Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:981e6654b92c0915ac20ab377d1b1ec9ac709b2071d6a905a05a2fb122ab1d62
+oid sha256:2bb03febfbfb8c72443091e777e9dd1d22d70c2bf6d75e56926537a4caa06d5f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab3c90a79b69c7b7db79967ce5b5a14345c59e110ce35c73b70dfc8465a3695
+oid sha256:6c254bcc8e932667cc1889fd35d35d9d69ccc53f2cfa339f7e8b08c918014a4e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ade794c9ae8f60a23a4e2303e71e00584e515f475138cbbe69c00a1df0a54eb
+oid sha256:2641fe94f6f5285a893d26b6a83b6bc1718c94cdba5b09f9fe77818d5a69d3a2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23e2214bcafb439ebc7528dcc283ef6218d509a276c0baff0743503ecbe3d92
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.684931506849315,
+  "epoch": 0.91324200913242,
   "eval_steps": 9,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -604,6 +604,205 @@
       "learning_rate": 1.7860619515673033e-05,
       "loss": 2.3986,
       "step": 75
+    },
+    {
+      "epoch": 0.6940639269406392,
+      "grad_norm": 0.5468965768814087,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9288,
+      "step": 76
+    },
+    {
+      "epoch": 0.7031963470319634,
+      "grad_norm": 0.4898984432220459,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.0482,
+      "step": 77
+    },
+    {
+      "epoch": 0.7123287671232876,
+      "grad_norm": 0.6228100657463074,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.903,
+      "step": 78
+    },
+    {
+      "epoch": 0.7214611872146118,
+      "grad_norm": 0.6375327110290527,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.49,
+      "step": 79
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 0.5555298328399658,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.5199,
+      "step": 80
+    },
+    {
+      "epoch": 0.7397260273972602,
+      "grad_norm": 0.6126773953437805,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.4759,
+      "step": 81
+    },
+    {
+      "epoch": 0.7397260273972602,
+      "eval_loss": 2.2166996002197266,
+      "eval_runtime": 20.8348,
+      "eval_samples_per_second": 4.464,
+      "eval_steps_per_second": 0.576,
+      "step": 81
+    },
+    {
+      "epoch": 0.7488584474885844,
+      "grad_norm": 0.5838559865951538,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1914,
+      "step": 82
+    },
+    {
+      "epoch": 0.7579908675799086,
+      "grad_norm": 0.7605540156364441,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.1758,
+      "step": 83
+    },
+    {
+      "epoch": 0.7671232876712328,
+      "grad_norm": 0.6348507404327393,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.2758,
+      "step": 84
+    },
+    {
+      "epoch": 0.776255707762557,
+      "grad_norm": 0.5870646834373474,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3142,
+      "step": 85
+    },
+    {
+      "epoch": 0.7853881278538812,
+      "grad_norm": 0.5460823774337769,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.2798,
+      "step": 86
+    },
+    {
+      "epoch": 0.7945205479452054,
+      "grad_norm": 0.6042826175689697,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.2346,
+      "step": 87
+    },
+    {
+      "epoch": 0.8036529680365296,
+      "grad_norm": 0.5716707706451416,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.1999,
+      "step": 88
+    },
+    {
+      "epoch": 0.8127853881278538,
+      "grad_norm": 0.550568699836731,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.0574,
+      "step": 89
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 0.5823182463645935,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.9946,
+      "step": 90
+    },
+    {
+      "epoch": 0.821917808219178,
+      "eval_loss": 2.2124736309051514,
+      "eval_runtime": 20.813,
+      "eval_samples_per_second": 4.468,
+      "eval_steps_per_second": 0.577,
+      "step": 90
+    },
+    {
+      "epoch": 0.8310502283105022,
+      "grad_norm": 0.5822633504867554,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.0597,
+      "step": 91
+    },
+    {
+      "epoch": 0.8401826484018264,
+      "grad_norm": 0.5779334306716919,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.2442,
+      "step": 92
+    },
+    {
+      "epoch": 0.8493150684931506,
+      "grad_norm": 0.5636650323867798,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.2871,
+      "step": 93
+    },
+    {
+      "epoch": 0.8584474885844748,
+      "grad_norm": 0.6365733742713928,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.2949,
+      "step": 94
+    },
+    {
+      "epoch": 0.867579908675799,
+      "grad_norm": 0.8823941946029663,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.2909,
+      "step": 95
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 0.507706880569458,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2422,
+      "step": 96
+    },
+    {
+      "epoch": 0.8858447488584474,
+      "grad_norm": 0.8357117772102356,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.2351,
+      "step": 97
+    },
+    {
+      "epoch": 0.8949771689497716,
+      "grad_norm": 0.694574236869812,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.3319,
+      "step": 98
+    },
+    {
+      "epoch": 0.9041095890410958,
+      "grad_norm": 0.47206035256385803,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.2751,
+      "step": 99
+    },
+    {
+      "epoch": 0.9041095890410958,
+      "eval_loss": 2.2115933895111084,
+      "eval_runtime": 20.8491,
+      "eval_samples_per_second": 4.461,
+      "eval_steps_per_second": 0.576,
+      "step": 99
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 0.864282488822937,
+      "learning_rate": 0.0,
+      "loss": 2.3232,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -618,12 +817,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.112830925340672e+17,
+  "total_flos": 1.483774567120896e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null