

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb5345a289d4a53f402f15e634a8c996066a0cc15acecb088281e8a0d6bebe14
+oid sha256:8e2dcede9587ab22755030ae96055d45c6f43eb0935e95330000f0d3cb8472a8
 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": 0.05737234652897304,
+  "epoch": 0.08605851979345955,
   "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": 13.414,
       "eval_steps_per_second": 6.707,
       "step": 50
+    },
+    {
+      "epoch": 0.058519793459552494,
+      "grad_norm": 0.1377524882555008,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0194,
+      "step": 51
+    },
+    {
+      "epoch": 0.05966724039013196,
+      "grad_norm": 0.18886782228946686,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.0154,
+      "step": 52
+    },
+    {
+      "epoch": 0.060814687320711415,
+      "grad_norm": 0.37080180644989014,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.017,
+      "step": 53
+    },
+    {
+      "epoch": 0.06196213425129088,
+      "grad_norm": 0.19527259469032288,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0126,
+      "step": 54
+    },
+    {
+      "epoch": 0.06310958118187034,
+      "grad_norm": 0.18304114043712616,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0188,
+      "step": 55
+    },
+    {
+      "epoch": 0.0642570281124498,
+      "grad_norm": 0.16556933522224426,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.0117,
+      "step": 56
+    },
+    {
+      "epoch": 0.06540447504302926,
+      "grad_norm": 0.14504587650299072,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.016,
+      "step": 57
+    },
+    {
+      "epoch": 0.06655192197360872,
+      "grad_norm": 0.13935603201389313,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.0116,
+      "step": 58
+    },
+    {
+      "epoch": 0.06769936890418818,
+      "grad_norm": 0.18318995833396912,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.021,
+      "step": 59
+    },
+    {
+      "epoch": 0.06884681583476764,
+      "grad_norm": 0.17003515362739563,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.018,
+      "step": 60
+    },
+    {
+      "epoch": 0.0699942627653471,
+      "grad_norm": 0.16662214696407318,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.0149,
+      "step": 61
+    },
+    {
+      "epoch": 0.07114170969592656,
+      "grad_norm": 0.2166244387626648,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.0115,
+      "step": 62
+    },
+    {
+      "epoch": 0.07228915662650602,
+      "grad_norm": 0.2247883826494217,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0275,
+      "step": 63
+    },
+    {
+      "epoch": 0.07343660355708548,
+      "grad_norm": 0.19006967544555664,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.0186,
+      "step": 64
+    },
+    {
+      "epoch": 0.07458405048766495,
+      "grad_norm": 0.18058659136295319,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.0156,
+      "step": 65
+    },
+    {
+      "epoch": 0.0757314974182444,
+      "grad_norm": 0.24158023297786713,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.02,
+      "step": 66
+    },
+    {
+      "epoch": 0.07687894434882386,
+      "grad_norm": 0.25969210267066956,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0192,
+      "step": 67
+    },
+    {
+      "epoch": 0.07802639127940333,
+      "grad_norm": 0.254467248916626,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.0215,
+      "step": 68
+    },
+    {
+      "epoch": 0.07917383820998279,
+      "grad_norm": 0.1745733618736267,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0125,
+      "step": 69
+    },
+    {
+      "epoch": 0.08032128514056225,
+      "grad_norm": 0.2833689749240875,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.0258,
+      "step": 70
+    },
+    {
+      "epoch": 0.0814687320711417,
+      "grad_norm": 0.17747850716114044,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.0168,
+      "step": 71
+    },
+    {
+      "epoch": 0.08261617900172118,
+      "grad_norm": 0.2795718312263489,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0238,
+      "step": 72
+    },
+    {
+      "epoch": 0.08376362593230063,
+      "grad_norm": 0.3440586030483246,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.0383,
+      "step": 73
+    },
+    {
+      "epoch": 0.08491107286288009,
+      "grad_norm": 0.2360229790210724,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.0118,
+      "step": 74
+    },
+    {
+      "epoch": 0.08605851979345955,
+      "grad_norm": 0.244166761636734,
+      "learning_rate": 0.0,
+      "loss": 0.0241,
+      "step": 75
+    },
+    {
+      "epoch": 0.08605851979345955,
+      "eval_loss": 0.0341278538107872,
+      "eval_runtime": 54.5534,
+      "eval_samples_per_second": 13.455,
+      "eval_steps_per_second": 6.727,
+      "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": 1.0473198361509888e+16,
+  "total_flos": 1.6101318976339968e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null