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:d784918062809adab38d96de73f8a6d2307264464c9e6c99ab5be25c60e0edbe
+oid sha256:f9d096ecec86faae9683611e4fe405f34e5f884e9c91df630b4548422b1b38fb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2bc455574310189264c1525868c247f17b1070d3b25cebddf4376471c345062
+oid sha256:83e5c0377eca0a91670c066fb7f1a120a83c49839031e4bf5cea594b2d341cf2
 size 335922386

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52fccfd1b8c54400836b1f560133e9fc50af3ddebc0615ff28398e1e5ce887a9
+oid sha256:44ec296b0b5d34e831ff79c0dca82c5a5dce2cc06d0afec81e05c473f1d9d2dd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18259e58314b4ea7c9ab8ed785bce4c4419596e28db8bdd64430783ae4aeb12f
+oid sha256:49f32059a26b3b26819095f7b2287da4d500c1dec388ba010f6b6f98b94bb1c5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1321fcddcaa70421d5a753abe41bad66ade5e0871a2c553d195d0cd4d6e82f1f
+oid sha256:92242c634f86bc1596c306e7590d095196b8c4566c9a14a7774d1d4ede5070fb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fa7a33c3153f16e6bfcfb08f11291e21413db226de6dbe812e1786bdfc5a482
+oid sha256:9c94b87914a07a9e4322a51b715167b849fbef93873d7d27c3e8267076384b36
 size 15024

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": 0.2857142857142857,
+  "epoch": 0.38095238095238093,
   "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": 2.1821,
       "step": 75
+    },
+    {
+      "epoch": 0.2895238095238095,
+      "grad_norm": 0.6272994875907898,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 2.2606,
+      "step": 76
+    },
+    {
+      "epoch": 0.29333333333333333,
+      "grad_norm": 0.5300612449645996,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 2.0936,
+      "step": 77
+    },
+    {
+      "epoch": 0.29714285714285715,
+      "grad_norm": 0.5692737102508545,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.0541,
+      "step": 78
+    },
+    {
+      "epoch": 0.30095238095238097,
+      "grad_norm": 0.6007286310195923,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 2.1888,
+      "step": 79
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.5657607913017273,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.1796,
+      "step": 80
+    },
+    {
+      "epoch": 0.30857142857142855,
+      "grad_norm": 0.6097643971443176,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 2.1622,
+      "step": 81
+    },
+    {
+      "epoch": 0.30857142857142855,
+      "eval_loss": 2.208329916000366,
+      "eval_runtime": 23.4359,
+      "eval_samples_per_second": 37.72,
+      "eval_steps_per_second": 1.195,
+      "step": 81
+    },
+    {
+      "epoch": 0.31238095238095237,
+      "grad_norm": 0.6333368420600891,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.1319,
+      "step": 82
+    },
+    {
+      "epoch": 0.3161904761904762,
+      "grad_norm": 0.7318187355995178,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 2.327,
+      "step": 83
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8585187792778015,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 2.127,
+      "step": 84
+    },
+    {
+      "epoch": 0.3238095238095238,
+      "grad_norm": 0.937681257724762,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.2171,
+      "step": 85
+    },
+    {
+      "epoch": 0.32761904761904764,
+      "grad_norm": 0.559676468372345,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 2.2199,
+      "step": 86
+    },
+    {
+      "epoch": 0.3314285714285714,
+      "grad_norm": 0.6197167634963989,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 2.0758,
+      "step": 87
+    },
+    {
+      "epoch": 0.3352380952380952,
+      "grad_norm": 0.5611276626586914,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 2.2858,
+      "step": 88
+    },
+    {
+      "epoch": 0.33904761904761904,
+      "grad_norm": 0.5831174254417419,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 2.1612,
+      "step": 89
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 0.6797851324081421,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.2531,
+      "step": 90
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "eval_loss": 2.2069602012634277,
+      "eval_runtime": 23.5044,
+      "eval_samples_per_second": 37.61,
+      "eval_steps_per_second": 1.191,
+      "step": 90
+    },
+    {
+      "epoch": 0.3466666666666667,
+      "grad_norm": 0.5669330954551697,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.1284,
+      "step": 91
+    },
+    {
+      "epoch": 0.3504761904761905,
+      "grad_norm": 0.6221609711647034,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.1393,
+      "step": 92
+    },
+    {
+      "epoch": 0.35428571428571426,
+      "grad_norm": 0.5420305728912354,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.1128,
+      "step": 93
+    },
+    {
+      "epoch": 0.3580952380952381,
+      "grad_norm": 0.5762845277786255,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.2614,
+      "step": 94
+    },
+    {
+      "epoch": 0.3619047619047619,
+      "grad_norm": 0.693850576877594,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.1347,
+      "step": 95
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.5280032157897949,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.1706,
+      "step": 96
+    },
+    {
+      "epoch": 0.36952380952380953,
+      "grad_norm": 0.6207125782966614,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 2.2263,
+      "step": 97
+    },
+    {
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.5548049211502075,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.1802,
+      "step": 98
+    },
+    {
+      "epoch": 0.37714285714285717,
+      "grad_norm": 0.5405362844467163,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 2.1485,
+      "step": 99
+    },
+    {
+      "epoch": 0.37714285714285717,
+      "eval_loss": 2.2066235542297363,
+      "eval_runtime": 23.4644,
+      "eval_samples_per_second": 37.674,
+      "eval_steps_per_second": 1.193,
+      "step": 99
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 0.6534842252731323,
+      "learning_rate": 0.0,
+      "loss": 2.2749,
+      "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": 4.451323701362688e+17,
+  "total_flos": 5.935098268483584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null