Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5a1f2ec1d475492f3059cae40cf7c32deef804b6f63ca30ddf82f00951eee0
+oid sha256:55da4b14db819aec3c4f852f98167a07e268454bcb4554274f12ec31742ab2e7
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e35173d0693f827b87b5e8bd0262762b95a04dcc720fa42468f02bab086428bc
+oid sha256:02c577bf0d198f371547addcfe0ee253a3d06f315aadcbb544985b96bdd956eb
 size 864785974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5d43f3578de2b4189ff8d2c0d8ea51645e1b70e7605e6b5d481932800505c7f
+oid sha256:809632d7ea4838a46bb5283c3982f9040a416e1f2ff72461d8224d5a4d54ace3
 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": 0.011059500110595002,
+  "epoch": 0.0165892501658925,
   "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": 4.847,
       "eval_steps_per_second": 2.423,
       "step": 50
+    },
+    {
+      "epoch": 0.0112806901128069,
+      "grad_norm": 0.16115131974220276,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3509,
+      "step": 51
+    },
+    {
+      "epoch": 0.0115018801150188,
+      "grad_norm": 0.3114362359046936,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 0.3439,
+      "step": 52
+    },
+    {
+      "epoch": 0.011723070117230701,
+      "grad_norm": 0.48010456562042236,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 0.3154,
+      "step": 53
+    },
+    {
+      "epoch": 0.011944260119442602,
+      "grad_norm": 0.8629705905914307,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.286,
+      "step": 54
+    },
+    {
+      "epoch": 0.012165450121654502,
+      "grad_norm": 0.7464887499809265,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.301,
+      "step": 55
+    },
+    {
+      "epoch": 0.0123866401238664,
+      "grad_norm": 0.33294060826301575,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 0.3435,
+      "step": 56
+    },
+    {
+      "epoch": 0.012607830126078301,
+      "grad_norm": 0.3918580710887909,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3383,
+      "step": 57
+    },
+    {
+      "epoch": 0.012829020128290201,
+      "grad_norm": 0.5649017691612244,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 0.3182,
+      "step": 58
+    },
+    {
+      "epoch": 0.013050210130502102,
+      "grad_norm": 1.2315820455551147,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.38,
+      "step": 59
+    },
+    {
+      "epoch": 0.013271400132714002,
+      "grad_norm": 0.675856351852417,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.3344,
+      "step": 60
+    },
+    {
+      "epoch": 0.0134925901349259,
+      "grad_norm": 0.6763534545898438,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 0.3016,
+      "step": 61
+    },
+    {
+      "epoch": 0.013713780137137801,
+      "grad_norm": 1.2554537057876587,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 0.3732,
+      "step": 62
+    },
+    {
+      "epoch": 0.013934970139349702,
+      "grad_norm": 0.835084080696106,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.339,
+      "step": 63
+    },
+    {
+      "epoch": 0.014156160141561602,
+      "grad_norm": 1.4089100360870361,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 0.4019,
+      "step": 64
+    },
+    {
+      "epoch": 0.0143773501437735,
+      "grad_norm": 0.7557712197303772,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 0.3682,
+      "step": 65
+    },
+    {
+      "epoch": 0.014598540145985401,
+      "grad_norm": 0.7409688234329224,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3083,
+      "step": 66
+    },
+    {
+      "epoch": 0.014819730148197301,
+      "grad_norm": 0.4949645400047302,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.3501,
+      "step": 67
+    },
+    {
+      "epoch": 0.015040920150409202,
+      "grad_norm": 1.9559446573257446,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 0.4467,
+      "step": 68
+    },
+    {
+      "epoch": 0.015262110152621102,
+      "grad_norm": 0.5140382051467896,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3153,
+      "step": 69
+    },
+    {
+      "epoch": 0.015483300154833,
+      "grad_norm": 1.1127138137817383,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 0.3506,
+      "step": 70
+    },
+    {
+      "epoch": 0.015704490157044903,
+      "grad_norm": 1.229326605796814,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 0.2987,
+      "step": 71
+    },
+    {
+      "epoch": 0.015925680159256803,
+      "grad_norm": 0.7345213294029236,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.3419,
+      "step": 72
+    },
+    {
+      "epoch": 0.0161468701614687,
+      "grad_norm": 0.5045095086097717,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 0.3207,
+      "step": 73
+    },
+    {
+      "epoch": 0.0163680601636806,
+      "grad_norm": 1.0728390216827393,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 0.3256,
+      "step": 74
+    },
+    {
+      "epoch": 0.0165892501658925,
+      "grad_norm": 0.49065038561820984,
+      "learning_rate": 0.0,
+      "loss": 0.3341,
+      "step": 75
+    },
+    {
+      "epoch": 0.0165892501658925,
+      "eval_loss": 0.31507450342178345,
+      "eval_runtime": 785.8407,
+      "eval_samples_per_second": 4.846,
+      "eval_steps_per_second": 2.423,
+      "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": 8.2892273221632e+16,
+  "total_flos": 1.24338409832448e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null