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:c5ab6744f3645cab5636a3be6fa5e6b94c0c7e5be47a01919993360d5627f423
+oid sha256:613f2d13b202afc32fe1de28f680ab3c0392d8fc6f9dd63db5adff44a3469734
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed27088a35cccecdf764dab6ae0886766ce964b3ac2a8cd78ab22e1cb13efdb1
+oid sha256:188a940909ad240a0122f50e1242a57db1bde2a832fe743e32780ed2513bc8fa
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a43d6674077812ecf0205e0cfd08a3e37e98ae195f094b9f693adae07d1ce9c6
+oid sha256:23dd234d57601f91687886bf40ace335ed9e767182bc98b3dded1a9cee18799f
 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": 0.24311183144246354,
+  "epoch": 0.3241491085899514,
   "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": 1.8626,
       "step": 75
+    },
+    {
+      "epoch": 0.24635332252836303,
+      "grad_norm": 1.0571489334106445,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.9725,
+      "step": 76
+    },
+    {
+      "epoch": 0.24959481361426256,
+      "grad_norm": 0.7617626190185547,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 1.8038,
+      "step": 77
+    },
+    {
+      "epoch": 0.25283630470016205,
+      "grad_norm": 0.98393315076828,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 2.0169,
+      "step": 78
+    },
+    {
+      "epoch": 0.2560777957860616,
+      "grad_norm": 0.9455400109291077,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.7648,
+      "step": 79
+    },
+    {
+      "epoch": 0.2593192868719611,
+      "grad_norm": 0.99833744764328,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8161,
+      "step": 80
+    },
+    {
+      "epoch": 0.2625607779578606,
+      "grad_norm": 0.8089686632156372,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.8539,
+      "step": 81
+    },
+    {
+      "epoch": 0.2625607779578606,
+      "eval_loss": 1.8421069383621216,
+      "eval_runtime": 30.558,
+      "eval_samples_per_second": 8.508,
+      "eval_steps_per_second": 1.08,
+      "step": 81
+    },
+    {
+      "epoch": 0.26580226904376014,
+      "grad_norm": 1.0099201202392578,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.8115,
+      "step": 82
+    },
+    {
+      "epoch": 0.26904376012965964,
+      "grad_norm": 0.9346497058868408,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.9065,
+      "step": 83
+    },
+    {
+      "epoch": 0.27228525121555913,
+      "grad_norm": 0.7902043461799622,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.6215,
+      "step": 84
+    },
+    {
+      "epoch": 0.2755267423014587,
+      "grad_norm": 0.9881759881973267,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.929,
+      "step": 85
+    },
+    {
+      "epoch": 0.2787682333873582,
+      "grad_norm": 0.8457426428794861,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7417,
+      "step": 86
+    },
+    {
+      "epoch": 0.2820097244732577,
+      "grad_norm": 0.7483598589897156,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.6865,
+      "step": 87
+    },
+    {
+      "epoch": 0.2852512155591572,
+      "grad_norm": 0.9153674244880676,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9731,
+      "step": 88
+    },
+    {
+      "epoch": 0.2884927066450567,
+      "grad_norm": 0.9437265992164612,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.7751,
+      "step": 89
+    },
+    {
+      "epoch": 0.2917341977309562,
+      "grad_norm": 1.077127456665039,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.1184,
+      "step": 90
+    },
+    {
+      "epoch": 0.2917341977309562,
+      "eval_loss": 1.840531826019287,
+      "eval_runtime": 30.4979,
+      "eval_samples_per_second": 8.525,
+      "eval_steps_per_second": 1.082,
+      "step": 90
+    },
+    {
+      "epoch": 0.29497568881685576,
+      "grad_norm": 1.0355558395385742,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 2.0273,
+      "step": 91
+    },
+    {
+      "epoch": 0.29821717990275526,
+      "grad_norm": 0.6711990237236023,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.4758,
+      "step": 92
+    },
+    {
+      "epoch": 0.3014586709886548,
+      "grad_norm": 1.0566705465316772,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 2.2128,
+      "step": 93
+    },
+    {
+      "epoch": 0.3047001620745543,
+      "grad_norm": 0.7678670883178711,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.8195,
+      "step": 94
+    },
+    {
+      "epoch": 0.3079416531604538,
+      "grad_norm": 0.8789794445037842,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.801,
+      "step": 95
+    },
+    {
+      "epoch": 0.31118314424635335,
+      "grad_norm": 0.9785366058349609,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.7027,
+      "step": 96
+    },
+    {
+      "epoch": 0.31442463533225284,
+      "grad_norm": 0.9214769005775452,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 1.8092,
+      "step": 97
+    },
+    {
+      "epoch": 0.31766612641815234,
+      "grad_norm": 0.9695401191711426,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0306,
+      "step": 98
+    },
+    {
+      "epoch": 0.3209076175040519,
+      "grad_norm": 0.8423238396644592,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.8981,
+      "step": 99
+    },
+    {
+      "epoch": 0.3209076175040519,
+      "eval_loss": 1.8405555486679077,
+      "eval_runtime": 30.5474,
+      "eval_samples_per_second": 8.511,
+      "eval_steps_per_second": 1.08,
+      "step": 99
+    },
+    {
+      "epoch": 0.3241491085899514,
+      "grad_norm": 1.0919097661972046,
+      "learning_rate": 0.0,
+      "loss": 2.0046,
+      "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": 6.083581381391155e+16,
+  "total_flos": 8.049616827816346e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null