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:a2df9f00f1d2b5188f28ea52109388be88cb2006abddaec7fc4ee96f058c90d6
+oid sha256:e9b28f01e8a863596d1377fe8d092e967c2f95740b1301a640ca5fe11d886296
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8a6b39b1bb56b32cc3a7f1ef6301a6d2ed378bafc40b067f87920ead7a38dea
+oid sha256:820a39cf65aa06a533fcf8b121d178449cd3509b4280f1aea7af6f0792d137c7
 size 332574358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6f8262103edafde9ab6b4b93b7d766a8600aa7afd7e6b1793d6bb3b7f9d9c6
+oid sha256:b5118a007b087f3510b00d71807e637a17b7d3e8b356e488f0f602cf1a5046dd
 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": 0.01886080724254998,
+  "epoch": 0.02829121086382497,
   "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": 8.933,
       "eval_steps_per_second": 4.468,
       "step": 50
+    },
+    {
+      "epoch": 0.01923802338740098,
+      "grad_norm": 1.7687246799468994,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8913,
+      "step": 51
+    },
+    {
+      "epoch": 0.01961523953225198,
+      "grad_norm": 1.832263708114624,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 1.7582,
+      "step": 52
+    },
+    {
+      "epoch": 0.01999245567710298,
+      "grad_norm": 2.0533218383789062,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 1.8514,
+      "step": 53
+    },
+    {
+      "epoch": 0.02036967182195398,
+      "grad_norm": 1.902577519416809,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9063,
+      "step": 54
+    },
+    {
+      "epoch": 0.02074688796680498,
+      "grad_norm": 2.0547704696655273,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.9272,
+      "step": 55
+    },
+    {
+      "epoch": 0.021124104111655977,
+      "grad_norm": 1.9024983644485474,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 1.7496,
+      "step": 56
+    },
+    {
+      "epoch": 0.02150132025650698,
+      "grad_norm": 1.7016141414642334,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.905,
+      "step": 57
+    },
+    {
+      "epoch": 0.02187853640135798,
+      "grad_norm": 1.8714863061904907,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 1.7749,
+      "step": 58
+    },
+    {
+      "epoch": 0.022255752546208978,
+      "grad_norm": 1.7974597215652466,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.7632,
+      "step": 59
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 1.6825218200683594,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.8978,
+      "step": 60
+    },
+    {
+      "epoch": 0.023010184835910975,
+      "grad_norm": 1.8190650939941406,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 1.7671,
+      "step": 61
+    },
+    {
+      "epoch": 0.023387400980761978,
+      "grad_norm": 1.753597617149353,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 1.6744,
+      "step": 62
+    },
+    {
+      "epoch": 0.023764617125612977,
+      "grad_norm": 1.6556949615478516,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.8486,
+      "step": 63
+    },
+    {
+      "epoch": 0.024141833270463976,
+      "grad_norm": 1.8840663433074951,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 1.7873,
+      "step": 64
+    },
+    {
+      "epoch": 0.024519049415314974,
+      "grad_norm": 1.7227132320404053,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 1.8526,
+      "step": 65
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 1.8766735792160034,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.9803,
+      "step": 66
+    },
+    {
+      "epoch": 0.025273481705016976,
+      "grad_norm": 1.913208246231079,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.7791,
+      "step": 67
+    },
+    {
+      "epoch": 0.025650697849867975,
+      "grad_norm": 1.606818675994873,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 1.6366,
+      "step": 68
+    },
+    {
+      "epoch": 0.026027913994718974,
+      "grad_norm": 1.7870965003967285,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.794,
+      "step": 69
+    },
+    {
+      "epoch": 0.026405130139569973,
+      "grad_norm": 1.6979774236679077,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 1.5391,
+      "step": 70
+    },
+    {
+      "epoch": 0.026782346284420975,
+      "grad_norm": 1.9064507484436035,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.7034,
+      "step": 71
+    },
+    {
+      "epoch": 0.027159562429271974,
+      "grad_norm": 1.8551948070526123,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6344,
+      "step": 72
+    },
+    {
+      "epoch": 0.027536778574122973,
+      "grad_norm": 1.7518131732940674,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 1.5952,
+      "step": 73
+    },
+    {
+      "epoch": 0.02791399471897397,
+      "grad_norm": 1.8491065502166748,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 1.5739,
+      "step": 74
+    },
+    {
+      "epoch": 0.02829121086382497,
+      "grad_norm": 1.7698376178741455,
+      "learning_rate": 0.0,
+      "loss": 1.6641,
+      "step": 75
+    },
+    {
+      "epoch": 0.02829121086382497,
+      "eval_loss": 1.5686583518981934,
+      "eval_runtime": 250.0886,
+      "eval_samples_per_second": 8.929,
+      "eval_steps_per_second": 4.466,
+      "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": 2.03101109747712e+16,
+  "total_flos": 3.04651664621568e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null