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:a4b6e610091e15bb9fc1f7dfc74de0fc47b350b51efaccb38c3cb3a6733b7c60
+oid sha256:aeccf3fcb866f7fac8d7ee18306a772da2bd946ebd8cb937b446c0baac697248
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff6a9477f4e5ae654862228a3da2259da1a71535ffb5c9e0daf42194ed8cd585
+oid sha256:777d9f1d73c18ad2066ed7c7fa3c1127ca6ba3f18ae99235d377573477d9b640
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f58b155e5123c7f1976665fc15d0993b62f2994fac0848287641211bae5ae5bc
+oid sha256:d665228d5c674a5322354b2cbabcdb77447213d0273363aa47e9189b164a4bf9
 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": 0.14691478942213515,
+  "epoch": 0.1958863858961802,
   "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": 0.9313,
       "step": 75
+    },
+    {
+      "epoch": 0.14887365328109697,
+      "grad_norm": 0.8500004410743713,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.9716,
+      "step": 76
+    },
+    {
+      "epoch": 0.15083251714005877,
+      "grad_norm": 0.8731956481933594,
+      "learning_rate": 1.526708147705013e-05,
+      "loss": 0.9631,
+      "step": 77
+    },
+    {
+      "epoch": 0.15279138099902057,
+      "grad_norm": 0.8892145752906799,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.8615,
+      "step": 78
+    },
+    {
+      "epoch": 0.15475024485798236,
+      "grad_norm": 1.024143934249878,
+      "learning_rate": 1.2842758726130283e-05,
+      "loss": 1.1187,
+      "step": 79
+    },
+    {
+      "epoch": 0.15670910871694418,
+      "grad_norm": 1.179613471031189,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.1868,
+      "step": 80
+    },
+    {
+      "epoch": 0.15866797257590598,
+      "grad_norm": 1.2375884056091309,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.1178,
+      "step": 81
+    },
+    {
+      "epoch": 0.15866797257590598,
+      "eval_loss": 0.5064930319786072,
+      "eval_runtime": 77.7099,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.695,
+      "step": 81
+    },
+    {
+      "epoch": 0.16062683643486778,
+      "grad_norm": 1.013840675354004,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.0417,
+      "step": 82
+    },
+    {
+      "epoch": 0.16258570029382957,
+      "grad_norm": 1.0417487621307373,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.0885,
+      "step": 83
+    },
+    {
+      "epoch": 0.16454456415279137,
+      "grad_norm": 0.8136703968048096,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.9909,
+      "step": 84
+    },
+    {
+      "epoch": 0.1665034280117532,
+      "grad_norm": 0.8972939848899841,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.8215,
+      "step": 85
+    },
+    {
+      "epoch": 0.168462291870715,
+      "grad_norm": 1.0475735664367676,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.0297,
+      "step": 86
+    },
+    {
+      "epoch": 0.17042115572967678,
+      "grad_norm": 1.019552230834961,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 1.002,
+      "step": 87
+    },
+    {
+      "epoch": 0.17238001958863858,
+      "grad_norm": 1.4625893831253052,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.0048,
+      "step": 88
+    },
+    {
+      "epoch": 0.1743388834476004,
+      "grad_norm": 1.1439257860183716,
+      "learning_rate": 3.6408072716606346e-06,
+      "loss": 1.2146,
+      "step": 89
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "grad_norm": 0.8621885776519775,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.7792,
+      "step": 90
+    },
+    {
+      "epoch": 0.1762977473065622,
+      "eval_loss": 0.5049313306808472,
+      "eval_runtime": 77.7203,
+      "eval_samples_per_second": 5.533,
+      "eval_steps_per_second": 0.695,
+      "step": 90
+    },
+    {
+      "epoch": 0.178256611165524,
+      "grad_norm": 1.0577645301818848,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.9036,
+      "step": 91
+    },
+    {
+      "epoch": 0.1802154750244858,
+      "grad_norm": 0.9616133570671082,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.9035,
+      "step": 92
+    },
+    {
+      "epoch": 0.1821743388834476,
+      "grad_norm": 1.2831529378890991,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.0449,
+      "step": 93
+    },
+    {
+      "epoch": 0.1841332027424094,
+      "grad_norm": 0.9351686835289001,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 1.156,
+      "step": 94
+    },
+    {
+      "epoch": 0.1860920666013712,
+      "grad_norm": 1.0163346529006958,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 1.1315,
+      "step": 95
+    },
+    {
+      "epoch": 0.188050930460333,
+      "grad_norm": 1.0136922597885132,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.1075,
+      "step": 96
+    },
+    {
+      "epoch": 0.19000979431929482,
+      "grad_norm": 0.8940609693527222,
+      "learning_rate": 2.7390523158633554e-07,
+      "loss": 0.893,
+      "step": 97
+    },
+    {
+      "epoch": 0.19196865817825662,
+      "grad_norm": 1.0098772048950195,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.1835,
+      "step": 98
+    },
+    {
+      "epoch": 0.1939275220372184,
+      "grad_norm": 0.994354248046875,
+      "learning_rate": 3.04586490452119e-08,
+      "loss": 1.0804,
+      "step": 99
+    },
+    {
+      "epoch": 0.1939275220372184,
+      "eval_loss": 0.5047321915626526,
+      "eval_runtime": 77.66,
+      "eval_samples_per_second": 5.537,
+      "eval_steps_per_second": 0.695,
+      "step": 99
+    },
+    {
+      "epoch": 0.1958863858961802,
+      "grad_norm": 1.6256389617919922,
+      "learning_rate": 0.0,
+      "loss": 1.0082,
+      "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": 9.80187302854656e+16,
+  "total_flos": 1.306916403806208e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null